TY  - PAT
AU  - Radulović, Lazar
AU  - Koštreba, Zlatan
AU  - Stiković, Nikola
AU  - Peulić, Aleksandar
AU  - Stefanović, Nenad
PY  - 2023
UR  - https://worldwide.espacenet.com/patent/search/family/086949486/publication/RS1788U1?q=RS1788U1
UR  - http://gery.gef.bg.ac.rs/handle/123456789/1516
AB  - Sistem za automatizovano uključivanje računara zasnovan na internet stvarima se sastoji od sledećih elemenata: Pametni telefon (1) je povezan sa baznom stanicom (3) putem mobilne veze (2), koja je dalje na internet mrežu (5) povezana pomoću prvog optičkog kabla (4). Na internet mrežu (5) je pomoću drugog optičkog kabla (6) povezan ruter uređaj (7), na koji je pomoću bežične veze (8) povezan Raspberry Pi računar (9). Raspberry Pi računar (9) je povezan sa personalnim računarom (11) putem žične veze (10). Ovakva vrsta povezanosti sistema obezbeđuje komunikaciju između pametnog telefona (1) i  personalnog računara (11)
PB  - Beograd : Zavod za intelektualnu svojinu
T2  - Glasnik intelektualne svojine 2023/6, Spis malog patenta 1788 U1
T1  - Sistem za automatizovano uključivanje računara zasnovan na internetu stvari
T1  - The system for automated switching on of computer based on the internet of things
IS  - 6
SP  - 40
UR  - https://hdl.handle.net/21.15107/rcub_gery_1516
ER  - 

@misc{
author = "Radulović, Lazar and Koštreba, Zlatan and Stiković, Nikola and Peulić, Aleksandar and Stefanović, Nenad",
year = "2023",
abstract = "Sistem za automatizovano uključivanje računara zasnovan na internet stvarima se sastoji od sledećih elemenata: Pametni telefon (1) je povezan sa baznom stanicom (3) putem mobilne veze (2), koja je dalje na internet mrežu (5) povezana pomoću prvog optičkog kabla (4). Na internet mrežu (5) je pomoću drugog optičkog kabla (6) povezan ruter uređaj (7), na koji je pomoću bežične veze (8) povezan Raspberry Pi računar (9). Raspberry Pi računar (9) je povezan sa personalnim računarom (11) putem žične veze (10). Ovakva vrsta povezanosti sistema obezbeđuje komunikaciju između pametnog telefona (1) i  personalnog računara (11)",
publisher = "Beograd : Zavod za intelektualnu svojinu",
journal = "Glasnik intelektualne svojine 2023/6, Spis malog patenta 1788 U1",
title = "Sistem za automatizovano uključivanje računara zasnovan na internetu stvari, The system for automated switching on of computer based on the internet of things",
number = "6",
pages = "40",
url = "https://hdl.handle.net/21.15107/rcub_gery_1516"
}

Radulović, L., Koštreba, Z., Stiković, N., Peulić, A.,& Stefanović, N.. (2023). Sistem za automatizovano uključivanje računara zasnovan na internetu stvari. in Glasnik intelektualne svojine 2023/6, Spis malog patenta 1788 U1
Beograd : Zavod za intelektualnu svojinu.(6), 40.
https://hdl.handle.net/21.15107/rcub_gery_1516

Radulović L, Koštreba Z, Stiković N, Peulić A, Stefanović N. Sistem za automatizovano uključivanje računara zasnovan na internetu stvari. in Glasnik intelektualne svojine 2023/6, Spis malog patenta 1788 U1. 2023;(6):40.
https://hdl.handle.net/21.15107/rcub_gery_1516 .

Radulović, Lazar, Koštreba, Zlatan, Stiković, Nikola, Peulić, Aleksandar, Stefanović, Nenad, "Sistem za automatizovano uključivanje računara zasnovan na internetu stvari" in Glasnik intelektualne svojine 2023/6, Spis malog patenta 1788 U1, no. 6 (2023):40,
https://hdl.handle.net/21.15107/rcub_gery_1516 .

TY  - CONF
AU  - Peulić, Aleksandar
AU  - Jovanović, Dušica
AU  - Stojković, Sanja
PY  - 2023
UR  - http://gery.gef.bg.ac.rs/handle/123456789/1566
AB  - Kada je reč o veštačkoj inteligenciji (VI) i prostornom planiranju, Huawei Ascend  310 procesor može biti korišćen za ubrzavanje različitih aspekata procesa prostornog  planiranja. Korišćenjem VI algoritama, moguće je identifi kovati obrasce, prepoznati objekte,  izvršiti klasifi kaciju terena i analizirati prostorne karakteristike.Veštačka inteligencija može se  koristiti za predviđanje kretanja i modeliranje različitih elemenata u prostoru. Na primer, može  se primeniti za predviđanje saobraćajnog toka, kretanja ljudi ili identifi kaciju potencijalnih  lokacija za izgradnju infrastrukture. Ascend 310 procesor pruža mogućnost ubrzane obrade  ovih algoritama, čime se omogućava brže i efi kasnije planiranje. U prostornom planiranju,  VI može se koristiti za optimizaciju korišćenja resursa poput vode, energije ili zemljišta.  Huawei Ascend 310 procesor može ubrzati analizu i optimizaciju resursa, što omogućava  bolje upravljanje i racionalno korišćenje prostornih resursa. VI može biti korisna i za  simulaciju scenarija i vizualizaciju planiranih prostornih intervencija. Korišćenjem Ascend  310 procesora za ubrzavanje obrade simulacija i vizualizacija, može se dobiti realističan  prikaz predloženih planova, što pomaže donosiocima odluka da bolje razumeju i procene  implikacije planiranih intervencija. Huawei Ascend 310 je specijalizovani procesor (ASIC)  za ubrzanje veštačke inteligencije koji je razvijen od strane kompanije Huawei. ASCEND je  arhitektura za ubrzavanje VI koja koristi nisku snagu i visoku propusnost.
PB  - Beograd : Asocijacija prostornih planera Srbije
PB  - Beograd : Univerzitet u Beogradu - Geografski fakultet
C3  - Zbornik radova Dvanaestog naučno-stručnog skupa sa međunarodnim učešćem "Planska i normativna zaštita prostora i životne sredine", Novi Pazar
T1  - Ubrzanje algoritama veštačke inteligencije sa primenom u prostornom planiranju korišćenjem Huawei ASCEND 310 arhitekture
SP  - 49
EP  - 55
UR  - https://hdl.handle.net/21.15107/rcub_gery_1566
ER  - 

@conference{
author = "Peulić, Aleksandar and Jovanović, Dušica and Stojković, Sanja",
year = "2023",
abstract = "Kada je reč o veštačkoj inteligenciji (VI) i prostornom planiranju, Huawei Ascend  310 procesor može biti korišćen za ubrzavanje različitih aspekata procesa prostornog  planiranja. Korišćenjem VI algoritama, moguće je identifi kovati obrasce, prepoznati objekte,  izvršiti klasifi kaciju terena i analizirati prostorne karakteristike.Veštačka inteligencija može se  koristiti za predviđanje kretanja i modeliranje različitih elemenata u prostoru. Na primer, može  se primeniti za predviđanje saobraćajnog toka, kretanja ljudi ili identifi kaciju potencijalnih  lokacija za izgradnju infrastrukture. Ascend 310 procesor pruža mogućnost ubrzane obrade  ovih algoritama, čime se omogućava brže i efi kasnije planiranje. U prostornom planiranju,  VI može se koristiti za optimizaciju korišćenja resursa poput vode, energije ili zemljišta.  Huawei Ascend 310 procesor može ubrzati analizu i optimizaciju resursa, što omogućava  bolje upravljanje i racionalno korišćenje prostornih resursa. VI može biti korisna i za  simulaciju scenarija i vizualizaciju planiranih prostornih intervencija. Korišćenjem Ascend  310 procesora za ubrzavanje obrade simulacija i vizualizacija, može se dobiti realističan  prikaz predloženih planova, što pomaže donosiocima odluka da bolje razumeju i procene  implikacije planiranih intervencija. Huawei Ascend 310 je specijalizovani procesor (ASIC)  za ubrzanje veštačke inteligencije koji je razvijen od strane kompanije Huawei. ASCEND je  arhitektura za ubrzavanje VI koja koristi nisku snagu i visoku propusnost.",
publisher = "Beograd : Asocijacija prostornih planera Srbije, Beograd : Univerzitet u Beogradu - Geografski fakultet",
journal = "Zbornik radova Dvanaestog naučno-stručnog skupa sa međunarodnim učešćem "Planska i normativna zaštita prostora i životne sredine", Novi Pazar",
title = "Ubrzanje algoritama veštačke inteligencije sa primenom u prostornom planiranju korišćenjem Huawei ASCEND 310 arhitekture",
pages = "49-55",
url = "https://hdl.handle.net/21.15107/rcub_gery_1566"
}

Peulić, A., Jovanović, D.,& Stojković, S.. (2023). Ubrzanje algoritama veštačke inteligencije sa primenom u prostornom planiranju korišćenjem Huawei ASCEND 310 arhitekture. in Zbornik radova Dvanaestog naučno-stručnog skupa sa međunarodnim učešćem "Planska i normativna zaštita prostora i životne sredine", Novi Pazar
Beograd : Asocijacija prostornih planera Srbije., 49-55.
https://hdl.handle.net/21.15107/rcub_gery_1566

Peulić A, Jovanović D, Stojković S. Ubrzanje algoritama veštačke inteligencije sa primenom u prostornom planiranju korišćenjem Huawei ASCEND 310 arhitekture. in Zbornik radova Dvanaestog naučno-stručnog skupa sa međunarodnim učešćem "Planska i normativna zaštita prostora i životne sredine", Novi Pazar. 2023;:49-55.
https://hdl.handle.net/21.15107/rcub_gery_1566 .

Peulić, Aleksandar, Jovanović, Dušica, Stojković, Sanja, "Ubrzanje algoritama veštačke inteligencije sa primenom u prostornom planiranju korišćenjem Huawei ASCEND 310 arhitekture" in Zbornik radova Dvanaestog naučno-stručnog skupa sa međunarodnim učešćem "Planska i normativna zaštita prostora i životne sredine", Novi Pazar (2023):49-55,
https://hdl.handle.net/21.15107/rcub_gery_1566 .

TY  - CONF
AU  - Jovanović, Dušica
AU  - Peulić, Aleksandar
PY  - 2023
UR  - http://gery.gef.bg.ac.rs/handle/123456789/1576
AB  - Deforestacija je proces krčenja ili uklanjanja šuma ili drveća sa određenog  područja. Često uključuje seču drveća kako bi se napravio prostor za poljoprivredu,  urbanizaciju ili komercijalne svrhe i ima značajne ekološke posledice, uključujući gubitak  biodiverziteta, narušavanje ekosistema i povećane emisije gasova sa efektom staklene bašte.  U radu će biti predstavljeno kako pomoću satelitskih snimaka prepoznati proces deforestacije  sa ciljem da se ukaže na važnost ovog problema. Python programski jezik danas predstavlja  osnovu mnogih automatizovanih kompjuterskih procesa. Kao alat, Python može da posluži  i za obradu slike u funkciji zaštite životne sredine. Ovakav pristup zahteva kvalitetne izvore  podataka i poznavanje materije u oblasti u okviru koje se koristi, kao i poznavanje osnova  programiranja. Biće korišćene različite Python biblioteke. Pomoću biblioteka moguće je istaći  konkretan prostor gde je povećana deforestacija, a ceo proces se zasniva na prepoznavanju  boje piksela na satelitskim snimcima. Snimci se učitavaju u program i kroz kod se proverava  da li su zadovoljeni postavljeni uslovi (npr. boja piksela, rezolucija i dr.). Koristeći svestranost  i prilagodljivost programskog jezika moguće je sprovesti efi kasno istraživanje uz maksimalnu  uštedu vremena i fokus na najvažnije elemente.
PB  - Beograd : Asocijacija prostornih planera Srbije
PB  - Beograd : Univerzitet u Beogradu - Geografski fakultet
C3  - Zbornik radova Dvanaestog naučno-stručnog skupa sa međunarodnim učešćem "Planska i normativna zaštita prostora i životne sredine", Novi Pazar
T1  - Prepoznavanje deforestacije digitalnom obradom slike
SP  - 253
EP  - 259
UR  - https://hdl.handle.net/21.15107/rcub_gery_1576
ER  - 

@conference{
author = "Jovanović, Dušica and Peulić, Aleksandar",
year = "2023",
abstract = "Deforestacija je proces krčenja ili uklanjanja šuma ili drveća sa određenog  područja. Često uključuje seču drveća kako bi se napravio prostor za poljoprivredu,  urbanizaciju ili komercijalne svrhe i ima značajne ekološke posledice, uključujući gubitak  biodiverziteta, narušavanje ekosistema i povećane emisije gasova sa efektom staklene bašte.  U radu će biti predstavljeno kako pomoću satelitskih snimaka prepoznati proces deforestacije  sa ciljem da se ukaže na važnost ovog problema. Python programski jezik danas predstavlja  osnovu mnogih automatizovanih kompjuterskih procesa. Kao alat, Python može da posluži  i za obradu slike u funkciji zaštite životne sredine. Ovakav pristup zahteva kvalitetne izvore  podataka i poznavanje materije u oblasti u okviru koje se koristi, kao i poznavanje osnova  programiranja. Biće korišćene različite Python biblioteke. Pomoću biblioteka moguće je istaći  konkretan prostor gde je povećana deforestacija, a ceo proces se zasniva na prepoznavanju  boje piksela na satelitskim snimcima. Snimci se učitavaju u program i kroz kod se proverava  da li su zadovoljeni postavljeni uslovi (npr. boja piksela, rezolucija i dr.). Koristeći svestranost  i prilagodljivost programskog jezika moguće je sprovesti efi kasno istraživanje uz maksimalnu  uštedu vremena i fokus na najvažnije elemente.",
publisher = "Beograd : Asocijacija prostornih planera Srbije, Beograd : Univerzitet u Beogradu - Geografski fakultet",
journal = "Zbornik radova Dvanaestog naučno-stručnog skupa sa međunarodnim učešćem "Planska i normativna zaštita prostora i životne sredine", Novi Pazar",
title = "Prepoznavanje deforestacije digitalnom obradom slike",
pages = "253-259",
url = "https://hdl.handle.net/21.15107/rcub_gery_1576"
}

Jovanović, D.,& Peulić, A.. (2023). Prepoznavanje deforestacije digitalnom obradom slike. in Zbornik radova Dvanaestog naučno-stručnog skupa sa međunarodnim učešćem "Planska i normativna zaštita prostora i životne sredine", Novi Pazar
Beograd : Asocijacija prostornih planera Srbije., 253-259.
https://hdl.handle.net/21.15107/rcub_gery_1576

Jovanović D, Peulić A. Prepoznavanje deforestacije digitalnom obradom slike. in Zbornik radova Dvanaestog naučno-stručnog skupa sa međunarodnim učešćem "Planska i normativna zaštita prostora i životne sredine", Novi Pazar. 2023;:253-259.
https://hdl.handle.net/21.15107/rcub_gery_1576 .

Jovanović, Dušica, Peulić, Aleksandar, "Prepoznavanje deforestacije digitalnom obradom slike" in Zbornik radova Dvanaestog naučno-stručnog skupa sa međunarodnim učešćem "Planska i normativna zaštita prostora i životne sredine", Novi Pazar (2023):253-259,
https://hdl.handle.net/21.15107/rcub_gery_1576 .

TY  - JOUR
AU  - Šušteršič, Tijana
AU  - Peulić, Aleksandar
PY  - 2023
UR  - http://gery.gef.bg.ac.rs/handle/123456789/1220
AB  - The aim of this research is to create a medical expert system based on Bayes theorem to diagnose level of disc hernia based on real foot force measurement signals obtained using sensors and implement the whole system on field programable gate array (FPGA). We have created a database of attributes based on recorded foot force values of 33 patients pre-diagnosed with herniated disc on levels L4/L5 or L5/S1 on the left or right side. The results obtained by software (Matlab) and hardware (FPGA simulation) are matching well, achieving high accuracy, which shows that VHDL implementation of Naïve Bayes theorem for disc hernia diagnostics is adequate. The output on FPGA is easy to understand for any user, as it is implemented as four-bit output where the position of bit value 1 indicates the level of disc herniation. The system is able to distinguish between the healthy subjects and subjects with disc herniation and is able to detect if improvement in stability is present after surgery or physical therapy. Our proposed measurement platform can be coupled with FPGA to create a portable and not expensive tool for real time signal acquisition, processing and decision support system in disc hernia diagnosis and post-surgical recovery.
PB  - World Scientific Publishing Co Pte Ltd
T2  - Journal of Circuits, Systems and Computers
T1  - FPGA Implementation of Expert System for Medical Diagnosis of Disc Hernia Diagnosis Based on Bayes Theorem
VL  - 32
IS  - 3
SP  - 2350038
DO  - 10.1142/S021812662350038X
ER  - 

@article{
author = "Šušteršič, Tijana and Peulić, Aleksandar",
year = "2023",
abstract = "The aim of this research is to create a medical expert system based on Bayes theorem to diagnose level of disc hernia based on real foot force measurement signals obtained using sensors and implement the whole system on field programable gate array (FPGA). We have created a database of attributes based on recorded foot force values of 33 patients pre-diagnosed with herniated disc on levels L4/L5 or L5/S1 on the left or right side. The results obtained by software (Matlab) and hardware (FPGA simulation) are matching well, achieving high accuracy, which shows that VHDL implementation of Naïve Bayes theorem for disc hernia diagnostics is adequate. The output on FPGA is easy to understand for any user, as it is implemented as four-bit output where the position of bit value 1 indicates the level of disc herniation. The system is able to distinguish between the healthy subjects and subjects with disc herniation and is able to detect if improvement in stability is present after surgery or physical therapy. Our proposed measurement platform can be coupled with FPGA to create a portable and not expensive tool for real time signal acquisition, processing and decision support system in disc hernia diagnosis and post-surgical recovery.",
publisher = "World Scientific Publishing Co Pte Ltd",
journal = "Journal of Circuits, Systems and Computers",
title = "FPGA Implementation of Expert System for Medical Diagnosis of Disc Hernia Diagnosis Based on Bayes Theorem",
volume = "32",
number = "3",
pages = "2350038",
doi = "10.1142/S021812662350038X"
}

Šušteršič, T.,& Peulić, A.. (2023). FPGA Implementation of Expert System for Medical Diagnosis of Disc Hernia Diagnosis Based on Bayes Theorem. in Journal of Circuits, Systems and Computers
World Scientific Publishing Co Pte Ltd., 32(3), 2350038.
https://doi.org/10.1142/S021812662350038X

Šušteršič T, Peulić A. FPGA Implementation of Expert System for Medical Diagnosis of Disc Hernia Diagnosis Based on Bayes Theorem. in Journal of Circuits, Systems and Computers. 2023;32(3):2350038.
doi:10.1142/S021812662350038X .

Šušteršič, Tijana, Peulić, Aleksandar, "FPGA Implementation of Expert System for Medical Diagnosis of Disc Hernia Diagnosis Based on Bayes Theorem" in Journal of Circuits, Systems and Computers, 32, no. 3 (2023):2350038,
https://doi.org/10.1142/S021812662350038X . .

TY  - PAT
AU  - Kaličanin, Nikola
AU  - Knežević, Marko
AU  - Cen, Yigang
AU  - Peulić, Aleksandar
AU  - Mladenović, Vladimir
PY  - 2022
UR  - https://worldwide.espacenet.com/patent/search/family/081076553/publication/RS1747U1?q=pn%3DRS1747U1
UR  - http://gery.gef.bg.ac.rs/handle/123456789/1381
AB  - Sistem za video nadzor preko internet mreže (4) zasnovan na uredaju (1) za prepoznavanje lica se sastoji od uredaja (1) prepoznavanje lica, žičanih veza (2), ruter uredaja (3), internet mreže (4), laptop računara (5) i video kamere (6). Uredaj (1) prepoznavanje lica komunicira sa ruterom uredajem (3) putem žične veze (2-0) koja je povezana na internet mrežu (4). Video kamera (6) je povezana na internet mrežu (4) putem žične veze (2-2) i šalje signal na laptop računar (5) koji je povezan preko ruter uređaja (3) na internet mrežu (4).
PB  - Beograd : Zavod za intelektualnu svojinu 
T2  - Glasnik intelektualne svojine 2022/3, Spis malog patenta 1747 U1
T1  - Sistem za video nadzor preko internet mreže zasnovan na uređaju za prepoznavanje lica
T1  - Video surveillance system over the internet based on the device for the face recognition
IS  - 3
SP  - 57
UR  - https://hdl.handle.net/21.15107/rcub_gery_1381
ER  - 

@misc{
author = "Kaličanin, Nikola and Knežević, Marko and Cen, Yigang and Peulić, Aleksandar and Mladenović, Vladimir",
year = "2022",
abstract = "Sistem za video nadzor preko internet mreže (4) zasnovan na uredaju (1) za prepoznavanje lica se sastoji od uredaja (1) prepoznavanje lica, žičanih veza (2), ruter uredaja (3), internet mreže (4), laptop računara (5) i video kamere (6). Uredaj (1) prepoznavanje lica komunicira sa ruterom uredajem (3) putem žične veze (2-0) koja je povezana na internet mrežu (4). Video kamera (6) je povezana na internet mrežu (4) putem žične veze (2-2) i šalje signal na laptop računar (5) koji je povezan preko ruter uređaja (3) na internet mrežu (4).",
publisher = "Beograd : Zavod za intelektualnu svojinu ",
journal = "Glasnik intelektualne svojine 2022/3, Spis malog patenta 1747 U1",
title = "Sistem za video nadzor preko internet mreže zasnovan na uređaju za prepoznavanje lica, Video surveillance system over the internet based on the device for the face recognition",
number = "3",
pages = "57",
url = "https://hdl.handle.net/21.15107/rcub_gery_1381"
}

Kaličanin, N., Knežević, M., Cen, Y., Peulić, A.,& Mladenović, V.. (2022). Sistem za video nadzor preko internet mreže zasnovan na uređaju za prepoznavanje lica. in Glasnik intelektualne svojine 2022/3, Spis malog patenta 1747 U1
Beograd : Zavod za intelektualnu svojinu .(3), 57.
https://hdl.handle.net/21.15107/rcub_gery_1381

Kaličanin N, Knežević M, Cen Y, Peulić A, Mladenović V. Sistem za video nadzor preko internet mreže zasnovan na uređaju za prepoznavanje lica. in Glasnik intelektualne svojine 2022/3, Spis malog patenta 1747 U1. 2022;(3):57.
https://hdl.handle.net/21.15107/rcub_gery_1381 .

Kaličanin, Nikola, Knežević, Marko, Cen, Yigang, Peulić, Aleksandar, Mladenović, Vladimir, "Sistem za video nadzor preko internet mreže zasnovan na uređaju za prepoznavanje lica" in Glasnik intelektualne svojine 2022/3, Spis malog patenta 1747 U1, no. 3 (2022):57,
https://hdl.handle.net/21.15107/rcub_gery_1381 .

TY  - PAT
AU  - Radulović, Darko
AU  - Radulović, Marko
AU  - Milovanović, Željko
AU  - Peulić, Aleksandar
AU  - Mladenović, Vladimir
PY  - 2022
UR  - https://worldwide.espacenet.com/patent/search/family/082701573/publication/RS1762U1?q=pn%3DRS1762U1
UR  - http://gery.gef.bg.ac.rs/handle/123456789/1380
AB  - Sistem za praćenje koordinate položaja tela zasnovan na internetu stvari pripada oblasti mašina za prenos podataka o promeni koordinata tela, sa senzora žiroskopa do robotske ruke. Tehnički problem rešen je tako što žiroskop (1) prvom žičanom vezom (2) povezan na prvi komunikacioni modul (3) koji je drugom žičanom vezom (4) povezan na prvi računar (5) koji prvom bežičnom vezom (6) šalje podatke do prvog ruter uređaja (7). Podaci se prvim optičkim kablom (8) šalju na Internet mrežu (9), a dalje se drugim optičkim kablom (10) prosleđuju na drugi ruter uređaj (11), koji te podatke drugom bežičnom vezom (12) šalje na drugi računar (13). Drugi računar (13) te podatke trećom žičanom vezom (14) šalje do drugog komunikacionog modula (15), koji te podatke četvrtom žičanom vezom (16) prosleđuje prototipu robotske ruke (17), koji primenjuje nove koordinate položaja tela i pomera prototip robotske ruke dovodeći je u položaj koji odgovara novim koordinatama.
PB  - Beograd : Zavod za intelektualnu svojinu 
T2  - Glasnik intelektualne svojine 2022/7, Spis malog patenta 1762 U1
T1  - Sistem za praćenje koordinate položaja tela zasnovan na Internet stvarima
T1  - The internet-based body position coordinate tracking system
IS  - 7
SP  - 35
UR  - https://hdl.handle.net/21.15107/rcub_gery_1380
ER  - 

@misc{
author = "Radulović, Darko and Radulović, Marko and Milovanović, Željko and Peulić, Aleksandar and Mladenović, Vladimir",
year = "2022",
abstract = "Sistem za praćenje koordinate položaja tela zasnovan na internetu stvari pripada oblasti mašina za prenos podataka o promeni koordinata tela, sa senzora žiroskopa do robotske ruke. Tehnički problem rešen je tako što žiroskop (1) prvom žičanom vezom (2) povezan na prvi komunikacioni modul (3) koji je drugom žičanom vezom (4) povezan na prvi računar (5) koji prvom bežičnom vezom (6) šalje podatke do prvog ruter uređaja (7). Podaci se prvim optičkim kablom (8) šalju na Internet mrežu (9), a dalje se drugim optičkim kablom (10) prosleđuju na drugi ruter uređaj (11), koji te podatke drugom bežičnom vezom (12) šalje na drugi računar (13). Drugi računar (13) te podatke trećom žičanom vezom (14) šalje do drugog komunikacionog modula (15), koji te podatke četvrtom žičanom vezom (16) prosleđuje prototipu robotske ruke (17), koji primenjuje nove koordinate položaja tela i pomera prototip robotske ruke dovodeći je u položaj koji odgovara novim koordinatama.",
publisher = "Beograd : Zavod za intelektualnu svojinu ",
journal = "Glasnik intelektualne svojine 2022/7, Spis malog patenta 1762 U1",
title = "Sistem za praćenje koordinate položaja tela zasnovan na Internet stvarima, The internet-based body position coordinate tracking system",
number = "7",
pages = "35",
url = "https://hdl.handle.net/21.15107/rcub_gery_1380"
}

Radulović, D., Radulović, M., Milovanović, Ž., Peulić, A.,& Mladenović, V.. (2022). Sistem za praćenje koordinate položaja tela zasnovan na Internet stvarima. in Glasnik intelektualne svojine 2022/7, Spis malog patenta 1762 U1
Beograd : Zavod za intelektualnu svojinu .(7), 35.
https://hdl.handle.net/21.15107/rcub_gery_1380

Radulović D, Radulović M, Milovanović Ž, Peulić A, Mladenović V. Sistem za praćenje koordinate položaja tela zasnovan na Internet stvarima. in Glasnik intelektualne svojine 2022/7, Spis malog patenta 1762 U1. 2022;(7):35.
https://hdl.handle.net/21.15107/rcub_gery_1380 .

Radulović, Darko, Radulović, Marko, Milovanović, Željko, Peulić, Aleksandar, Mladenović, Vladimir, "Sistem za praćenje koordinate položaja tela zasnovan na Internet stvarima" in Glasnik intelektualne svojine 2022/7, Spis malog patenta 1762 U1, no. 7 (2022):35,
https://hdl.handle.net/21.15107/rcub_gery_1380 .

TY  - PAT
AU  - Nešić, Aleksa
AU  - Kar, Asutosh
AU  - Peulić, Aleksandar
AU  - Mladenović, Vladimir
PY  - 2022
UR  - https://worldwide.espacenet.com/patent/search?q=pn%3DRS1753U1
UR  - http://gery.gef.bg.ac.rs/handle/123456789/1379
AB  - MicroCloud sistem za skladištenje podataka putem internet mreže sastoji se od Raspberry Pi računara (1) koji je povezan preko žičanog kabla (2) sa ruter uređajem (3), ruter uređaj (3) je povezan sa internet mrežom (5) žičanim kablom (4), mobilni telefon (7) je bežičnom vezom (6) povezan na ruter uređaj (3). PC računar (9) je žičanim kablom (8) povezan na internet mrežu (5), kao i laptop računar (11) koji je na isti način povezan žičanim kablom (10) na internet mrežu (5). Mobilni telefon (15) je bežičnom vezom (14) povezan na baznu stanicu (13) preko koje ostvaruje vezu sa internet mrežom (5) preko žičanog kabla (12).
PB  - Beograd : Zavod za intelektualnu svojinu 
T2  - Glasnik intelektualne svojine 2022/4, Spis malog patenta 1753 U1
T1  - MicroCloud sistem za skladištenje podataka putem internet mreže
T1  - Microcloud system for storing data via the internet
IS  - 4
SP  - 46
UR  - https://hdl.handle.net/21.15107/rcub_gery_1379
ER  - 

@misc{
author = "Nešić, Aleksa and Kar, Asutosh and Peulić, Aleksandar and Mladenović, Vladimir",
year = "2022",
abstract = "MicroCloud sistem za skladištenje podataka putem internet mreže sastoji se od Raspberry Pi računara (1) koji je povezan preko žičanog kabla (2) sa ruter uređajem (3), ruter uređaj (3) je povezan sa internet mrežom (5) žičanim kablom (4), mobilni telefon (7) je bežičnom vezom (6) povezan na ruter uređaj (3). PC računar (9) je žičanim kablom (8) povezan na internet mrežu (5), kao i laptop računar (11) koji je na isti način povezan žičanim kablom (10) na internet mrežu (5). Mobilni telefon (15) je bežičnom vezom (14) povezan na baznu stanicu (13) preko koje ostvaruje vezu sa internet mrežom (5) preko žičanog kabla (12).",
publisher = "Beograd : Zavod za intelektualnu svojinu ",
journal = "Glasnik intelektualne svojine 2022/4, Spis malog patenta 1753 U1",
title = "MicroCloud sistem za skladištenje podataka putem internet mreže, Microcloud system for storing data via the internet",
number = "4",
pages = "46",
url = "https://hdl.handle.net/21.15107/rcub_gery_1379"
}

Nešić, A., Kar, A., Peulić, A.,& Mladenović, V.. (2022). MicroCloud sistem za skladištenje podataka putem internet mreže. in Glasnik intelektualne svojine 2022/4, Spis malog patenta 1753 U1
Beograd : Zavod za intelektualnu svojinu .(4), 46.
https://hdl.handle.net/21.15107/rcub_gery_1379

Nešić A, Kar A, Peulić A, Mladenović V. MicroCloud sistem za skladištenje podataka putem internet mreže. in Glasnik intelektualne svojine 2022/4, Spis malog patenta 1753 U1. 2022;(4):46.
https://hdl.handle.net/21.15107/rcub_gery_1379 .

Nešić, Aleksa, Kar, Asutosh, Peulić, Aleksandar, Mladenović, Vladimir, "MicroCloud sistem za skladištenje podataka putem internet mreže" in Glasnik intelektualne svojine 2022/4, Spis malog patenta 1753 U1, no. 4 (2022):46,
https://hdl.handle.net/21.15107/rcub_gery_1379 .

TY  - CONF
AU  - Stojković, Sanja
AU  - Peulić, Aleksandar S.
AU  - Jovanović, Dušica
PY  - 2022
UR  - http://gery.gef.bg.ac.rs/handle/123456789/1405
AB  - U poslednjoj deceniji volonterske geografske informacije (VGI) postaju sve značajnije kako za globalnu GIS (geografski informacioni sistem) zajednicu tako i za društvo u celini. Njihov značaj prvenstveno se ogleda u uključivanju volontera u proces kreiranja, prikupljanja i širenja geografskih informacija putem veba. Građani upotrebljavaju ručne uređaje da prikupljaju geografske informacije koristeći kartografske interfejse zasnovane na vebu da markiraju geografske objekte, pojave i procese ili da dodaju geolokacije fotografijama, video zapisima, tekstu itd. koji se dele na mreži. Ovakvo uzajamno prožimanje novih interaktivnih tehnologija zasnovanih na vebu sa rastućom količinom sadržaja koje generišu građani i koji se distribuiraju na internetu generiše potpuno novi oblik geografskih informacija. Jedno od ključnih pitanja upotrebe VGI je pitanje tačnosti tako dobijenih informacija jer „građani kao senzori” najčešće imaju vrlo malo formalnih kvalifikacija za ovakav vid prikupljanja podataka. Cilj rada je da se ukaže na potencijale i ograničenja upotrebe VGI u uređenju prostora i naselja kroz identifikaciju sadržaja i karakteristika VGI, neophodnih tehnologija i novonastalih društvenih i političkih pitanja koje VGI sve više pokreće. U radu je dat i osvrt na jedinstveni Ekološki informacioni sistem, koji predstavlja najnoviji primer upotrebe VGI u lokalnim samoupravama na teritoriji Republike Srbije.
PB  - Beograd : Asocijacija prostornih planera Srbije
PB  - Beograd : Univerzitet u Beogradu - Geografski fakultet
C3  - Zbornik radova Devetog naučno-stručnog skupa sa međunarodnim učešćem "Lokalna samouprava u planiranju i uređenju prostora i naselja", Veliko Gradište
T1  - Volonterske geografske informacije u funkciji uređenja prostora na lokalnom nivou
SP  - 485
EP  - 491
UR  - https://hdl.handle.net/21.15107/rcub_gery_1405
ER  - 

@conference{
author = "Stojković, Sanja and Peulić, Aleksandar S. and Jovanović, Dušica",
year = "2022",
abstract = "U poslednjoj deceniji volonterske geografske informacije (VGI) postaju sve značajnije kako za globalnu GIS (geografski informacioni sistem) zajednicu tako i za društvo u celini. Njihov značaj prvenstveno se ogleda u uključivanju volontera u proces kreiranja, prikupljanja i širenja geografskih informacija putem veba. Građani upotrebljavaju ručne uređaje da prikupljaju geografske informacije koristeći kartografske interfejse zasnovane na vebu da markiraju geografske objekte, pojave i procese ili da dodaju geolokacije fotografijama, video zapisima, tekstu itd. koji se dele na mreži. Ovakvo uzajamno prožimanje novih interaktivnih tehnologija zasnovanih na vebu sa rastućom količinom sadržaja koje generišu građani i koji se distribuiraju na internetu generiše potpuno novi oblik geografskih informacija. Jedno od ključnih pitanja upotrebe VGI je pitanje tačnosti tako dobijenih informacija jer „građani kao senzori” najčešće imaju vrlo malo formalnih kvalifikacija za ovakav vid prikupljanja podataka. Cilj rada je da se ukaže na potencijale i ograničenja upotrebe VGI u uređenju prostora i naselja kroz identifikaciju sadržaja i karakteristika VGI, neophodnih tehnologija i novonastalih društvenih i političkih pitanja koje VGI sve više pokreće. U radu je dat i osvrt na jedinstveni Ekološki informacioni sistem, koji predstavlja najnoviji primer upotrebe VGI u lokalnim samoupravama na teritoriji Republike Srbije.",
publisher = "Beograd : Asocijacija prostornih planera Srbije, Beograd : Univerzitet u Beogradu - Geografski fakultet",
journal = "Zbornik radova Devetog naučno-stručnog skupa sa međunarodnim učešćem "Lokalna samouprava u planiranju i uređenju prostora i naselja", Veliko Gradište",
title = "Volonterske geografske informacije u funkciji uređenja prostora na lokalnom nivou",
pages = "485-491",
url = "https://hdl.handle.net/21.15107/rcub_gery_1405"
}

Stojković, S., Peulić, A. S.,& Jovanović, D.. (2022). Volonterske geografske informacije u funkciji uređenja prostora na lokalnom nivou. in Zbornik radova Devetog naučno-stručnog skupa sa međunarodnim učešćem "Lokalna samouprava u planiranju i uređenju prostora i naselja", Veliko Gradište
Beograd : Asocijacija prostornih planera Srbije., 485-491.
https://hdl.handle.net/21.15107/rcub_gery_1405

Stojković S, Peulić AS, Jovanović D. Volonterske geografske informacije u funkciji uređenja prostora na lokalnom nivou. in Zbornik radova Devetog naučno-stručnog skupa sa međunarodnim učešćem "Lokalna samouprava u planiranju i uređenju prostora i naselja", Veliko Gradište. 2022;:485-491.
https://hdl.handle.net/21.15107/rcub_gery_1405 .

Stojković, Sanja, Peulić, Aleksandar S., Jovanović, Dušica, "Volonterske geografske informacije u funkciji uređenja prostora na lokalnom nivou" in Zbornik radova Devetog naučno-stručnog skupa sa međunarodnim učešćem "Lokalna samouprava u planiranju i uređenju prostora i naselja", Veliko Gradište (2022):485-491,
https://hdl.handle.net/21.15107/rcub_gery_1405 .

TY  - JOUR
AU  - Isailović, Velibor
AU  - Peulić, Aleksandar
AU  - Đapan, Marko
AU  - Savković, Marija
AU  - Vukićević, Arso M.
PY  - 2022
UR  - http://gery.gef.bg.ac.rs/handle/123456789/1218
AB  - The compliance of industrial personal protective equipment (PPE) still represents a challenging problem considering size of industrial halls and number of employees that operate within them. Since there is a high variability of PPE types/designs that could be used for protecting various body parts and physiological functions, this study was focused on assessing the use of computer vision algorithms to automate the compliance of head-mounted PPE. As a solution, we propose a pipeline that couples the head ROI estimation with the PPE detection. Compared to alternative approaches, it excludes false positive cases while it largely speeds up data collection and labeling. A comprehensive dataset was created by merging public datasets PictorPPE and Roboflow with author’s collected images, containing twelve different types of PPE was used for the development and assessment of three deep learning architectures (Faster R-CNN, MobileNetV2-SSD and YOLOv5)—which in literature were studied only separately. The obtained results indicated that various deep learning architectures reached different performances for the compliance of various PPE types—while the YOLOv5 slightly outperformed considered alternatives (precision 0.920 ± 0.147, and recall 0.611 ± 0.287). It is concluded that further studies on the topic should invest more effort into assessing various deep learning architectures in order to objectively find the optimal ones for the compliance of a particular PPE type. Considering the present technological and data privacy barriers, the proposed solution may be applicable for the PPE compliance at certain checkpoints where employees can confirm their identity.
PB  - Nature Research
T2  - Scientific Reports
T1  - The compliance of head-mounted industrial PPE by using deep learning object detectors
VL  - 12
SP  - 16347
DO  - 10.1038/s41598-022-20282-9
ER  - 

@article{
author = "Isailović, Velibor and Peulić, Aleksandar and Đapan, Marko and Savković, Marija and Vukićević, Arso M.",
year = "2022",
abstract = "The compliance of industrial personal protective equipment (PPE) still represents a challenging problem considering size of industrial halls and number of employees that operate within them. Since there is a high variability of PPE types/designs that could be used for protecting various body parts and physiological functions, this study was focused on assessing the use of computer vision algorithms to automate the compliance of head-mounted PPE. As a solution, we propose a pipeline that couples the head ROI estimation with the PPE detection. Compared to alternative approaches, it excludes false positive cases while it largely speeds up data collection and labeling. A comprehensive dataset was created by merging public datasets PictorPPE and Roboflow with author’s collected images, containing twelve different types of PPE was used for the development and assessment of three deep learning architectures (Faster R-CNN, MobileNetV2-SSD and YOLOv5)—which in literature were studied only separately. The obtained results indicated that various deep learning architectures reached different performances for the compliance of various PPE types—while the YOLOv5 slightly outperformed considered alternatives (precision 0.920 ± 0.147, and recall 0.611 ± 0.287). It is concluded that further studies on the topic should invest more effort into assessing various deep learning architectures in order to objectively find the optimal ones for the compliance of a particular PPE type. Considering the present technological and data privacy barriers, the proposed solution may be applicable for the PPE compliance at certain checkpoints where employees can confirm their identity.",
publisher = "Nature Research",
journal = "Scientific Reports",
title = "The compliance of head-mounted industrial PPE by using deep learning object detectors",
volume = "12",
pages = "16347",
doi = "10.1038/s41598-022-20282-9"
}

Isailović, V., Peulić, A., Đapan, M., Savković, M.,& Vukićević, A. M.. (2022). The compliance of head-mounted industrial PPE by using deep learning object detectors. in Scientific Reports
Nature Research., 12, 16347.
https://doi.org/10.1038/s41598-022-20282-9

Isailović V, Peulić A, Đapan M, Savković M, Vukićević AM. The compliance of head-mounted industrial PPE by using deep learning object detectors. in Scientific Reports. 2022;12:16347.
doi:10.1038/s41598-022-20282-9 .

Isailović, Velibor, Peulić, Aleksandar, Đapan, Marko, Savković, Marija, Vukićević, Arso M., "The compliance of head-mounted industrial PPE by using deep learning object detectors" in Scientific Reports, 12 (2022):16347,
https://doi.org/10.1038/s41598-022-20282-9 . .

TY  - JOUR
AU  - Petrović, Miloš
AU  - Vukićević, Arso M.
AU  - Đapan, Marko
AU  - Peulić, Aleksandar
AU  - Jovičić, Miloš
AU  - Mijailović, Nikola
AU  - Milovanović, Petar
AU  - Grajić, Mirko
AU  - Savković, Marija
AU  - Caiazzo, Carlo
AU  - Isailović, Velibor
AU  - Mačužić, Ivan
AU  - Jovanović, Kosta
PY  - 2022
UR  - http://gery.gef.bg.ac.rs/handle/123456789/1217
AB  - Non-ergonomic execution of repetitive physical tasks represents a major cause of work-related musculoskeletal disorders (WMSD). This study was focused on the pushing and pulling (P&P) of an industrial handcart (which is a generic physical task present across many industries), with the aim to investigate the dependence of P&P execution on the operators’ psychological status and the presence of pain syndromes of the upper limbs and spine. The developed acquisition system integrated two three-axis force sensors (placed on the left and right arm) and six electromyography (EMG) electrodes (placed on the chest, back, and hand flexor muscles). The conducted experiment involved two groups of participants (with and without increased psychological scores and pain syndromes). Ten force parameters (for both left and right side), one EMG parameter (for three different muscles, both left and right side), and two time-domain parameters were extracted from the acquired signals. Data analysis showed intergroup differences in the examined parameters, especially in force integral values and EMG mean absolute values. To the best of our knowledge, this is the first study that evaluated the composite effects of pain syndromes, spine mobility, and psychological status of the participants on the execution of P&P tasks—concluding that they have a significant impact on the P&P task execution and potentially on the risk of WMSD. The future work will be directed towards the development of a personalized risk assessment system by considering more muscle groups, supplementary data derived from operators’ poses (extracted with computer vision algorithms), and cognitive parameters (extracted with EEG sensors).
PB  - MDIP, Basel
T2  - Sensors
T1  - Experimental Analysis of Handcart Pushing and Pulling Safety in an Industrial Environment by Using IoT Force and EMG Sensors: Relationship with Operators’ Psychological Status and Pain Syndromes
VL  - 22
IS  - 19
SP  - 7467
DO  - 10.3390/s22197467
ER  - 

@article{
author = "Petrović, Miloš and Vukićević, Arso M. and Đapan, Marko and Peulić, Aleksandar and Jovičić, Miloš and Mijailović, Nikola and Milovanović, Petar and Grajić, Mirko and Savković, Marija and Caiazzo, Carlo and Isailović, Velibor and Mačužić, Ivan and Jovanović, Kosta",
year = "2022",
abstract = "Non-ergonomic execution of repetitive physical tasks represents a major cause of work-related musculoskeletal disorders (WMSD). This study was focused on the pushing and pulling (P&P) of an industrial handcart (which is a generic physical task present across many industries), with the aim to investigate the dependence of P&P execution on the operators’ psychological status and the presence of pain syndromes of the upper limbs and spine. The developed acquisition system integrated two three-axis force sensors (placed on the left and right arm) and six electromyography (EMG) electrodes (placed on the chest, back, and hand flexor muscles). The conducted experiment involved two groups of participants (with and without increased psychological scores and pain syndromes). Ten force parameters (for both left and right side), one EMG parameter (for three different muscles, both left and right side), and two time-domain parameters were extracted from the acquired signals. Data analysis showed intergroup differences in the examined parameters, especially in force integral values and EMG mean absolute values. To the best of our knowledge, this is the first study that evaluated the composite effects of pain syndromes, spine mobility, and psychological status of the participants on the execution of P&P tasks—concluding that they have a significant impact on the P&P task execution and potentially on the risk of WMSD. The future work will be directed towards the development of a personalized risk assessment system by considering more muscle groups, supplementary data derived from operators’ poses (extracted with computer vision algorithms), and cognitive parameters (extracted with EEG sensors).",
publisher = "MDIP, Basel",
journal = "Sensors",
title = "Experimental Analysis of Handcart Pushing and Pulling Safety in an Industrial Environment by Using IoT Force and EMG Sensors: Relationship with Operators’ Psychological Status and Pain Syndromes",
volume = "22",
number = "19",
pages = "7467",
doi = "10.3390/s22197467"
}

Petrović, M., Vukićević, A. M., Đapan, M., Peulić, A., Jovičić, M., Mijailović, N., Milovanović, P., Grajić, M., Savković, M., Caiazzo, C., Isailović, V., Mačužić, I.,& Jovanović, K.. (2022). Experimental Analysis of Handcart Pushing and Pulling Safety in an Industrial Environment by Using IoT Force and EMG Sensors: Relationship with Operators’ Psychological Status and Pain Syndromes. in Sensors
MDIP, Basel., 22(19), 7467.
https://doi.org/10.3390/s22197467

Petrović M, Vukićević AM, Đapan M, Peulić A, Jovičić M, Mijailović N, Milovanović P, Grajić M, Savković M, Caiazzo C, Isailović V, Mačužić I, Jovanović K. Experimental Analysis of Handcart Pushing and Pulling Safety in an Industrial Environment by Using IoT Force and EMG Sensors: Relationship with Operators’ Psychological Status and Pain Syndromes. in Sensors. 2022;22(19):7467.
doi:10.3390/s22197467 .

Petrović, Miloš, Vukićević, Arso M., Đapan, Marko, Peulić, Aleksandar, Jovičić, Miloš, Mijailović, Nikola, Milovanović, Petar, Grajić, Mirko, Savković, Marija, Caiazzo, Carlo, Isailović, Velibor, Mačužić, Ivan, Jovanović, Kosta, "Experimental Analysis of Handcart Pushing and Pulling Safety in an Industrial Environment by Using IoT Force and EMG Sensors: Relationship with Operators’ Psychological Status and Pain Syndromes" in Sensors, 22, no. 19 (2022):7467,
https://doi.org/10.3390/s22197467 . .

TY  - JOUR
AU  - Vagić, Nemanja
AU  - Peulić, Aleksandar
AU  - Stojković, Sanja
PY  - 2022
UR  - http://gery.gef.bg.ac.rs/handle/123456789/1648
AB  - The intensive construction of road infrastructure due to urbanization and industrialization around the world carries with it negative environmental impacts, primarily due to increased emissions of gases, but also due to the separation of natural habitats and ecosystems. In order to overcome this problem, without affecting the mobility of the population, it is necessary to allow wild animals to cross over or below the roads, i.e. to create wildlife crossings, which requires knowledge of the locations where the corridors of animal movements intersect with existing or planned roads. This paper analysis the establishment of a camera system and the application of a deep learning methodology for the automatic identification of animals by species and number, in order to determine locations for the construction of crossings for large wildlife. Also, the paper presents the possibility of using geographic information systems to analyze information obtained by monitoring built wildlife crossings.
PB  - Beograd : Univerzitet u Beogradu - Geografski fakultet
T2  - Zbornik radova - Geografski fakultet Univerziteta u Beogradu
T1  - Object detection in order to determine locations for wildlife crossings
IS  - 70
SP  - 23
EP  - 36
DO  - 10.5937/zrgfub2270023V
ER  - 

@article{
author = "Vagić, Nemanja and Peulić, Aleksandar and Stojković, Sanja",
year = "2022",
abstract = "The intensive construction of road infrastructure due to urbanization and industrialization around the world carries with it negative environmental impacts, primarily due to increased emissions of gases, but also due to the separation of natural habitats and ecosystems. In order to overcome this problem, without affecting the mobility of the population, it is necessary to allow wild animals to cross over or below the roads, i.e. to create wildlife crossings, which requires knowledge of the locations where the corridors of animal movements intersect with existing or planned roads. This paper analysis the establishment of a camera system and the application of a deep learning methodology for the automatic identification of animals by species and number, in order to determine locations for the construction of crossings for large wildlife. Also, the paper presents the possibility of using geographic information systems to analyze information obtained by monitoring built wildlife crossings.",
publisher = "Beograd : Univerzitet u Beogradu - Geografski fakultet",
journal = "Zbornik radova - Geografski fakultet Univerziteta u Beogradu",
title = "Object detection in order to determine locations for wildlife crossings",
number = "70",
pages = "23-36",
doi = "10.5937/zrgfub2270023V"
}

Vagić, N., Peulić, A.,& Stojković, S.. (2022). Object detection in order to determine locations for wildlife crossings. in Zbornik radova - Geografski fakultet Univerziteta u Beogradu
Beograd : Univerzitet u Beogradu - Geografski fakultet.(70), 23-36.
https://doi.org/10.5937/zrgfub2270023V

Vagić N, Peulić A, Stojković S. Object detection in order to determine locations for wildlife crossings. in Zbornik radova - Geografski fakultet Univerziteta u Beogradu. 2022;(70):23-36.
doi:10.5937/zrgfub2270023V .

Vagić, Nemanja, Peulić, Aleksandar, Stojković, Sanja, "Object detection in order to determine locations for wildlife crossings" in Zbornik radova - Geografski fakultet Univerziteta u Beogradu, no. 70 (2022):23-36,
https://doi.org/10.5937/zrgfub2270023V . .

TY  - JOUR
AU  - Vukićević, Arso M.
AU  - Mačužić, Ivan
AU  - Mijailović, Nikola
AU  - Peulić, Aleksandar
AU  - Radović, Miloš
PY  - 2021
UR  - http://gery.gef.bg.ac.rs/handle/123456789/1222
AB  - Pushing and pulling (P&P) are common and repetitive tasks in industry, which non-ergonomic execution is among major causes of musculoskeletal disorders (MSD). The current safety management of P&P assumes restrictions of maximal weight, distance, height – while variable individual parameters (such as the P&P pose ergonomic) remain difficult to account for with the standardized guides. Since manual detection of unsafe P&P acts is subjective and inefficient, the aim of this study was to utilize IoT force sensors and IP cameras to detect unsafe P&P acts timely and objectively. Briefly, after the IoT module detects moments with increased P&P forces, the assessment of pose ergonomics was performed from the employee pose reconstructed with the VIBE algorithm. The experiments showed that turn-points correspond to the high torsion of torso, and that in such moments poses are commonly non ergonomic (although P&P forces are below values defined as critical in previous studies – their momentum cause serious load on the human body). Moreover, the analysis revealed that the loading/unloading of a cargo are also moments of frequent unsafe P&P acts – although they are commonly neglected when studying P&P. The experimental validation of the solution showed good agreement with motion sensors and high potential for monitoring and improving P&P workplace safety. Accordingly, future research will be directed towards: 1) acquisition of P&P data sets for direct recognition and classification of unsafe P&P acts; 2) incorporation of wearable sensors (EMG and EEG) for detecting fatigue and decrease of physical abilities.
PB  - Elsevier
T2  - Expert Systems with Applications
T1  - Assessment of the handcart pushing and pulling safety by using deep learning 3D pose estimation and IoT force sensors
VL  - 183
SP  - 115371
DO  - 10.1016/j.eswa.2021.115371
ER  - 

@article{
author = "Vukićević, Arso M. and Mačužić, Ivan and Mijailović, Nikola and Peulić, Aleksandar and Radović, Miloš",
year = "2021",
abstract = "Pushing and pulling (P&P) are common and repetitive tasks in industry, which non-ergonomic execution is among major causes of musculoskeletal disorders (MSD). The current safety management of P&P assumes restrictions of maximal weight, distance, height – while variable individual parameters (such as the P&P pose ergonomic) remain difficult to account for with the standardized guides. Since manual detection of unsafe P&P acts is subjective and inefficient, the aim of this study was to utilize IoT force sensors and IP cameras to detect unsafe P&P acts timely and objectively. Briefly, after the IoT module detects moments with increased P&P forces, the assessment of pose ergonomics was performed from the employee pose reconstructed with the VIBE algorithm. The experiments showed that turn-points correspond to the high torsion of torso, and that in such moments poses are commonly non ergonomic (although P&P forces are below values defined as critical in previous studies – their momentum cause serious load on the human body). Moreover, the analysis revealed that the loading/unloading of a cargo are also moments of frequent unsafe P&P acts – although they are commonly neglected when studying P&P. The experimental validation of the solution showed good agreement with motion sensors and high potential for monitoring and improving P&P workplace safety. Accordingly, future research will be directed towards: 1) acquisition of P&P data sets for direct recognition and classification of unsafe P&P acts; 2) incorporation of wearable sensors (EMG and EEG) for detecting fatigue and decrease of physical abilities.",
publisher = "Elsevier",
journal = "Expert Systems with Applications",
title = "Assessment of the handcart pushing and pulling safety by using deep learning 3D pose estimation and IoT force sensors",
volume = "183",
pages = "115371",
doi = "10.1016/j.eswa.2021.115371"
}

Vukićević, A. M., Mačužić, I., Mijailović, N., Peulić, A.,& Radović, M.. (2021). Assessment of the handcart pushing and pulling safety by using deep learning 3D pose estimation and IoT force sensors. in Expert Systems with Applications
Elsevier., 183, 115371.
https://doi.org/10.1016/j.eswa.2021.115371

Vukićević AM, Mačužić I, Mijailović N, Peulić A, Radović M. Assessment of the handcart pushing and pulling safety by using deep learning 3D pose estimation and IoT force sensors. in Expert Systems with Applications. 2021;183:115371.
doi:10.1016/j.eswa.2021.115371 .

Vukićević, Arso M., Mačužić, Ivan, Mijailović, Nikola, Peulić, Aleksandar, Radović, Miloš, "Assessment of the handcart pushing and pulling safety by using deep learning 3D pose estimation and IoT force sensors" in Expert Systems with Applications, 183 (2021):115371,
https://doi.org/10.1016/j.eswa.2021.115371 . .

TY  - JOUR
AU  - Šušteršič, Tijana
AU  - Peulić, Miodrag
AU  - Peulić, Aleksandar
PY  - 2021
UR  - http://gery.gef.bg.ac.rs/handle/123456789/1223
AB  - The aim of this study was to create a decision support system for disc hernia diagnostics based on real measurements of foot force values from sensors and fuzzy logic, as well as to implement the system on Field Programmable Gate Array (FPGA). The results show that the created fuzzy logic system had the 92.8% accuracy for pre-operational diagnosis and very high match between the Matlab and FPGA output (94.2% match for pre-operational condition, and 100% match for the post-operational and after physical therapy conditions). Interestingly enough, our system is also able to detect improvements in patient condition after the surgery and physical therapy. The main benefit of using FPGAs in this study is to create an inexpensive, portable expert system for real time acquisition, processing and providing the objective recommendation for disc hernia diagnosis and tracking the condition improvement.
PB  - ComSIS Consortium
T2  - Computer Science and Information Systems
T1  - FPGA implementation of fuzzy medical decision support system for disc hernia diagnosis
VL  - 18
IS  - 3
SP  - 619
EP  - 640
DO  - 10.2298/CSIS200224015S
ER  - 

@article{
author = "Šušteršič, Tijana and Peulić, Miodrag and Peulić, Aleksandar",
year = "2021",
abstract = "The aim of this study was to create a decision support system for disc hernia diagnostics based on real measurements of foot force values from sensors and fuzzy logic, as well as to implement the system on Field Programmable Gate Array (FPGA). The results show that the created fuzzy logic system had the 92.8% accuracy for pre-operational diagnosis and very high match between the Matlab and FPGA output (94.2% match for pre-operational condition, and 100% match for the post-operational and after physical therapy conditions). Interestingly enough, our system is also able to detect improvements in patient condition after the surgery and physical therapy. The main benefit of using FPGAs in this study is to create an inexpensive, portable expert system for real time acquisition, processing and providing the objective recommendation for disc hernia diagnosis and tracking the condition improvement.",
publisher = "ComSIS Consortium",
journal = "Computer Science and Information Systems",
title = "FPGA implementation of fuzzy medical decision support system for disc hernia diagnosis",
volume = "18",
number = "3",
pages = "619-640",
doi = "10.2298/CSIS200224015S"
}

Šušteršič, T., Peulić, M.,& Peulić, A.. (2021). FPGA implementation of fuzzy medical decision support system for disc hernia diagnosis. in Computer Science and Information Systems
ComSIS Consortium., 18(3), 619-640.
https://doi.org/10.2298/CSIS200224015S

Šušteršič T, Peulić M, Peulić A. FPGA implementation of fuzzy medical decision support system for disc hernia diagnosis. in Computer Science and Information Systems. 2021;18(3):619-640.
doi:10.2298/CSIS200224015S .

Šušteršič, Tijana, Peulić, Miodrag, Peulić, Aleksandar, "FPGA implementation of fuzzy medical decision support system for disc hernia diagnosis" in Computer Science and Information Systems, 18, no. 3 (2021):619-640,
https://doi.org/10.2298/CSIS200224015S . .

TY  - JOUR
AU  - Peulić, Aleksandar
AU  - Peulić, Miodrag
AU  - Jovanović, Željko
AU  - Joković, Miloš
AU  - Stojković, Sanja
AU  - Vagić, Nemanja
PY  - 2021
UR  - http://gery.gef.bg.ac.rs/handle/123456789/1221
AB  - This article presents geographic information system usage in transportation management for comfort calculations, analysing vehicle vibration data measured during patient transportation. The main goal of this article is to develop a methodology for automatic discomfort cause recognition (DCR) that may be tested under real life conditions. We analysed differences between uncomfortable locations detected by passengers during patient transportation (according to their subjective opinions) and uncomfortable locations detected by the measurement system. The measuring system is based on the three-axis accelerometer which is used to determine road comfort values for specific locations gathered by a GPS module. The results obtained were compared with data collected by passengers. During driving, when they experienced discomfort, passengers marked locations in near real time using the GIS. The data thus obtained were analysed with the data obtained by DCR. For the first time, the application of GIS provides analytical tools to create spatial data and define spatial data relations that determine comfort. Testing under real conditions, involving three separate cases, shows a high degree of correlation between the results. The proposed system allows dynamic comfort threshold criteria management and provides a visual representation of summarized tabular data.
PB  - John Wiley & Sons, Ltd
T2  - Transactions in GIS
T1  - Locating and categorizing causes of discomfort during transport of patients to medical facilities
VL  - 25
IS  - 6
SP  - 2963
EP  - 2981
DO  - 10.1111/tgis.12797
ER  - 

@article{
author = "Peulić, Aleksandar and Peulić, Miodrag and Jovanović, Željko and Joković, Miloš and Stojković, Sanja and Vagić, Nemanja",
year = "2021",
abstract = "This article presents geographic information system usage in transportation management for comfort calculations, analysing vehicle vibration data measured during patient transportation. The main goal of this article is to develop a methodology for automatic discomfort cause recognition (DCR) that may be tested under real life conditions. We analysed differences between uncomfortable locations detected by passengers during patient transportation (according to their subjective opinions) and uncomfortable locations detected by the measurement system. The measuring system is based on the three-axis accelerometer which is used to determine road comfort values for specific locations gathered by a GPS module. The results obtained were compared with data collected by passengers. During driving, when they experienced discomfort, passengers marked locations in near real time using the GIS. The data thus obtained were analysed with the data obtained by DCR. For the first time, the application of GIS provides analytical tools to create spatial data and define spatial data relations that determine comfort. Testing under real conditions, involving three separate cases, shows a high degree of correlation between the results. The proposed system allows dynamic comfort threshold criteria management and provides a visual representation of summarized tabular data.",
publisher = "John Wiley & Sons, Ltd",
journal = "Transactions in GIS",
title = "Locating and categorizing causes of discomfort during transport of patients to medical facilities",
volume = "25",
number = "6",
pages = "2963-2981",
doi = "10.1111/tgis.12797"
}

Peulić, A., Peulić, M., Jovanović, Ž., Joković, M., Stojković, S.,& Vagić, N.. (2021). Locating and categorizing causes of discomfort during transport of patients to medical facilities. in Transactions in GIS
John Wiley & Sons, Ltd., 25(6), 2963-2981.
https://doi.org/10.1111/tgis.12797

Peulić A, Peulić M, Jovanović Ž, Joković M, Stojković S, Vagić N. Locating and categorizing causes of discomfort during transport of patients to medical facilities. in Transactions in GIS. 2021;25(6):2963-2981.
doi:10.1111/tgis.12797 .

Peulić, Aleksandar, Peulić, Miodrag, Jovanović, Željko, Joković, Miloš, Stojković, Sanja, Vagić, Nemanja, "Locating and categorizing causes of discomfort during transport of patients to medical facilities" in Transactions in GIS, 25, no. 6 (2021):2963-2981,
https://doi.org/10.1111/tgis.12797 . .

TY  - JOUR
AU  - Sustersić, Tijana
AU  - Ranković, Vesna
AU  - Peulić, Miodrag
AU  - Peulić, Aleksandar
PY  - 2020
UR  - https://gery.gef.bg.ac.rs/handle/123456789/1055
AB  - The aim of this research was to analyze objectively the process of disc herniation identification using Bayes Theorem. One of the symptoms of discus hernia is muscle weakness on the foot that is caused by displaced discs in the space of two vertebrae. This fact is used by experts in initial diagnosis of herniated discs and we used it to create non-invasive platform for the same purposes by measuring force values from four sensors placed on both feet (first, second, and fourth metatarsal head as well as the heel). Dataset consisted of several minute force recordings of 56 subjects with discus hernia and 15 healthy individuals during normal standing, standing on forefeet and heels. The subjects were diagnosed by a specialist with either L4/L5 or L5/S1 discus hernia. Collected recordings were processed in several steps including filtering, extraction of forefeet and heel recordings, classification of average values for forefeet, and heel sensors to the groups with or without foot muscle weakness. Application of Bayes Theorem on the attributes of interest showed average 78.3 accuracy with 62.6 sensitivity and 80.9 specificity, while application of naive Bayes Network showed average 83.1 accuracy with 57.6 sensitivity and 88.2 specificity. Very weak or no correlation was observed between gender and disc hernia diagnosis (or obesity type and disc hernia diagnosis). Obtained results show that this method can be used in initial screening of patients and be a supportive tool to doctors to send the same patients for further examination.
PB  - IEEE -Inst Electrical Electronics Engineers Inc, Piscataway
T2  - IEEE Journal of Biomedical and Health Informatics
T1  - An Early Disc Herniation Identification System for Advancement in the Standard Medical Screening Procedure Based on Bayes Theorem
VL  - 24
IS  - 1
SP  - 151
EP  - 159
DO  - 10.1109/JBHI.2019.2899665
UR  - https://hdl.handle.net/21.15107/rcub_gery_1055
ER  - 

@article{
author = "Sustersić, Tijana and Ranković, Vesna and Peulić, Miodrag and Peulić, Aleksandar",
year = "2020",
abstract = "The aim of this research was to analyze objectively the process of disc herniation identification using Bayes Theorem. One of the symptoms of discus hernia is muscle weakness on the foot that is caused by displaced discs in the space of two vertebrae. This fact is used by experts in initial diagnosis of herniated discs and we used it to create non-invasive platform for the same purposes by measuring force values from four sensors placed on both feet (first, second, and fourth metatarsal head as well as the heel). Dataset consisted of several minute force recordings of 56 subjects with discus hernia and 15 healthy individuals during normal standing, standing on forefeet and heels. The subjects were diagnosed by a specialist with either L4/L5 or L5/S1 discus hernia. Collected recordings were processed in several steps including filtering, extraction of forefeet and heel recordings, classification of average values for forefeet, and heel sensors to the groups with or without foot muscle weakness. Application of Bayes Theorem on the attributes of interest showed average 78.3 accuracy with 62.6 sensitivity and 80.9 specificity, while application of naive Bayes Network showed average 83.1 accuracy with 57.6 sensitivity and 88.2 specificity. Very weak or no correlation was observed between gender and disc hernia diagnosis (or obesity type and disc hernia diagnosis). Obtained results show that this method can be used in initial screening of patients and be a supportive tool to doctors to send the same patients for further examination.",
publisher = "IEEE -Inst Electrical Electronics Engineers Inc, Piscataway",
journal = "IEEE Journal of Biomedical and Health Informatics",
title = "An Early Disc Herniation Identification System for Advancement in the Standard Medical Screening Procedure Based on Bayes Theorem",
volume = "24",
number = "1",
pages = "151-159",
doi = "10.1109/JBHI.2019.2899665",
url = "https://hdl.handle.net/21.15107/rcub_gery_1055"
}

Sustersić, T., Ranković, V., Peulić, M.,& Peulić, A.. (2020). An Early Disc Herniation Identification System for Advancement in the Standard Medical Screening Procedure Based on Bayes Theorem. in IEEE Journal of Biomedical and Health Informatics
IEEE -Inst Electrical Electronics Engineers Inc, Piscataway., 24(1), 151-159.
https://doi.org/10.1109/JBHI.2019.2899665
https://hdl.handle.net/21.15107/rcub_gery_1055

Sustersić T, Ranković V, Peulić M, Peulić A. An Early Disc Herniation Identification System for Advancement in the Standard Medical Screening Procedure Based on Bayes Theorem. in IEEE Journal of Biomedical and Health Informatics. 2020;24(1):151-159.
doi:10.1109/JBHI.2019.2899665
https://hdl.handle.net/21.15107/rcub_gery_1055 .

Sustersić, Tijana, Ranković, Vesna, Peulić, Miodrag, Peulić, Aleksandar, "An Early Disc Herniation Identification System for Advancement in the Standard Medical Screening Procedure Based on Bayes Theorem" in IEEE Journal of Biomedical and Health Informatics, 24, no. 1 (2020):151-159,
https://doi.org/10.1109/JBHI.2019.2899665 .,
https://hdl.handle.net/21.15107/rcub_gery_1055 .

TY  - JOUR
AU  - Peulić, Miodrag
AU  - Joković, Miloš
AU  - Sustersić, Tijana
AU  - Peulić, Aleksandar
PY  - 2020
UR  - https://gery.gef.bg.ac.rs/handle/123456789/1052
AB  - The purpose of this study is the application of pressure sensors in diagnostics and evaluation of the accuracy diagnostics of lumbar disc herniation at levels L4/L5 and L5/S1 using the aforementioned platform. The motivation behind the idea to apply the pressure measurement platform is the fact that the motor weakness of plantar and dorsal flexia of the feet is one of the absolute indications for the operative treatment of patients with lumbar disc herniation at the indicated levels. In patients, MRI diagnosis of the lumbosacral spine served as the ground truth in the diagnosis of herniation at L4/L5 and L5/S1 levels. The inclusive criteria for the study were the proven muscle weakness based on manual muscle tests performed prior to surgery, after seven days of surgery and after physical therapy. The results obtained with the manual muscular test were compared with the results obtained using our platform. The study included 33 patients who met the inclusion criteria. The results of the measurements indicate that the application of our platform with pressure sensors has the same sensitivity diagnostics as a manual muscle test, when done preoperatively and postoperatively. After physical therapy, pressure sensors show statistically significantly better sensitivity compared to the clinical manual muscle test. The obtained results are encouraging in the sense that the pressure platform can be an additional diagnostic method for lumbar disc herniation detection and can indicate the effectiveness of operative treatment and physical therapy after operation. The main advantage of the system is the cost; the whole system with platform and sensors is not expensive.
PB  - Hindawi Ltd, London
T2  - Computational and Mathematical Methods In Medicine
T1  - A Noninvasive Assistant System in Diagnosis of Lumbar Disc Herniation
VL  - 2020
DO  - 10.1155/2020/6320126
UR  - https://hdl.handle.net/21.15107/rcub_gery_1052
ER  - 

@article{
author = "Peulić, Miodrag and Joković, Miloš and Sustersić, Tijana and Peulić, Aleksandar",
year = "2020",
abstract = "The purpose of this study is the application of pressure sensors in diagnostics and evaluation of the accuracy diagnostics of lumbar disc herniation at levels L4/L5 and L5/S1 using the aforementioned platform. The motivation behind the idea to apply the pressure measurement platform is the fact that the motor weakness of plantar and dorsal flexia of the feet is one of the absolute indications for the operative treatment of patients with lumbar disc herniation at the indicated levels. In patients, MRI diagnosis of the lumbosacral spine served as the ground truth in the diagnosis of herniation at L4/L5 and L5/S1 levels. The inclusive criteria for the study were the proven muscle weakness based on manual muscle tests performed prior to surgery, after seven days of surgery and after physical therapy. The results obtained with the manual muscular test were compared with the results obtained using our platform. The study included 33 patients who met the inclusion criteria. The results of the measurements indicate that the application of our platform with pressure sensors has the same sensitivity diagnostics as a manual muscle test, when done preoperatively and postoperatively. After physical therapy, pressure sensors show statistically significantly better sensitivity compared to the clinical manual muscle test. The obtained results are encouraging in the sense that the pressure platform can be an additional diagnostic method for lumbar disc herniation detection and can indicate the effectiveness of operative treatment and physical therapy after operation. The main advantage of the system is the cost; the whole system with platform and sensors is not expensive.",
publisher = "Hindawi Ltd, London",
journal = "Computational and Mathematical Methods In Medicine",
title = "A Noninvasive Assistant System in Diagnosis of Lumbar Disc Herniation",
volume = "2020",
doi = "10.1155/2020/6320126",
url = "https://hdl.handle.net/21.15107/rcub_gery_1052"
}

Peulić, M., Joković, M., Sustersić, T.,& Peulić, A.. (2020). A Noninvasive Assistant System in Diagnosis of Lumbar Disc Herniation. in Computational and Mathematical Methods In Medicine
Hindawi Ltd, London., 2020.
https://doi.org/10.1155/2020/6320126
https://hdl.handle.net/21.15107/rcub_gery_1052

Peulić M, Joković M, Sustersić T, Peulić A. A Noninvasive Assistant System in Diagnosis of Lumbar Disc Herniation. in Computational and Mathematical Methods In Medicine. 2020;2020.
doi:10.1155/2020/6320126
https://hdl.handle.net/21.15107/rcub_gery_1052 .

Peulić, Miodrag, Joković, Miloš, Sustersić, Tijana, Peulić, Aleksandar, "A Noninvasive Assistant System in Diagnosis of Lumbar Disc Herniation" in Computational and Mathematical Methods In Medicine, 2020 (2020),
https://doi.org/10.1155/2020/6320126 .,
https://hdl.handle.net/21.15107/rcub_gery_1052 .

TY  - CHAP
AU  - Peulić, Aleksandar S.
AU  - Milanković, Ivan
AU  - Mijailović, Nikola V.
AU  - Filipović, Nenad
PY  - 2019
UR  - http://gery.gef.bg.ac.rs/handle/123456789/1383
AB  - Image segmentation is one of the most common procedures in medical imaging applications. It is also very important task in breast cancer detection. Breast cancer detection procedure based on mammography can be divided into several stages. The first stage is the extraction of region of interest from a breast image, after which the identification of suspicious mass regions, their classification, and comparison with the existing image database follows. It is often the case that already existing image databases have large sets of data for which processing requires a lot of time, thus the acceleration of each of the processing stages in breast cancer detection is a very important issue. Image filtering is also one of the most common and important tasks in image processing applications. It is, in most cases, preprocessing procedure for 3D visualization of an image stack. In order to achieve high-quality 3D visualization of a 2D image stack, it is of particular importance that all the images of the input stack are clear and sharp, thus their filtering should be executed carefully. There are also many algorithms for 3D visualization, so it is important to choose the right one which will execute fast enough and produce satisfied quality. In this chapter, the implementation of the already existing algorithm for region-of-interest-based image segmentation for mammogram images on High-Performance Reconfigurable DataFlow Computers (HPRDC) is proposed. As a DataFlow Engine (DFE) of such HPRDC, Maxeler’s acceleration card is used. The experiments for examining the acceleration of that algorithm on the Reconfigurable DataFlow Computers (RDC) are performed with two types of mammogram images with different resolutions. There were, also, several DFE configurations and each of them gave different acceleration of algorithm execution. Those accelerations are presented and experimental results have been shown good acceleration. Also, image processing using a mean filtering algorithm combined with thresholding and binarization algorithms and 3D visualization of murine lungs using marching cubes method are explained. These algorithms are mapped on the Maxeler’s DFE to significantly increase calculation speed. Optimal algorithm calculation speed was up to 20-fold baseline calculation speed.
PB  - Springer Cham
T2  - Exploring the DataFlow Supercomputing Paradigm: Example Algorithms for Selected Applications
T2  - Part of the book series: Computer Communications and Networks (CCN)
T1  - Biomedical Images Processing Using Maxeler DataFlow Engines
SP  - 197
EP  - 227
DO  - 10.1007/978-3-030-13803-5_7
ER  - 

@inbook{
author = "Peulić, Aleksandar S. and Milanković, Ivan and Mijailović, Nikola V. and Filipović, Nenad",
year = "2019",
abstract = "Image segmentation is one of the most common procedures in medical imaging applications. It is also very important task in breast cancer detection. Breast cancer detection procedure based on mammography can be divided into several stages. The first stage is the extraction of region of interest from a breast image, after which the identification of suspicious mass regions, their classification, and comparison with the existing image database follows. It is often the case that already existing image databases have large sets of data for which processing requires a lot of time, thus the acceleration of each of the processing stages in breast cancer detection is a very important issue. Image filtering is also one of the most common and important tasks in image processing applications. It is, in most cases, preprocessing procedure for 3D visualization of an image stack. In order to achieve high-quality 3D visualization of a 2D image stack, it is of particular importance that all the images of the input stack are clear and sharp, thus their filtering should be executed carefully. There are also many algorithms for 3D visualization, so it is important to choose the right one which will execute fast enough and produce satisfied quality. In this chapter, the implementation of the already existing algorithm for region-of-interest-based image segmentation for mammogram images on High-Performance Reconfigurable DataFlow Computers (HPRDC) is proposed. As a DataFlow Engine (DFE) of such HPRDC, Maxeler’s acceleration card is used. The experiments for examining the acceleration of that algorithm on the Reconfigurable DataFlow Computers (RDC) are performed with two types of mammogram images with different resolutions. There were, also, several DFE configurations and each of them gave different acceleration of algorithm execution. Those accelerations are presented and experimental results have been shown good acceleration. Also, image processing using a mean filtering algorithm combined with thresholding and binarization algorithms and 3D visualization of murine lungs using marching cubes method are explained. These algorithms are mapped on the Maxeler’s DFE to significantly increase calculation speed. Optimal algorithm calculation speed was up to 20-fold baseline calculation speed.",
publisher = "Springer Cham",
journal = "Exploring the DataFlow Supercomputing Paradigm: Example Algorithms for Selected Applications, Part of the book series: Computer Communications and Networks (CCN)",
booktitle = "Biomedical Images Processing Using Maxeler DataFlow Engines",
pages = "197-227",
doi = "10.1007/978-3-030-13803-5_7"
}

Peulić, A. S., Milanković, I., Mijailović, N. V.,& Filipović, N.. (2019). Biomedical Images Processing Using Maxeler DataFlow Engines. in Exploring the DataFlow Supercomputing Paradigm: Example Algorithms for Selected Applications
Springer Cham., 197-227.
https://doi.org/10.1007/978-3-030-13803-5_7

Peulić AS, Milanković I, Mijailović NV, Filipović N. Biomedical Images Processing Using Maxeler DataFlow Engines. in Exploring the DataFlow Supercomputing Paradigm: Example Algorithms for Selected Applications. 2019;:197-227.
doi:10.1007/978-3-030-13803-5_7 .

Peulić, Aleksandar S., Milanković, Ivan, Mijailović, Nikola V., Filipović, Nenad, "Biomedical Images Processing Using Maxeler DataFlow Engines" in Exploring the DataFlow Supercomputing Paradigm: Example Algorithms for Selected Applications (2019):197-227,
https://doi.org/10.1007/978-3-030-13803-5_7 . .

TY  - JOUR
AU  - Sustersić, Tijana
AU  - Peulić, Aleksandar
PY  - 2019
UR  - https://gery.gef.bg.ac.rs/handle/123456789/972
AB  - The aim of this study is to implement an algorithm for face recognition, based on fast fourier transform (FFT), on the field programmable gate array (FPGA) chip. Implemented program included the initialization process of two single-IP-core ROM blocks, each with an image of a human face, which are sent to the real components of two-channel IP CoreFFT block. The result of classification could be displayed in the form of either a word "yes" or "no" on the seven-segment display or the information about the reference to the folder with the found match face. Due to the lack of memory on the chip, the results are discussed based on the results obtained by the simulation, whilst the implemented part of the system included displaying images on VGA monitor and result of the algorithm shown on seven-segment display or realized as a software solution in Matlab. The results show 79% accuracy and the advantage of presented system lies in the possibility of working with images in real time. The results obtained in this study can be a good starting point in the implementation of complex algorithms for face recognition using all the benefits that FPGAs offer.
PB  - World Scientific Publ Co Pte Ltd, Singapore
T2  - Journal of Circuits Systems and Computers
T1  - Implementation of Face Recognition Algorithm on Field Programmable Gate Array (FPGA)
VL  - 28
IS  - 8
DO  - 10.1142/S0218126619501299
UR  - https://hdl.handle.net/21.15107/rcub_gery_972
ER  - 

@article{
author = "Sustersić, Tijana and Peulić, Aleksandar",
year = "2019",
abstract = "The aim of this study is to implement an algorithm for face recognition, based on fast fourier transform (FFT), on the field programmable gate array (FPGA) chip. Implemented program included the initialization process of two single-IP-core ROM blocks, each with an image of a human face, which are sent to the real components of two-channel IP CoreFFT block. The result of classification could be displayed in the form of either a word "yes" or "no" on the seven-segment display or the information about the reference to the folder with the found match face. Due to the lack of memory on the chip, the results are discussed based on the results obtained by the simulation, whilst the implemented part of the system included displaying images on VGA monitor and result of the algorithm shown on seven-segment display or realized as a software solution in Matlab. The results show 79% accuracy and the advantage of presented system lies in the possibility of working with images in real time. The results obtained in this study can be a good starting point in the implementation of complex algorithms for face recognition using all the benefits that FPGAs offer.",
publisher = "World Scientific Publ Co Pte Ltd, Singapore",
journal = "Journal of Circuits Systems and Computers",
title = "Implementation of Face Recognition Algorithm on Field Programmable Gate Array (FPGA)",
volume = "28",
number = "8",
doi = "10.1142/S0218126619501299",
url = "https://hdl.handle.net/21.15107/rcub_gery_972"
}

Sustersić, T.,& Peulić, A.. (2019). Implementation of Face Recognition Algorithm on Field Programmable Gate Array (FPGA). in Journal of Circuits Systems and Computers
World Scientific Publ Co Pte Ltd, Singapore., 28(8).
https://doi.org/10.1142/S0218126619501299
https://hdl.handle.net/21.15107/rcub_gery_972

Sustersić T, Peulić A. Implementation of Face Recognition Algorithm on Field Programmable Gate Array (FPGA). in Journal of Circuits Systems and Computers. 2019;28(8).
doi:10.1142/S0218126619501299
https://hdl.handle.net/21.15107/rcub_gery_972 .

Sustersić, Tijana, Peulić, Aleksandar, "Implementation of Face Recognition Algorithm on Field Programmable Gate Array (FPGA)" in Journal of Circuits Systems and Computers, 28, no. 8 (2019),
https://doi.org/10.1142/S0218126619501299 .,
https://hdl.handle.net/21.15107/rcub_gery_972 .

TY  - JOUR
AU  - Peulić, Aleksandar
AU  - Sustersić, Tijana
AU  - Peulić, Miodrag
PY  - 2019
UR  - https://gery.gef.bg.ac.rs/handle/123456789/971
AB  - This paper presents the improved technique for classification of the type of lumbar discus hernia based on fuzzy logic. The reduced mobility of the foot is one of the symptoms of the disease that occurs because of the displaced discs in the space of two vertebrae. This fact was used for non-invasive discus hernia diagnosis by measuring force values from four sensors placed on both feet (first, second and fourth metatarsal head as well as the heel). Hardware and software systems were constructed for the doctor to perform the measurements and have a graphical representation during the measuring procedure. The procedure included measuring force values of 18 subjects during normal standing, standing on forefeet and heels. All subjects were diagnosed by a specialist with either L4/L5 or L5/S1 discus hernia. Filtering and further preprocessing of acquired values included separation of forefeet and heel segments that were used as inputs to fuzzy system. The results showed that the accuracy of such a fuzzy system was around 72%, and the proposed system correctly recognizes healthy individuals. Obtained information about forces on characteristic points on the foot represents useful data in diagnosis which further can be processed in order to be a supportive tool to doctors.
PB  - Walter De Gruyter Gmbh, Berlin
T2  - Biomedical Engineering-Biomedizinische Technik
T1  - Non-invasive improved technique for lumbar discus hernia classification based on fuzzy logic
VL  - 64
IS  - 4
SP  - 421
EP  - 428
DO  - 10.1515/bmt-2018-0013
UR  - https://hdl.handle.net/21.15107/rcub_gery_971
ER  - 

@article{
author = "Peulić, Aleksandar and Sustersić, Tijana and Peulić, Miodrag",
year = "2019",
abstract = "This paper presents the improved technique for classification of the type of lumbar discus hernia based on fuzzy logic. The reduced mobility of the foot is one of the symptoms of the disease that occurs because of the displaced discs in the space of two vertebrae. This fact was used for non-invasive discus hernia diagnosis by measuring force values from four sensors placed on both feet (first, second and fourth metatarsal head as well as the heel). Hardware and software systems were constructed for the doctor to perform the measurements and have a graphical representation during the measuring procedure. The procedure included measuring force values of 18 subjects during normal standing, standing on forefeet and heels. All subjects were diagnosed by a specialist with either L4/L5 or L5/S1 discus hernia. Filtering and further preprocessing of acquired values included separation of forefeet and heel segments that were used as inputs to fuzzy system. The results showed that the accuracy of such a fuzzy system was around 72%, and the proposed system correctly recognizes healthy individuals. Obtained information about forces on characteristic points on the foot represents useful data in diagnosis which further can be processed in order to be a supportive tool to doctors.",
publisher = "Walter De Gruyter Gmbh, Berlin",
journal = "Biomedical Engineering-Biomedizinische Technik",
title = "Non-invasive improved technique for lumbar discus hernia classification based on fuzzy logic",
volume = "64",
number = "4",
pages = "421-428",
doi = "10.1515/bmt-2018-0013",
url = "https://hdl.handle.net/21.15107/rcub_gery_971"
}

Peulić, A., Sustersić, T.,& Peulić, M.. (2019). Non-invasive improved technique for lumbar discus hernia classification based on fuzzy logic. in Biomedical Engineering-Biomedizinische Technik
Walter De Gruyter Gmbh, Berlin., 64(4), 421-428.
https://doi.org/10.1515/bmt-2018-0013
https://hdl.handle.net/21.15107/rcub_gery_971

Peulić A, Sustersić T, Peulić M. Non-invasive improved technique for lumbar discus hernia classification based on fuzzy logic. in Biomedical Engineering-Biomedizinische Technik. 2019;64(4):421-428.
doi:10.1515/bmt-2018-0013
https://hdl.handle.net/21.15107/rcub_gery_971 .

Peulić, Aleksandar, Sustersić, Tijana, Peulić, Miodrag, "Non-invasive improved technique for lumbar discus hernia classification based on fuzzy logic" in Biomedical Engineering-Biomedizinische Technik, 64, no. 4 (2019):421-428,
https://doi.org/10.1515/bmt-2018-0013 .,
https://hdl.handle.net/21.15107/rcub_gery_971 .

TY  - JOUR
AU  - Jovanović, Željko
AU  - Milošević, Marina
AU  - Janković, Dragan
AU  - Peulić, Aleksandar
PY  - 2019
UR  - https://gery.gef.bg.ac.rs/handle/123456789/970
AB  - BACKGROUND: Passenger comfort is affected by many factors. Patient comfort is even more specific due to its mental and physical health condition. OBJECTIVE: Developing a system for monitoring patient transport conditions with the comfort level classification, which is affected by the patient parameters. METHODS: Smartphone with the developed Android application was installed in an EMS to monitor patient transport between medical institutions. As a result, 10 calculated parameters are generated in addition to the GPS data and the subjective comfort level. Three classifiers are used to classify the transportation. At the end, the adjustment of classified comfort levels is performed based on the patient's medical condition, age and gender. RESULTS: Modified SVM classifier provided the best overall classification results with the precision of 90.8%. Furthermore, a model that represents patient sensitivity to transport vibration, based on the patient's medical condition, is proposed and the final classification results are presented. CONCLUSIONS: The Android application is mobile, simple to install and use. According to the obtained results, SVM and Naive Bayes classifier gave satisfying results while KNN should be avoided. The developed model takes transport comfort and the patient's medical condition into consideration, so it is suitable for the patient transport comfort classification.
PB  - IOS Press, Amsterdam
T2  - Technology and Health Care
T1  - Comfort level classification during patients transport
VL  - 27
IS  - 1
SP  - 61
EP  - 77
DO  - 10.3233/THC-181411
UR  - https://hdl.handle.net/21.15107/rcub_gery_970
ER  - 

@article{
author = "Jovanović, Željko and Milošević, Marina and Janković, Dragan and Peulić, Aleksandar",
year = "2019",
abstract = "BACKGROUND: Passenger comfort is affected by many factors. Patient comfort is even more specific due to its mental and physical health condition. OBJECTIVE: Developing a system for monitoring patient transport conditions with the comfort level classification, which is affected by the patient parameters. METHODS: Smartphone with the developed Android application was installed in an EMS to monitor patient transport between medical institutions. As a result, 10 calculated parameters are generated in addition to the GPS data and the subjective comfort level. Three classifiers are used to classify the transportation. At the end, the adjustment of classified comfort levels is performed based on the patient's medical condition, age and gender. RESULTS: Modified SVM classifier provided the best overall classification results with the precision of 90.8%. Furthermore, a model that represents patient sensitivity to transport vibration, based on the patient's medical condition, is proposed and the final classification results are presented. CONCLUSIONS: The Android application is mobile, simple to install and use. According to the obtained results, SVM and Naive Bayes classifier gave satisfying results while KNN should be avoided. The developed model takes transport comfort and the patient's medical condition into consideration, so it is suitable for the patient transport comfort classification.",
publisher = "IOS Press, Amsterdam",
journal = "Technology and Health Care",
title = "Comfort level classification during patients transport",
volume = "27",
number = "1",
pages = "61-77",
doi = "10.3233/THC-181411",
url = "https://hdl.handle.net/21.15107/rcub_gery_970"
}

Jovanović, Ž., Milošević, M., Janković, D.,& Peulić, A.. (2019). Comfort level classification during patients transport. in Technology and Health Care
IOS Press, Amsterdam., 27(1), 61-77.
https://doi.org/10.3233/THC-181411
https://hdl.handle.net/21.15107/rcub_gery_970

Jovanović Ž, Milošević M, Janković D, Peulić A. Comfort level classification during patients transport. in Technology and Health Care. 2019;27(1):61-77.
doi:10.3233/THC-181411
https://hdl.handle.net/21.15107/rcub_gery_970 .

Jovanović, Željko, Milošević, Marina, Janković, Dragan, Peulić, Aleksandar, "Comfort level classification during patients transport" in Technology and Health Care, 27, no. 1 (2019):61-77,
https://doi.org/10.3233/THC-181411 .,
https://hdl.handle.net/21.15107/rcub_gery_970 .

TY  - JOUR
AU  - Jovanović, Željko
AU  - Blagojević, Maria
AU  - Janković, Dragan
AU  - Peulić, Aleksandar
PY  - 2019
UR  - https://gery.gef.bg.ac.rs/handle/123456789/969
AB  - Since patient comfort during transport is a matter of paramount importance, this paper aims to determine the possibilities of applying neural networks for its prediction and monitoring. Specific objectives of the research include monitoring and predicting patient transport comfort, with subjective assessment of comfort by medical personnel. An original Android application that collects signals from an accelerometer and a GPS sensor was used with the aim of achieving the research goals. The collected signals were processed and a total of twelve parameters were calculated. A multilayer perceptron was created in the proposed research. The evaluation results indicate acceptable accuracy and give the possibility to apply the same model to the next patient transport. The root mean square error was 0.0215 and the overall confusion matrix prediction accuracy was 90.07%. Moreover, the results were validated in real usage. The limitations and future work are highlighted.
PB  - Tubitak Scientific & Technical Research Council Turkey, Ankara
T2  - Turkish Journal of Electrical Engineering and Computer Sciences
T1  - Patient comfort level prediction during transport using artificial neural network
VL  - 27
IS  - 4
SP  - 2817
EP  - 2832
DO  - 10.3906/elk-1807-258
UR  - https://hdl.handle.net/21.15107/rcub_gery_969
ER  - 

@article{
author = "Jovanović, Željko and Blagojević, Maria and Janković, Dragan and Peulić, Aleksandar",
year = "2019",
abstract = "Since patient comfort during transport is a matter of paramount importance, this paper aims to determine the possibilities of applying neural networks for its prediction and monitoring. Specific objectives of the research include monitoring and predicting patient transport comfort, with subjective assessment of comfort by medical personnel. An original Android application that collects signals from an accelerometer and a GPS sensor was used with the aim of achieving the research goals. The collected signals were processed and a total of twelve parameters were calculated. A multilayer perceptron was created in the proposed research. The evaluation results indicate acceptable accuracy and give the possibility to apply the same model to the next patient transport. The root mean square error was 0.0215 and the overall confusion matrix prediction accuracy was 90.07%. Moreover, the results were validated in real usage. The limitations and future work are highlighted.",
publisher = "Tubitak Scientific & Technical Research Council Turkey, Ankara",
journal = "Turkish Journal of Electrical Engineering and Computer Sciences",
title = "Patient comfort level prediction during transport using artificial neural network",
volume = "27",
number = "4",
pages = "2817-2832",
doi = "10.3906/elk-1807-258",
url = "https://hdl.handle.net/21.15107/rcub_gery_969"
}

Jovanović, Ž., Blagojević, M., Janković, D.,& Peulić, A.. (2019). Patient comfort level prediction during transport using artificial neural network. in Turkish Journal of Electrical Engineering and Computer Sciences
Tubitak Scientific & Technical Research Council Turkey, Ankara., 27(4), 2817-2832.
https://doi.org/10.3906/elk-1807-258
https://hdl.handle.net/21.15107/rcub_gery_969

Jovanović Ž, Blagojević M, Janković D, Peulić A. Patient comfort level prediction during transport using artificial neural network. in Turkish Journal of Electrical Engineering and Computer Sciences. 2019;27(4):2817-2832.
doi:10.3906/elk-1807-258
https://hdl.handle.net/21.15107/rcub_gery_969 .

Jovanović, Željko, Blagojević, Maria, Janković, Dragan, Peulić, Aleksandar, "Patient comfort level prediction during transport using artificial neural network" in Turkish Journal of Electrical Engineering and Computer Sciences, 27, no. 4 (2019):2817-2832,
https://doi.org/10.3906/elk-1807-258 .,
https://hdl.handle.net/21.15107/rcub_gery_969 .

TY  - CONF
AU  - Mijailović, Nikola V.
AU  - Radaković, Radivoje
AU  - Peulić, Aleksandar
AU  - Vidanović, Neda
AU  - Dimitrijević, Djordje
AU  - Filipović, Nenad
PY  - 2018
UR  - https://gery.gef.bg.ac.rs/handle/123456789/918
AB  - In this paper the basic information about methodology of assessment human body stiffness during vertical jump analysis is presented. Ten subjects (professional football player) perform ten periodic jumps and vertical ground reaction force is measured using a force plate with one axial load cell force sensor. The stiffness calculation is based on the analogy of the periodic jumping and oscillation movement of the system which consists of spring and body appropriate mass. The frequency of oscillation is obtained using Fourier transform.
PB  - Springer Verlag
C3  - Conference proceedings of the International Symposium: Pervasive Computing Paradigms for Mental Health
C3  - Book series: Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering (LNICST)
T1  - Assessment of mechanical stiffness of jumping using force plate
VL  - 207
SP  - 81
EP  - 86
DO  - 10.1007/978-3-319-74935-8_11
UR  - https://hdl.handle.net/21.15107/rcub_gery_918
ER  - 

@conference{
editor = "Oliver, Nuria, Serino, Silvia, Matic, Aleksandar, Cipresso, Pietro, Filipovic, Nenad, Gavrilovska, Liljana",
author = "Mijailović, Nikola V. and Radaković, Radivoje and Peulić, Aleksandar and Vidanović, Neda and Dimitrijević, Djordje and Filipović, Nenad",
year = "2018",
abstract = "In this paper the basic information about methodology of assessment human body stiffness during vertical jump analysis is presented. Ten subjects (professional football player) perform ten periodic jumps and vertical ground reaction force is measured using a force plate with one axial load cell force sensor. The stiffness calculation is based on the analogy of the periodic jumping and oscillation movement of the system which consists of spring and body appropriate mass. The frequency of oscillation is obtained using Fourier transform.",
publisher = "Springer Verlag",
journal = "Conference proceedings of the International Symposium: Pervasive Computing Paradigms for Mental Health, Book series: Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering (LNICST)",
title = "Assessment of mechanical stiffness of jumping using force plate",
volume = "207",
pages = "81-86",
doi = "10.1007/978-3-319-74935-8_11",
url = "https://hdl.handle.net/21.15107/rcub_gery_918"
}

Oliver, N., Serino, S., Matic, A., Cipresso, P., Filipovic, N., Gavrilovska, L., Mijailović, N. V., Radaković, R., Peulić, A., Vidanović, N., Dimitrijević, D.,& Filipović, N.. (2018). Assessment of mechanical stiffness of jumping using force plate. in Conference proceedings of the International Symposium: Pervasive Computing Paradigms for Mental Health
Springer Verlag., 207, 81-86.
https://doi.org/10.1007/978-3-319-74935-8_11
https://hdl.handle.net/21.15107/rcub_gery_918

Oliver N, Serino S, Matic A, Cipresso P, Filipovic N, Gavrilovska L, Mijailović NV, Radaković R, Peulić A, Vidanović N, Dimitrijević D, Filipović N. Assessment of mechanical stiffness of jumping using force plate. in Conference proceedings of the International Symposium: Pervasive Computing Paradigms for Mental Health. 2018;207:81-86.
doi:10.1007/978-3-319-74935-8_11
https://hdl.handle.net/21.15107/rcub_gery_918 .

Oliver, Nuria, Serino, Silvia, Matic, Aleksandar, Cipresso, Pietro, Filipovic, Nenad, Gavrilovska, Liljana, Mijailović, Nikola V., Radaković, Radivoje, Peulić, Aleksandar, Vidanović, Neda, Dimitrijević, Djordje, Filipović, Nenad, "Assessment of mechanical stiffness of jumping using force plate" in Conference proceedings of the International Symposium: Pervasive Computing Paradigms for Mental Health, 207 (2018):81-86,
https://doi.org/10.1007/978-3-319-74935-8_11 .,
https://hdl.handle.net/21.15107/rcub_gery_918 .

TY  - CONF
AU  - Luković, Vanja
AU  - Krneta, Radojka
AU  - Vulović, Ana
AU  - Damnjanović, Đorđe
AU  - Peulić, Aleksandar
AU  - Dimopoulos, Christos
AU  - Katzis, Konstantinos
PY  - 2017
UR  - https://gery.gef.bg.ac.rs/handle/123456789/841
AB  - This paper describes the findings from our study on the parallel usage of Logisim software tool and remote experiment based on Nexys 2 FPGA hardware platform for learning digital circuits design and computer architecture by students of the first and the second-year of Electrical, Computer and Mechatronics Engineering undergraduate study programs at the Faculty of Technical Science Cacak, University of Kragujevac. For the purpose of comparison of the effectiveness of these two learning tools, a survey was conducted between students who used these tools in learning digital circuits design within the course Foundations in Computer Technics 2 during the winter semester of the academic year 2016-2107. Based on analysis of given results some conclusions were drawn regarding to parallel usage of Logisim software tool and remote experiments based on FPGA hardware platform in learning digital circuits design.
PB  - IEEE, New York
C3  - Proceedings of 4th Experiment"International Conference (EXP.At'17)
T1  - Comparison of the effectiveness of Logisim software tool and remote experiments based on Nexys 2 FPGA platform in learning digital circuits design
SP  - 247
EP  - 252
UR  - https://hdl.handle.net/21.15107/rcub_gery_841
ER  - 

@conference{
author = "Luković, Vanja and Krneta, Radojka and Vulović, Ana and Damnjanović, Đorđe and Peulić, Aleksandar and Dimopoulos, Christos and Katzis, Konstantinos",
year = "2017",
abstract = "This paper describes the findings from our study on the parallel usage of Logisim software tool and remote experiment based on Nexys 2 FPGA hardware platform for learning digital circuits design and computer architecture by students of the first and the second-year of Electrical, Computer and Mechatronics Engineering undergraduate study programs at the Faculty of Technical Science Cacak, University of Kragujevac. For the purpose of comparison of the effectiveness of these two learning tools, a survey was conducted between students who used these tools in learning digital circuits design within the course Foundations in Computer Technics 2 during the winter semester of the academic year 2016-2107. Based on analysis of given results some conclusions were drawn regarding to parallel usage of Logisim software tool and remote experiments based on FPGA hardware platform in learning digital circuits design.",
publisher = "IEEE, New York",
journal = "Proceedings of 4th Experiment"International Conference (EXP.At'17)",
title = "Comparison of the effectiveness of Logisim software tool and remote experiments based on Nexys 2 FPGA platform in learning digital circuits design",
pages = "247-252",
url = "https://hdl.handle.net/21.15107/rcub_gery_841"
}

Luković, V., Krneta, R., Vulović, A., Damnjanović, Đ., Peulić, A., Dimopoulos, C.,& Katzis, K.. (2017). Comparison of the effectiveness of Logisim software tool and remote experiments based on Nexys 2 FPGA platform in learning digital circuits design. in Proceedings of 4th Experiment"International Conference (EXP.At'17)
IEEE, New York., 247-252.
https://hdl.handle.net/21.15107/rcub_gery_841

Luković V, Krneta R, Vulović A, Damnjanović Đ, Peulić A, Dimopoulos C, Katzis K. Comparison of the effectiveness of Logisim software tool and remote experiments based on Nexys 2 FPGA platform in learning digital circuits design. in Proceedings of 4th Experiment"International Conference (EXP.At'17). 2017;:247-252.
https://hdl.handle.net/21.15107/rcub_gery_841 .

Luković, Vanja, Krneta, Radojka, Vulović, Ana, Damnjanović, Đorđe, Peulić, Aleksandar, Dimopoulos, Christos, Katzis, Konstantinos, "Comparison of the effectiveness of Logisim software tool and remote experiments based on Nexys 2 FPGA platform in learning digital circuits design" in Proceedings of 4th Experiment"International Conference (EXP.At'17) (2017):247-252,
https://hdl.handle.net/21.15107/rcub_gery_841 .

TY  - JOUR
AU  - Milanković, Ivan L.
AU  - Mijailović, Nikola V.
AU  - Filipović, Nenad
AU  - Peulić, Aleksandar
PY  - 2017
UR  - https://gery.gef.bg.ac.rs/handle/123456789/833
AB  - Image segmentation is one of the most common procedures in medical imaging applications. It is also a very important task in breast cancer detection. Breast cancer detection procedure based on mammography can be divided into several stages. The first stage is the extraction of the region of interest from a breast image, followed by the identification of suspicious mass regions, their classification, and comparison with the existing image database. It is often the case that already existing image databases have large sets of data whose processing requires a lot of time, and thus the acceleration of each of the processing stages in breast cancer detection is a very important issue. In this paper, the implementation of the already existing algorithm for region-of-interest based image segmentation for mammogram images on High-Performance Reconfigurable Dataflow Computers (HPRDCs) is proposed. As a dataflow engine (DFE) of such HPRDC, Maxeler's acceleration card is used. The experiments for examining the acceleration of that algorithm on the Reconfigurable Dataflow Computers (RDCs) are performed with two types of mammogram images with different resolutions. There were, also, several DFE configurations and each of them gave a different acceleration value of algorithm execution. Those acceleration values are presented and experimental results showed good acceleration.
PB  - Hindawi Ltd, London
T2  - Computational and Mathematical Methods In Medicine
T1  - Acceleration of Image Segmentation Algorithm for (Breast) Mammogram Images Using High-Performance Reconfigurable Dataflow Computers
DO  - 10.1155/2017/7909282
UR  - https://hdl.handle.net/21.15107/rcub_gery_833
ER  - 

@article{
author = "Milanković, Ivan L. and Mijailović, Nikola V. and Filipović, Nenad and Peulić, Aleksandar",
year = "2017",
abstract = "Image segmentation is one of the most common procedures in medical imaging applications. It is also a very important task in breast cancer detection. Breast cancer detection procedure based on mammography can be divided into several stages. The first stage is the extraction of the region of interest from a breast image, followed by the identification of suspicious mass regions, their classification, and comparison with the existing image database. It is often the case that already existing image databases have large sets of data whose processing requires a lot of time, and thus the acceleration of each of the processing stages in breast cancer detection is a very important issue. In this paper, the implementation of the already existing algorithm for region-of-interest based image segmentation for mammogram images on High-Performance Reconfigurable Dataflow Computers (HPRDCs) is proposed. As a dataflow engine (DFE) of such HPRDC, Maxeler's acceleration card is used. The experiments for examining the acceleration of that algorithm on the Reconfigurable Dataflow Computers (RDCs) are performed with two types of mammogram images with different resolutions. There were, also, several DFE configurations and each of them gave a different acceleration value of algorithm execution. Those acceleration values are presented and experimental results showed good acceleration.",
publisher = "Hindawi Ltd, London",
journal = "Computational and Mathematical Methods In Medicine",
title = "Acceleration of Image Segmentation Algorithm for (Breast) Mammogram Images Using High-Performance Reconfigurable Dataflow Computers",
doi = "10.1155/2017/7909282",
url = "https://hdl.handle.net/21.15107/rcub_gery_833"
}

Milanković, I. L., Mijailović, N. V., Filipović, N.,& Peulić, A.. (2017). Acceleration of Image Segmentation Algorithm for (Breast) Mammogram Images Using High-Performance Reconfigurable Dataflow Computers. in Computational and Mathematical Methods In Medicine
Hindawi Ltd, London..
https://doi.org/10.1155/2017/7909282
https://hdl.handle.net/21.15107/rcub_gery_833

Milanković IL, Mijailović NV, Filipović N, Peulić A. Acceleration of Image Segmentation Algorithm for (Breast) Mammogram Images Using High-Performance Reconfigurable Dataflow Computers. in Computational and Mathematical Methods In Medicine. 2017;.
doi:10.1155/2017/7909282
https://hdl.handle.net/21.15107/rcub_gery_833 .

Milanković, Ivan L., Mijailović, Nikola V., Filipović, Nenad, Peulić, Aleksandar, "Acceleration of Image Segmentation Algorithm for (Breast) Mammogram Images Using High-Performance Reconfigurable Dataflow Computers" in Computational and Mathematical Methods In Medicine (2017),
https://doi.org/10.1155/2017/7909282 .,
https://hdl.handle.net/21.15107/rcub_gery_833 .

TY  - JOUR
AU  - Đorđević, Nataša
AU  - Paunović, Milica G.
AU  - Peulić, Aleksandar
PY  - 2017
UR  - https://gery.gef.bg.ac.rs/handle/123456789/822
AB  - In recent years, extremely low-frequency electromagnetic field (ELF-EMF) has received considerable attention for its potential biological effects. Numerous studies have shown the role of ELF-EMF in behaviour modulation. The aim of this study was to investigate the effect of short-term ELF-EMF (50 Hz) in the development of anxiety-like behaviour in rats through change hypothalamic oxidative stress and NO. Ten adult male rats (Wistar albino) were divided in two groups: control group-without exposure to ELF-EMF and experimental group-exposed to ELF-EMF during 7 days. After the exposure, time open field test and elevated plus maze were used to evaluate the anxiety-like behaviour of rats. Upon completion of the behavioural tests, concentrations of superoxide anion (O-2 center dot(-)), nitrite (NO2-, as an indicator of NO) and peroxynitrite (ONOO-) were determined in the hypothalamus of the animals. Obtained results show that ELF-EMF both induces anxiety-like behaviour and increases concentrations of O-2 center dot(-) and NO, whereas it did not effect on ONOO- concentration in hypothalamus of rats. In conclusion, the development of anxiety-like behaviour is mediated by oxidative stress and increased NO concentration in hypothalamus of rats exposed to ELF-EMF during 7 days.
PB  - Springer Heidelberg, Heidelberg
T2  - Environmental Science and Pollution Research
T1  - Anxiety-like behavioural effects of extremely low-frequency electromagnetic field in rats
VL  - 24
VL  - 24
IS  - 27
SP  - 21693
EP  - 21699
DO  - 10.1007/s11356-017-9710-1
UR  - https://hdl.handle.net/21.15107/rcub_gery_822
ER  - 

@article{
author = "Đorđević, Nataša and Paunović, Milica G. and Peulić, Aleksandar",
year = "2017",
abstract = "In recent years, extremely low-frequency electromagnetic field (ELF-EMF) has received considerable attention for its potential biological effects. Numerous studies have shown the role of ELF-EMF in behaviour modulation. The aim of this study was to investigate the effect of short-term ELF-EMF (50 Hz) in the development of anxiety-like behaviour in rats through change hypothalamic oxidative stress and NO. Ten adult male rats (Wistar albino) were divided in two groups: control group-without exposure to ELF-EMF and experimental group-exposed to ELF-EMF during 7 days. After the exposure, time open field test and elevated plus maze were used to evaluate the anxiety-like behaviour of rats. Upon completion of the behavioural tests, concentrations of superoxide anion (O-2 center dot(-)), nitrite (NO2-, as an indicator of NO) and peroxynitrite (ONOO-) were determined in the hypothalamus of the animals. Obtained results show that ELF-EMF both induces anxiety-like behaviour and increases concentrations of O-2 center dot(-) and NO, whereas it did not effect on ONOO- concentration in hypothalamus of rats. In conclusion, the development of anxiety-like behaviour is mediated by oxidative stress and increased NO concentration in hypothalamus of rats exposed to ELF-EMF during 7 days.",
publisher = "Springer Heidelberg, Heidelberg",
journal = "Environmental Science and Pollution Research",
title = "Anxiety-like behavioural effects of extremely low-frequency electromagnetic field in rats",
volume = "24, 24",
number = "27",
pages = "21693-21699",
doi = "10.1007/s11356-017-9710-1",
url = "https://hdl.handle.net/21.15107/rcub_gery_822"
}

Đorđević, N., Paunović, M. G.,& Peulić, A.. (2017). Anxiety-like behavioural effects of extremely low-frequency electromagnetic field in rats. in Environmental Science and Pollution Research
Springer Heidelberg, Heidelberg., 24(27), 21693-21699.
https://doi.org/10.1007/s11356-017-9710-1
https://hdl.handle.net/21.15107/rcub_gery_822

Đorđević N, Paunović MG, Peulić A. Anxiety-like behavioural effects of extremely low-frequency electromagnetic field in rats. in Environmental Science and Pollution Research. 2017;24(27):21693-21699.
doi:10.1007/s11356-017-9710-1
https://hdl.handle.net/21.15107/rcub_gery_822 .

Đorđević, Nataša, Paunović, Milica G., Peulić, Aleksandar, "Anxiety-like behavioural effects of extremely low-frequency electromagnetic field in rats" in Environmental Science and Pollution Research, 24, no. 27 (2017):21693-21699,
https://doi.org/10.1007/s11356-017-9710-1 .,
https://hdl.handle.net/21.15107/rcub_gery_822 .