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  - JOUR
AU  - Milošević, Marina
AU  - Janković, Dragan
AU  - Peulić, Aleksandar
PY  - 2015
UR  - https://gery.gef.bg.ac.rs/handle/123456789/718
AB  - In this paper, we present a system based on feature extraction techniques for detecting abnormal patterns in digital mammograms and thermograms. A comparative study of texture-analysis methods is performed for three image groups: mammograms from the Mammographic Image Analysis Society mammographic database; digital mammograms from the local database; and thermography images of the breast. Also, we present a procedure for the automatic separation of the breast region from the mammograms. Computed features based on gray-level co-occurrence matrices are used to evaluate the effectiveness of textural information possessed by mass regions. A total of 20 texture features are extracted from the region of interest. The ability of feature set in differentiating abnormal from normal tissue is investigated using a support vector machine classifier, Naive Bayes classifier and K-Nearest Neighbor classifier. To evaluate the classification performance, five-fold cross-validation method and receiver operating characteristic analysis was performed.
PB  - Walter De Gruyter Gmbh, Berlin
T2  - Biomedical Engineering-Biomedizinische Technik
T1  - Comparative analysis of breast cancer detection in mammograms and thermograms
VL  - 60
IS  - 1
SP  - 49
EP  - 56
DO  - 10.1515/bmt-2014-0047
UR  - https://hdl.handle.net/21.15107/rcub_gery_718
ER  - 

@article{
author = "Milošević, Marina and Janković, Dragan and Peulić, Aleksandar",
year = "2015",
abstract = "In this paper, we present a system based on feature extraction techniques for detecting abnormal patterns in digital mammograms and thermograms. A comparative study of texture-analysis methods is performed for three image groups: mammograms from the Mammographic Image Analysis Society mammographic database; digital mammograms from the local database; and thermography images of the breast. Also, we present a procedure for the automatic separation of the breast region from the mammograms. Computed features based on gray-level co-occurrence matrices are used to evaluate the effectiveness of textural information possessed by mass regions. A total of 20 texture features are extracted from the region of interest. The ability of feature set in differentiating abnormal from normal tissue is investigated using a support vector machine classifier, Naive Bayes classifier and K-Nearest Neighbor classifier. To evaluate the classification performance, five-fold cross-validation method and receiver operating characteristic analysis was performed.",
publisher = "Walter De Gruyter Gmbh, Berlin",
journal = "Biomedical Engineering-Biomedizinische Technik",
title = "Comparative analysis of breast cancer detection in mammograms and thermograms",
volume = "60",
number = "1",
pages = "49-56",
doi = "10.1515/bmt-2014-0047",
url = "https://hdl.handle.net/21.15107/rcub_gery_718"
}

Milošević, M., Janković, D.,& Peulić, A.. (2015). Comparative analysis of breast cancer detection in mammograms and thermograms. in Biomedical Engineering-Biomedizinische Technik
Walter De Gruyter Gmbh, Berlin., 60(1), 49-56.
https://doi.org/10.1515/bmt-2014-0047
https://hdl.handle.net/21.15107/rcub_gery_718

Milošević M, Janković D, Peulić A. Comparative analysis of breast cancer detection in mammograms and thermograms. in Biomedical Engineering-Biomedizinische Technik. 2015;60(1):49-56.
doi:10.1515/bmt-2014-0047
https://hdl.handle.net/21.15107/rcub_gery_718 .

Milošević, Marina, Janković, Dragan, Peulić, Aleksandar, "Comparative analysis of breast cancer detection in mammograms and thermograms" in Biomedical Engineering-Biomedizinische Technik, 60, no. 1 (2015):49-56,
https://doi.org/10.1515/bmt-2014-0047 .,
https://hdl.handle.net/21.15107/rcub_gery_718 .

TY  - JOUR
AU  - Milošević, Marina
AU  - Janković, Dragan
AU  - Peulić, Aleksandar
PY  - 2014
UR  - https://gery.gef.bg.ac.rs/handle/123456789/609
AB  - Microcalcification clusters appear as groups of small, bright particles with arbitrary shapes on mammographic images. They are the earliest sign of breast carcinomas and their detection is the key for improving breast cancer prognosis. But due to the low contrast of microcalcifications and same properties as noise, it is difficult to detect microcalcification. This work is devoted to developing a system for the detection of microcalcification in digital mammograms. After removing noise from mammogram using the Discrete Wavelet Transformation (DWT), we first selected the region of interest (ROI) in order to demarcate the breast region on a mammogram. Segmenting region of interest represents one of the most important stages of mammogram processing procedure. The proposed segmentation method is based on a filtering using the Sobel filter. This process will identify the significant pixels, that belong to edges of microcalcifications. Microcalcifications were detected by increasing the contrast of the images obtained by applying Sobel operator. In order to confirm the effectiveness of this microcalcification segmentation method, the Support Vector Machine (SVM) and k-Nearest Neighborhood (k-NN) algorithm are employed for the classification task using cross-validation technique.
PB  - IOS Press, Amsterdam
T2  - Technology and Health Care
T1  - Segmentation for the enhancement of microcalcifications in digital mammograms
VL  - 22
IS  - 5
SP  - 701
EP  - 715
DO  - 10.3233/THC-140841
UR  - https://hdl.handle.net/21.15107/rcub_gery_609
ER  - 

@article{
author = "Milošević, Marina and Janković, Dragan and Peulić, Aleksandar",
year = "2014",
abstract = "Microcalcification clusters appear as groups of small, bright particles with arbitrary shapes on mammographic images. They are the earliest sign of breast carcinomas and their detection is the key for improving breast cancer prognosis. But due to the low contrast of microcalcifications and same properties as noise, it is difficult to detect microcalcification. This work is devoted to developing a system for the detection of microcalcification in digital mammograms. After removing noise from mammogram using the Discrete Wavelet Transformation (DWT), we first selected the region of interest (ROI) in order to demarcate the breast region on a mammogram. Segmenting region of interest represents one of the most important stages of mammogram processing procedure. The proposed segmentation method is based on a filtering using the Sobel filter. This process will identify the significant pixels, that belong to edges of microcalcifications. Microcalcifications were detected by increasing the contrast of the images obtained by applying Sobel operator. In order to confirm the effectiveness of this microcalcification segmentation method, the Support Vector Machine (SVM) and k-Nearest Neighborhood (k-NN) algorithm are employed for the classification task using cross-validation technique.",
publisher = "IOS Press, Amsterdam",
journal = "Technology and Health Care",
title = "Segmentation for the enhancement of microcalcifications in digital mammograms",
volume = "22",
number = "5",
pages = "701-715",
doi = "10.3233/THC-140841",
url = "https://hdl.handle.net/21.15107/rcub_gery_609"
}

Milošević, M., Janković, D.,& Peulić, A.. (2014). Segmentation for the enhancement of microcalcifications in digital mammograms. in Technology and Health Care
IOS Press, Amsterdam., 22(5), 701-715.
https://doi.org/10.3233/THC-140841
https://hdl.handle.net/21.15107/rcub_gery_609

Milošević M, Janković D, Peulić A. Segmentation for the enhancement of microcalcifications in digital mammograms. in Technology and Health Care. 2014;22(5):701-715.
doi:10.3233/THC-140841
https://hdl.handle.net/21.15107/rcub_gery_609 .

Milošević, Marina, Janković, Dragan, Peulić, Aleksandar, "Segmentation for the enhancement of microcalcifications in digital mammograms" in Technology and Health Care, 22, no. 5 (2014):701-715,
https://doi.org/10.3233/THC-140841 .,
https://hdl.handle.net/21.15107/rcub_gery_609 .

TY  - JOUR
AU  - Milošević, Marina
AU  - Janković, Dragan
AU  - Peulić, Aleksandar
PY  - 2014
UR  - https://gery.gef.bg.ac.rs/handle/123456789/606
AB  - In this paper, we present a system based on feature extraction techniques and image segmentation techniques for detecting and diagnosing abnormal patterns in breast thermograms. The proposed system consists of three major steps: feature extraction, classification into normal and abnormal pattern and segmentation of abnormal pattern. Computed features based on Gray Level Co-occurrence Matrices (GLCM) are used to evaluate the effectiveness of textural information possessed by mass regions. A total of 20 GLCM features are extracted from thermograms. The ability of feature set in differentiating abnormal from normal tissue is investigated using a Support Vector Machine classifier, Naive Bayes classifier and K-Nearest Neighbor classifier. To evaluate the classification performance, five-fold cross validation method and Receiver operating characteristic analysis was performed. The verification results show that the proposed algorithm gives the best classification results using K-Nearest Neighbor classifier and a accuracy of 92.5 %. Image segmentation techniques can play an important role to segment and extract suspected hot regions of interests in the breast infrared images. Three image segmentation techniques: minimum variance quantization, dilation of image and erosion of image are discussed. The hottest regions of thermal breast images are extracted and compared to the original images. According to the results, the proposed method has potential to extract almost exact shape of tumors.
PB  - Excli Journal Managing Office, Dortmund
T2  - Excli Journal
T1  - Thermography based breast cancer detection using texture features and minimum variance quantization
VL  - 13
SP  - 1204
EP  - 1215
UR  - https://hdl.handle.net/21.15107/rcub_gery_606
ER  - 

@article{
author = "Milošević, Marina and Janković, Dragan and Peulić, Aleksandar",
year = "2014",
abstract = "In this paper, we present a system based on feature extraction techniques and image segmentation techniques for detecting and diagnosing abnormal patterns in breast thermograms. The proposed system consists of three major steps: feature extraction, classification into normal and abnormal pattern and segmentation of abnormal pattern. Computed features based on Gray Level Co-occurrence Matrices (GLCM) are used to evaluate the effectiveness of textural information possessed by mass regions. A total of 20 GLCM features are extracted from thermograms. The ability of feature set in differentiating abnormal from normal tissue is investigated using a Support Vector Machine classifier, Naive Bayes classifier and K-Nearest Neighbor classifier. To evaluate the classification performance, five-fold cross validation method and Receiver operating characteristic analysis was performed. The verification results show that the proposed algorithm gives the best classification results using K-Nearest Neighbor classifier and a accuracy of 92.5 %. Image segmentation techniques can play an important role to segment and extract suspected hot regions of interests in the breast infrared images. Three image segmentation techniques: minimum variance quantization, dilation of image and erosion of image are discussed. The hottest regions of thermal breast images are extracted and compared to the original images. According to the results, the proposed method has potential to extract almost exact shape of tumors.",
publisher = "Excli Journal Managing Office, Dortmund",
journal = "Excli Journal",
title = "Thermography based breast cancer detection using texture features and minimum variance quantization",
volume = "13",
pages = "1204-1215",
url = "https://hdl.handle.net/21.15107/rcub_gery_606"
}

Milošević, M., Janković, D.,& Peulić, A.. (2014). Thermography based breast cancer detection using texture features and minimum variance quantization. in Excli Journal
Excli Journal Managing Office, Dortmund., 13, 1204-1215.
https://hdl.handle.net/21.15107/rcub_gery_606

Milošević M, Janković D, Peulić A. Thermography based breast cancer detection using texture features and minimum variance quantization. in Excli Journal. 2014;13:1204-1215.
https://hdl.handle.net/21.15107/rcub_gery_606 .

Milošević, Marina, Janković, Dragan, Peulić, Aleksandar, "Thermography based breast cancer detection using texture features and minimum variance quantization" in Excli Journal, 13 (2014):1204-1215,
https://hdl.handle.net/21.15107/rcub_gery_606 .