Pub Date : 2020-11-19DOI: 10.1109/TIPTEKNO50054.2020.9299266
Fatma Muberra Yener, A. B. Oktay
Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) first broke out in Wuhan, China and COVID-19 disease spread throughout the world by its highly contagious nature. High death numbers have caused a massive panic across the globe. Fast and early diagnosis is the key for preventing the virus from spreading. Besides PCR test, computed tomography (CT) of lungs is also used for diagnosis of COVID-19. Since the amount of testing kits for the diagnosis is insufficient and the conventional diagnosis methods are slow, developing AI-based fast diagnosis tools is not only an alternative way but also an urgent requirement for such alarming situations as those people faced with today. In this study, we employed three popular CNN models, VGG16, VGG19, and Xception, to classify CT scans of suspected patient cases as COVID-19 infected and non-COVID-19. VGG16 achieved 93% accuracy with the best parameters on the test set.
{"title":"Diagnosis of COVID-19 with a Deep Learning Approach on Chest CT Slices","authors":"Fatma Muberra Yener, A. B. Oktay","doi":"10.1109/TIPTEKNO50054.2020.9299266","DOIUrl":"https://doi.org/10.1109/TIPTEKNO50054.2020.9299266","url":null,"abstract":"Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) first broke out in Wuhan, China and COVID-19 disease spread throughout the world by its highly contagious nature. High death numbers have caused a massive panic across the globe. Fast and early diagnosis is the key for preventing the virus from spreading. Besides PCR test, computed tomography (CT) of lungs is also used for diagnosis of COVID-19. Since the amount of testing kits for the diagnosis is insufficient and the conventional diagnosis methods are slow, developing AI-based fast diagnosis tools is not only an alternative way but also an urgent requirement for such alarming situations as those people faced with today. In this study, we employed three popular CNN models, VGG16, VGG19, and Xception, to classify CT scans of suspected patient cases as COVID-19 infected and non-COVID-19. VGG16 achieved 93% accuracy with the best parameters on the test set.","PeriodicalId":426945,"journal":{"name":"2020 Medical Technologies Congress (TIPTEKNO)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127741321","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-11-19DOI: 10.1109/TIPTEKNO50054.2020.9299322
Iraz Çinar, İrem Aksoy, Günnur Güler
Investigation of the protein-drug active substance interactions has great importance in the fields of medicine, chemistry, pharmaceutical, biomedical and toxicology. In this study, binding properties of a potential anti-cancer drug agent ifosfamide with bovine serum albumin (BSA), one of the main ligand transporters in blood plasma, was analyzed by using ultraviolet and visible light (UV-Vis) spectroscopy along with molecular docking studies. The UV-Vis spectra of the constant BSA solution (20x $10^{-6}$ M) in complexes with various concentrations of ifosfamide (20x $10^{-6}$ M to 140x $10^{-6}$ M) were obtained at physiological pH. Besides, the BSA protein was docked with ifosfamide drug active substance via computational molecular docking method. Amino acids in the binding sites of the BSA protein and the binding distances of these amino acids to the ligand (ifosfamide), their scores and RMSD values were determined, revealing that the interaction is a spontaneous process. Both molecular docking and the spectral results demonstrated that the anti-cancer drug agent binds to BSA via non-covalent interactions, resulting in minute conformational changes in BSA.
{"title":"Spectroscopic and Computational Molecular Docking studies on the protein-drug interactions","authors":"Iraz Çinar, İrem Aksoy, Günnur Güler","doi":"10.1109/TIPTEKNO50054.2020.9299322","DOIUrl":"https://doi.org/10.1109/TIPTEKNO50054.2020.9299322","url":null,"abstract":"Investigation of the protein-drug active substance interactions has great importance in the fields of medicine, chemistry, pharmaceutical, biomedical and toxicology. In this study, binding properties of a potential anti-cancer drug agent ifosfamide with bovine serum albumin (BSA), one of the main ligand transporters in blood plasma, was analyzed by using ultraviolet and visible light (UV-Vis) spectroscopy along with molecular docking studies. The UV-Vis spectra of the constant BSA solution (20x $10^{-6}$ M) in complexes with various concentrations of ifosfamide (20x $10^{-6}$ M to 140x $10^{-6}$ M) were obtained at physiological pH. Besides, the BSA protein was docked with ifosfamide drug active substance via computational molecular docking method. Amino acids in the binding sites of the BSA protein and the binding distances of these amino acids to the ligand (ifosfamide), their scores and RMSD values were determined, revealing that the interaction is a spontaneous process. Both molecular docking and the spectral results demonstrated that the anti-cancer drug agent binds to BSA via non-covalent interactions, resulting in minute conformational changes in BSA.","PeriodicalId":426945,"journal":{"name":"2020 Medical Technologies Congress (TIPTEKNO)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127097538","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-11-19DOI: 10.1109/TIPTEKNO50054.2020.9299218
Emel Bakay, N. Topaloglu
The healing effect of light at low power and energy density can be used as a treatment or alternative supportive method in various diseases. The photobiostimulation effect created on neural cells is also a very promising approach in the treatment of important neurodegenerative diseases such as Alzheimer’s disease. In this study, the response of PC12 cells to photobiomodulation was investigated as a result of the low level laser therapy with 655 nm diode laser after triple treatment. The red light at an energy density of 1, 3 and 5 J/cm2 was applied to PC12 cells three times with 24h intervals. The differentiation capacity of the cells and the elongation rates of neurites were assessed. The neurite lengths were calculated by analyzing the microscopic images of the cells. Neurite-forming capacity and differentiation rate of PC12 cells was at the maximum level after the application with 1 J/cm2 energy, nearly 2 times of the control group. 5 J/cm2 of energy density strongly inhibited the cell proliferation and the elongation of the neurites. The cell viability percentages of the cells showed that 5 J/cm2 energy density inhibited cell viability with a rate of nearly 30%. The outcomes of this study emphasized that the adjustment of light parameters in photobiomodulation applications may result in biostimulation or bioinhibition depending on the intensity and the irradiance levels applied on the cells.
{"title":"Photobiomodulation with 655-nm Laser Light to Induce the Differentiation of PC12 Cells","authors":"Emel Bakay, N. Topaloglu","doi":"10.1109/TIPTEKNO50054.2020.9299218","DOIUrl":"https://doi.org/10.1109/TIPTEKNO50054.2020.9299218","url":null,"abstract":"The healing effect of light at low power and energy density can be used as a treatment or alternative supportive method in various diseases. The photobiostimulation effect created on neural cells is also a very promising approach in the treatment of important neurodegenerative diseases such as Alzheimer’s disease. In this study, the response of PC12 cells to photobiomodulation was investigated as a result of the low level laser therapy with 655 nm diode laser after triple treatment. The red light at an energy density of 1, 3 and 5 J/cm2 was applied to PC12 cells three times with 24h intervals. The differentiation capacity of the cells and the elongation rates of neurites were assessed. The neurite lengths were calculated by analyzing the microscopic images of the cells. Neurite-forming capacity and differentiation rate of PC12 cells was at the maximum level after the application with 1 J/cm2 energy, nearly 2 times of the control group. 5 J/cm2 of energy density strongly inhibited the cell proliferation and the elongation of the neurites. The cell viability percentages of the cells showed that 5 J/cm2 energy density inhibited cell viability with a rate of nearly 30%. The outcomes of this study emphasized that the adjustment of light parameters in photobiomodulation applications may result in biostimulation or bioinhibition depending on the intensity and the irradiance levels applied on the cells.","PeriodicalId":426945,"journal":{"name":"2020 Medical Technologies Congress (TIPTEKNO)","volume":"36 173 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125923063","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-11-19DOI: 10.1109/TIPTEKNO50054.2020.9299320
Ç. Erdaş, Didem Ölçer
One of the diseases with high prevalence among the consequences of cardiovascular diseases is heart failure. Heart failure is a condition in which the muscles in the heart wall become faded and dilated, limiting the heart’s ability to pump blood. As time passes, the heart cannot meet the proper blood requirement in the body, and as a result, the person has difficulty breathing. As the human age increases, the incidence of heart failure gradually increases, and the rate of mortality due to heart failure also increases. In this context, close monitoring of people suffering from this disease will significantly increase the survival rate. In this study, a machine learning-based system is proposed to predict the mortality-survival status of patients with heart failure. Thus, by identifying people with mortality risk, the survival probability of the patients may increase with more effective and close follow-up.
{"title":"A Machine Learning-Based Approach to Detect Survival of Heart Failure Patients","authors":"Ç. Erdaş, Didem Ölçer","doi":"10.1109/TIPTEKNO50054.2020.9299320","DOIUrl":"https://doi.org/10.1109/TIPTEKNO50054.2020.9299320","url":null,"abstract":"One of the diseases with high prevalence among the consequences of cardiovascular diseases is heart failure. Heart failure is a condition in which the muscles in the heart wall become faded and dilated, limiting the heart’s ability to pump blood. As time passes, the heart cannot meet the proper blood requirement in the body, and as a result, the person has difficulty breathing. As the human age increases, the incidence of heart failure gradually increases, and the rate of mortality due to heart failure also increases. In this context, close monitoring of people suffering from this disease will significantly increase the survival rate. In this study, a machine learning-based system is proposed to predict the mortality-survival status of patients with heart failure. Thus, by identifying people with mortality risk, the survival probability of the patients may increase with more effective and close follow-up.","PeriodicalId":426945,"journal":{"name":"2020 Medical Technologies Congress (TIPTEKNO)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124927308","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-11-19DOI: 10.1109/TIPTEKNO50054.2020.9299312
Oyku Sarigil, Muge Anil-Inevi, Esra Yılmaz, Ozge S Ozcelik, Gulistan Mese, H. Tekin, E. Ozcivici
Magnetic levitation is a promising technique for tissue engineering with contact- and label-free approach. Levitation-based biofabrication systems emerge as a simple, rapid and versatile alternative to traditional tissue culture systems, since biofabrication specs can easily be tailored via magnet shape and configuration. This study aims at possible magnetic levitation systems for culture of adipose tissue cells. In this study, we performed two different magnet configurations, vertical and horizontal deployment, in an effort to be utilized in adipose tissue engineering.
{"title":"Magnetic levitation-based adipose tissue engineering using horizontal magnet deployment","authors":"Oyku Sarigil, Muge Anil-Inevi, Esra Yılmaz, Ozge S Ozcelik, Gulistan Mese, H. Tekin, E. Ozcivici","doi":"10.1109/TIPTEKNO50054.2020.9299312","DOIUrl":"https://doi.org/10.1109/TIPTEKNO50054.2020.9299312","url":null,"abstract":"Magnetic levitation is a promising technique for tissue engineering with contact- and label-free approach. Levitation-based biofabrication systems emerge as a simple, rapid and versatile alternative to traditional tissue culture systems, since biofabrication specs can easily be tailored via magnet shape and configuration. This study aims at possible magnetic levitation systems for culture of adipose tissue cells. In this study, we performed two different magnet configurations, vertical and horizontal deployment, in an effort to be utilized in adipose tissue engineering.","PeriodicalId":426945,"journal":{"name":"2020 Medical Technologies Congress (TIPTEKNO)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124895882","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-11-19DOI: 10.1109/TIPTEKNO50054.2020.9299274
M. B. Terzi, V. Arikan
In this study, a new technique which detects anomalies in skin sympathetic nerve activity (SKNA) by using state-of-the-art signal processing and machine learning methods is developed to perform the robust detection of cardiac arrhythmia (CA). For this purpose, a signal processing technique that simultaneously obtains SKNA and ECG from wideband recordings on MIT-BIH database is developed. By using preprocessed data, a novel feature extraction technique which obtains SKNA features that are critical for the reliable detection of CA is developed. By using extracted features, a supervised learning technique based on artificial neural network (ANN) and an unsupervised learning technique based on Gaussian mixture model (GMM) are developed to perform the robust detection of SKNA anomalies. A Neyman-Pearson type of approach is developed to perform the robust detection of outliers that correspond to CA. The performance results of the proposed technique over MIT-BIH database showed that the technique provides highly reliable detection of CA by performing the robust detection of SKNA anomalies. Therefore, in cases where the diagnostic information of ECG is not sufficient for the reliable diagnosis of CA, the proposed technique can provide early diagnosis of the disease, which can lead to a significant reduction in the mortality rates of cardiovascular diseases.
{"title":"Detection of Cardiac Arrhythmia using Autonomic Nervous System, Gaussian Mixture Model and Artificial Neural Network","authors":"M. B. Terzi, V. Arikan","doi":"10.1109/TIPTEKNO50054.2020.9299274","DOIUrl":"https://doi.org/10.1109/TIPTEKNO50054.2020.9299274","url":null,"abstract":"In this study, a new technique which detects anomalies in skin sympathetic nerve activity (SKNA) by using state-of-the-art signal processing and machine learning methods is developed to perform the robust detection of cardiac arrhythmia (CA). For this purpose, a signal processing technique that simultaneously obtains SKNA and ECG from wideband recordings on MIT-BIH database is developed. By using preprocessed data, a novel feature extraction technique which obtains SKNA features that are critical for the reliable detection of CA is developed. By using extracted features, a supervised learning technique based on artificial neural network (ANN) and an unsupervised learning technique based on Gaussian mixture model (GMM) are developed to perform the robust detection of SKNA anomalies. A Neyman-Pearson type of approach is developed to perform the robust detection of outliers that correspond to CA. The performance results of the proposed technique over MIT-BIH database showed that the technique provides highly reliable detection of CA by performing the robust detection of SKNA anomalies. Therefore, in cases where the diagnostic information of ECG is not sufficient for the reliable diagnosis of CA, the proposed technique can provide early diagnosis of the disease, which can lead to a significant reduction in the mortality rates of cardiovascular diseases.","PeriodicalId":426945,"journal":{"name":"2020 Medical Technologies Congress (TIPTEKNO)","volume":"107 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122553188","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-11-19DOI: 10.1109/TIPTEKNO50054.2020.9299319
Emre Kayan, ve Tarık Kavuşan, Sevgi Önal, D. P. Okvur, ve Özden Y. Özuysal, B. U. Töreyin, D. Ünay
Analyses of morphology, polarity, and motility of cells is important for cell biology research such as metastatic and invasive capacity of cells, wound healing, and embryonic development. Automation of such analyses using image series of phase-contrast optical microscopy, which allows label-free imaging of live cells in their living environment, is a need. With this purpose, in this study image series of a cell motility experiment is manually annotated, and an automation algorithm realizing motion and shape analyses of cells using the annotated data is developed. In addition, due to the low number of annotated data at hand, a U-Net based solution is devised for automated segmentation of the cells and its performance is evaluated.
{"title":"A Preliminary Study on Cell Motility Analysis from Phase-Contrast Microscopy Image Series","authors":"Emre Kayan, ve Tarık Kavuşan, Sevgi Önal, D. P. Okvur, ve Özden Y. Özuysal, B. U. Töreyin, D. Ünay","doi":"10.1109/TIPTEKNO50054.2020.9299319","DOIUrl":"https://doi.org/10.1109/TIPTEKNO50054.2020.9299319","url":null,"abstract":"Analyses of morphology, polarity, and motility of cells is important for cell biology research such as metastatic and invasive capacity of cells, wound healing, and embryonic development. Automation of such analyses using image series of phase-contrast optical microscopy, which allows label-free imaging of live cells in their living environment, is a need. With this purpose, in this study image series of a cell motility experiment is manually annotated, and an automation algorithm realizing motion and shape analyses of cells using the annotated data is developed. In addition, due to the low number of annotated data at hand, a U-Net based solution is devised for automated segmentation of the cells and its performance is evaluated.","PeriodicalId":426945,"journal":{"name":"2020 Medical Technologies Congress (TIPTEKNO)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117208591","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-11-19DOI: 10.1109/TIPTEKNO50054.2020.9299289
A. Narin
Covid-19 is a very serious deadly disease that has been announced as a pandemic by the world health organization (WHO). The whole world is working with all its might to end Covid-19 pandemic, which puts countries in serious health and economic problems, as soon as possible. The most important of these is to correctly identify those who get the Covid-19. Methods and approaches to support the reverse transcription polymerase chain reaction (RT-PCR) test have begun to take place in the literature. In this study, chest X-ray images, which can be accessed easily and quickly, were used because the covid19 attacked the respiratory systems. Classification performances with support vector machines have been obtained by using the features extracted with residual networks (ResNet-50), one of the convolutional neural network models, from these images. While Covid-19 detection is obtained with support vector machines (SVM)-quadratic with the highest sensitivity value of 96.35% with the 5-fold cross-validation method, the highest overall performance value has been detected with both SVM-quadratic and SVM-cubic above 99%. According to these high results, it is thought that this method, which has been studied, will help radiology specialists and reduce the rate of false detection.
{"title":"Detection of Covid-19 Patients with Convolutional Neural Network Based Features on Multi-class X-ray Chest Images","authors":"A. Narin","doi":"10.1109/TIPTEKNO50054.2020.9299289","DOIUrl":"https://doi.org/10.1109/TIPTEKNO50054.2020.9299289","url":null,"abstract":"Covid-19 is a very serious deadly disease that has been announced as a pandemic by the world health organization (WHO). The whole world is working with all its might to end Covid-19 pandemic, which puts countries in serious health and economic problems, as soon as possible. The most important of these is to correctly identify those who get the Covid-19. Methods and approaches to support the reverse transcription polymerase chain reaction (RT-PCR) test have begun to take place in the literature. In this study, chest X-ray images, which can be accessed easily and quickly, were used because the covid19 attacked the respiratory systems. Classification performances with support vector machines have been obtained by using the features extracted with residual networks (ResNet-50), one of the convolutional neural network models, from these images. While Covid-19 detection is obtained with support vector machines (SVM)-quadratic with the highest sensitivity value of 96.35% with the 5-fold cross-validation method, the highest overall performance value has been detected with both SVM-quadratic and SVM-cubic above 99%. According to these high results, it is thought that this method, which has been studied, will help radiology specialists and reduce the rate of false detection.","PeriodicalId":426945,"journal":{"name":"2020 Medical Technologies Congress (TIPTEKNO)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123684102","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-11-19DOI: 10.1109/TIPTEKNO50054.2020.9299315
Z. Karhan, F. Akal
Covid-19 virus, which has emerged in the Republic of China in an undetermined cause, has affected the whole world quickly. It is important to detect positive cases early to prevent further spread of the outbreak. In the diagnostic phase, radiological images of the chest are determinative as well as the RT-PCR (Reverse Transcription-Polymerase Chain Reaction) test. It was classified with the ResNet50 model, which is a convolutional neural network architecture in Covid-19 detection using chest x-ray images. Chest X-Ray image analysis can be done and infected individuals can be identified thanks to artificial intelligence quickly. The experimental results are encouraging in terms of the use of computer-aided in the field of pathology. It can also be used in situations where the possibilities and RT-PCR tests are insufficient.
{"title":"Covid-19 Classification Using Deep Learning in Chest X-Ray Images","authors":"Z. Karhan, F. Akal","doi":"10.1109/TIPTEKNO50054.2020.9299315","DOIUrl":"https://doi.org/10.1109/TIPTEKNO50054.2020.9299315","url":null,"abstract":"Covid-19 virus, which has emerged in the Republic of China in an undetermined cause, has affected the whole world quickly. It is important to detect positive cases early to prevent further spread of the outbreak. In the diagnostic phase, radiological images of the chest are determinative as well as the RT-PCR (Reverse Transcription-Polymerase Chain Reaction) test. It was classified with the ResNet50 model, which is a convolutional neural network architecture in Covid-19 detection using chest x-ray images. Chest X-Ray image analysis can be done and infected individuals can be identified thanks to artificial intelligence quickly. The experimental results are encouraging in terms of the use of computer-aided in the field of pathology. It can also be used in situations where the possibilities and RT-PCR tests are insufficient.","PeriodicalId":426945,"journal":{"name":"2020 Medical Technologies Congress (TIPTEKNO)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127798034","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-11-19DOI: 10.1109/TIPTEKNO50054.2020.9299262
Murside Degirmenci, A. Akan
Epilepsy is a type of neurological disorder that causes abnormal brain activities and creates epileptic seizures. Traditionally epileptic seizure prediction is realized with a visual examination of Electroencephalogram (EEG) signals. But this technique needs a long time EEG monitoring. So, the automatic epileptic seizures prediction schemes become a requirement at this point. This study proposes a method to classify epileptic seizures and normal EEG data by utilizing the Intrinsic Time-scale Decomposition (ITD)-based features. The dataset has been supplied from the database of the Epileptology Department of Bonn University. It contains 5 data groups A, B, C, D, E. The study aims to classify healthy and epileptic data, so data of groups A and E are used to perform evaluations of proposed methods. The EEG data are decomposed into Proper Rotation Components (PRCs) by ITD. The feature extraction methods are applied to the first five PRCs of each EEG data from healthy and epileptic individuals. These features are classified using K-Nearest Neighbors (KNN), Linear Discriminant Analysis (LDA), Naive Bayes, Support Vector Machine (SVM) and Logistic Regression classifiers. The results demonstrated that the epileptic data is differentiated from normal data by applying the nonlinear ITD with outstanding classification performance.
癫痫是一种神经系统疾病，会导致大脑活动异常，并导致癫痫发作。传统的癫痫发作预测是通过脑电图(EEG)信号的视觉检查来实现的。但该技术需要长时间的脑电图监测。因此，癫痫发作的自动预测方案在这一点上成为一种需求。本研究提出了一种利用固有时间尺度分解(ITD)特征对癫痫发作和正常脑电图数据进行分类的方法。数据集来自波恩大学癫痫学系的数据库。它包含A, B, C, D, E 5组数据。本研究的目的是对健康数据和癫痫数据进行分类，因此使用A组和E组的数据对所提出的方法进行评估。利用ITD将脑电数据分解为适当旋转分量(PRCs)。将特征提取方法应用于健康和癫痫个体的每个EEG数据的前五个prc。这些特征使用k近邻(KNN)、线性判别分析(LDA)、朴素贝叶斯、支持向量机(SVM)和逻辑回归分类器进行分类。结果表明，应用非线性过渡段可将癫痫数据与正常数据区分开来，分类效果较好。
{"title":"EEG based Epileptic Seizures Detection using Intrinsic Time-Scale Decomposition","authors":"Murside Degirmenci, A. Akan","doi":"10.1109/TIPTEKNO50054.2020.9299262","DOIUrl":"https://doi.org/10.1109/TIPTEKNO50054.2020.9299262","url":null,"abstract":"Epilepsy is a type of neurological disorder that causes abnormal brain activities and creates epileptic seizures. Traditionally epileptic seizure prediction is realized with a visual examination of Electroencephalogram (EEG) signals. But this technique needs a long time EEG monitoring. So, the automatic epileptic seizures prediction schemes become a requirement at this point. This study proposes a method to classify epileptic seizures and normal EEG data by utilizing the Intrinsic Time-scale Decomposition (ITD)-based features. The dataset has been supplied from the database of the Epileptology Department of Bonn University. It contains 5 data groups A, B, C, D, E. The study aims to classify healthy and epileptic data, so data of groups A and E are used to perform evaluations of proposed methods. The EEG data are decomposed into Proper Rotation Components (PRCs) by ITD. The feature extraction methods are applied to the first five PRCs of each EEG data from healthy and epileptic individuals. These features are classified using K-Nearest Neighbors (KNN), Linear Discriminant Analysis (LDA), Naive Bayes, Support Vector Machine (SVM) and Logistic Regression classifiers. The results demonstrated that the epileptic data is differentiated from normal data by applying the nonlinear ITD with outstanding classification performance.","PeriodicalId":426945,"journal":{"name":"2020 Medical Technologies Congress (TIPTEKNO)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116178382","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：