Pub Date : 2020-11-19DOI: 10.1109/TIPTEKNO50054.2020.9299226
Merve Bas, S. Dağlilar, C. Kalkandelen, O. Gunduz
In the presented study; Hydroxyapatite (HA) used in many areas such as filling of cavities, bone tissue treatments, chin-face, orthopedic and dental surgeries, was obtained from waste salmon fish bones. Instead of producing chemically in a laboratory environment, hard tissue waste of natural resources was used. As trace elements such as magnesium, zinc, and strontium in the structure of natural resources support bone formation, waste salmon fish bones, which are a natural source, were preferred as raw materials. Other advantages include being easy to access raw materials, cheap and environmentally friendly. HA was obtained from salmon bones by the thermal calcination method. The obtained pure salmon hydroxyapatites were sintered at different temperatures, and the effect of changing sintering temperature on the density, microhardness, compressive strength, and elasticity module in the material was investigated. Crystal phase analysis of salmon hydroxyapatite powder and thermal analysis up to a certain temperature were made. MTT cytotoxicity test was performed to measure whether the materials were toxic. This study has the potential to contribute to the development of biomaterial studies for bone repair.
{"title":"Use of Waste Salmon Bones as a Biomaterial","authors":"Merve Bas, S. Dağlilar, C. Kalkandelen, O. Gunduz","doi":"10.1109/TIPTEKNO50054.2020.9299226","DOIUrl":"https://doi.org/10.1109/TIPTEKNO50054.2020.9299226","url":null,"abstract":"In the presented study; Hydroxyapatite (HA) used in many areas such as filling of cavities, bone tissue treatments, chin-face, orthopedic and dental surgeries, was obtained from waste salmon fish bones. Instead of producing chemically in a laboratory environment, hard tissue waste of natural resources was used. As trace elements such as magnesium, zinc, and strontium in the structure of natural resources support bone formation, waste salmon fish bones, which are a natural source, were preferred as raw materials. Other advantages include being easy to access raw materials, cheap and environmentally friendly. HA was obtained from salmon bones by the thermal calcination method. The obtained pure salmon hydroxyapatites were sintered at different temperatures, and the effect of changing sintering temperature on the density, microhardness, compressive strength, and elasticity module in the material was investigated. Crystal phase analysis of salmon hydroxyapatite powder and thermal analysis up to a certain temperature were made. MTT cytotoxicity test was performed to measure whether the materials were toxic. This study has the potential to contribute to the development of biomaterial studies for bone repair.","PeriodicalId":426945,"journal":{"name":"2020 Medical Technologies Congress (TIPTEKNO)","volume":"6 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":"134506326","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/TIPTEKNO50054.2020.9299313
F. Yilmaz, Ahmet Demir
Malignant melanoma is the most dangerous and lethal skin cancer type. In time and early diagnosis increases the possibility of successful treatment. Studies done in recent years show that skin cancer diagnosis can be done by using computer aided diagnosis systems. In this study, a classification using a dataset with two classes which are malign and benign melanom is realized. Nasnet deep learning architecture is used for the classification. Two different experiments are done in this study. While first experiment classifies dataset directly by using Nasnet architecture, second experiment does classification by first creating 8 images from train and validation part of dataset and starting training by using this new dataset. While an accuracy rate of 82.94% is get without cutting operation, an accuracy rate of 86.49% is get with cutting operation. A better classification performance is reached with cutting operation.
{"title":"Cutting Effect on Classification Using Nasnet Architecture","authors":"F. Yilmaz, Ahmet Demir","doi":"10.1109/TIPTEKNO50054.2020.9299313","DOIUrl":"https://doi.org/10.1109/TIPTEKNO50054.2020.9299313","url":null,"abstract":"Malignant melanoma is the most dangerous and lethal skin cancer type. In time and early diagnosis increases the possibility of successful treatment. Studies done in recent years show that skin cancer diagnosis can be done by using computer aided diagnosis systems. In this study, a classification using a dataset with two classes which are malign and benign melanom is realized. Nasnet deep learning architecture is used for the classification. Two different experiments are done in this study. While first experiment classifies dataset directly by using Nasnet architecture, second experiment does classification by first creating 8 images from train and validation part of dataset and starting training by using this new dataset. While an accuracy rate of 82.94% is get without cutting operation, an accuracy rate of 86.49% is get with cutting operation. A better classification performance is reached with cutting operation.","PeriodicalId":426945,"journal":{"name":"2020 Medical Technologies Congress (TIPTEKNO)","volume":"1 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":"132371112","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/TIPTEKNO50054.2020.9299316
E. C. Erkus, V. Purutçuoğlu, F. Arı, D. Gökçay
Detection of arousal intervals, especially stress detection via a human-machine interface is a trending topic. Stress detection algorithms with high accuracy can be used in many fields such as criminal interrogations or a variety of stress-related experiments. There are many indicators of the stress on the human body, especially on the face area, such as galvanic skin response (GSR), pupil diameter, heart rate (HR), and electromyography (EMG). Hereby, the measurement of such physiological data in stressful, joyful and non-stressful cases can reveal the effects of the stress on the body signals.This preliminary study aims to compare several machine learning approaches, namely, linear discriminant analysis (LDA), k-nearest neighbour (k-NN), Naive Bayes, support vector machines (SVM) and coarse tree algorithms in a classification study. To perform the analyses, the pupil data are collected from a total of 9 subjects while the subject was watching three types of movies, independently. The classifications are performed among the labelled data with multivariate features such as mean, median, maximum to minimum difference and variance, and their univariate versions in order to observe their independent discrimination performances. Moreover, the preprocessed raw data are also used in classification, independently. Here, the movies are selected such that they include either annotated positive, negative or neutral scenes, which may indicate the stressful, joyful and non-stressful intervals, respectively. Therefore, the classification results of these algorithms for the annotated labels in each channel separately are found to observe their effectiveness in detection of arousal intervals. Hence, the main aim is to contribute to the stress detection literature by providing a comparison between both the classification algorithms, features and raw data classification.
{"title":"Comparison of Several Machine Learning Classifiers for Arousal Classification: A Preliminary study","authors":"E. C. Erkus, V. Purutçuoğlu, F. Arı, D. Gökçay","doi":"10.1109/TIPTEKNO50054.2020.9299316","DOIUrl":"https://doi.org/10.1109/TIPTEKNO50054.2020.9299316","url":null,"abstract":"Detection of arousal intervals, especially stress detection via a human-machine interface is a trending topic. Stress detection algorithms with high accuracy can be used in many fields such as criminal interrogations or a variety of stress-related experiments. There are many indicators of the stress on the human body, especially on the face area, such as galvanic skin response (GSR), pupil diameter, heart rate (HR), and electromyography (EMG). Hereby, the measurement of such physiological data in stressful, joyful and non-stressful cases can reveal the effects of the stress on the body signals.This preliminary study aims to compare several machine learning approaches, namely, linear discriminant analysis (LDA), k-nearest neighbour (k-NN), Naive Bayes, support vector machines (SVM) and coarse tree algorithms in a classification study. To perform the analyses, the pupil data are collected from a total of 9 subjects while the subject was watching three types of movies, independently. The classifications are performed among the labelled data with multivariate features such as mean, median, maximum to minimum difference and variance, and their univariate versions in order to observe their independent discrimination performances. Moreover, the preprocessed raw data are also used in classification, independently. Here, the movies are selected such that they include either annotated positive, negative or neutral scenes, which may indicate the stressful, joyful and non-stressful intervals, respectively. Therefore, the classification results of these algorithms for the annotated labels in each channel separately are found to observe their effectiveness in detection of arousal intervals. Hence, the main aim is to contribute to the stress detection literature by providing a comparison between both the classification algorithms, features and raw data classification.","PeriodicalId":426945,"journal":{"name":"2020 Medical Technologies Congress (TIPTEKNO)","volume":"20 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":"122347523","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/TIPTEKNO50054.2020.9299321
Omer Faruk Karaaslan, G. Bilgin
In this study, it is aimed to increase the segmen- tation performance of the cells in the digital histopathological images by data compatible feature extraction methods. For this purpose, it is proposed to use empirical mode decomposition and variational mode decomposition methods as a comparison. Initially, the conversion of digital histopathological images from RGB color space to gray level is performed. Then, empirical mode decomposition and variational mode decomposition methods are applied to these images, and the obtained features are classified by using support vector machines which is a kernel-based classifier and random forests which is an ensemble-based classifier. The results are evaluated according to three different metrics. In the application results section, the results obtained in this study are presented in detail.
{"title":"Comparison of Variational Mode Decomposition and Empirical Mode Decomposition Features for Cell Segmentation in Histopathological Images","authors":"Omer Faruk Karaaslan, G. Bilgin","doi":"10.1109/TIPTEKNO50054.2020.9299321","DOIUrl":"https://doi.org/10.1109/TIPTEKNO50054.2020.9299321","url":null,"abstract":"In this study, it is aimed to increase the segmen- tation performance of the cells in the digital histopathological images by data compatible feature extraction methods. For this purpose, it is proposed to use empirical mode decomposition and variational mode decomposition methods as a comparison. Initially, the conversion of digital histopathological images from RGB color space to gray level is performed. Then, empirical mode decomposition and variational mode decomposition methods are applied to these images, and the obtained features are classified by using support vector machines which is a kernel-based classifier and random forests which is an ensemble-based classifier. The results are evaluated according to three different metrics. In the application results section, the results obtained in this study are presented in detail.","PeriodicalId":426945,"journal":{"name":"2020 Medical Technologies Congress (TIPTEKNO)","volume":"75 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":"127284716","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/TIPTEKNO50054.2020.9299239
A. Ekim, Önder Aydemir, Mengu Demir
Cognitive fatigue is the natural result of longtime mental effort during the execution of a high mental workload or a strenuous task. This situation often leads to decreased productivity and increased security risks. In this study, it was aimed to detect cognitive fatigue quickly and accurately, regardless of subjective data. CogBeacon dataset was used for this. Data that make up the CogBeacon dataset were collected from 19 participants in 76 sessions with the help of a 4-electrode MUSE electroencephalography (EEG) device. The collected raw EEGs were randomly separated and feature extraction was performed. Support Vector Machine (SVM) and k-Nearest Neighbor (KNN) algorithms were used in the classification process. Katz and Higuchi Fractal Dimension, standard deviation, median, variance and covariance were tested as features. When the classification was made with SVM, the education average was 93.99% and the test average was 83.14%. The average success rate increased between 4.43% and 7.40%, compared to the trials that were not used in the trials where Fractal Dimension features were used. When the classification was made with KNN, the education averange was 91.71% and the test average was 83.34%. The average success rate increased between 5.10% and 8.92% compared to the trials that were not used in the trials in which Fractal Dimension features were used.
{"title":"Classification of Cognitive Fatigue with EEG Signals","authors":"A. Ekim, Önder Aydemir, Mengu Demir","doi":"10.1109/TIPTEKNO50054.2020.9299239","DOIUrl":"https://doi.org/10.1109/TIPTEKNO50054.2020.9299239","url":null,"abstract":"Cognitive fatigue is the natural result of longtime mental effort during the execution of a high mental workload or a strenuous task. This situation often leads to decreased productivity and increased security risks. In this study, it was aimed to detect cognitive fatigue quickly and accurately, regardless of subjective data. CogBeacon dataset was used for this. Data that make up the CogBeacon dataset were collected from 19 participants in 76 sessions with the help of a 4-electrode MUSE electroencephalography (EEG) device. The collected raw EEGs were randomly separated and feature extraction was performed. Support Vector Machine (SVM) and k-Nearest Neighbor (KNN) algorithms were used in the classification process. Katz and Higuchi Fractal Dimension, standard deviation, median, variance and covariance were tested as features. When the classification was made with SVM, the education average was 93.99% and the test average was 83.14%. The average success rate increased between 4.43% and 7.40%, compared to the trials that were not used in the trials where Fractal Dimension features were used. When the classification was made with KNN, the education averange was 91.71% and the test average was 83.34%. The average success rate increased between 5.10% and 8.92% compared to the trials that were not used in the trials in which Fractal Dimension features were used.","PeriodicalId":426945,"journal":{"name":"2020 Medical Technologies Congress (TIPTEKNO)","volume":"86 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":"129290656","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/TIPTEKNO50054.2020.9299300
Sertan Serte, Ali Serener
Pleural effusion is the build-up of excess fluid between the pleura layers around the lung. This fluid may be transudative or exudative. Pneumonia and cancer are common exudative causes of pleural effusion. Other causes include tuberculosis and recently discovered COVID-19. Physicians are able to diagnose pleural effusion through the use of chest radiographs. In this work, we propose, instead, the early detection of pleural effusion from tuberculosis, pneumonia, and COVID-19 diseases on chest radiographs using deep learning. The performance results show that the early detection of pleural effusion from pneumonia and tuberculosis have the highest accuracy. They further show that the deep learning architecture can distinguish bacterial pneumonia and COVID-19 diseases from pleural effusion the best.
{"title":"Early pleural effusion detection from respiratory diseases including COVID-19 via deep learning","authors":"Sertan Serte, Ali Serener","doi":"10.1109/TIPTEKNO50054.2020.9299300","DOIUrl":"https://doi.org/10.1109/TIPTEKNO50054.2020.9299300","url":null,"abstract":"Pleural effusion is the build-up of excess fluid between the pleura layers around the lung. This fluid may be transudative or exudative. Pneumonia and cancer are common exudative causes of pleural effusion. Other causes include tuberculosis and recently discovered COVID-19. Physicians are able to diagnose pleural effusion through the use of chest radiographs. In this work, we propose, instead, the early detection of pleural effusion from tuberculosis, pneumonia, and COVID-19 diseases on chest radiographs using deep learning. The performance results show that the early detection of pleural effusion from pneumonia and tuberculosis have the highest accuracy. They further show that the deep learning architecture can distinguish bacterial pneumonia and COVID-19 diseases from pleural effusion the best.","PeriodicalId":426945,"journal":{"name":"2020 Medical Technologies Congress (TIPTEKNO)","volume":"269 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":"122471798","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/TIPTEKNO50054.2020.9299282
Deniz Hande Kisa, Mehmet Akif Ozdemir, Onan Guren, A. Akan
Computer systems working with artificial intelligence can recognize movements and gestures to be used for many purposes. In order to perform recognition, the electrical activity of the muscles can be utilized which is represented by electromyography (EMG) and EMG is not a stationary biological signal. EMG based movement recognition systems have an important place in distinct areas like in human-computer interactions, virtual reality, prosthesis, and hand exoskeletons. In this study, a new approach based on deep learning (DL) and Empirical Mode Decomposition (EMD) is proposed to improve the accuracy rate for recognition of hand movements in its application areas. Firstly, 4-channel surface EMG (sEMG) signals were measured while simulating 7 different hand gestures, which are extension, flexion, ulnar deviation, radial deviation, punch, open hand, and rest, from 30 subjects. After that, noiseless signals were procured utilizing filters as a result of preprocessing. Then, pre-processed signals were subjected to segmentation. Thereafter, the EMD process was applied to each segmented signal and Intrinsic Mode Functions (IMFs) were obtained. The IMFs time-series which are some kind of screen images of the first 3 IMFs have been recorded. For classification, IMFs images have given as inputs and have trained to the 101layer Convolution Neural Network (CNN) based on Residual Networks (ResNet) architecture, which is a DL model.
{"title":"EMG based Hand Gesture Classification using Empirical Mode Decomposition Time-Series and Deep Learning","authors":"Deniz Hande Kisa, Mehmet Akif Ozdemir, Onan Guren, A. Akan","doi":"10.1109/TIPTEKNO50054.2020.9299282","DOIUrl":"https://doi.org/10.1109/TIPTEKNO50054.2020.9299282","url":null,"abstract":"Computer systems working with artificial intelligence can recognize movements and gestures to be used for many purposes. In order to perform recognition, the electrical activity of the muscles can be utilized which is represented by electromyography (EMG) and EMG is not a stationary biological signal. EMG based movement recognition systems have an important place in distinct areas like in human-computer interactions, virtual reality, prosthesis, and hand exoskeletons. In this study, a new approach based on deep learning (DL) and Empirical Mode Decomposition (EMD) is proposed to improve the accuracy rate for recognition of hand movements in its application areas. Firstly, 4-channel surface EMG (sEMG) signals were measured while simulating 7 different hand gestures, which are extension, flexion, ulnar deviation, radial deviation, punch, open hand, and rest, from 30 subjects. After that, noiseless signals were procured utilizing filters as a result of preprocessing. Then, pre-processed signals were subjected to segmentation. Thereafter, the EMD process was applied to each segmented signal and Intrinsic Mode Functions (IMFs) were obtained. The IMFs time-series which are some kind of screen images of the first 3 IMFs have been recorded. For classification, IMFs images have given as inputs and have trained to the 101layer Convolution Neural Network (CNN) based on Residual Networks (ResNet) architecture, which is a DL model.","PeriodicalId":426945,"journal":{"name":"2020 Medical Technologies Congress (TIPTEKNO)","volume":"41 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":"132637767","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/TIPTEKNO50054.2020.9299237
M. Mikaeili, H. Ş. Bilge
Image registration plays a crucial role in biomedical imaging, especially in image-guided surgery. Obtaining real-time images with an Ultrasound Imaging System (US) makes it possible to register them with magnetic resonance (MR) or computed tomography (CT) images and increase the accuracy of imageguided surgery. Differences in the resolution and intensity of these images motivated us to register ultrasound images with each other. Ultrasound images suffer from low contrast and resolution in comparison to other image modalities such as MR. By acknowledging the fact that the transformation matrix is the building block of the registration concept. Also, given the success of deep learning in classification, we choose to apply it to identify the angle difference and rotation matrix of three consecutive ultrasound images. This paper attempts to find the Euler angles and rotation matrix of three consecutive ultrasound images by applying a deep learning method. At the end of the study, we attain promising results when our learning rate is 0.00002 and the scaling factor is 64× 32. Furthermore, the comparison of positive and negative angles demonstrates that the overall network performs better in predicting positive angles.
{"title":"Estimating Rotation Angle and Transformation Matrix Between Consecutive Ultrasound Images Using Deep Learning","authors":"M. Mikaeili, H. Ş. Bilge","doi":"10.1109/TIPTEKNO50054.2020.9299237","DOIUrl":"https://doi.org/10.1109/TIPTEKNO50054.2020.9299237","url":null,"abstract":"Image registration plays a crucial role in biomedical imaging, especially in image-guided surgery. Obtaining real-time images with an Ultrasound Imaging System (US) makes it possible to register them with magnetic resonance (MR) or computed tomography (CT) images and increase the accuracy of imageguided surgery. Differences in the resolution and intensity of these images motivated us to register ultrasound images with each other. Ultrasound images suffer from low contrast and resolution in comparison to other image modalities such as MR. By acknowledging the fact that the transformation matrix is the building block of the registration concept. Also, given the success of deep learning in classification, we choose to apply it to identify the angle difference and rotation matrix of three consecutive ultrasound images. This paper attempts to find the Euler angles and rotation matrix of three consecutive ultrasound images by applying a deep learning method. At the end of the study, we attain promising results when our learning rate is 0.00002 and the scaling factor is 64× 32. Furthermore, the comparison of positive and negative angles demonstrates that the overall network performs better in predicting positive angles.","PeriodicalId":426945,"journal":{"name":"2020 Medical Technologies Congress (TIPTEKNO)","volume":"63 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":"124284526","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/TIPTEKNO50054.2020.9299229
Mehmet Nasuhcan Türker, Yağız Can Çağan, Batuhan Yildirim, Mücahit Demirel, A. Özmen, B. Tander, Mesut Cevik
In this study, a device named smart stethoscope that uses digital sensor technology for sound capture, active acoustics for noise cancellation and artificial intelligence (AI) for diagnosis of heart and lung diseases is developed to help the health workers to make accurate diagnoses. Furthermore, the respiratory diseases are classified by using Deep Learning and Long Short-Term Memory (LSTM) techniques whereas the probability of these diseases are obtained.
{"title":"Smart Stethoscope","authors":"Mehmet Nasuhcan Türker, Yağız Can Çağan, Batuhan Yildirim, Mücahit Demirel, A. Özmen, B. Tander, Mesut Cevik","doi":"10.1109/TIPTEKNO50054.2020.9299229","DOIUrl":"https://doi.org/10.1109/TIPTEKNO50054.2020.9299229","url":null,"abstract":"In this study, a device named smart stethoscope that uses digital sensor technology for sound capture, active acoustics for noise cancellation and artificial intelligence (AI) for diagnosis of heart and lung diseases is developed to help the health workers to make accurate diagnoses. Furthermore, the respiratory diseases are classified by using Deep Learning and Long Short-Term Memory (LSTM) techniques whereas the probability of these diseases are obtained.","PeriodicalId":426945,"journal":{"name":"2020 Medical Technologies Congress (TIPTEKNO)","volume":"65 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":"123799478","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/TIPTEKNO50054.2020.9299228
O. Ateş, Önder Aydemir
Brain-computer interfaces (BCI) are the systems that enable to provide communication between users and an external device through only brain activities. One of significant purposes of BBA technology is to enable communication of the patients like who has motor disability or are paralyzed. This communication can be performed by electroencephalogram (EEG) that is a method providing to be followed brain activities through electrical system. In this study, the EEG data set recorded during brain imagination of right or left hand grasp attemtp movements of subjects having hand functional disability was used. It is aimed to have high classification accuracy (CA) for eight different subjects by creating feature vectors using statistical based features. k-nearest neigbors (kNN), support vector machines (SVM) and linear discriminant analysis (LDA) methods were used for classification. We obtained the highest average CA as 81.17% for eight subjects using kNN algorithm. The results indicate that these proposed features can be used for the classification of motor imagery EEG signals.
{"title":"Classification of EEG Signals Recorded During Imagery of Hand Grasp Movement","authors":"O. Ateş, Önder Aydemir","doi":"10.1109/TIPTEKNO50054.2020.9299228","DOIUrl":"https://doi.org/10.1109/TIPTEKNO50054.2020.9299228","url":null,"abstract":"Brain-computer interfaces (BCI) are the systems that enable to provide communication between users and an external device through only brain activities. One of significant purposes of BBA technology is to enable communication of the patients like who has motor disability or are paralyzed. This communication can be performed by electroencephalogram (EEG) that is a method providing to be followed brain activities through electrical system. In this study, the EEG data set recorded during brain imagination of right or left hand grasp attemtp movements of subjects having hand functional disability was used. It is aimed to have high classification accuracy (CA) for eight different subjects by creating feature vectors using statistical based features. k-nearest neigbors (kNN), support vector machines (SVM) and linear discriminant analysis (LDA) methods were used for classification. We obtained the highest average CA as 81.17% for eight subjects using kNN algorithm. The results indicate that these proposed features can be used for the classification of motor imagery EEG signals.","PeriodicalId":426945,"journal":{"name":"2020 Medical Technologies Congress (TIPTEKNO)","volume":"5 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":"123810172","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：