Onur Kocak, Faruk Beytar, H. Fırat, Z. Telatar, O. Eroğul
{"title":"Comparison of non-parametric PSD detection methods in the anaylsis of EEG signals in sleep apnea","authors":"Onur Kocak, Faruk Beytar, H. Fırat, Z. Telatar, O. Eroğul","doi":"10.1109/TIPTEKNO.2016.7863133","DOIUrl":"https://doi.org/10.1109/TIPTEKNO.2016.7863133","url":null,"abstract":"Sleep apnea is characterized by complete cessation of airflow in the mouth and nose for at least 10 seconds and it is a disease that causes significant disruption of sleep patterns. In the absence of treatment, it can lead to serious health problems such as heart attack and stroke. Polysomnography is the gold standard examination methods used in the diagnosis of the disease. In this study, EEG signals obtained from the polysomnography recording are divided into sub-bands and their epochs in pre apnea, intra apnea and post apnea were analyzed. Non-parametric power spectral density (PSD) detection methods (Periodogram, Welch and Multi Taper) applied to the EEG signals were compared.","PeriodicalId":431660,"journal":{"name":"2016 Medical Technologies National Congress (TIPTEKNO)","volume":"87 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115816174","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}
{"title":"Analysis of a network of electrically coupled neurons in fractional domain","authors":"Mahmut Ün, Manolya Ün, Faruk Sanberk Kızıltaş","doi":"10.1109/TIPTEKNO.2016.7863078","DOIUrl":"https://doi.org/10.1109/TIPTEKNO.2016.7863078","url":null,"abstract":"Synaptic signal transduction between nerve cells is mediated by electrical coupling in biological systems, implying the dynamic behavior of each cell in such a cluster of functionally similar neurons is inevitably influenced by the electrical properties of the whole network. This study demonstrates that when cell membranes are modeled after fractional order circuit elements, analytical solutions to the network equations can be found that describe the dynamic responses of any given cell to a single stimulus in greater and more accurate detail. Transfer function and the driving point impedance for this circuit network are derived in the fractional domain based on the application of the transmission matrices concept. Furthermore, necessary MATLAB simulations are performed on the network and are included as a numerical example.","PeriodicalId":431660,"journal":{"name":"2016 Medical Technologies National Congress (TIPTEKNO)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116881492","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}
{"title":"Familiarity effect of emotional stimuli onto EEG signals","authors":"Hasan Polat, M. S. Özerdem","doi":"10.1109/TIPTEKNO.2016.7863119","DOIUrl":"https://doi.org/10.1109/TIPTEKNO.2016.7863119","url":null,"abstract":"The aim of this study was to investigate the familiarity effect of emotional stimuli onto EEG signal. Familiar and non familiar stimuli were determined according to participants' rating and EEG segments related to familiar and non familiar stimuli were analyzed. Discrete wavelet transform (DWT) was used as filter to get the interested frequency range of EEG signals. Power spectral density (PSD) of filtered EEG signals was obtained by using Welch method. The power spectrum of EEG signals was considered as familiarity effects of emotional stimulus. As a conclusion, it was observed that different states of familiarities related to emotional stimulus cause different values of PSD over EEG signals.","PeriodicalId":431660,"journal":{"name":"2016 Medical Technologies National Congress (TIPTEKNO)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124847633","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}
A. J. Pahnvar, Anıl Işıkhan, Ibrahim Akkaya, Yusuf Efteli, M. Engin, E. Z. Engin
{"title":"Estimation of oxygen saturation with laser optical imaging method","authors":"A. J. Pahnvar, Anıl Işıkhan, Ibrahim Akkaya, Yusuf Efteli, M. Engin, E. Z. Engin","doi":"10.1109/TIPTEKNO.2016.7863082","DOIUrl":"https://doi.org/10.1109/TIPTEKNO.2016.7863082","url":null,"abstract":"The aim of this study is to determine the estimation of hemoglobin concentration and oxygen saturation of tissue by non-invasively functional laser imaging for early skin cancer diagnosis. The early diagnosis of melanoma is a key factor that remarkably reduces the mortality rate. Diffuse reflectance spectroscopy is a very useful device for diagnosis and treatment purposes under in-vivo conditions. At this point, the aforementioned device, which takes into account the scattering of tissue, is to determine the concentration of chromophores (or optical absorbers) due to attenuated light strikes to the superficial layer of tissue. Laser-type light based imaging techniques in medical diagnosis substantially produce good results. So the aim of this study is to estimate HbO2 % and Hb% concentrations.","PeriodicalId":431660,"journal":{"name":"2016 Medical Technologies National Congress (TIPTEKNO)","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121643276","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}
T. Palabas, O. Osman, T. Ergin, U. Teomete, Özgür Dandin, N. Aydin
{"title":"Assessment of similarity rates of liver images using geometric transformations","authors":"T. Palabas, O. Osman, T. Ergin, U. Teomete, Özgür Dandin, N. Aydin","doi":"10.1109/TIPTEKNO.2016.7863136","DOIUrl":"https://doi.org/10.1109/TIPTEKNO.2016.7863136","url":null,"abstract":"In this study, similarity rates of the liver images are determined using 3D geometric transformation methods and numerical comparisons are made. Three geometric transformation methods scaling, rotating, and translating are consecutively applied to 10 intact liver images which are drawn by the radiologists. Atlases of liver images are generated, Dice coefficients are calculated according to the specified atlases and are assessed for various cases. This study is presented as a step to prepare atlas database for segmentation of the injured liver.","PeriodicalId":431660,"journal":{"name":"2016 Medical Technologies National Congress (TIPTEKNO)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125105578","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}
{"title":"Neuromuscular disease diagnosis of SVM, K-NN and DA algorithm based classification part-II","authors":"Hanife Küçük, Ilyas Eminoglu","doi":"10.1109/TIPTEKNO.2016.7863105","DOIUrl":"https://doi.org/10.1109/TIPTEKNO.2016.7863105","url":null,"abstract":"This study includes a classification structure consisting of second part for the automatic diagnosis of the neuromuscular disease of ALS (Amyotrophic Lateral Sclerosis) and myopathy being a muscular disease. In this study feature vectors containing time domain parameters, frequency domain parameters (a total of 25 feature vectors) as well as feature vectors composed of combination of these parameters were used. In the classification stage, Support Vector Machines (SVM), K-Nearest Neighbors (K-NN) and Discriminant Analysis (DA) algorithms were employed. Experimental results showed that the multiple feature vectors proved to be more successful compared to the individual feature vectors. It is understood with this study; the classification performance depends highly on separability of feature vectors between different classes.","PeriodicalId":431660,"journal":{"name":"2016 Medical Technologies National Congress (TIPTEKNO)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122086808","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}
Baha Kılıç, Eyüp Agah İslam, E. Sinir, M. Bi̇lgi̇c
{"title":"Microbiological safety and performance criteria for microbiological safety cabinets","authors":"Baha Kılıç, Eyüp Agah İslam, E. Sinir, M. Bi̇lgi̇c","doi":"10.1109/TIPTEKNO.2016.7863141","DOIUrl":"https://doi.org/10.1109/TIPTEKNO.2016.7863141","url":null,"abstract":"Microbiological Safety Cabinets (MSC) designed to minimize hazards inherent in work with agents assigned to biosafety levels 1, 2, 3, or 4by keeping hazards work in controled area via filtered air flow. This work defines the tests that shall be passed by such cabinetry to meet the EN 12469 standard. In this work, 5 different types of MSCs' were tested according to the EN 12469 standards and 5 different test methods were analysed.","PeriodicalId":431660,"journal":{"name":"2016 Medical Technologies National Congress (TIPTEKNO)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122181024","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}
{"title":"Emotion recognition via random forest and galvanic skin response: Comparison of time based feature sets, window sizes and wavelet approaches","authors":"Değer Ayata, Y. Yaslan, M. Kamasak","doi":"10.1109/TIPTEKNO.2016.7863130","DOIUrl":"https://doi.org/10.1109/TIPTEKNO.2016.7863130","url":null,"abstract":"Emotions play a significant and powerful role in everyday life of human beings. Developing algorithms for computers to recognize emotional expression is a widely studied area. In this study, emotion recognition from Galvanic signals was performed using time domain and wavelet based features. Feature extraction has been done with various feature set attributes. Various length windows have been used for feature extraction. Various feature attribute sets have been implemented. Valence and arousal have been categorized and relationship between physiological signals and arousal and valence has been studied using Random Forest machine learning algorithm. We have achieved 71.53% and 71.04% accuracy rate for arousal and valence respectively by using only galvanic skin response signal. We have also showed that using convolution has positive affect on accuracy rate compared to non-overlapping window based feature extraction.","PeriodicalId":431660,"journal":{"name":"2016 Medical Technologies National Congress (TIPTEKNO)","volume":"346 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134289615","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}
{"title":"Personal tracking in hospitals by using active RF-ID","authors":"Ugur Can Icen, Ömer Herekoğlu, M. Ertas","doi":"10.1109/TIPTEKNO.2016.7863142","DOIUrl":"https://doi.org/10.1109/TIPTEKNO.2016.7863142","url":null,"abstract":"The applications of wireless communication system dramatically increase day by day. Nowadays, these technologies have been widely used in personal tracking. RFID is one of the most actively used technologies among them. Along with its effective use in daily life, it allows localization and personal tracking by using location detection algorithms. In this study, tracking of personal and patients in the hospitals has been performed by using this feature of active RF-ID system. Thus, by tracking personal within the hospital it is aimed to take mandatory actions for hygiene control at special locations where hygiene rules must be strictly followed. Within this context, a system has been designed for personal to fulfill his responsibilities at this regard. The tracking of movement of personal inside the hospital building and rooms has been performed by using this system and problems have been investigated.","PeriodicalId":431660,"journal":{"name":"2016 Medical Technologies National Congress (TIPTEKNO)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133592350","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}
H. Badem, Abdullah Çalıskan, A. Basturk, M. E. Yuksel
{"title":"Classification of human activity by using a Stacked Autoencoder","authors":"H. Badem, Abdullah Çalıskan, A. Basturk, M. E. Yuksel","doi":"10.1109/TIPTEKNO.2016.7863135","DOIUrl":"https://doi.org/10.1109/TIPTEKNO.2016.7863135","url":null,"abstract":"This paper investigates the application of a deep neural network architecture that consists of stackted autoencoder with two autoencoders and a softmax layer for the purpose of human activity classification. Th performance of the proposed architecture is tested on a commonly used data set known as Human Activity Recognition Using Smartphones. It is observed that the proposed method yields better classification results than the representative state-of-the-art methods provided that the parameters of the deep network are suitably optimized.","PeriodicalId":431660,"journal":{"name":"2016 Medical Technologies National Congress (TIPTEKNO)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133741119","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}