Yazar "Yildirim, Esen" seçeneğine göre listele
Listeleniyor 1 - 14 / 14
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe Channel Selection from EEG Signals and Application of Support Vector Machine on EEG Data(Ieee, 2017) Arslan, Mustafa Turan; Eraldemir, Server Goksel; Yildirim, EsenIn this study, EEG data recorded during mental arithmetic operations and silent reading were analyzed by discrete wavelet transform and feature vectors were obtained. The obtained feature vectors are classified by Support Vector Machines (SVM). Results are given for 26 channels, all recorded channels, and for 10 most effective channels. Correlation based feature selection based algorithm is used for choosing the most effective channels. Decreasing the number of channels without compromising the accuracy, is an important issue for real time applications for which a short analysis time is crucial. In this study, mental arithmetic and silent reading tasks are classified with an accuracy of 90.71%, a precision rate of 91.03% and F-measure rate of 90.63% on the average using 26 channels, whereas the accuracy, precision and F-measure were 90.44%, 90.61% and 90.08, respectively which were comparable to that of obtained using all channels, for reduced number of channels.Öğe Classification of Emotion Primitives from EEG Signals Using Visual and Audio Stimuli(Ieee, 2015) Dasdemir, Yasar; Yildirim, Serdar; Yildirim, EsenEmotion recognition from EEG signals has an important role in designing Brain-Computer Interface. This paper compares effects of audio and visual stimuli, used for collecting emotional EEG signals, on emotion classification performance. For this purpose EEG data from 25 subjects are collected and binary classification (low/high) for valence and activation emotion dimensions are performed. Wavelet transform is used for feature extraction and 3 classifiers are used for classification. True positive rates of 71.7% and 78.5% are obtained using audio and video stimuli for valence dimension 71% and 82% are obtained using audio and video stimuli for arousal dimension, respectively.Öğe Classification of Emotional Valence Dimension Using Artificial Neural Networks(Ieee, 2015) Ozdemir, Merve Erkmay; Yildirim, Esen; Yildirim, SerdarEmotions play an important role in human interaction. Emotion recognition should be considered to design an effective Brain-Computer Interface. In this work binary classification (low/high) for valence which is one of the primitives used in expressing emotions is performed. Hilbert-Huang Transform is used for feature extraction, multi layer feed forward Artificial Neural Networks is used for subject independent classification and 69% of true positive rate is obtained.Öğe Classification of Intensive-less Intensive and Related-Unrelated Tasks(Prof.Dr. İskender AKKURT, 2024) Arslan, Mustafa Turan; Yildirim, EsenThis study investigates the classification of electrical brain activity during intensive-less intensive and related-unrelated tasks. EEG signals were collected from 20 physically and mentally healthy university students (15 males, 5 females) residing in Adana and Hatay, Turkey, through 14 channels. Continuous Wavelet Transform analysis was applied for feature extraction. Subsequently, subject-dependent and subject-independent classifications were performed using the k-nearest Neighbour algorithm. In subjectdependent classification, the accuracy range for intensive-less intensive tasks varied between 77.6% and 89.8%, while the range for related-unrelated tasks was between 73.2% and 88%. Subject-independent classification yielded an accuracy of 79.2% for intensive-less intensive tasks and 77.5% for related unrelated tasks. © IJCESENÖğe Classification of Simple Text Reading and Mathematical Tasks from EEG(Ieee, 2014) Eraldemir, S. Goksel; Yildirim, EsenAll types of brain activity produce electrical signals. These signals emerge during body movement, as well as at the stage of thinking and they can be recorded using an EEG device. In this study EEG signals of healthy volunteers were recorded during simple mathematical tasks and text reading. The aim of the study is to discriminate these activities from recorded EEG signals. For this purpose we used EEG signals recorded from healthy volunteers using international 10-20 electrode placing system. Features are extracted using wavelet transform and they used for classification using Bayesian Classifiers. As a result of the study EEG signals, recorded during mathematical operations and text reading, were classified with a true positive rate of 89.1% and a precision rate of 89.2% on the average.Öğe Comparison of Wavelets for Classification of Cognitive EEG Signals(Ieee, 2015) Eraldemir, S. Goksel; Yildirim, EsenIn this work, different wavelet types, that have been frequently used in EEG signal analysis and classification, are compared for cognitive EEG classification. EEG signals are collected from 18 healthy subjects during math processing and simple text reading. Symlet, coiflet and bior wavelet types are used for feature extraction and classification performances of BayesNet and J48 classifiers are compared. The best true positive rate of 90.6% is obtained using Boir 2.4 wavelet type with J48 classifier.Öğe Emotion estimation from EEG signals using wavelet transform analysis(2012) Uzun, Süheyla Sinem; Oflazoglu, Ça?lar; Yildirim, Serdar; Yildirim, EsenEmotion recognition is important for an effective human-machine interaction. Information obtained from speech, gestures and mimics, heart rate, and temperature can be used in emotion estimation. In this study, emotion estimation from EEG signals using wavelet decomposition is performed. For this purpose, EEG signals were recorded from 20 subjects and audio stimuli are used to evoke emotions. Delta, Theta, Alfa, Beta and Gamma sub-bands of signals are computed using wavelet transform. Statistical features and energy of each band are computed. Correlation based feature selection algorithm is applied to the base feature set to obtain the most relevant subset and emotion primitives are estimated using Support Vector Regression. Emotion estimation results in terms of mean absolute error using db4, db8 and coif5 mother wavelets are 0.28, 0.26, and 0.29 for valence, 0.20, 0.20, and 0.19 for activation and 0.11, 0.10, and 0.10 for dominance respectively. © 2012 IEEE.Öğe Emotion primitives estimation from EEG signals using Hilbert Huang Transform(2012) Uzun, S. Sinem; Yildirim, Serdar; Yildirim, EsenThis paper addresses the problem of emotion primitives estimation using information obtained from EEG signals. The EEG data were collected from 18 subjects, 9 male and 9 female, aged from 19 to 26 years old. We used audio clips from International Affective Digital Sounds (IADS) as stimuli for emotion elicitation. Hilbert-Huang Transform, a proper method for non-linear and non-stationary signal processing, was used for feature extraction. EEG signals were first decomposed into their Intrinsic Mode Functions (IMFs). Then 990 features were computed from the first five IMFs. To identify the most salient features and eliminate the redundant and irrelevant ones, we performed correlation based feature selection (CFS). This feature selection process reduced the number of features dramatically while increasing the performance remarkably. In this work, we used support vector regression for estimation of each emotion primitive value. Regression mean absolute error values and their standard deviations over all subjects for valence, activation, and dominance were obtained as 1.11 (0.13), 0.65 (0.09) and 0.38 (0.06) respectively. © 2012 IEEE.Öğe Emotion Recognition From Speech Using Fisher's Discriminant Analysis and Bayesian Classifier(Ieee, 2015) Atasoy, Huseyin; Yildirim, Serdar; Yildirim, EsenIn this study, a large number of features that were obtained to classify speech emotions were projected into different spaces, selecting different numbers of principal components in principal component analysis and Fisher's discriminant analysis. Classifications were performed in those spaces using Naive-Bayes classifier and obtained results were compared. While the highest accuracy obtained in the Fisher space was 57.87%, it was calculated as 48.02% in the principal component space.Öğe Epileptic seizureprediction based on Hilbert Huang Transform and Artificial Neural Networks(2012) Özdemir, Nilufer; Yildirim, EsenFor a patient diagnosed with epilepsy, a neurological disorder that affects the patient only during a seizure, and the following short duration for some cases, it is important to predict a seizure before it happens. EEG signal processing plays an important role in detection and prediction of epileptic seizures. The aim of this study is to develop a patient specific seizure prediction method based on Hilbert-Huang Transform. In this method EEG signals are decomposed into Intrinsic Mode Functions and first six IMFs are used to obtain features for classification of preictal and interictal recordings employing Artificial Neural Networks. Proposed method was tested on Freiburg iEEG database. A total of 58 hours of preictal data, prior to 87 seizures, and 504 hours of interictal data were examined. Algorithm resulted in 93.1% sensitivity (81 of 87 seizures) and 0.71 FPs/h using 30 seconds EEG segment with 50% overlap. © 2012 IEEE.Öğe Patient specific seizure prediction algorithm using Hilbert-Huang Transform(2012) Duman, Firat; Özdemir, Nilüfer; Yildirim, EsenEpilepsy is a neurological disorder that affects about 50 million people around the world. EEG signal processing plays an important role in detection and prediction of epileptic seizures. The aim of this study is to develop a method for early seizure prediction based on Hilbert-Huang Transform. In this patient specific method, EEG signals are decomposed into Intrinsic Mode Functions (IMFs) and first 5 IMFs are used to obtain features for classification of preictal and interictal recordings. Proposed method was tested on Freiburg EEG database. A total of 58 hours of preictal data, prior to 87 seizures, and 490 hours of interictal data were examined. Algorithm resulted in 89.66% sensitivity (78 of 87 seizures) and 0.49 FPs/h using 30 seconds EEG segment with 50% overlap. © 2012 IEEE.Öğe Patient Specific Seizure Prediction System Using Hilbert Spectrum and Bayesian Networks Classifiers(Hindawi Ltd, 2014) Ozdemir, Nilufer; Yildirim, EsenThe aim of this paper is to develop an automated system for epileptic seizure prediction from intracranial EEG signals based on Hilbert-Huang transform (HHT) and Bayesian classifiers. Proposed system includes decomposition of the signals into intrinsic mode functions for obtaining features and use of Bayesian networks with correlation based feature selection for binary classification of preictal and interictal recordings. The system was trained and tested on Freiburg EEG database. 58 hours of preictal data, 40-minute data blocks prior to each of 87 seizures collected from 21 patients, and 503.1 hours of interictal data were examined resulting in 96.55% sensitivity with 0.21 false alarms per hour, 13.896% average proportion of time spent in warning, and 33.21 minutes of average detection latency using 30-second EEG segments with 50% overlap and a simple postprocessing technique resulting in a decision (a seizure is expected/not expected) every 5 minutes. High sensitivity and low false positive rate with reasonable detection latency show that HHT based features are acceptable for patient specific seizure prediction from intracranial EEG data. Time spent for testing an EEG segment was 4.1451 seconds on average, which makes the system viable for use in real-time seizure control systems.Öğe Seizure detection via empirical mode decomposition(2011) Özdemir, Nilüfer; Duman, Firat; Yildirim, EsenEpilepsy is a neurological disorder that affects a serious number of people all around the world. Detection of epileptic seizures using EEG signals occupies an important part in the diagnosis of epilepsy. The aim of this study is to develop a method for seizure detection based on Empirical Mode Decomposition. In this method, EEG signals are decomposed to their Intrinsic Mode Functions and first 4 IMFs's maximum, minimum, mean, standart deviation and energy values are used for classification. This method was tested on 123 minutes of iktal data and 200 minutes of inter-iktal data using 3 different classifiers. For all clasifiers, over %80 sensitivity and over %95 specificity were otained. These results show that epileptic seizure detection in EEG records via EMD is very promising. © 2011 IEEE.Öğe Ultra-Wideband (UWB) characteristic estimation of elliptic patch antenna based on machine learning techniques(Walter De Gruyter Gmbh, 2020) Gencoglan, Duygu Nazan; Arslan, Mustafa Turan; Colak, Sule; Yildirim, EsenIn this study, estimation of Ultra-Wideband (UWB) characteristics of microstrip elliptic patch antenna is investigated by means of k-nearest neighborhood algorithm. A total of 16,940 antennas are simulated by changing antenna dimensions and substrate material. Antennas are examined by observing Return Loss and Voltage Standing Wave Ratio (VSWR) characteristics. In the study, classification of antennas in terms of having UWB characteristics results in accuracies higher than 97%. Additionally, Consistency based Feature Selection method is applied to eliminate redundant and irrelevant features. This method yields that substrate material does not affect the UWB characteristics of the antenna. Classification process is repeated for the reduced feature set, reaching to 97.44% accuracy rate. This result is validated by 854 antennas, which are not included in the original antenna set. Antennas are designed for seven different substrate materials keeping all other parameters constant. Computer Simulation Technology Microwave Studio (CST MWS) is used for the design and simulation of the antennas.
