Yazar "Mert, Ahmet" seçeneğine göre listele
Listeleniyor 1 - 8 / 8
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe Amputee Electromyography Signal Classification Using Convolutional Neural Network(Institute of Electrical and Electronics Engineers Inc., 2020) Onay, F.; Mert, AhmetThe classification of EMG signals for the amputees is important to develop a powered-prosthetic that is capable of replacing with lost limbs. The EMG signals collected from residual limbs reduce the classification accuracy due to muscle movements that cannot be realized properly. In this study, classification performance is aimed to be increased by combining CNN with root mean square (RMS) and waveform length (WL) that are used in analysis of EMG signals successfully. The features such as RMS and WL extracted from EMG signals for the classification of six hand movements at the low, medium, and high force levels were applied to CNN input, and classification results were compared with nearest neighbour and linear discriminant analysis. © 2020 IEEE.Öğe Değişken Kuvvetli EMG Sinyallerinin Çok Değişkenli Görgül Kip Ayrışımı ile Analizi ve Sınıflandırılması(2020) Onay, Fatih; Mert, AhmetElektromiyografi (EMG) sinyalleri, insan-makine etkileşimli akıllı el protezlerinin kontrolünde önemli bir rol oynamaktadır. Kas aktivesinin bir sonucu olarak ortaya çıkan EMG sinyalleri, yapılan aktiviteye dair özel bilgileri kendi içerisinde ihtiva etmektedir. Dolayısıyla akıllı el protezlerinin işlevselliğinin arttırılması, kas bölgesinden toplanan EMG sinyalinin doğru bir şekilde analiz edilip yorumlanmasına önemli ölçüde bağlıdır. Bu konsepte uygun olarak, akıllı el protezi hareketlerinin karar verme sürecinde, EMG sinyallerinin güvenilir bir şekilde kullanılabilmesi için, var olan yöntemlerin geliştirilmesi ya da bu yöntemlere üstünlük sağlayacak yeni yöntemler önerilmesi gerekmektedir. Bu çalışma kapsamında, çok kanallı EMG sinyallerinin analizinin geliştirilmesi amacıyla, çok değişkenli görgül kip ayrışımı (ÇDGKA) tabanlı öznitelik çıkarma yöntemi, geleneksel metotlara alternatif olarak sunulmuştur. Sinyali adaptif olarak salınım modlarına ayıran ÇDGKA yöntemi kullanılarak, EMG sinyalinden daha anlamlı bilgi edinilmesi amaçlanmıştır. ÇDGKA tabanlı özniteliklerin farklı el ve parmak hareketlerini ayırt etme performansı ve farklı kuvvet seviyelerine karşı gösterdiği performans incelenmiştir. Bu amaçla ampute katılımcıların artık uzuvlarından toplanan düşük, orta ve yüksek kuvvet seviyelerine ait EMG sinyalleri üzerinde ÇDGKA yöntemi uygulanarak özgül kip fonksiyonları (ÖKF) elde edilmiştir. Elde edilen ÖKF’lerden çıkarılan öznitelikler kullanılarak altı farklı el ve parmak hareketi, en yakın komşu (k-NN), doğrusal ayrım analizi (LDA) ve destek vektör makinesi (SVM) sınıflandırıcıları kullanılarak sınıflandırılmıştır. Aynı kuvvet seviyesinde eğitilip test edilerek (Senaryo 1) ve tüm kuvvet seviyelerinde eğitilip tek bir kuvvet seviyesinde test edilerek (Senaryo 2) gerçekleştirilen sınıflandırmalar neticesinde, önerilen ÇDGKA tabanlı özniteliklerin ham sinyal tabanlı özniteliklere göre, senaryo 1 için %10 - %15, senaryo 2 için %18’e kadar üstünlük sağladığı belirlenmiştir.Öğe Emotion recognition based on time-frequency distribution of EEG signals using multivariate synchrosqueezing transform(Academic Press Inc Elsevier Science, 2018) Mert, Ahmet; Akan, AydinThis paper investigates the feasibility of using time-frequency (TF) representation of EEG signals for emotional state recognition. A recent and advanced TF analyzing method, multivariate synchrosqueezing transform (MSST) is adopted as a feature extraction method due to multi-channel signal processing and compact component localization capabilities. First, the 32 participants' EEG recordings from DEAP emotional EEG database are analyzed using MSST to reveal oscillations. Second, independent component analysis (ICA), and feature selection are applied to reduce the high dimensional 2D TF distribution without losing distinctive component information in the 2D image. Thus, only one method for feature extraction using MSST is performed to analyze time, and frequency-domain properties of the EEG signals instead of using some signal analyzing combinations (e.g., power spectral density, energy in bands, Hjorth parameters, statistical values, and time differences etc.). As well, the TF-domain reduction performance of ICA is compared to non-negative matrix factorization (NMF) to discuss the accuracy levels of high/low arousal, and high/low valence emotional state recognition. The proposed MSST-ICA feature extraction approach yields up to correct rates of 82.11%, and 82.03% for arousal, and valence state recognition using artificial neural network. The performances of the MSST and ICA are compared with Wigner-Ville distribution (WVD) and NMF to investigate the effects of TF distributions as feature set with reduction techniques on emotion recognition. (C) 2018 Elsevier Inc. All rights reserved.Öğe Emotion recognition from EEG signals by using multivariate empirical mode decomposition(Springer, 2018) Mert, Ahmet; Akan, AydinThis paper explores the advanced properties of empirical mode decomposition (EMD) and its multivariate extension (MEMD) for emotion recognition. Since emotion recognition using EEG is a challenging study due to nonstationary behavior of the signals caused by complicated neuronal activity in the brain, sophisticated signal processing methods are required to extract the hidden patterns in the EEG. In addition, multichannel analysis is another issue to be considered when dealing with EEG signals. EMD is a recently proposed iterative method to analyze nonlinear and nonstationary time series. It decomposes a signal into a set of oscillations called intrinsic mode functions (IMFs) without requiring a set of basis functions. In this study, a MEMD-based feature extraction method is proposed to process multichannel EEG signals for emotion recognition. The multichannel IMFs extracted by MEMD are analyzed using various time and frequency domain techniques such as power ratio, power spectral density, entropy, Hjorth parameters and correlation as features of valance and arousal scales of the participants. The proposed method is applied to the DEAP emotional EEG data set, and the results are compared with similar previous studies for benchmarking.Öğe Emotion recognition using time-frequency ridges of EEG signals based on multivariate synchrosqueezing transform(De Gruyter Open Ltd, 2021) Mert, Ahmet; Celik H.H.The feasibility of using time-frequency (TF) ridges estimation is investigated on multi-channel electroencephalogram (EEG) signals for emotional recognition. Without decreasing accuracy rate of the valence/arousal recognition, the informative component extraction with low computational cost will be examined using multivariate ridge estimation. The advanced TF representation technique called multivariate synchrosqueezing transform (MSST) is used to obtain well-localized components of multi-channel EEG signals. Maximum-energy components in the 2D TF distribution are determined using TF-ridges estimation to extract instantaneous frequency and instantaneous amplitude, respectively. The statistical values of the estimated ridges are used as a feature vector to the inputs of machine learning algorithms. Thus, component information in multi-channel EEG signals can be captured and compressed into low dimensional space for emotion recognition. Mean and variance values of the five maximum-energy ridges in the MSST based TF distribution are adopted as feature vector. Properties of five TF-ridges in frequency and energy plane (e.g., mean frequency, frequency deviation, mean energy, and energy deviation over time) are computed to obtain 20-dimensional feature space. The proposed method is performed on the DEAP emotional EEG recordings for benchmarking, and the recognition rates are yielded up to 71.55, and 70.02% for high/low arousal, and high/low valence, respectively.Öğe Multivariate Empirical Mode Decomposition Based EMG Signal Analysis For Smart Prosthesis(Ieee, 2018) Onay, Fatih; Mert, AhmetElectromyography (EMG) signals are successfully used for human-robot interaction with biomedical applications. One of the basic components of many modern prosthesis is the myoelectric control system which controls prosthetic movements through EMG signals. In this study, multivariate empirical mode decomposition (MEMD) based signal processing and analysis of EMG signals was investigated in the decision making process of smart hand proshesis movements of transradial amputees. Due to MEMD's non-linear and non-stationary signal processing capability, the obtained MEMD-based features are intended to increase the performance of the controlled prosthesis using multi-channel EMG signals. The MEMD-based features obtained through the EMG signals recorded for 6 positions from 9 transradial amputees were classified by the nearest neighbors and decision tree algorithms and an average of 77% (up to 100% for some amputees) accuracy was obtained for a maximum of 9 amputees.Öğe Phasor represented EMG feature extraction against varying contraction level of prosthetic control(Elsevier Sci Ltd, 2020) Onay, Fatih; Mert, AhmetThis paper introduces phasor representation of electromyography (EMG) feature extraction (PRE). The well-known EMG signal analysis methods, namely root mean square (RMS), and waveform length (WL) are adopted into phasor form depending electrode placement. The values of these methods are computed from 8-channel EMG signals, and their magnitudes with respect to origin are used to construct phasor represented features in this study. The class separability of the PRE is strengthened by adding difference EMG and Euclidean distanced phasor in order to obtain improved feature set against force and electrode variations. The simulations (three schemes) are performed on publicly available EMG dataset on transradial amputees, and the results are presented in terms of accuracy and processing time considering the control strategies of a prosthetic hand. Linear (LDA), and quadratic (QDA) discriminant analysis, and knearest neighbor (k-NN) classifiers are trained, and tested by the PRE features. Our method outperforms previous accuracy rates in some cases, and reaches to accuracy results of the first study using this dataset without using any reduction method. In our simulations, accuracy rates up to 71.17% (PRE with QDA) for six classes hand movements with three force levels are obtained decreasing processing time by 81.83%. (C) 2020 Elsevier Ltd. All rights reserved.Öğe Seizure onset detection based on frequency domain metric of empirical mode decomposition(Springer London Ltd, 2018) Mert, Ahmet; Akan, AydinThis paper explores the data-driven properties of the empirical mode decomposition (EMD) for detection of epileptic seizures. A new method in frequency domain is presented to analyze intrinsic mode functions (IMFs) decomposed by EMD. They are used to determine whether the electroencephalogram (EEG) recordings contain seizure or not. Energy levels of the IMFs are extracted as threshold level to detect the changes caused by seizure activity. A scalar value energy resulting from the energy levels is individually used as an indicator of the epileptic EEG without the requirements of multidimensional feature vector and complex machine learning algorithms. The proposed methods are tested on different EEG recordings to evaluate the effectiveness of the proposed method and yield accuracy rate up to 97.89%.
