Yazar "Mert, Ahmet" seçeneğine göre listele
Listeleniyor 1 - 15 / 15
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 Enhanced photoacoustic signal processing using empirical mode decomposition and machine learning(Taylor & Francis Ltd, 2025) Balci, Zekeriya; Mert, AhmetIn this study, we propose a robust photoacoustic (PA) signal processing framework for a material independent defect detection using empirical mode decomposition (EMD) and machine learning algorithms. First, a database of the PA signals with 960 samples has been obtained from aluminium, iron, plastic and wood materials using a laser, microphone and data acquisition board-based PA apparatus. Second, the EMD based time and time-frequency domain techniques are proposed to extract robust cross-material feature space focusing on laser induced acoustic signal, and the decomposed intrinsic mode (IMF) with 14 extracted features are performed on totally 960 samples PA signals to evaluate k-nearest neighbour (k-NN), decision tree (DT) and support vector machine (SVM) classifiers. Inter- material and cross-material evaluations are performed, and the accuracy rates up to 100% for SVM and 97.77% for k-NN are yielded.Öğe Farklı Katı Malzemelerde Görgül Kip Analizi Tabanlı Foto Akustik Sinyal İşleme ile Kusur Tespiti(2024) Balcı, Zekeriya; Mert, AhmetBu çalışmada, görgül kip ayrışımı (GKA) ve makine öğrenimi algoritması kullanılarak malzeme kusurlarının tespiti için bir fotoakustik (FA) sinyal işleme çerçevesi önerilmiştir. Zaman ve zaman-frekans düzleminde çıkarılan özellikler ve gelişmiş sinyal işleme yöntemlerinin yardımıyla kusurların başarılı bir şekilde tespit edilmesini sağlamıştır. Lazer, mikrofon ve veri toplama kartı tabanlı bir FA sistem kullanılarak alüminyum, demir ve ahşap malzemelerden FA sinyallerinden oluşan veritabanı elde edilmiştir. Her bir malzeme grubundan toplam 240 örnek (120 sağlam örnek ve 120 kusurlu örnek) ve toplam 720 örnek, GKA uygulandıktan sonra zaman ve zaman-frekans düzlemi özelliklerini çıkarmak için kullanılmıştır. Daha sonra k-en yakın komşu sınıflandırıcısı veri tabanındaki kusurlu ve sağlam malzemelerin tespiti için çıkarılan 14 özellik kullanılarak eğitilmiş ve test edilmiştir. Materyaller özelinde ve materyaller arası sınıflandırma yapılmış ve doğruluk oranları sırasıyla %100 ve %97.77 olarak elde edilmiştir.Öğe Feature weighting concatenated multi-head self-attention for amputee EMG classification(Elsevier Sci Ltd, 2025) Bilgin, Metin; Mert, AhmetReliefF and neighborhood component analysis (NCA) concatenated multi-head self-attention (MSA) based multi-channel amputee EMG signals classification model is proposed in this paper. It is inspired by the Transformer and Vision Transformer models, and designed to be lightweight for prosthetic applications. The ReliefF and NCA layers are integrated to the MSA for class separability concatenation of 8-channel EMG signals. The contribution as weight concatenation is performed on publicly available amputee dataset, and the effects of ReliefF and NCA are compared to the conventional MSA architecture against varying contraction levels. Six hand gestures with three contraction levels are recognized using the popular features of waveform length (WL) and root mean square (RMS) depending on three evaluation schemes (within the same force level, unseen level and all levels). The proposed class separability concatenation yields up to 2.08% increase rates when compared to the conventional MSA model.Öğe Gated transformer network based EEG emotion recognition(Springer London Ltd, 2024) Bilgin, Metin; Mert, AhmetMulti-channel Electroencephalogram (EEG) based emotion recognition is focused on several analysis of frequency bands of the acquired signals. In this paper, spectral properties appeared on five EEG bands (delta\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\delta $$\end{document}, theta\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\theta $$\end{document}, alpha\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\alpha $$\end{document}, beta\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\beta $$\end{document}, gamma\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\gamma $$\end{document}) and gated transformer network (GTN) based emotion recognition using EEG signal are proposed. Spectral energies and differential entropies of 62-channel signals are converted to 3D (sequence-channel-trial) form to feed the GTN. The GTN with enhanced gated two tower based transformer architecture is fed by 3D sequences extracted from SEED and SEED-IV emotional datasets. 15 participants' states in session 1-3 are evaluated using the proposed GTN based sequence classification, and the results are repeated by 3x\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$3\small \times $$\end{document} shuffling. Totally, 135 times training and testing are performed on each dataset, and the results are presented. The proposed GTN model achieves mean accuracy rates of 98.82% on the SEED dataset and 96.77% on the SEED-IV dataset for three and four emotional state recognition tasks, respectively. The proposed emotion recognition model can be employed as a promising approach for EEG emotion recognition.Öğe Lightweight deep neural network models for electromyography signal recognition for prosthetic control(2023) Mert, AhmetIn this paper, lightweight deep learning methods are proposed to recognize multichannel electromyography (EMG) signals against varying contraction levels. The classical machine learning, and signal processing methods namely, linear discriminant analysis (LDA), quadratic discriminant analysis (QDA), root mean square (RMS), and waveform length (WL) are adopted to convolutional neural network (CNN), and long short-term memory neural network (LSTM). Eight-channel recordings of nine amputees from a publicly available dataset are used for training and testing the proposed models considering prosthetic control strategies. Six class hand movements with three contraction levels are applied to WL and RMS-based feature extraction. After that, they are formed into appropriate input dimensions, and classified using the LDA, QDA, LDA-CNN, QDA-CNN, LSTM, and CNN. Depending on three prosthetic EMG validation approaches (Scheme 1-3), the accuracy rates of 41.68%, and 47.27% are yielded by LDA, and QDA with 32- dimensional RMS, and WL features while CNN with 2 × 16 input has 82.87% (up to 88.10%). The effect of the learnable filters of the DL approaches, and signal windowing on the success rate and delay time are discussed in the paper. The simulations show that 2D-CNN (accuracy of 82.87% with 1.7 ms delay) can be successfully adapted to prosthetic control devices.Öğe Low-Cost Android Based Tele-Monitoring System for Body Temperature Measurement(Bursa Teknik Üniversitesi, 2021) Özcan, Ahmet Remzi; Mert, AhmetThe increasing number of pandemic issues require to pay attention to health conditions and social distance. The explicit sign of COVID-19 is body fever. It is a simple and affordable detection method when compared to other blood tests. However, it is required to be physically close to a visitor to measure body temperature. For this reason, we have designed and developed a low-cost microprocessor measurement system with an infrared non-contact temperature sensor, and a Bluetooth for sending to long distance. Android application has been developed to read and set the alarm function using a smart telephone or a tablet far from the visitors. With the help of these circuit and application designs, body temperatures can be checked from long distance considering the pandemic situations. The printed circuit of the microcontroller, Bluetooth, sensor, and light-dependent resistor (LDR) triggering are manufactured, and the software of the controller and the application are integrated and tested successfully.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 Photoacoustic signal to image based convolutional neural network for defect detection(Aip Publishing, 2025) Balci, Zekeriya; Mert, AhmetIn this paper, we propose a novel photoacoustic (PA) signal to image conversion based convolutional neural network (CNN) model for defect detection in materials. A low-cost computer aided PA triggering and acquisition device has been developed, and then, PA signals are stored for four types of defected and intact materials. Variational mode decomposition is applied to the dataset to extract intrinsic mode functions to convert PA signals to images as the first step of the feature extraction, and then, a lightweight CNN architecture is trained and tested using converted grayscale PA images to detect as defected or intact material. The proposed model is performed on the PA signals of aluminum, iron, wood, and plastic depending on the within-class and all-class evaluation strategies. The mean accuracy levels of 0.977 (up to 1.0) for within-class (material dependent) and 0.942 (up to 0.955) for all-class (material independent) are yielded.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%.
