Elektrik-Elektronik Mühendisliği Bölümü Koleksiyonu

Bu koleksiyon için kalıcı URI

https://hdl.handle.net/20.500.12899/18

Listeleniyor 1 - 20 / 23

Deep learning model developed by multiparametric MRI in differential diagnosis of parotid gland tumors
(Springer, 2022) Gündüz, Emrah; Alçin, Ömer Faruk; Kızılay, Ahmet; Yıldırım, İsmail Okan
Purpose: To create a new artificial intelligence approach based on deep learning (DL) from multiparametric MRI in the differential diagnosis of common parotid tumors. Methods: Parotid tumors were classified using the InceptionResNetV2 DL model and majority voting approach with MRI images of 123 patients. The study was conducted in three stages. At stage I, the classification of the control, pleomorphic adenoma, Warthin tumor and malignant tumor (MT) groups was examined, and two approaches in which MRI sequences were given in combined and non-combined forms were established. At stage II, the classification of the benign tumor, MT and control groups was made. At stage III, patients with a tumor in the parotid gland and those with a healthy parotid gland were classified. Results: A stage I, the accuracy value for classification in the non-combined and combined approaches was 86.43% and 92.86%, respectively. This value at stage II and stage III was found respectively as 92.14% and 99.29%. Conclusions: The approach presented in this study classifies parotid tumors automatically and with high accuracy using DL models.
Inductive Power Transfer for Electric Vehicle Charging Applications: A Comprehensive Review
(Multidisciplinary Digital Publishing Institute (MDPI), 2022) Aydın, Emrullah; Aydemir, Mehmet Timur; Aksöz, Ahmet; Hegazy, Omar
Nowadays, Wireless Power Transfer (WPT) technology is receiving more attention in the automotive sector, introducing a safe, flexible and promising alternative to the standard battery chargers. Considering these advantages, charging electric vehicle (EV) batteries using the WPT method can be an important alternative to plug-in charging systems. This paper focuses on the Inductive Power Transfer (IPT) method, which is based on the magnetic coupling of coils exchanging power from a stationary primary unit to a secondary system onboard the EV. A comprehensive review has been performed on the history of the evolution, working principles and phenomena, design considerations, control methods and health issues of IPT systems, especially those based on EV charging. In particular, the coil design, operating frequency selection, efficiency values and the preferred compensation topologies in the literature have been discussed. The published guidelines and reports that have studied the effects of WPT systems on human health are also given. In addition, suggested methods in the literature for protection from exposure are discussed. The control section gives the common charging control techniques and focuses on the constant current-constant voltage (CC-CV) approach, which is usually used for EV battery chargers.
An efficient fault classification method in solar photovoltaic modules using transfer learning and multi-scale convolutional neural network
(Elsevier, 2022) Korkmaz, Deniz; Açıkgöz, Hakan
Photovoltaic (PV) power generation is one of the remarkable energy types to provide clean and sustainable energy. Therefore, rapid fault detection and classification of PV modules can help to increase the reliability of the PV systems and reduce operating costs. In this study, an efficient PV fault detection method is proposed to classify different types of PV module anomalies using thermographic images. The proposed method is designed as a multi-scale convolutional neural network (CNN) with three branches based on the transfer learning strategy. The convolutional branches include multi-scale kernels with levels of visual perception and utilize pre-trained knowledge of the transferred network to improve the representation capability of the network. To overcome the imbalanced class distribution of the raw dataset, the oversampling technique is performed with the offline augmentation method, and the network performance is increased. In the experiments, 11 types of PV module faults such as cracking, diode, hot spot, offline module, and other classes are utilized. The average accuracy is obtained as 97.32% for fault detection and 93.51% for 11 anomaly types. The experimental results indicate that the proposed method gives higher classification accuracy and robustness in PV panel faults and outperforms the other deep learning methods and existing studies
A New Signal to Image Mapping Procedure and Convolutional Neural Networks for Efficient Schizophrenia Detection in EEG Recordings
(Institute of Electrical and Electronics Engineers Inc., 2022) Sobahi, Nebras; Çakar, Hakan; Arı, Berna; Alçin, Ömer Faruk; Şengür, Abdulkadir
Machine learning has been densely used in most computer-aided medical diagnosis systems. These systems not only supported the physician’s decision but also accelerate the necessitated procedures. Electroencephalography (EEG) is an essential device for measuring the brain’s electrical activities. EEG is used to detect a series of brain disorders such as epilepsy, dementia, Parkinson’s disease, and Schizophrenia (SZ). In this work, a novel method for detecting SZ using EEG recordings is suggested. Initially, the presented technique breaks down each channel of the input EEG recordings into EEG rhythms. The wavelet transform is employed to achieve this. The 1D local binary pattern (LBP) is then used to code the acquired rhythm signals. Each row of the input picture is formed by concatenating the uniform histograms of the 1D LBP coded beats. The rows of the images are formed from the channels of the input EEG signal, while the columns of the images are constructed from the rhythms. Extreme learning machines (ELM) based autoencoders (AE) are utilized at a data augmentation step. After data augmentation, the SZ and healthy cases are classified using well-known deep transfer learning. Deep transfer learning employs a variety of pre-trained deep Convolutional Neural Network (CNN) models. Various performance assessment indicators are used to evaluate the produced outcomes. An EEG dataset that Lomonosov Moscow State University released is used in experiments, and a 97.7% accuracy score is obtained. The obtained results are also compared with several recently published methods. The comparisons show that the proposed method outperforms the compared methods. IEEE
When machine learning meets fractional-order chaotic signals: detecting dynamical variations
(Elsevier, 2022) Kavuran, Gürkan
The challenge of classifying multivariate time series generated by discrete and continuous dynamical systems according to their chaotic or non-chaotic behavior has been studied extensively in the literature. The examination of noise or the variation of variables that affect a dynamic system's chaoticity will not be beneficial in analyzing structures employing random number generators (RNG) that are already assured to be chaotic. However, detecting the structural changes and their time intervals in deterministic systems with proven chaoticity can contribute to the literature in encryption applications. Machine Learning algorithms provide flexible possibilities to analyze and predict manipulations that may occur in the dynamics of chaotic and complex systems. This study proposes a deep Long-Short-Term-Memory (LSTM) network with a classification process to predict dynamical changes in a fractional-order chaotic (FOC) system. First, the appropriate system parameters are calculated to satisfy the chaotic behavior in the fractional-order Chen system. The predictive-corrective Adams-Bashforth-Moulton algorithm is used to simulate the FOC Chen system in the time domain. The Lyapunov exponents of the system were obtained according to the Wolf method. Next, three different scenarios have been designed to test and demonstrate the effectiveness of the proposed method. Synthetic FOC signals obtained after sub-sampling and statistical feature extraction processes fed the input of the deep bidirectional LSTM (BiLSTM) network to perform the training and testing process. The classification performance for "q" and "c" classes reaches 100% with the proposed model. The overall average testing accuracy, sensitivity, specificity, precision, F1 score and MCC are 98%, 98%, 99.3%, 98.1%, 98%, and 97.3%, respectively. Our results demonstrate the utility of using a deep BiLSTM network for detecting dynamical variations in nonlinear FOC systems.
Altitude and Attitude Control of a Quadcopter Based on Neuro-Fuzzy Controller
(Springer Science and Business Media Deutschland GmbH, 2022) Korkmaz, Deniz; Açıkgöz, Hakan; Üstündağ, Mehmet
In this paper, a 6-degrees of freedom (DoF) nonlinear dynamic model of the quadcopter is derived and a robust altitude and attitude control is proposed. The motion control is performed with four neuro-fuzzy controllers that ensure rapid and robust performances for nonlinear and uncertain systems. The aim of the designed control scheme is to provide to track the desired yaw, pitch, roll, and altitude trajectories simultaneously. The simulations are realized in the MATLAB/Simulink environment. The obtained results show that the designed control scheme is robust and efficient in both altitude and attitude responses with different uncertain trajectories.
Optimal PI Kontrolör Tasarımı için Üçgenler Ağında Lineer Enterpolasyon Yöntemiyle Kararlılık Sınır Yüzeyinin Oluşturulması
(Bitlis Eren Üniversitesi, 2020) Kavuran, Gürkan
Bu çalışmada, PI parametrelerinin grafiksel olarak hesaplanması için geliştirilen kararlılık sınır eğrisi kullanılarak, yeni bir yaklaşım önerilmiştir. Geleneksel kararlılık sınır eğrisi, kapalı çevrim sistemin karakteristik polinomu kullanılarak, kontrolör parametrelerinin belirli bir frekans aralığında birbirine göre çizimiyle elde edilir. Kararlılık sınır eğrisi altında kalan bölgedeki herhangi kp ve ki değerinin sistemi kararlı yaptığı bilinmektedir. Ancak hatanın değişimine göre hangi parametrelerin optimal sonuç verdiği kesin değildir. KSE altında kalan her nokta belirli bir frekans aralığında dağınık veri enterpolasyon yöntemine göre belirlenerek, 3 boyutlu kararlılık sınır yüzeyi (KSY) oluşturulmuştur. Çoğunlukla sistem kararlılığını garanti eden bu noktalar kullanılarak, kararlı kp ve ki parametre havuzu oluşturulmuştur. Havuzdaki her bir kp ve ki değerinin birbiriyle olan kombinasyonu kullanılarak, ITAE kriterine göre referans girdi ile sistem çıkışı arasındaki farkı minimize eden optimal PI parametreleri elde edilmiştir. Böylece hem kararlılık hem de optimallik sağlanmıştır. Benzetim çalışmalarının yanı sıra, çift rotorlu model helikopter sistemi üzerinde önerilen yöntemin geçerliliği test edilmiştir.
EMG Sinyalleri Kullanılarak GoogLeNet ve Çok Seviyeli DPD ile El Tutma Hareketlerinin Sınıflandırılması
(Fırat University, 2022) Özküçük, Muhammed Buğracan; Alçin, Ömer Faruk; Gençoğlu, Muhsin Tunay
Elektromiyografi (EMG) elektriksel aktiviteyi ölçmek için kullanılan bir yöntemdir. Bu yöntem günümüzde hastalık tespitinde kullanılmasıyla yaygınlaşmış olsa da robotik, protez kontrolü, video oyunları gibi popüler alanlarda yer edinmiştir. Bu çalışmada altı temel el hareketinin EMG sinyalleri kullanılarak sınıflandırılması amaçlanmıştır. Bu amaç doğrultusunda transfer öğrenme yaklaşımı kullanılmıştır. EMG sinyalleri çok seviyeli dalgacık paket dönüşümü (DPD) ile zaman-frekans (ZF) görüntülerine çevrilmiştir. Bütün kanallara ait ZF görüntülerinin %80’i birleştirilerek GoogLeNet mimarisini eğitmek için kullanılmıştır. Hareket tanımada başarımı artırmak için GoogLeNet’ten elde edilen öznitelikler Destek Vektör Makinesi (DVM) ile sınıflandırılmıştır. Önerilen yöntem altı temel el hareketini tanımada %98.833 doğruluk oranına sahiptir. Önerilen yöntem aynı veri setini kullanan yöntemler ile karşılaştırılmıştır. Yapılan karşılaştırmalar sonucunda önerilen yöntemin mevcut yöntemlerden %0.8 daha yüksek performans sergilediği görülmüştür. Deneysel çalışmalar önerilen yaklaşımın EMG ile hareket tanımada kullanılabilecek etkin ve verimli bir yöntem olduğunu göstermiştir
A Novel Analog Modulation Classification: Discrete Wavelet Transform-Extreme Learning Machine (DWT-ELM)
(Bitlis Eren Üniversitesi, 2021) Üstündağ, Mehmet
The aim of this study is to propose a method using discrete wavelet transform and extreme learning machine (DWT-ELM) in classification of communication signals. Six types of analog modulated signals as “AM”, “DSB”, “USB”, “LSB”, “FM” and “PM” are used for classification and analog modulated signal dataset consists of 1920 signals. These signals are also added white noise. Feature extraction is performed using different DWT filters. The feature vector obtained from DWT is used in classification. ELM is preferred due to its advantages over conventional back-propagation based classification. The feature vector is fed by the inputs of the ELM. The performance of the proposed method is evaluated for different types of DWT filters. In addition, compared results with similar study are presented to be able to determine the success of the proposed method.
Long Short-Term Memory Network-based Speed Estimation Model of an Asynchronous Motor
(IEEE (Institute of Electrical and Electronics Engineers), 2021) Açıkgöz‬, ‪Hakan; Korkmaz, Deniz
In this paper, an effective deep rotor speed estimation model of an asynchronous motor is presented. The estimation model is based on the long short-term memory (LSTM) network which is one of the deep learning models. The designed model includes three main steps as the preprocessing, training of the deep speed estimation model, and evaluation of the model with testing. The dataset of the asynchronous motor model is obtained in MATLAB/Simulink environment under variable step speed references. The input parameters of the network are the dq-axis currents (id, iq) and voltages (vd, vq). The output is selected as the rotor speed (wr). The whole data is normalized to increase the estimation performance and then randomly divided into the training and validation. For the testing stage, different test data is also constructed. In the training process, the variation of the network performance is analyzed according to the neuron number increasing and optimum neuron number is achieved. The obtained results show that the proposed model is robust and efficient under the variable step speed references.
A 1-kW wireless power transfer system for electric vehicle charging with hexagonal flat spiral coil
(TÜBİTAK / Turkiye Bilimsel ve Teknik Araştırma Kurumu, 2021) Aydın, Emrullah; Aydemir‬‪, Mehmet Timur
Wireless power transfer (WPT) technology is getting more attention in these days as a clean, safe, and easy alternative to charging batteries in several power levels. Different coil types and system structures have been proposed in the literature. Hexagonal coils, which have a common usage for low power applications, have not been well studied for high and mid power applications such as in electric vehicle (EV) battery charging. In order to fill this knowledge gap, the self and mutual inductance equations of a hexagonal coil are obtained, and these equations have been used to design a 1 kW WPT system with hexagonal coils for a mid-power stage EV charging. The theoretical and simulation results have been validated with an implementation in the laboratory and a DC-to-DC power efficiency of 85% is achieved across a 10 cm air gap between the perfect aligned coils. The misalignment performance of the system was observed for different positioning of the secondary coil, and the output power variation is given. In addition, the effect of shielding on magnetic field exposition of a driver sitting in an EV was obtained, and these simulation results were compared in order to check the compliance with international health standards.
MTU-COVNet: A hybrid methodology for diagnosing the COVID-19 pneumonia with optimized features from multi-net
(Elsevier, 2022) Kavuran, Gürkan; İn, Erdal; Altıntop Geçkil, Ayşegül; Şahin, Mahmut; Kırıcı Berber, Nurcan
COVID-19PneumoniaArtificial intelligence (AI)Deep learningComputed tomography (CT)
Deep rhythm and long short term memory-based drowsiness detection
(Elsevier, 2021) Türkoğlu, Muammer; Alçin, Ömer Faruk; Aslan, Muzaffer; Al-Zebari, Adel; Şengur, Abdülkadir
In this paper, a deep-rhythm-based approach is proposed for the efficient detection of drowsiness based on EEG recordings. In the proposed approach, EEG images are used instead of signals where the time and frequency information of the EEG signals are incorporated. The EEG signals are converted to EEG images using the time-frequency transformation method. The Short-Time-Fourier-Transform (STFT) is used for this transformation due to its simplicity. The rhythm images are then extracted by dividing the EEG images based on frequency intervals. EEG signals contain five rhythms, namely Delta rhythm (0–4?Hz), Theta rhythm (4–8?Hz), Alpha rhythm (8–12?Hz), Beta rhythm (12–30?Hz), and Gamma rhythm (30–50?Hz). From each rhythm image, deep features are extracted based on a pre-trained convolutional neural network (CNN) model, with pre-trained residual network (ResNet) models such as ResNet18, ResNet50, and ResNet101. The obtained deep features from each rhythm image are fed into the Long-Short-Term-Memory (LSTM) layer, and the LSTM layers are then sequentially connected to each other. After the last LSTM layer, a fully-connected layer, a softmax layer, and a classification layer are employed in order to detect the class labels of the input EEG signals. Various experiments were conducted with the MIT/BIH Polysomnographic Dataset. The experiments showed that the concatenated ResNet features achieved an accuracy score of 97.92%. The obtained accuracy score was also compared with the state-of-the-art scores and, to the best of our knowledge, the proposed method achieved the best accuracy score among the methods compared.
A new semi-analytical approach for self and mutual inductance calculation of hexagonal spiral coil used in wireless power transfer systems
(Springer, 2021) Aydın, Emrullah; Yıldız, Emin; Aydemir, Mehmet Timur
Several methods have been proposed in the literature for the calculation of self and mutual inductance. These methods include the use of complex integral analysis, the necessity of having primary and secondary coils with the same dimensions and the limitations of the ratio of the coil dimension to the distance between the coils. To overcome these restrictions, a new semi-analytical estimation method has been proposed in this paper. Calculation the self and mutual inductance by using the same basic formula which is based on Biot Savart Law prevents the formation of complex integrals and helps create a simple solution method. In order to verify the results obtained with the analytical approach, two hexagonal coils with 10 and 20 cm outer side lengths were produced by using litz wire with a conductive cross section of 1.78 mm2. The results obtained with the new approach are compared with the finite element analysis, other work presented in the literature and experimental results in order to prove the accuracy of the proposed method.
A New Framework for Automatic Detection of Patients With Mild Cognitive Impairment Using Resting-State EEG Signals
(IEEE (Institute of Electrical and Electronics Engineers), 2020) Siuly, Siuly; Alçin, Ömer Faruk; Kabir, Enamul; Şengür, Abdulkadir; Wang, Hua; Zhang, Yanchun; Whittaker, Frank
Mild cognitive impairment (MCI) can be an indicator representing the early stage of Alzheimier's disease (AD). AD, which is the most common form of dementia, is a major public health problem worldwide. Efficient detection of MCI is essential to identify the risks of AD and dementia. Currently Electroencephalography (EEG) is the most popular tool to investigate the presenence of MCI biomarkers. This study aims to develop a new framework that can use EEG data to automatically distinguish MCI patients from healthy control subjects. The proposed framework consists of noise removal (baseline drift and power line interference noises), segmentation, data compression, feature extraction, classification, and performance evaluation. This study introduces Piecewise Aggregate Approximation (PAA) for compressing massive volumes of EEG data for reliable analysis. Permutation entropy (PE) and auto-regressive (AR) model features are investigated to explore whether the changes in EEG signals can effectively distinguish MCI from healthy control subjects. Finally, three models are developed based on three modern machine learning techniques: Extreme Learning Machine (ELM); Support Vector Machine (SVM) and K-Nearest Neighbours (KNN) for the obtained feature sets. Our developed models are tested on a publicly available MCI EEG database and the robustness of our models is evaluated by using a 10-fold cross validation method. The results show that the proposed ELM based method achieves the highest classification accuracy (98.78%) with lower execution time (0.281 seconds) and also outperforms the existing methods. The experimental results suggest that our proposed framework could provide a robust biomarker for efficient detection of MCI patients.
Electrocardiogram beat classification using deep convolutional neural network techniques
(Institute of Physics Publishing, 2020) Cömert, Zafer; Akbulut, Yaman; Akpınar, Muhammed H.; Alçin, Ömer Faruk; Budak, Ümit; Aslan, Muzaffer; Şengür, Abdulkadir
The electrocardiogram (ECG) is a useful method which enables the monitoring of various cardiac conditions, such as arrhythmia and heart rate variability (HRV). ECG beats help to determine various heart failures such as cardiac disease and ventricular tachyarrhythmia. In the literature, it can be seen that various advanced signal processing and machine learning techniques and deep learning algorithms have been employed for ECG beat categorization. These methods were generally based on either the time domain or frequency domain. Time-frequency (T-F) based techniques have also been proposed for ECG beat classification. In this chapter, a different model is proposed for the ECG beat classification task. In the proposed approach, the ECG beats are initially represented by images. Instead of using a time-frequency approach for converting the ECG beats to ECG images, we opt to use the ECG beats directly to construct the ECG images. In other words, the ECG beat values are directly saved as ECG images. Three deep convolutional neural network (CNN) approaches are considered in ECG beat classification. These approaches ensure end-to-end learning schema, fine-tuning of pre-trained CNN models, extraction of deep features and their classification using a traditional classifier, such as the support vector machine (SVM) or deep machine learning approaches. The well-known MIT-BIH arrhythmia database is considered in the evaluation of the proposed deep learning approaches. The database is separated into two sets, the training and test dataset in proportions of 75% and 25%, respectively. The experimental results are evaluated using the classification accuracy score. The results show that the proposed methods have potential for use in ECG beat classification.
Classification of physical actions from surface EMG signals using the wavelet packet transform and local binary patterns
(Institute of Physics Publishing, 2020) Alçin, Ömer Faruk; Budak, Ümit; Aslan, Muzaffer; Akbulut, Yaman; Cömert, Zafer; Akpınar, Muhammed H.; Şengür, Abdulkadir
Physical action recognition is a hot topic in human-machine interactions. It has potential uses in helping disabled people and in various robotic applications. Electromyography (EMG) signals measure the electrical activity of the muscular systems involved in physical actions. In this chapter, an efficient approach is developed for physical action recognition in humans based on EMG signals. The proposed method is composed of signal decomposition, feature extraction and feature classification. The signal decomposition is carried out using the wavelet packet transform (WPT). The WPT successively decomposes an input signal into its approximation and detail coefficients, which offers a more productive signal analysis. A one-dimensional local binary pattern (LBP) is used to code the approximation and detail coefficients of the decomposed EMG signals. The histogram of the LBP is used as the feature vectors of the EMG physical action classes. The support vector machine (SVM), decision tree, linear discriminant, k-nearest neighbors (k-NN), boosted and bagged tree ensemble classifiers are used in the classification stage. A dataset taken from the UCI machine learning repository is used in the experiments. The Delsys EMG apparatus, which has eight electrodes, is used to record the surface EMG signals. Each class of the dataset contains three male subjects and one female subject. The dataset contains ten physical actions, namely hugging, jumping, bowing, clapping, handshaking, running, sitting, standing, walking and waving. The experiments are carried out on each electrode with a ten-fold cross-validation test, and the average accuracy score is calculated. The experimental results show that the proposed method is quite efficient in EMG signal classification. The calculated average accuracy is 100% for each electrode.
SolarNet: A hybrid reliable model based on convolutional neural network and variational mode decomposition for hourly photovoltaic power forecasting
(Elsevier, 2021) Korkmaz, Deniz
Photovoltaic (PV) power generation has high uncertainties due to the randomness and imbalance nature of solar energy and meteorological parameters. Hence, accurate PV power forecasts are essential in the operation of PV power plants (PVPP) for short-term dispatches and power generation schedules. In this study, a novel convolutional neural network (CNN) model, namely SolarNet, is proposed for short-term PV output power forecasting under different weather conditions and seasons. The proposed CNN model is designed as a parallel pooling structure to increase the forecasting performance. This structure consists of max-pooling and average-pooling blocks. The input parameters are the measured historical solar radiation, temperature, humidity, and active power data. The power data is decomposed into sub-components with the variational mode decomposition method and a data preprocessing and reconstruction process is utilized to obtain deep input feature maps. After input parameters are converted to hue-saturation-value (HSV) color space, the subsets feed to the input of the network. The experimental studies are performed with a case study using a 23.40 kW PVPP dataset from the Desert Knowledge Australia Solar Centre. The design CNN model is also compared with benchmark deep learning methods. In the experiments, the average correlation coefficient (R), root mean square error (RMSE), and mean absolute error (MAE) of the proposed method for 1-h different weather conditions are achieved as 0.9871, 0.3090, and 0.1750, respectively. The experimental results show that the proposed deep forecasting method has higher accuracy and stability in short-term PV power forecasting and outperforms the other deep learning methods.
WSFNet: An efficient wind speed forecasting model using channel attention-based densely connected convolutional neural network
(Elsevier, 2021) Açıkgöz‬, ‪Hakan; Budak, Ümit; Korkmaz, Deniz; Yıldız, Ceyhun
This paper introduces a novel deep neural network (WSFNet) to efficiently forecast multi-step ahead wind speed. WSFNet forms the basis of the stacked convolutional neural network (CNN) with dense connections of different blocks equipped with the channel attention (CA) module. Dense connections create direct transition paths between the input and all subsequent convolutional blocks. This encourages the reuse of all activations at the network input without loss of gradients in subsequent layers. The CA modules contribute significantly to the performance of the network by suppressing non-useful features extracted by each convolution block. In the proposed method, variational mode decomposition (VMD) was utilized to provide an effective preprocessing and improve the forecasting ability. The case study was conducted on publicly available data from Sotavento Galicia (SG) wind farm. In the evaluations, three variants of the proposed network were analyzed and compared with state-of-the-art deep learning methods. When the results were analyzed, the overall correlation coefficient (R), root mean square error (RMSE), mean absolute error (MAE), and symmetric mean absolute percentage error (SMAPE) were obtained as 0.9705, 0.7383, 0.5826, and 0.0466, respectively. The obtained results indicate that the proposed method achieved a competitive performance and can be effectively used for smart-grid operations.
Two-stepped majority voting for efficient EEG-based emotion classification
(Springer, 2020) Ismael, Aras Masood; Alçin, Ömer Faruk; Abdalla, Karmand Hussein; Şengür, Abdulkadir
In this paper, a novel approach that is based on two-stepped majority voting is proposed for efficient EEG-based emotion classification. Emotion recognition is important for human-machine interactions. Facial features- and body gestures-based approaches have been generally proposed for emotion recognition. Recently, EEG-based approaches become more popular in emotion recognition. In the proposed approach, the raw EEG signals are initially low-pass filtered for noise removal and band-pass filters are used for rhythms extraction. For each rhythm, the best performed EEG channels are determined based on wavelet-based entropy features and fractal dimension-based features. The k-nearest neighbor (KNN) classifier is used in classification. The best five EEG channels are used in majority voting for getting the final predictions for each EEG rhythm. In the second majority voting step, the predictions from all rhythms are used to get a final prediction. The DEAP dataset is used in experiments and classification accuracy, sensitivity and specificity are used for performance evaluation metrics. The experiments are carried out to classify the emotions into two binary classes such as high valence (HV) vs low valence (LV) and high arousal (HA) vs low arousal (LA). The experiments show that 86.3% HV vs LV discrimination accuracy and 85.0% HA vs LA discrimination accuracy is obtained. The obtained results are also compared with some of the existing methods. The comparisons show that the proposed method has potential in the use of EEG-based emotion classification.

Güncel Gönderiler