Mardin Meslek Yüksekokulu

Permanent URI for this communityhttps://hdl.handle.net/20.500.12514/28

Browse

Now showing 1 - 9 of 9

Classification and analysis of epileptic EEG recordings using convolutional neural network and class activation mapping
(2021) Yildiz, Abdulnasir; Zan, Hasan; Said, Sherif; Zan, Hasan
Electrical bio-signals have the potential to be used in different applications due to their hidden nature and their ability to facilitate liveness detection. This paper investigates the feasibility of using the Convolutional Neural Network (CNN) to classify and analyze electroencephalogram (EEG) data with their time-frequency representations and class activation mapping (CAM) to detect epilepsy disease. Several types of pre-trained CNNs are employed for a multi-class classification task (AlexNet, GoogLeNet, ResNet-18, and ResNet-50) and their results are compared. Also, a novel convolutional neural network architecture comprised of two horizontally concatenated GoogLeNets is proposed with two inputs scalograms and spectrogram of the eplictic EEG signal. Four segment lengths (4097, 2048, 1024, and 512 sampling points) with three time-frequency representations (short-time Fourier, Wavelet, and Hilbert-Huang transform) are statistically evaluated. The dataset used in this research is collected at the University of Bonn. The dataset is reorganized as normal, interictal, and ictal. The maximum achieved accuracies for 4097, 2048, 1024, and 512 sampling points are 100 %, 100 %, 100 %, and 99.5 % respectively. The CAM method is used to analyze discriminative regions of time-frequency representations of EEG segments and networks' decisions. This method showed CNN models used different time and frequency regions of input images for each class with correct and incorrect predictions.
Classification and analysis of epileptic EEG recordings using convolutional neural network and class activation mapping
(Biomedical Signal Processing and Control, 2021) Zan, Hasan; Yıldız, Abdulnasir; Said, Sherif; Zan, Hasan
Electrical bio-signals have the potential to be used in different applications due to their hidden nature and their ability to facilitate liveness detection. This paper investigates the feasibility of using the Convolutional Neural Network (CNN) to classify and analyze electroencephalogram (EEG) data with their time-frequency representations and class activation mapping (CAM) to detect epilepsy disease. Several types of pre-trained CNNs are employed for a multi-class classification task (AlexNet, GoogLeNet, ResNet-18, and ResNet-50) and their results are compared. Also, a novel convolutional neural network architecture comprised of two horizontally concatenated GoogLeNets is proposed with two inputs scalograms and spectrogram of the eplictic EEG signal. Four segment lengths (4097, 2048, 1024, and 512 sampling points) with three time-frequency representations (short-time Fourier, Wavelet, and Hilbert-Huang transform) are statistically evaluated. The dataset used in this research is collected at the University of Bonn. The dataset is reorganized as normal, interictal, and ictal. The maximum achieved accuracies for 4097, 2048, 1024, and 512 sampling points are 100 %, 100 %, 100 %, and 99.5 % respectively. The CAM method is used to analyze discriminative regions of time-frequency representations of EEG segments and networks' decisions. This method showed CNN models used different time and frequency regions of input images for each class with correct and incorrect predictions.
Design and Implementation of a Maximum Power Point Tracking System for a Piezoelectric Wind Energy Harvester Generating High Harmonicity
(Sustainability, 2021) Kurt, Erol; Özhan, Davut; Bizon, Nicu; Lopez-Guede, Jose Manuel
In this work, a maximum power point tracking (MPPT) system for its application to a new piezoelectric wind energy harvester (PWEH) has been designed and implemented. The motivation for such MPPT unit comes from the power scales of the piezoelectric layers being in the order of μW. In addition, the output generates highly disturbed voltage waveforms with high total harmonic distortion (THD), thereby high THD values cause a certain power loss at the output of the PWEH system and an intense motivation is given to design and implement the system. The proposed MPPT system is widely used for many different harvesting studies, however, in this paper it has been used at the first time for such a distorted waveform to our best knowledge. The MPPT consists of a rectifier unit storing the rectified energy into a capacitor with a certain voltage called VOC (i.e., the open circuit voltage of the harvester), then a dc-dc converter is used with the help of the MPPT unit using the half of VOC as the critical value for the performance of the control. It has been demonstrated that the power loss is nearly half of the power for the MPPT-free system, the efficiency has been increased with a rate of 98% and power consumption is measured as low as 5.29 μW
Epilepsy Detection by Using Scalogram Based Convolutional Neural Network from EEG Signals
(MDPI, 2019) Türk, Ömer; Özerdem, Mehmet Siraç; Türk, Ömer
The studies implemented with Electroencephalogram (EEG) signals are progressing very rapidly and brain computer interfaces (BCI) and disease determinations are carried out at certain success rates thanks to new methods developed in this field. The effective use of these signals, especially in disease detection, is very important in terms of both time and cost. Currently, in general, EEG studies are used in addition to conventional methods as well as deep learning networks that have recently achieved great success. The most important reason for this is that in conventional methods, increasing classification accuracy is based on too many human efforts as EEG is being processed, obtaining the features is the most important step. This stage is based on both the time-consuming and the investigation of many feature methods. Therefore, there is a need for methods that do not require human effort in this area and can learn the features themselves. Based on that, two-dimensional (2D) frequency-time scalograms were obtained in this study by applying Continuous Wavelet Transform to EEG records containing five different classes. Convolutional Neural Network structure was used to learn the properties of these scalogram images and the classification performance of the structure was compared with the studies in the literature. In order to compare the performance of the proposed method, the data set of the University of Bonn was used. The data set consists of five EEG records containing healthy and epilepsy disease which are labeled as A, B, C, D, and E. In the study, A-E and B-E data sets were classified as 99.50%, A-D and B-D data sets were classified as 100% in binary classifications, A-D-E data sets were 99.00% in triple classification, A-C-D-E data sets were 90.50%, B-C-D-E data sets were 91.50% in quaternary classification, and A-B-C-D-E data sets were in the fifth class classification with an accuracy of 93.60%.
Experimental analysis and modeling of the thermal conductivities for a novel building material providing environmental transformation
(Energy Sources, Part A: Recovery, Utilization and Environmental Effects, 2021) Ünal, Fatih; Koçyiğit, Fatih; Koçyiğit, Şermin
In this study, a mathematical equation was developed to determine the thermal conductivity of the materials by producing porous heterogeneous materials with expanded vermiculite aggregates, waste basalt powder, and the mixture of molten tragacanth added building materials. Experimental thermal conductivity of the samples was determined by using the hot wire method. Experimental thermal conductivity of the samples produced varied between 0.196 W/mK and 0.522 W/mK depending on the expanded vermiculite ratio, the ratio of waste basalt powder, and the ratios of tragacanth and cement. In addition, the developed mathematical thermal conductivity ranges from 0.201 W/mK to 0.455 W/mK. The experimental values deviated from the values in the developed model in the range of 3–19%. This equation was developed based on the porosity ratio of the produced samples, the density and thermal conductivity of the materials in the samples. The thermal conductivity results obtained by the experimental and theoretically developed equation were compared with each other and it was observed that the results were compatible.
Fuels properties, characterizations and engine and emission performance analyses of ternary waste cooking oil biodiesel-diesel-propanol blends
(SUSTAINABLE ENERGY TECHNOLOGIES AND ASSESSMENTS, 2019) Bencheikh, Kamel; Atabani, A. E; Shobana, Sutha; Mohammed, M. N.; Uguz, Gediz; Arpa, Orhan; Kumar, Gopalakrishnan; Ayanoglu, Abdulkadir; Bokhari, Awais
Application of biodiesel synthesized from waste-based raw materials with numerous solvents (higher chain alcohols) in diesel engines is a topic of great interest. This article examines the effect of biodiesel-diesel-propanol ternary blends. Physio-chemical properties, fatty acids composition (FAC), FT-IR, TGA, DSC, NMR along with some selected engine and emissions performance parameters were examined. Biodiesel was produced from waste cooking oil and exhibits excellent FAC that yields kinematic viscosity, cetane number, oxidation stability, higher heating value and iodine value of 3.93mm(2)/s, 58.88, 7.43 h, 39.45 MJ/kg and 64.92 g/100 g. Propanol blended biodiesel depicted an affirmative improvement in cold flow properties and decremented density. FT-IR and NMR results confirms the existence of biodiesel-diesel-propanol and prove their qualities as reliable methods. DSC and TGA results confirm that propanol reduces the onset and crystallization temperatures of the blends. Engine and emissions performance revealed that propanol addition further increased brake specific energy consumption (BSEC) and brake specific fuel consumption (BSFC) and reduced carbon monoxide (CO), exhaust gas temperature (EGT), nitrogen oxides (NOx) and smoke. This study proves the feasibility of the ternary blends with rewarding benefits in cold flow properties and densities besides acceptable engine and emissions performance results.
Local Pattern Transformation-Based convolutional neural network for sleep stage scoring
(2023) Zan, Hasan; Yıldız, Abdulnasır; Zan, Hasan
Sleep stage scoring is essential for the diagnosis and treatment of sleep disorders. However, manual sleep scoring is a tedious, time-consuming, and subjective task. Therefore, this paper proposes a novel framework based on local pattern transformation (LPT) methods and convolutional neural networks for automatic sleep stage scoring. Unlike in previous works in other fields, these methods were not employed for manual feature extraction, which requires expert knowledge and the pipeline behind it might bias results. The transformed signals were directly fed into a CNN model (called EpochNet) that can accept multiple successive epochs. The model learns features from multiple input epochs and considers inter-epoch context during classification. To evaluate and validate the effectiveness of the proposed approach, we conducted several experiments on the Sleep-EDF dataset. Four LPT methods, including One-dimensional Local Binary Pattern (1D-LBP), Local Neighbor Descriptive Pattern (LNDP), Local Gradient Pattern (LGP), and Local Neighbor Gradient Pattern (LNGP), and different polysomnography (PSG) signals were analyzed as sequence length (number of input epochs) increased from one to five. 1D-LBP and LNDP achieved similar performances, outperforming other LPT methods that are less sensitive to local variations. The best performance was achieved when an input sequence containing five epochs of PSG signals transformed by 1D-LBP was employed. The best accuracy, F1 score, and Kohen's kappa coefficient were 0.848, 0.782, and 0.790, respectively. The results showed that our approach can achieve comparable performance to other state-of-the-art methods while occupying fewer computing resources because of the compact size of EpochNet.
Local Pattern Transformation-Based convolutional neural network for sleep stage scoring
(ScienceDirect, 2023) Zan, Hasan; Yildiz, Abdulnasır; Zan, Hasan
Sleep stage scoring is essential for the diagnosis and treatment of sleep disorders. However, manual sleep scoring is a tedious, time-consuming, and subjective task. Therefore, this paper proposes a novel framework based on local pattern transformation (LPT) methods and convolutional neural networks for automatic sleep stage scoring. Unlike in previous works in other fields, these methods were not employed for manual feature extraction, which requires expert knowledge and the pipeline behind it might bias results. The transformed signals were directly fed into a CNN model (called EpochNet) that can accept multiple successive epochs. The model learns features from multiple input epochs and considers inter-epoch context during classification. To evaluate and validate the effectiveness of the proposed approach, we conducted several experiments on the Sleep-EDF dataset. Four LPT methods, including One-dimensional Local Binary Pattern (1D-LBP), Local Neighbor Descriptive Pattern (LNDP), Local Gradient Pattern (LGP), and Local Neighbor Gradient Pattern (LNGP), and different polysomnography (PSG) signals were analyzed as sequence length (number of input epochs) increased from one to five. 1D-LBP and LNDP achieved similar performances, outperforming other LPT methods that are less sensitive to local variations. The best performance was achieved when an input sequence containing five epochs of PSG signals transformed by 1D-LBP was employed. The best accuracy, F1 score, and Kohen’s kappa coefficient were 0.848, 0.782, and 0.790, respectively. The results showed that our approach can achieve comparable performance to other state-ofthe-art methods while occupying fewer computing resources because of the compact size of EpochNet.
Multi-task learning for arousal and sleep stage detection using fully convolutional networks
(2023) Zan, Hasan; Yıldız, Abdulnasır; Zan, Hasan
Objective. Sleep is a critical physiological process that plays a vital role in maintaining physical and mental health. Accurate detection of arousals and sleep stages is essential for the diagnosis of sleep disorders, as frequent and excessive occurrences of arousals disrupt sleep stage patterns and lead to poor sleep quality, negatively impacting physical and mental health. Polysomnography is a traditional method for arousal and sleep stage detection that is time-consuming and prone to high variability among experts. Approach. In this paper, we propose a novel multi-task learning approach for arousal and sleep stage detection using fully convolutional neural networks. Our model, FullSleepNet, accepts a full-night single-channel EEG signal as input and produces segmentation masks for arousal and sleep stage labels. FullSleepNet comprises four modules: a convolutional module to extract local features, a recurrent module to capture long-range dependencies, an attention mechanism to focus on relevant parts of the input, and a segmentation module to output final predictions. Main results. By unifying the two interrelated tasks as segmentation problems and employing a multi-task learning approach, FullSleepNet achieves state-of-the-art performance for arousal detection with an area under the precision-recall curve of 0.70 on Sleep Heart Health Study and Multi-Ethnic Study of Atherosclerosis datasets. For sleep stage classification, FullSleepNet obtains comparable performance on both datasets, achieving an accuracy of 0.88 and an F1-score of 0.80 on the former and an accuracy of 0.83 and an F1-score of 0.76 on the latter. Significance. Our results demonstrate that FullSleepNet offers improved practicality, efficiency, and accuracy for the detection of arousal and classification of sleep stages using raw EEG signals as input.

Browse

Browsing Mardin Meslek Yüksekokulu by WoS Q "Q2"