Mardin Meslek Yüksekokulu

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

Browse

Now showing 1 - 15 of 15

Citation - WoS: 5
Near ideals in near semigroups
(EUROPEAN JOURNAL PURE & APPLIED MATHEMATICS, 2018) Bağırmaz, Nurettin
In this paper, we introduced the notion of near subsemigroups, near ideals, near bi-ideals and homomorphisms of near semigroups on near approximation spaces. Then we give some properties of these near structures.
Citation - WoS: 23
Citation - Scopus: 36
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
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.
Citation - WoS: 32
Citation - Scopus: 32
Development software program for extraction of photovoltaic cell equivalent circuit model parameters based on the Newton–Raphson method
(SpringerLink, 2022) Adak, Süleyman; Cangi, Hasan; Yılmaz, Ahmet Serdar; Arifoğlu, Uğur
Finding the equivalent circuit parameters for photovoltaic (PV) cells is crucial as they are used in the modeling and analysis of PV arrays. PV cells are made of silicon. These materials have a nonlinear characteristic. This distorts the sinusoidal waveform of the current and voltage. As a result, harmonic components are formed in the system. The PV cell is the smallest building block of the PV system and produces voltages between 0.5 V and 0.7 V. It serves as a source of current. The amount of radiation hitting the cell determines how much current it produces. In an ideal case, a diode and a parallel current source make up the equivalent circuit of the PV cell. In practice, the addition of a series and parallel resistor is made to the ideal equivalent circuit. There are many equivalent circuits in the literature on modeling the equivalent circuit of a PV cell. The PV cell single–diode model is the most used model due to its ease of analysis. In this study, the iterative method by Newton–Raphson was used to find the equivalent circuit parameters of a PV cell. This method is one of the most widely used methods for determining the roots of nonlinear equations in numerical analysis. In this study, five unknown parameters (Iph, Io, Rs, Rsh and m) of the PV cell equivalent circuit were quickly discovered with the software program prepared based on the Newton–Raphson method in MATLAB
Citation - WoS: 3
Citation - Scopus: 6
Thin-Layer Drying Modeling in the Hot Oil-Heated Stenter
(International Journal of Thermophysics, 2020) Ünal, Fatih; Akan, Ahmet Erhan
Although the drying processes have an important place in the textile industry in terms of drying or various textile finishing applications, they are considered as an expensive process in terms of energy and time consumed. Therefore, it is of great importance to simulate with mathematical models the drying behavior of a stenter (ram machine), one of the most preferred convection dryers in the textile industry. For this purpose, in this study, modeling was attempted of the drying behavior of 67 % Cotton + 33 % Polyester containing Thessaloniki knit fabrics, using experimental data obtained from drying processes performed in 9 different drying operations in a 10-chamber hot oil-heated stenter and 12 different empirical and semi-empirical thin-layer models that are frequently used in the literature. R2 values from regression analysis were evaluated as the primary factor in the model fit selection. According to the results obtained, it was understood that the Diffusion Approach model with R2 values ranging from 0.9991 to 0.9999, Two Term Model with R2 values ranging from 0.9995 to 0.9999, and the Modified Henderson and Pabis model with R2 values ranging from 0.9995 to 0.9999 gave the most appropriate results upon simulating drying behavior. In this regard, this study, which contains explanatory information on the drying behavior in a stenter, is thought to be useful to researchers.
Citation - WoS: 11
Citation - Scopus: 13
Multi-task learning for arousal and sleep stage detection using fully convolutional networks
(IOP Publishing, 2023) Zan, Hasan; Yıldız, Abdulnasir
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.
Citation - WoS: 12
Citation - Scopus: 14
Local Pattern Transformation-Based convolutional neural network for sleep stage scoring
(ScienceDirect, 2023) Zan, Hasan; Yildiz, Abdulnasır
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.
Local Pattern Transformation-Based convolutional neural network for sleep stage scoring
(2023) Zan, Hasan; Yıldız, Abdulnasır
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.
Citation - WoS: 6
Citation - Scopus: 6
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
Physical properties of solution processable n-type Fe and Al co-doped ZnO nanostructured thin films: Role of Al doping levels and annealing
(ELSEVIER, 2018) BOZ, İbrahim; GÖKTAŞ, Abdullah; ASLAN, Ferhat; YEŞİLATA, Bülent
The role of annealing temperature and Fe and Al co-doping on structural, optical, electrical and magnetic properties of solution processable ZnO thin films were investigated. ZnO:Fe thin films fixed with 2% of typical ferrous component were obtained to examine the role of 1–10% Al doping. X-ray diffraction analyses clearly indicates that the films to be polycrystalline and preferentially oriented along the c-axis of the hexagonal wurtzite structure. The film thickness, homogeneous distribution and decreasing/increasing of grain size dependence on Al content/annealing temperature (TA) were assessed by scanning electron microscopy. X-ray photoelectron spectroscopy revealed that Al3+ and Fe2+ ions to substitute for Zn2+ without changing the wurtzite structure. A slight decrease in the optical band gap of ZnO at fixed Fe dopant and a considerable increase of the optical band gap with increased Al doping concentrations and TA were observed. The refractive index increases with the fixed Fe dopant level and then decreases by Al doping levels, whereas the extinction coefficient clearly increases depended on both of Fe and Al concentrations. The refractive index and extinction coefficient both decrease with TA. Hall measurements show n-type conductivity and the increase of charge carrier concentration by Al doping levels and TA. Magnetic studies indicate room temperature ferromagnetism in Al and Fe co-doped ZnO thin films, whereas no room temperature ferromagnetism for the Fe-doped ZnO thin films was observed. An enhanced room temperature ferromagnetism in Al and Fe co-doped ZnO thin films was observed to depend on TA.
Classification and analysis of epileptic EEG recordings using convolutional neural network and class activation mapping
(2021) Yildiz, Abdulnasir; Zan, Hasan; Said, Sherif
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.
Citation - WoS: 3
Citation - Scopus: 4
Classification of electroencephalogram records related to cursor movements with a hybrid method based on deep learning
(Wiley Online Library, 2021) Türk, Ömer
In brain computer interface (BCI), many transformation methods are used whenprocessing electroencephalogram (EEG) signals. Thus, the EEG can be represen-ted in different domains. However, designing an EEG-based BCI system withoutany transformation technique is a challenge. For this purpose, in this study, aBCI model is proposed without any transformation. The classification of cursordown and cursor up movements using the EEG signals received from the brain isaimed at in the proposed model. The EEG patterns were classified using twomethods. Firstly, EEG signals were classified by classic convolutional neural net-work (CNN). Secondly, proposed hybrid structure obtained the EEG features,which were classified by k-NN and SVM, using CNN. Classification with CNNarchitecture gave a result of 68.15% while the hybrid method using k-NN andSVM classifiers yielded 97.55% and 97.61% respectively. The hybrid proposedmethod were more successful than the studies in the literature.
Multi-task learning for arousal and sleep stage detection using fully convolutional networks
(2023) Zan, Hasan; Yıldız, Abdulnasır
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.
Citation - WoS: 78
Citation - Scopus: 91
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.
MONITORING OF WINE PROCESS AND PREDICTION OF ITS PARAMETERS WITH MID-INFRARED SPECTROSCOPY
(2015) Canal, Canan; Ozen, Banu
It was aimed to predict the chemical (ethanol, glycerol, organic acids, titratable acidity, °Brix, sugars, total phenolic and anthocyanin content) and microbiological parameters of red, rose and white wines during their processing from must to bottling using mid-infrared (IR) spectroscopy in combination with one of the multivariate statistical analysis techniques, partial least square (PLS) regression. Various spectral filtering techniques were employed before PLS regression analysis of mid-IR data. The best results were obtained from the second-order derivation for the chemical parameters except for alcohols. PLS models developed for the prediction of some of the chemical parameters have R2 values greater than 0.9, with low root mean square error values; however, prediction of microbial population from mid-IR spectroscopy did not provide accurate results. IR spectroscopic and chemical–chromatographic data were also used to investigate the differences between processing steps, and principal component analysis allowed clear separation of the beginning of the process from the rest.
Citation - WoS: 4
Citation - Scopus: 3
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.

Browse

Browsing Mardin Meslek Yüksekokulu by WoS Q "Q2"