Yazar "Ertugrul, Omer Faruk" seçeneğine göre listele
Listeleniyor 1 - 19 / 19
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe A novel approach for SEMG signal classification with adaptive local binary patterns(Springer Heidelberg, 2016) Ertugrul, Omer Faruk; Kaya, Yilmaz; Tekin, RamazanFeature extraction plays a major role in the pattern recognition process, and this paper presents a novel feature extraction approach, adaptive local binary pattern (aLBP). aLBP is built on the local binary pattern (LBP), which is an image processing method, and one-dimensional local binary pattern (1D-LBP). In LBP, each pixel is compared with its neighbors. Similarly, in 1D-LBP, each data in the raw is judged against its neighbors. 1D-LBP extracts feature based on local changes in the signal. Therefore, it has high a potential to be employed in medical purposes. Since, each action or abnormality, which is recorded in SEMG signals, has its own pattern, and via the 1D-LBP these (hidden) patterns may be detected. But, the positions of the neighbors in 1D-LBP are constant depending on the position of the data in the raw. Also, both LBP and 1D-LBP are very sensitive to noise. Therefore, its capacity in detecting hidden patterns is limited. To overcome these drawbacks, aLBP was proposed. In aLBP, the positions of the neighbors and their values can be assigned adaptively via the down-sampling and the smoothing coefficients. Therefore, the potential to detect (hidden) patterns, which may express an illness or an action, is really increased. To validate the proposed feature extraction approach, two different datasets were employed. Achieved accuracies by the proposed approach were higher than obtained results by employed popular feature extraction approaches and the reported results in the literature. Obtained accuracy results were brought out that the proposed method can be employed to investigate SEMG signals. In summary, this work attempts to develop an adaptive feature extraction scheme that can be utilized for extracting features from local changes in different categories of time-varying signals.Öğe A novel approach for spam email detection based on shifted binary patterns(Wiley-Hindawi, 2016) Kaya, Yilmaz; Ertugrul, Omer FarukAdvances in communication allow people flexibility to communicate in various ways. Electronic mail (email) is one of the most used communication methods for personal or business purposes. However, it brings one of the most tackling issues, called spam email, which also raises concerns about data safety. Thus, the requirement of detecting spams is crucial for keeping the users safe and saving them from the waste of time while tackling those issues. In this study, an effective approach based on the probability of the usage of the characters that has similar orders with respect to their UTF-8 value by employing shifted one-dimensional local binary pattern (shifted-1D-LBP) was used to extract quantitative features from emails for spam email detection. Shifted-1D-LBP, which can be described as an ordered set of binary comparisons of the center value with its neighboring values, is a content-based approach to spam detection with low-level information. To validate the performance of the proposed approach, three benchmark corpora, Spamassasian, Ling-Spam, and TREC email corpuses, were used. The average classification accuracies of the proposed approach were 92.34%, 92.57%, and 95.15%, respectively. Analysis and promising experimental results indicated that the proposed approach was a very competitive feature extraction method in spam email filtering. Copyright (c) 2016 John Wiley & Sons, Ltd.Öğe A Novel Approach to Diagnosis of Sleep Apnea from Snoring Signals: Ternary Pattern Method(IEEE, 2017) Kaya, Yilmaz; Sezgin, Necmettin; Ertugrul, Omer FarukIn this study, a new approach for estimation of Obstructive Sleep Apnea Syndrome (OSAS) was proposed. OSAS is a sleep disorder that affects the life comfortability in human life. Diagnosis of OSAS is usually done by expensive devices and specialist physicians. Since OSAS is serious, it should be diagnosed and treated early. In this study, a new feature extraction method is proposed for OSAS diagnosis from snoring signals. With one (1) dimensional ternary pattern method, effective attributes were extracted from raw snoring signals and identification process was performed by classification methods. According to the obtained results, 1D-TP method has shown significant success in diagnosing OSAS from snore signals. The results can be used in sleep laboratory for help to experts before put patient to the Polysomnography (PSG) test.Öğe A novel feature extraction approach for text-based language identification: Binary patterns(Gazi Univ, Fac Engineering Architecture, 2016) Kaya, Yilmaz; Ertugrul, Omer FarukLanguage identification (LI), which is a major task in natural language processing, is the process of determining the language from a given content. In this paper, a novel approach, which is based on the probability of the use of the characters that have the similar orders with respect to their UTF-8 values, was proposed. In order to evaluate and validate the proposed approach, four datasets, which contain texts in different numbers of languages, were employed. In the proposed approach, the features that were exacted by one-dimensional local binary pattern (1D-LBP) method were classified by various machine learning methods. Achieved LI accuracies in each of four employed datasets were 86.20%, 92.75%, 100% and 89.77%, respectively. The results showed that the proposed approach yields high success rates and it is an efficient way of language identification.Öğe A novel feature extraction approach in SMS spam filtering for mobile communication: one-dimensional ternary patterns(Wiley-Hindawi, 2016) Kaya, Yilmaz; Ertugrul, Omer FarukThe importance and utilization of mobile communication are increasing day by day, and the short message service (SMS) is one of them. Although SMS is a widely used communication way, it brings together a major problem, which is SMS spam messages. SMS spams do not only use vain in the mobile communication traffic but also disturb users. Based on this fact, blacklisting methods, statistical methods which are built on the frequency of occurrence of words or characters, and machine learning methods have been employed. Because punishments and legal laws are not enough to solve this problem and the Group Special Mobile number of SMS spam can easily be changed, a content-based approach must be proposed. Content-based methods showed high success in spam e-mail filtering, but it is hard in the SMS spam filtering because SMS messages are extremely short and generally contains many abbreviations. In this study, an image processing method, local ternary pattern was improved to extract features from SMS messages in the feature extraction stage. In the proposed one-dimensional ternary patterns, firstly, text message was converted to their UTF-8 values. Later, each character (its UTF-8 value) in the message was compared with its neighbors. Two different feature sets were extracted from the results of these comparisons. Finally, some machine learning methods were employed to classify these features. In order to validate the proposed approach, three different SMS corpora were used. The achieved accuracies and other employee performance measures showed that the proposed approach, one-dimensional ternary patterns, can be effectively employed in SMS spam filtering. Copyright (C) 2016 John Wiley & Sons, Ltd.Öğe A stable feature extraction method in classification epileptic EEG signals(Springer, 2018) Kaya, Yilmaz; Ertugrul, Omer FarukEpilepsy is one of the most common neurological disorders. Electroencephalogram (EEG) signals are generally employed in diagnosing epilepsy. Therefore, extracting relevant features from EEG signals is one of the major tasks in an accurate diagnosis. In this study, the local ternary patterns, which is an image processing method, was improved in order to extract robust features from epileptic EEG signals. The EEG signals that were recorded by the Department of Etymology in the Bonn University were employed in the evaluation and validation of the proposed approach. Low and up features, which were extracted by the proposed one-dimensional ternary patterns, were classified by some machine learning methods such that support vector machine, functional trees, random forest (RF), Bayes networks (BayesNet), and artificial neural network, while the highest accuracies were obtained by RF. Achieved accuracies were found successful according to the current literature.Öğe A survey on applications of machine learning algorithms in water quality assessment and water supply and management(Iwa Publishing, 2023) Oguz, Abdulhalik; Ertugrul, Omer FarukManaging water resources and determining the qualit y of surface and groundwater is one of the most significant issues fundamental to human and societal well-being. The process of maintaining water qualit y and managing water resources well involves complications due to human-induced errors. Therefore, applications that facilitate and enhance these processes have gained importance. In recent years, machine learning techniques have been applied successfully in the preservation of water quality and the management and planning of water resources. Water researchers have effectively used these techniques to integrate them into public management systems. In this study, data sources, pre-processing, and machine learning methods used in water research are briefly mentioned, and algorithms are cate-gorized. Then, a general summar y of the literature is presented on water qualit y determination and applications in water resources management. Finally, the study was detailed using machine learning investigations on two publicly shared datasets.Öğe Detection of Parkinson's disease by Shifted One Dimensional Local Binary Patterns from gait(Pergamon-Elsevier Science Ltd, 2016) Ertugrul, Omer Faruk; Kaya, Yilmaz; Tekin, Ramazan; Almali, Mehmet NuriThe Parkinson's disease (PD) is one of the most common diseases, especially in elderly people. Although the previous studies showed that the PD can be diagnosed by expert systems through its cardinal symptoms such as the tremor, muscular rigidity, disorders of movements and voice, it was reported that the presented approaches, which utilize simple motor tasks, were limited and lack of standardization. To achieve a standard approach in PD detection, an approach, which is built on shifted one-dimensional local binary patterns (Shifted 1D-LBP) and machine learning methods, was proposed. Shifted 1D-LBP is built on 1D-LBP, which is sensitive to local changes in a signal. In 1D-LBP the positions of neighbors around center data are constant and therefore, the number of patterns that can be exacted by it is limited. This drawback was solved by Shifted 1D-LBP by changeable positions of neighbors. In evaluation and validation stages, the Gait in Parkinson's Disease (gaitpdb) dataset, which consists of three gait datasets that were recorded in different tasks or experiment protocols, were employed. Statistical features were exacted from formed histograms of gait signals transformed by Shifted 1D-LBP. Whole features and selected features were classified by machine learning methods. Obtained results were compared with statistical features exacted from signals in both time and frequency domains and results reported in the literature. Achieved results showed that the proposed approach can be successfully employed in PD detection from gait. This work is not only an attempt to develop a PD detection method, but also a general-purpose approach that is based on detecting local changes in time ordered signals. (C) 2016 Elsevier Ltd. All rights reserved.Öğe Determining the optimal number of body-worn sensors for human activity recognition(Springer, 2017) Ertugrul, Omer Faruk; Kaya, YilmazRecent developments in sensors increased the importance of action recognition. Generally, the previous studies were based on the assumption that the complex actions can be recognized by more features. Therefore, generally more than required body-worn sensor types and sensor nodes were used by the researchers. On the other hand, this assumption leads many drawbacks, such as computational complexity, storage and communication requirements. The main aim of this paper is to investigate the applicability of recognizing the actions without degrading the accuracy with less number of sensors by using a more sophisticated feature extraction and classification method. Since, human activities are complex and include variable temporal information in nature, in this study one-dimensional local binary pattern, which is sensitive to local changes, and the grey relational analysis, which can successfully classify incomplete or insufficient datasets, were employed for feature extraction and classification purposes, respectively. Achieved mean classification accuracies by the proposed approach are 95.69, 98.88, and 99.08 % while utilizing all data, data obtained from a sensor node attached to left calf and data obtained from only 3D gyro sensors, respectively. Furthermore, the results of this study showed that the accuracy obtained by using only a 3D acceleration sensor attached in the left calf, 98.8 %, is higher than accuracy obtained by using all sensor nodes, 95.69 %, and reported accuracies in the previous studies that made use of the same dataset. This result highlighted that the position and type of sensors are much more important than the number of utilized sensors.Öğe EMG Signal Classification by Extreme Learning Machine(IEEE, 2013) Ertugrul, Omer Faruk; Tagluk, M. Emin; Kaya, Yilmaz; Tekin, RamazanFrom disease detection to action assessment EMG signals are used variety of field. Miscellaneous studies have been conducted toward analysis of EMG signals. In this study some statistical features of signal were derived, the best evocative features were selected via Linear Discriminant Analysis (LDA) and feature vectors were constructed. This analytic feature vectors were classified through Extreme Learning Machine (ELM). 8 channel EMG signals recorded from 10 normal and 10 aggressive actions were used as an example. By cross-comparison of the obtained results to the ones obtained via various feature identifying methods (AR coefficients, wavelet energy and entropy) and classification methods (NB, SVM, LR, ANN, PART, Jrip, J48 and LMT) the success of the proposed method was determined.Öğe Emotion recognition by skeleton-based spatial and temporal analysis(Pergamon-Elsevier Science Ltd, 2024) Oguz, Abdulhalik; Ertugrul, Omer FarukThis study introduces an automatic emotion recognition system (AER) focusing on skeletal-based kinematic datasets for enhanced human-computer interaction. Departing from conventional approaches, it achieves realtime emotion recognition in real-life situations. The dataset covers seven emotions and undergoes assessment by eight diverse machine and deep learning algorithms. A thorough investigation is undertaken by varying window sizes and data states, including raw positions and feature-extracted data. The findings imply that incorporating advanced techniques like joint-related feature extraction and robust classifier models yields promising outcomes. Dataset augmentation via varying window sizes enriches insights into real-world scenarios. Evaluations exhibit classification accuracy surpassing 99% for small windows, 94% for medium, and exceeding 88% for larger windows, thereby confirming the robust nature of the approach. Furthermore, we highlight window size's impact on emotion detection and the benefits of combining coordinate axes for efficiency and accuracy. The analysis intricately examines the contributions of features at both the joint and axis levels, assisting in making well-informed selections. The study's contributions include carefully curated datasets, transparent code, and models, all of which ensure the possibility of replication. The paper establishes a benchmark that bridges theory and practicality, solidifying the proposed approach's effectiveness in balancing accuracy and efficiency. By pioneering advanced AER through kinematic data, it sets a new standard for efficacy while driving seamless human-computer interaction through rigorous analysis and strategic design.Öğe Estimation of neurological status from non-electroencephalography bio-signals by motif patterns(Elsevier, 2019) Kaya, Yilmaz; Ertugrul, Omer FarukIn this paper, a novel feature extraction approach, which was called motif patterns, was proposed and it was employed to estimate the neurological status from non-electroencephalography (non-EEG) bio-signals. It was found from the literature that successful results were obtained by using the feature extraction methods that are sensitive to local changes such as one-dimensional local binary patterns (1D-LBP). In 1D-LBP, the local changes in a signal were determined based on the comparisons between each central value'' with its neighbors. In order to increase the sensitivity of extracted features from the local changes in a signal, each value'' in the signal was compared with its neighbor, and by this way, a motif was obtained in the result of the comparisons in a specified window. To evaluate and validate the proposed approach, the non-EEG bio-signals, which were recorded by electrodermal activity, temperature, accelerometer, heart rate, and arterial oxygen level sensors, were employed. The features that were extracted from these signals by the proposed motif patterns were classified by machine learning methods. The neurological status of each of the samples was classified accurately by the proposed approach. Furthermore, the optimal sensor types were investigated and it was found that heart rate signals are enough to estimate the neurological status. (C) 2019 Elsevier B.V. All rights reserved.Öğe Fault Detection at Power Transmission Lines by Extreme Learning Machine(IEEE, 2013) Ertugrul, Omer Faruk; Tagluk, M. Emin; Kaya, YilmazWith the increase of energy demand continuous energy transmission gained considerable attention. For a continuous energy transmission, the faulty power transmission line needs to be quickly isolated from the system. In this study, Extreme Learning Machine (ELM) possessing fast learning and high generalization capacity was used for this purpose and it was found as showing a good performance in detecting the faulty transmission line. In the study real fault signals recorded from transmission lines were used. A feature vector was formed from a cycle of the energy signal using relative entropy and classified via ELM. The obtained results were compared with the ones obtained through SVM, YSA, NB, J48 and PART learning techniques and the ones obtained in the previous studies. According the obtained results ELM both in terms of speed and performance was found superior.Öğe Gender classification from facial images using gray relational analysis with novel local binary pattern descriptors(Springer London Ltd, 2017) Kaya, Yilmaz; Ertugrul, Omer FarukGender classification (GC) is one of the major tasks in human identification that increase its accuracy. Local binary pattern (LBP) is a texture method that employed successfully. But LBP suffers a major problem; it cannot capture spatial relationships among local textures. Therefore, in order to increase the accuracy of GC, two LBP descriptors, which are based on (1) spatial relations between neighbors with a distance parameter, and (2) spatial relations between a reference pixel and its neighbor on the same orientation, were employed to extract features from facial images. Additionally, gray relational analysis (GRA) was carried out to identify gender through extracted features. Experiments on the FEI database illustrated the effectiveness of the proposed approaches. Achieved accuracies are 97.14, 93.33, and 92.50% by applying GRA with the nLBP, dLBP, and traditional LBP features, respectively. Experimental results indicated that the proposed approaches were very competitive feature extraction methods in GC. Present work also showed that the nLBP, dLBP methods were obtained more acceptable results than traditional LBP.Öğe Human identification based on accelerometer sensors obtained by mobile phone data(Elsevier Sci Ltd, 2022) Oguz, Abdulhalik; Ertugrul, Omer FarukIn order to achieve secure usage digitally, many different methodologies (i.e., pin code, fingerprint, face recognition) have been employed. In this study, a novel way of user identification, which can be expressed as a biometrical method, has been proposed. The proposed approach was based on the characteristics of mobile phone usage (position changes in carrying, talking, and other actions). To assess and validate the proposed method, a dataset, which consists of millions of data collected from users with the help of accelerometers for several months during their ordinary smartphone usage, was obtained. This large dataset was reduced by randomly taking 3000 samples from each of the 387 devices in the dataset. The arbitrarily selected signals were labeled according to one against all (or one vs. all) strategies. Extracted features were classified by the k nearest neighbor (kNN) and the randomized neural network (RNN), machine learning methods. It has been seen that behavior-based biometric recognition can be accomplished with mobile phone accelerometer data, with 99.994% success rates for kNN and 99.97% for RNN.Öğe New local binary pattern approaches based on color channels in texture classification(Springer, 2020) Tekin, Ramazan; Ertugrul, Omer Faruk; Kaya, YilmazIn this paper, four novel, simple and robust approaches, which are left to right local binary patterns (LBPLL2R), top to down local binary patterns (LBPT2D), cube surface local binary pattern (LBPSurfaces), and cube diagonal local binary pattern (LBPDiagonal), were proposed in order to exact texture features in color images. These approaches were based on the local binary pattern (LBP), which is an effective statistical texture descriptor and can be employed in gray images. Proposed approaches were evaluated and validated in four datasets, which are Outex, KTH_TIPS, KTH_TIPS2, and USPtex datasets. The images in these datasets are in RGB, HSV, YIQ, and YCbCr color formats. Achieved results by these approaches were compared with the obtained results by the classical LBP and literature findings. As a result, the proposed approaches performed better than the traditional LBP method and they found effective in the classification of color texture images, especially in images, which are in RGB and HSV formats. Furthermore, noise robustness and time complexity of the proposed approaches were validated.Öğe Randomized feed-forward artificial neural networks in estimating short-term power load of a small house: a case study(IEEE, 2017) Ertugrul, Omer Faruk; Tekin, Ramazan; Kaya, YilmazRandomized feed-forward artificial neural networks (ANNs) have been employed in various domains. This paper was written in order to assess the efficiency of the basic forms of randomized feed-forward ANNs, which are randomized weight artificial neural network, random vector functional link network, extreme learning machine, and radial bases function neural network. In order to compare these methods, a complex dataset, which is the power load of a small house dataset, was used. Obtained results showed that lower training error rates were achieved by randomized vector functional link network. On the other hand, lower test error rates were achieved by ELM. Furthermore, ELM has faster training and test stages than the other employed randomized ANNs.Öğe Smart City Planning by Estimating Energy Efficiency of Buildings by Extreme Learning Machine(IEEE, 2016) Ertugrul, Omer Faruk; Kaya, YilmazEstimation of energy efficiency is one of the major issues in smart city planning. Although, there are some papers about estimation of energy efficiency of the buildings, there is still a requirement of an effective method that can be used in all climatic zones. Therefore, extreme learning method (ELM), which is a training method for single hidden layer neural network, was employed in the dataset that contains the properties of buildings such as shape, area and height and cooling and heating loads were calculated. Achieved results by ELM were compared with the results in the literature and the results obtained by some popular machine learning methods such as artificial neural network, linear regression, and etc. Obtained results by ELM found acceptable.Öğe Two novel local binary pattern descriptors for texture analysis(Elsevier, 2015) Kaya, Yilmaz; Ertugrul, Omer Faruk; Tekin, RamazanThe recent developments in the image quality, storage and data transmission capabilities increase the importance of texture analysis, which plays an important role in computer vision and image processing. Local binary pattern (LBP) is an effective statistical texture descriptor, which has successful applications in texture classification. In this paper, two novel descriptors were proposed to search different patterns in images built on LBP. One of them is based on the relations between the sequential neighbors with a specified distance and the other one is based on determining the neighbors in the same orientation through central pixel parameter. These descriptors are tested with the Brodatz-1, Brodatz-2, Butterfly and Kylberg datasets to show the applicability of the proposed nLBP(d) and dLBP(alpha) descriptors. The proposed methods are also compared with classical LBP. The average accuracies obtained by ANN with 10 fold cross validation, which are 99.26% (LBPu2 and nLBP(d)), 94.44% (dLBP(alpha)), 95.71% (nLBP(d)(u2)) and %99.64 (nLBP(d)), for Brodatz-1, Brodatz-2, Butterfly and Kylberg datasets, respectively, show that the proposed methods outperform significant accuracies. (C) 2015 Elsevier B.V. All rights reserved.
