14 sonuçlar
Arama Sonuçları
Listeleniyor 1 - 10 / 14
Öğe Forecasting financial indicators by generalized behavioral learning method(Springer Nature, 2017-08-09) Ertuğrul, Ömer Faruk; Tağluk, Mehmet EminForecasting financial indicators (indexes/prices) is a complex and a quite difficult issue because they depend on many factors such as political events, financial ratios, and economic variables. Also, the psychological facts or decision-making styles of investors or experts are other major reasons for this difficulty. In this study, a generalized behavioral learning method (GBLM) was employed to forecast financial indicators, which are the indexes/prices of 34 different financial indicators (24 stock indexes, 2 forexes, 3 financial futures, and 5 commodities). The achieved results were compared with the reported results in the literature and the obtained results by artificial neural network, which is widely used and suggested for forecasting financial indicators. These results showed that GBLM can be successfully employed in short-term forecasting financial indicators by detecting hidden market behavior (pattern) from their previous values. Also, the results showed that GBLM has the ability to track the fluctuation and the main trend.Öğe Determining relevant features in estimating short-term power load of a small house via feature selection by extreme learning machine(IEEE, 2017-11-02) Ertuğrul, Ömer Faruk; Sezgin, Necmettin; Öztekin, Abdulkerim; Tağluk, Mehmet EminEstimating short-term power load is a fundamental issue in the power distribution system. Since short-term power load is related to many parameters such as weather conditions, and time. The aim of this study is to determine the relevant parameters in estimating short-term power load not only in order to decrease the computational cost, but also to achieve higher success rates. Furthermore, by using selected features the required memory, equipment and communication costs are also decreased in real time applications. Feature selection by extreme learning machine method was used in determining relevant features. The short-term power loads of two houses (one of them has a power generation capability) were used in tests and achieved results showed lower error rates were obtained by using less number of features.Öğe EMG sinyallerinin aşırı ögrenme makinesi ile sınıflandırılması(IEEE, 2013-06-13) Ertuğrul, Ömer Faruk; Tağluk, Mehmet Emin; Kaya, Yılmaz; Tekin, Ramazan; Batman Üniversitesi Mühendislik - Mimarlık Fakültesi Bilgisayar Mühendisliği BölümüFrom 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 Kortikal bir ağ modelinin çıkış verisindeki karmaşıklık ve uyumluluk analizi(IEEE, 2013-06-13) Tekin, Ramazan; Tağluk, Mehmet Emin; Ertuğrul, Ömer Faruk; Sezgin, NecmettinDepending on the complex interconnection of billions of neurons forming cortical network excitation times and the emergence of action potentials or spike trains becomes complex and irregular. The effect of various parameters such as synaptic connections, conductivity and voltage dependent channels on the output of the network has become of research issues. In this study, based on Hodgkin-Huxley neuron model an artificial cortical network that simulates a local region of cortex was designed and the effect of probabilistic values of network parameters used in this model on irregularity and complexity of the spike trains at the neurons' output were investigated. Approximation Entropy, Spectral Entropy and Magnitude Squared Coherence methods were used for irregularity analysis.Öğe A novel version of k nearest neighbor: Dependent nearest neighbor(Elsevier, 2017-06) Ertuğrul, Ömer Faruk; Tağluk, Mehmet Emink nearest neighbor (kNN) is one of the basic processes behind various machine learning methods In kNN, the relation of a query to a neighboring sample is basically measured by a similarity metric, such as Euclidean distance. This process starts with mapping the training dataset onto a one-dimensional distance space based on the calculated similarities, and then labeling the query in accordance with the most dominant or mean of the labels of the k nearest neighbors, in classification or regression issues, respectively. The number of nearest neighbors (k) is chosen according to the desired limit of success. Nonetheless, two distinct samples may have equal distances to query but, with different angles in the feature space. The similarity of the query to these two samples needs to be weighted in accordance with the angle going between the query and each of the samples to differentiate between the two distances in reference to angular information. This opinion can be analyzed in the context of dependency and can be utilized to increase the precision of classifier. With this point of view, instead of kNN, the query is labeled according to its nearest dependent neighbors that are determined by a joint function, which is built on the similarity and the dependency. This method, therefore, may be called dependent NN (d-NN). To demonstrate d-NN, it is applied to synthetic datasets, which have different statistical distributions, and 4 benchmark datasets, which are Pima Indian, Hepatitis, approximate Sinc and CASP datasets. Results showed the superiority of d-NN in terms of accuracy and computation cost as compared to other employed popular machine learning methods.Öğe Forecasting local mean sea level by generalized behavioral learning method(Springer Nature, 2017-03-13) Ertuğrul, Ömer Faruk; Tağluk, Mehmet EminDetermining and forecasting the local mean sea level (MSL), which is a major indicator of global warming, is an essential issue to set public policies to save our future. Owing to its importance, MSL values are measured and shared periodically by many agencies. It is not easy to model or forecast MSL because it depends on many dynamic sources such as global warming, geophysical phenomena, and circulations in the ocean and atmosphere. Several of researchers applied and recommended employing artificial neural network (ANN) in the estimation of MSL. However, ANN does not take into account the order of samples, which may consist essential information. In this study, the generalized behavioral learning method (GBLM), which is based on behavioral learning theories, was employed in order to achieve higher accuracies by using samples in the training dataset and the order of samples. To evaluate and validate GBLM, MSL of seven stations around the world was picked up. These datasets were employed to forecast the local MSL for the future. Obtained results were compared with the ones obtained by ANN that is trained by extreme learning machine and the literature. The GBLM is found to be successful in terms of the achieved high accuracies and the ability to tracking trends and fluctuations of a local MSL.Öğe Enerji iletim Hatlarında oluşan arızaların aşırı öğrenme makinesi ile tespiti(IEEE, 2013-06-13) Ertuğrul, Ömer Faruk; Tağluk, Mehmet EminWith 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 Enerji̇ i̇leti̇m hatlarında Wi̇gner Vi̇lle dağılımı, gri̇ düzey eş oluşum matri̇si̇ ve örüntü tanıma yöntemleri̇ i̇le arıza anali̇zi̇(IEEE, 2012-05-30) Ertuğrul, Ömer Faruk; Tağluk, Mehmet Emin; Kaya, YılmazArtan enerji ihtiyacı, enerji iletiminin önemini artırmıştır. Enerjinin kesintisiz iletimi için arızalı iletim hattının iletim sisteminden hızla izole edilmesi gerekmektedir. Yapılan çalışmada enerji iletim hatlarında arıza ve arıza tipinin tespiti için yeni bir yöntem geliştirilmiştir. Gerçek enerji iletim hattı arıza sinyallerinin Wigner-Ville zaman frekans dağılımı elde edilmiş ve bu enerji gri düzey eş oluşum matrisi üzerine transfer edilmiştir. Bu matristen arızaya özgün birtakım özellikler çıkarılmıştır. Bu özellikler istatistiksel ve yapay zeka modelleri ile sınıflandırılarak arıza tespiti yapılmıştır. Geliştirilen yöntemin sonuçları daha önce yapılan çalışmaların sonuçları ile karşılaştırılmıştır.Öğe Hari̇ci̇ uyartı akımı ve i̇yoni̇k konsantrasyonların Hodgki̇n-Huxley si̇ni̇r modeli̇ üzeri̇ndeki̇ etki̇leri̇(IEEE, 2012-05-30) Tekin, Ramazan; Tağluk, Mehmet Emin; Ertuğrul, Ömer FarukHodgkin-Huxley (HH) nöron modeli teorik sinirbilimde çok önemli bir yere sahiptir. Çalışmada HH nöron modelini esas alınarak uyartı akım değerinin ve hücre içi ve dışı iyonik sodyum ve potasyum konsantrasyonlarının Aksiyon Potansiyeli (AP) formu üzerindeki etkileri incelenmiştir. Sodyum konsantrasyonu daha çok AP’nin genliğini etkilerken, Potasyumun AP’nin dinlenim, eşik ve hiper-polarizasyon durumunu etkilediği tespit edildi. Uyartı akım Şiddetinin artışı ise AP’nin oluşumunu daha erken tetiklediği ve bu nedenle AP/saniye sayısında artış olduğu gözlenmiştir. Bu gözlemlerin teorik nörobilimde kullanılabileceği düşünülmektedir.Öğe İki kanal yüzey EMG işareti ile el aç/kapa ve el parmaklarının sınıflandırılması(IEEE, 2017-11-02) Sezgin, Necmettin; Ertuğrul, Ömer Faruk; Tekin, Ramazan; Tağluk, Mehmet EminIn this study, two-channel surface electromyogram (sEMG) signals were used to classify hand open/close with fingers. The bispectrum analysis of the sEMG signal recorded with surface electrodes near the region of the muscle bundles on the front and back of the forearm was classified by extreme learning machines (ELM) based on phase matches in the EMG signal. EMG signals belonging to 17 persons, 8 males and 9 females, with an average age of 24 were used in the study. The fingers were classified using ELM algorithm with 94.60% accuracy in average. From the information obtained through this study, it seems possible to control finger movements and hand opening/closing by using muscle activities of the forearm which we hope to lead to control of intelligent prosthesis hands with high degree of freedom.
