23 sonuçlar
Arama Sonuçları
Listeleniyor 1 - 10 / 23
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 Grasshopper optimization algorithm for automatic voltage regulator system(IEEE, 2018-06-21) Ekinci, Serdar; Hekimoğu, BaranA novel design method is presented to determine optimum proportional-integral-derivative (PID) controller parameters of an automatic voltage regulator (AVR) system utilizing the grasshopper optimization algorithm (GOA). The proposed approach is a simple and effective algorithm that is able to solve many optimization problems even those with unknown search spaces effectively. The simplicity of algorithm provides high quality tuning of optimal PID controller parameters. The integral of time weighted squared error (ITSE) is used as the performance index to confirm the performance of the proposed GOA-PID controller. When compared to the other PID controllers based on Ziegler- Nichols (ZN), differential evolution (DE), and artificial bee colony (ABC) tuning methods, the proposed method is found highly effective and robust to improve AVR system's transient response.Öğe Laws doku enerji ölçümü tabanli k-NN siniflandirici modeli ile iris tanima sistemi(IEEE, 20013-06-13) Acar, Emrullah; Özerdem, Mehmet SiraçBiyometrik tanıma teknolojisi genellikle çok pahallı ve son derece önemli güvenlik uygulamaları ile ilişkili olmuştur.İris tanıma sistemi, etkili biyometrik tanımasistemlerinden biridir. Bu çalışmada, farklı insanlardan elde edilen gözimgelerininiçerdiği irisdokuözelliklerinegörekişilerin tanınmasıamaçlanmıştır. İmgeler CASIAiris veritabanındanelde edilmiştir. İmge dokusuna duyarlı yeni yöntemlerdenbiri olanLawsDoku Enerji Ölçümü (Laws TEM) kullanılarak, iris dokusunun belirli yerelalanlarındanöznitelik vektörleri elde edilmiştir. kEn Yakın Komşu (k-NN) sınıflandırıcıparametrelerinden komşu sayısı(k) farklı değerlerde alınarak, elde edilen öznitelik vektörleri k-NN sınıflandırıcısı ile ayrıştırılmıştır. Farklı komşu sayılarına göre sisteminperformans değerlerikarşılaştırılmıştır. Sonuç olarak en yüksek ortalama performans,k-NNsınıflandırıcısınınk=1ve 2komşularıyapısında % 80.74olarak gözlemlenmiştir.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 Salp sürüsü algoritması kullanılarak AVR sistemi için PID kontrolör ayarı(IEEE, 2019-01-24) Ekinci, Serdar; Hekimoğu, BaranBu makalede salp sürüsü algoritması (SSA) adında yeni bir yapay zekaya dayalı optimizasyon metodu otomatik gerilim regülatörü (AVR) sisteminin en uygun oransal, integral, türevsel (PID) kontrolör parametrelerinin belirlemesi amacıyla kullanılmıştır. Algoritmanın basitliği, optimal PID kontrolör parametrelerinin yüksek kaliteli ayarını sağlar. Kontrolör parametrelerinin optimize edilmesi için zaman ağırlıklı karesel hatanın integrali (ITSE) amaç fonksiyonu olarak seçildi. Geçici hal cevap analizi, SSA metodunun Ziegler-Nichols (ZN) geleneksel ayarlama yönteminden ve yapay arı kolonisi (ABC) algoritmasından daha iyi bir ayarlama kabiliyetine sahip olduğunu ve bir AVR sisteminin basamak cevabını iyileştirmede daha verimli olduğunu ortaya koymuştur.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 Dalgacık dönüşümü tabanlı parmak izi tanıma(IEEE, 2015-06-19) Çalışkan, Abidin; Ertuğrul, Ömer FarukBir biyometrik sistem, bir bireyin sahip olduğu karakteristik veya eşsiz özniteliğe dayalı olarak otomatik tanımlamayı sağlar. Parmak izi, günümüzde birçok alanda geniş bir kullanım alanına sahip bir biyometrik sistemdir. Özellikle insan kimliğinin doğrulanması ve tespit edilmesinde kullanılan parmak izi, erişim için geleneksel olarak kullanılan yöntemlere göre daha güvenilirdir. Bu çalışmada, Gabor dalgacık dönüşümü tabanlı parmak izi tanıma sistemi gerçekleştirilmiştir. Gri seviye parmak izi imgelerinden dalgacık öznitelikleri çıkarılmıştır. Son olarak, parmak izi imgelerinin tanınmasında k en yakın komşuluk sınıflandırıcısı kullanılmıştır. Önerilen algoritma, PolyU yüksek çözünürlüklü parmak izi veri tabanı görüntüleri üzerinde test edilmiştir. Deneysel sonuçlar, önerilen yöntemin mevcut metotların doğruluğunu arttırabildiğini göstermiştir.Öğe Recognition of daily and sports activities(IEEE, 201-01-24) İnanç, Nihat; Kayri, Murat; Ertuğrul, Ömer FarukSince being physically inactive was reported as one of the major risk factor of mortality, classifying daily and sports activities becomes a critical task that may improve human life quality. In this paper, the daily and sports activities dataset was used in order to evaluate and validate the employed approach. In this approach, the statistical features were extracted from the histograms of the local changes in the wearable sensors logs were obtained by one-dimensional local binary patterns. Later, extracted features were classified by extreme learning machines. Results were showed that the proposed approach is enough to recognize the action type, but in order to recognize the actions, or gender, different feature extraction methods must be employed.Öğe Randomized feed-forward artificial neural networks in estimating short-term power load of a small house: A case study(IEEE, 2017-11-02) Ertuğrul, Ömer Faruk; Tekin, Ramazan; Kaya, YılmazRandomized 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 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.
- «
- 1 (current)
- 2
- 3
- »
