8 sonuçlar
Arama Sonuçları
Listeleniyor 1 - 8 / 8
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 electricity load by a novel recurrent extreme learning machines approach(Elsevier, 2016-06) Ertuğrul, Ömer FarukGrowth in electricity demand also gives a rise to the necessity of cheaper and safer electric supply and forecasting electricity load plays a key role in this goal. In this study recurrent extreme learning machine (RELM) was proposed as a novel approach to forecast electricity load more accurately. In RELM, extreme learning machine (ELM), which is a training method for single hidden layer feed forward neural network, was adapted to train a single hidden layer Jordan recurrent neural network. Electricity Load Diagrams 2011-2014 dataset was employed to evaluate and validate the proposed approach. Obtained results were compared with traditional ELM, linear regression, generalized regression neural network and some other popular machine learning methods. Achieved root mean square errors (RMSE) by RELM were nearly twice less than obtained results by other employed machine learning methods. The results showed that the recurrent type ANNs had extraordinary success in forecasting dynamic systems and also time-ordered datasets with comparison to feed forward ANNs. Also, used time in the training stage is similar to ELM and they are extremely fast than the others. This study showed that the proposed approach can be applied to forecast electricity load and RELM has high potential to be utilized in modeling dynamic systems effectively.Öğe Improved kidney-inspired algorithm approach for tuning of PID controller in AVR system(IEEE, 2019-03-22) Ekinci, Serdar; Hekimoğu, BaranThis paper proposes a novel tuning design of proportional integral derivative (PID) controller via an improved kidney-inspired algorithm (IKA) with a new objective function. The main objective of the proposed approach is to optimize the transient response of the AVR system by minimizing the maximum overshoot, settling time, rise time and peak time values of the terminal voltage, and eliminating the steady state error. After obtaining the optimal values of the three gains of the PID controller (K P , K I , and K D ) with the proposed approach, the transient response analysis was performed and compared with some of the current heuristic algorithms-based approaches in literature to show the superiority of the optimized PID controller. In order to evaluate the stability of the automatic voltage regulator (AVR) system tuned by IKA method, the pole/zero map analysis and Bode analysis are performed. Finally, the robustness analysis of the proposed approach has been carried out with variations in the parameters of the AVR system. The numerical simulation results demonstrated that the proposed IKA tuned PID controller has better control performances compared to the other existing approaches. The essence of the presented study points out that the proposed approach may successfully be applied for the AVR system.Öğe A novel type of activation function in artificial neural networks: Trained activation function(Elsevier, 2018-03) Ertuğrul, Ömer FarukDetermining optimal activation function in artificial neural networks is an important issue because it is directly linked with obtained success rates. But, unfortunately, there is not any way to determine them analytically, optimal activation function is generally determined by trials or tuning. This paper addresses, a simpler and a more effective approach to determine optimal activation function. In this approach, which can be called as trained activation function, an activation function was trained for each particular neuron by linear regression. This training process was done based on the training dataset, which consists the sums of inputs of each neuron in the hidden layer and desired outputs. By this way, a different activation function was generated for each neuron in the hidden layer. This approach was employed in random weight artificial neural network (RWN) and validated by 50 benchmark datasets. Achieved success rates by RWN that used trained activation functions were higher than obtained success rates by RWN that used traditional activation functions. Obtained results showed that proposed approach is a successful, simple and an effective way to determine optimal activation function instead of trials or tuning in both randomized single and multilayer ANNs.Öğe Extreme learning machine model for water network management(Springer Nature, 2017-04-22) Sattar, Ahmed M.A.; Ertuğrul, Ömer Faruk; Gharabaghi, Bahram; McBean, Edward Arthur; Cao, JiuwenA novel failure rate prediction model is developed by the extreme learning machine (ELM) to provide key information needed for optimum ongoing maintenance/rehabilitation of a water network, meaning the estimated times for the next failures of individual pipes within the network. The developed ELM model is trained using more than 9500 instances of pipe failure in the Greater Toronto Area, Canada from 1920 to 2005 with pipe attributes as inputs, including pipe length, diameter, material, and previously recorded failures. The models show recent, extensive usage of pipe coating with cement mortar and cathodic protection has significantly increased their lifespan. The predictive model includes the pipe protection method as pipe attributes and can reflect in its predictions, the effect of different pipe protection methods on the expected time to the next pipe failure. The developed ELM has a superior prediction accuracy relative to other available machine learning algorithms such as feed-forward artificial neural network that is trained by backpropagation, support vector regression, and non-linear regression. The utility of the models provides useful inputs when planning and budgeting for watermain inspection, maintenance, and rehabilitation.Öğe Detection of Parkinson's disease by Shifted One Dimensional Local Binary Patterns from gait(Elsevier, 2016-09) Ertuğrul, Ömer Faruk; Kaya, Yılmaz; Tekin, Ramazan; Almalı, 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.Öğe Developing correlations by extreme learning machine for calculating higher heating values of waste frying oils from their physical properties(Springer Nature, 2017-11-01) Altun, Şehmus; Ertuğrul, Ömer FarukIn this study, a novel approach was proposed based on extreme learning machine (ELM) for developing correlations in order to calculate higher heating values (HHVs, kj/kg) of waste frying oils from their physical properties such as density (ρ, kg/m 3 ) and kinematic viscosity (v, mm 2 /s) values. These values can easily be determined by using laboratory equipment. For developing the correlations, an experimental dataset from the literature covering 35 samples was collected to be employed in the training and validation steps. The obtained optimum parameters of artificial neural network in the training stage by ELM were employed to develop new correlations. The HHVs calculated by using density-based correlation (HHV = 50823.183 − 12.34095ρ) showed the mean absolute and relative errors of 145.8048 kJ/kg and 0.3695 %, respectively. In the case of the viscosity-based correlation (HHV = 40172.85 − 17.93615v), they were found as 129.04 kJ/kg and 0.327 %, respectively. Additionally, new correlations were performed better than those available in the literature and those obtained by other machine learning methods; therefore, it is highly suggested that the proposed approach can be used for developing new correlations.Öğe A novel machine learning method based on generalized behavioral learning theory(Springer Nature, 2016-04-09) Ertuğrul, Ömer Faruk; Tağluk, Mehmet EminLearning is an important talent for understanding the nature and accordingly controlling behavioral characteristics. Behavioral learning theories are one of the popular learning theories which are built on experimental findings. These theories are widely applied in psychotherapy, psychology, neurology as well as in advertisements and robotics. There is an abundant literature associated with understanding learning mechanism, and various models have been proposed for the realization of learning theories. Nevertheless, none of those models are able to satisfactorily simulate the concept of classical conditioning. In this study, popular behavioral learning theories were firstly simplified and the contentious issues with them were clarified by conducting intuitive experiments. The experimental results and information available in the literature were evaluated, and behavioral learning theories were jointly generalized accordingly. The proposed model, to our knowledge, is the first one that possesses not only modeling all features of classical conditioning but also including all features with behavioral theories such as Pavlov, Watson, Guthrie, Thorndike and Skinner. Also, a microcontroller card (Arduino Mega 2560) was used to validate the applicability of the proposed model in robotics. Obtained results showed that this generalized model has a high capacity for modeling human learning. Then, the proposed learning model was further improved to be utilized as a machine learning method that can continuously learn similar to human being. The result obtained from the use of this method, in terms of computational cost and accuracy, showed that the proposed method can be successfully employed in machine learning, especially for time ordered datasets.
