Browsing by Author "Karlik Bekir"

Now showing 1 - 5 of 5
  • No Thumbnail Available
    Item
    Performance analysis of induction motors with artificial neural networks
    (IEEE, 1995) Karlik Bekir; Gulez Kayhan
    Induction motors are exited machines used in a lot of areas in industry because of the features like the simpleness of the structure, the easiness of the control and the necessity of the fewer care. One of priority reasons of induction motors is that the speed adjusting can easily be done by wide ranges by means of the developing of solid-state technology. In this paper, it is put forward that ANN can firstly be used in the performance analysis of induction motors.
  • No Thumbnail Available
    Item
    EMG pattern discrimination for patient-response control of FES in paraplegics for walker supported using artificial neural network (ANN)
    (IEEE, 1996) Kocyigit Yucel; Karlik Bekir; Korurek Mehmet
    FES (functional electrical stimulation) encompasses the use of electricity in functioning neural substrates. FES is used to restore lower limb function to individuals paralyzed by spinal cord injury. The system determines a patient-responsive manner using above-lesion surface EMG signals to activate standing and walking functions. In this work, classification of EMG patterns which were used by FES to restore lower limb function of walker-supported walking patients was done by using ANN.
  • No Thumbnail Available
    Item
    New approach for arrhythmia classification
    (IEEE, 1996) Karlik Bekir; Ozbay Yuksel
    ECG signal is formed of P wave, QRS complex and T wave. P wave appears as a result of QRS complex ventricle contraction because of electrical stimulation initiation at sinoatrial node and spreading in cardiac muscles. T wave appears as a result of ventricle relaxation. In this study ECG signal is analyzed in time domain. For this purpose, arrhythmia are determined by taking related mean time intervals of ECG as future extraction. Arrhythmia are categorized by applying time elapsed between two R waves (RR intervals), appearing in ECG signals, as the input of Artificial Neural Networks (ANN).
  • No Thumbnail Available
    Item
    Artificial neural network case study: The control of work-in-process inventory in a manufacturing line
    (IEEE, 1997) Col Muhterem; Karlik Bekir
    The work-in-process in a middle-scale shoe factory is investigated. At the manufacturing center, there are five work departments composed of cutting, sewing, hand-leather working, assembling and quality control-packing. In these departments, there are work-in-process because of different processing time and insufficient number of labor-machines. Artificial neural network (ANN) with backpropagation is used for solving this work-in-process problem. The optimum number of labor-machines at work stations are obtained for work-in-process without hindering the production by considering processing times and flow at these work stations.
  • No Thumbnail Available
    Item
    Differentiating type of muscle movement via AR modeling and neural network classification
    (1999) Karlik Bekir
    The aim of this study is to classify electromyogram (EMG) signals for controlling multifunction proshetic devices. An artificial neural network (ANN) implementation was used for this purpose. Autoregressive (AR) parameters of a1, a2, a3, a4 and their signal power obtained from different arm muscle motions were applied to the input of ANN, which is a multilayer perceptron. At the output layer, for 5000 iterations, six movements were distinguished at a high accuracy of 97.6%.