Venue : Coral Deira - Dubai, Deira, Dubai, UAE..  &  Date : April 24 ~ 25, 2015

Accepted papers

  • A Comparison of Accuracies of Various Classifiers to Process Eeg Signals for Prosthesis Control Using Variational Mode Decomposition
    Venu Akhil Kumar Parakala, VIT University, India.
    ABSTRACT
    Modern prosthetics use electroencephalogram (EEG) signals to receive signals from individual’s muscles to control the prosthesis. The prosthetic of an amputee which cannot accurately detect the brain signals is a dead investment for him. This paper tries to maximize the classification accuracies of these signals so as to improve prosthetics by comparison between two main algorithms namely using Naïve Bayes and Part rule algorithms. The EEG dataset for the conditions using 27 different subjects with four different hand movements viz., finger open (fopen), finger close (fclose), clock wise wrist rotation (cw) and counter clock wise wrist rotation (ccw) were obtained from the NINAPRO DATABASE, a resource for bio robotics community of hand movements. The introduction of Variational Mode Decomposition (VMD) as a new signal pre-processing technique along with the different decision trees have provided good classification performance. VMD allows decomposition of the signal into various modes by identifying a compact frequency support around its central frequency, such that adding all the modes reconstructs the original signal. The statistical features were extracted .Out of these the useful features were identified using the J48 decision tree algorithm and selected features were classified using Naïve Bayes and Part rule algorithms. The classification accuracies of both classifiers have been compared for the EEG signals.
  • Development and Analysis of Linear Model Representations of the ST450 Quad-Rotor System
    Mohamed moness and Muhammad bakr,Minia University,Egypt .
    ABSTRACT
    A Quad-rotor, which is an airplane with four rotors, has many applications such as gravitational acceleration measurements, agriculture development, order surveillance, cloud and aerosol measurements, search and rescue, pollution air measurements, pipeline surveillance and nuclear factories surveillance. Since the design and analysis of control systems is usually started by careful consideration of mathematical models description of physical systems, the presented paper focus on the nonlinear modeling of an experimental type quad-rotor. The first objective of this paper aims to develop a nonlinear dynamical model based on Newton-Euler approach. Then, a linear model is obtained around an optimized hovering point. The state space, transfer function matrix and matrix fraction description models are derived. Finally, a linear controller is designed to achieve a stable compensated system around a hovering point. The methodology applied in this paper takes the ST-450 experimental quad-rotor as a case study.
  • Torque Ripples Minimization On Dtc Controlled Induction Motor With Adaptive Bandwidth Approach
    Fatih Korkmaz1,Yilmaz Korkmaz2,Ismail Topaloglu1 and Hayati Mamur1,Cankiri Karatekin University,Turkey.
    ABSTRACT
    Field oriented control (FOC) and direct torque control (DTC), also called vector control, are most famous control methods in high-performance motor applications. If we want to specify the basic handicaps of both methods: the FOC has parameter dependence while the DTC has high torque ripples. This paper proposes a new adaptive bandwidth approach to reduce torque ripples in DTC controlled induction motor drives. With the proposed method, instead of fixed bandwidth, adaptive bandwidth approach is investigated in hysteresis controllers on the DTC method. Both the conventional DTC(C-DTC) method and adaptive bandwidth DTC (AB-DTC) for induction motor are simulated in MATLAB/SIMULINK and the results are presented and discussed to verify the proposed control. The comparisons have shown that, torque ripples have been reduced remarkably with the proposed AB-DTC method.