+1 250 217 2800
INOUSSA NS. MOUICHE
MSc. in Eletronics, MSc. in Applied Mathematics and Computer Sciences, MEng in Telecom and Information Security, University of Victoria, Canada. Queen Elizabeth Scholar, speak and write English and French
``Internet of Things (IoT) Security Architecture for Smart Cities"
I. N. Mouiche, S. Samer, T. Aron, L. Kin, B. Essimbi Electrical & Computer Engineering, University of Victoria
``Stability of Slotted Aloha MAC protocol for Cognitive Radio Users using Tagged User Approach"
ICCCN 2017 conference in Vancouver, IEEE Xplore July 31 to August 3, 2017
Inoussa Mouiche and Maher Bourdani, Electrical and omputer Engineering, University of Victoria
"Domestic cats daily life describes a powerful optimization algorithm for multi-suboptimal problems in industry. One of such problems is the identification of nonlinear IIR filters (Infinite Impulse Response filters). Recently I have proposed its chaotic version (CCSO) for IIR system identification. Unfortunately, the reviewers replied that "the paper deserves some merits, although CCSO has no yet been used for system identification, Yang et al. just introduce it for numerical optimization." They suggested an additional effort to be made for the reputation Journal. Actually I am following an intensive program in UVic. I assigned this job to another student at home by suggesting Cuckoo Algorithm to be added”.
Write to me if any request
IIR SYSTEM IDENTIFICATION WITH CHAOTIC CAT SWARM OPTIMIZATION AND CHAOTIC DE
Mouiche Nsangou Inoussa (a), Samrat L Sabat(b) and Essimbi Zobo Bernard *(a) (a) Department of Physics, Faculty of Sciences, University of Yaoundé I, P.O. Box 812 Yaoundé, Cameroon (b) CASEST, School of Physics, University of Hyderabad, India, 500046
ABSTRACT
Infinite Impulse response (IIR) system identification task is formulated as an optimization problem with different meta-heuristics search algorithms. In this frame, Particle Swarm Optimization (PSO), Cats Swarm Optimization (CSO), Genetic Algorithm (GA), etc, have been applied for the optimization of system coefficients. Moreover, we presented Differential Evolution (DE), Chaotic Differential Evolution (CDE), Chaotic Cat Swarm Optimization (CCSO) and an improved CSO as a new population based learning rule generated by observing the behaviors of cats. The performances of these algorithms are compared using both actual and reduced order of IIR plants. Numerical study carried out in Matlab software demonstrates superior identification performance of CDE compared to that achieved by DE, CCSO, CSO and PSO. Otherwise, using chaotic sequences instead of random sequences is an efficient strategy to improve the performance of standard DE and CSO algorithms.
