Publications (14) View all
-
Conference Proceeding: New Hardware Engine for Genetic Algorithms
[show abstract] [hide abstract]
ABSTRACT: Genetic algorithm is a soft computing method that works on set of solutions. These solutions are called chromosome and the best one is the absolute solution of the problem. Unfortunately, most of the genetic algorithms are implemented in software and less works have been done on hardware implementation. Our work implements genetic algorithm in hardware. In this work, most of genetic operators are implemented and genetic diversity is preserved. Genetic diversity causes that not only don't this algorithm converge to local optimum but also reaching to global optimum. Without any doubts, proposed approach is so faster than software implementations. Evaluation results also show the proposed approach using diversity in alternate generations is faster than hardware ones.Genetic and Evolutionary Computing (ICGEC), 2011 Fifth International Conference on; 10/2011 -
Conference Proceeding: A GCSE maths tutoring game using neural networks
[show abstract] [hide abstract]
ABSTRACT: This paper investigates the use of neural networks to provide a challenging environment to motivate students of mathematics in further investigation of mathematical concepts. The research focuses on areas of shape, but similar methods could be used for a variety of mathematical topics. The paper presents a game in which a back-propagation neural network is trained by the player to compare areas of mathematical shapes. The original prototype in MATLAB is presented. A demonstration of the idea of a neural network as a opponent using the Python Programming Language further expands on this original work. The results show that a neural network can be used in a variety of ways to support students of differing levels of ability.Games Innovations Conference (ICE-GIC), 2010 International IEEE Consumer Electronics Society's; 01/2011 -
Conference Proceeding: Characterization of multi- and single-layer structure SAW sensor [gas sensor]
[show abstract] [hide abstract]
ABSTRACT: The design of CMOS compatible thin ZnO film base, and LiNbO<sub>3</sub> wafer base, surface acoustics wave (SAW) gas sensors, that are highly selective and sensitive, is described. Furthermore, design and post-CMOS processing fabrication steps that utilises micro-electro-mechanical systems (MEMS) techniques to implement the SAW gas sensor are presented. The Rayleigh wave velocity for various ZnO film thicknesses is simulated and results are presented. The velocity calculation is based on a computer simulation of a multilayer (ZnO/SiO<sub>2</sub>/Si) structure that uses wave equations. Simulation results and experimental measurements of SAW sensors with a single layer bulk LiNbO<sub>3</sub> wafer are shown, and compared. Moreover, results of experimentation and simulation of wave velocity for a yz-cut LiNbO<sub>3</sub> wafer are shown.Sensors, 2004. Proceedings of IEEE; 11/2004 -
Conference Proceeding: Minimum-variance phase prediction and frame interpolation algorithms for low bit rate sinusoidal speech coding
[show abstract] [hide abstract]
ABSTRACT: A number of improved algorithms for phase prediction and frame interpolation in the context of sinusoidal speech coding are presented. A minimum-variance sinusoidal phase estimation scheme is proposed. It is shown that reasonably accurate estimates for short-time sinusoidal phases corresponding to voiced frames can be obtained. In addition, improved algorithms for interpolation of sine wave parameters are presented which result in further reduction in bit rate while preserving the subjective equality of the reproduced speech at low bit rates. The performance of the proposed algorithms were evaluated on a large speech database and the results of statistical analysis are provided. The proposed algorithms were successfully integrated into a 2.4 kbps sinusoidal coder, where speech of good quality intelligibility, and naturalness was obtainedCircuits and Systems, 2000. Proceedings. ISCAS 2000 Geneva. The 2000 IEEE International Symposium on; 02/2000 -
Article: Cepstrum-based pitch detection using a new statistical V/UV classification algorithm
[show abstract] [hide abstract]
ABSTRACT: An improved cepstrum-based voicing detection and pitch determination algorithm is presented. Voicing decisions are made using a multifeature voiced/unvoiced classification algorithm based on statistical analysis of cepstral peak, zero-crossing rate, and energy of short-time segments of the speech signal. Pitch frequency information is extracted by a modified cepstrum-based method and then carefully refined using pitch tracking, correction, and smoothing algorithms. Performance analysis on a large database indicates considerable improvement relative to the conventional cepstrum method. The proposed algorithm is also shown to be robust to additive noiseIEEE Transactions on Speech and Audio Processing 06/1999; · 2.29 Impact Factor
