Bøger af Mayurkumar Ladumor

Recent research focuses on low power design techniques. This has been mainly motivated by the demand of hand-held electronic devices which must consume less power. This thesis presents a hybrid approach for designing a low power Multi-Layer Perceptron (MLP) based Neural Network (NN) for speech recognition. They are bipartite tabular method and banking organization method. The MLP based NN is trained in Matlab using TIDIGITS corpus. This approach is simulated in Xilinx xc3s1200. The system is evaluated using optimized model weights which are exported from Matlab. Performance parameter like area and power is computed.

Automatic design and optimization of CMOS Analog circuits is a technique for integrate circuit simulator with Heuristic swarm optimization algorithm for optimize circuit variables to achieve desired circuit specifications. Artificial bee colony algorithm is an evolutionary heuristic algorithm that mimics the foraging behaviour of honey bees. Objective of this work is to implement Artificial Bee Colony (ABC) Algorithm in Linux open source environment using GCC compiler as optimizer and it is integrated with Ng-Spice circuit simulator for design complex CMOS analog circuits. The problem of analog circuit design has become difficult due to increased complexity of MOSFET models, process variations, temperature and supply voltage variations, and requirement of low-power architectures. Therefore, analog circuit design task needs to be automated. In this work, we investigate the effectiveness of the ABC algorithm for this problem. The ABC algorithm is observed to be better in performance as compared to the PSO algorithm for the various low-power, low-voltage CMOS analog circuit design.