Mixed-Signal VLSI Robust Time-Frequency Feature Extraction

دانشگاه آزاد اسلامی اصفهان(خوراسگان)

منو

رکورد قبلی

رکورد بعدی

" Mixed-Signal VLSI Robust Time-Frequency Feature Extraction "

Document Type	:	Latin Dissertation
Language of Document	:	English
Record Number	:	150257
Doc. No	:	ET22049
Main Entry	:	Yunbin Deng
Title Proper	:	Mixed-Signal VLSI Robust Time-Frequency Feature Extraction
Note	:	This document is digital این مدرک بصورت الکترونیکی می باشد
Abstract	:	Robust feature extraction is critical to pattern recognition and intelligent systems. Theproblem of extracting reliable features from real-world signals is challenging because thesesignals are embedded in non-stationary noise; real-time operation requires fast adaptation;and mobile operation requires miniature hardware with low-power consumption. The needfor robust real-time, and low-power feature extraction solutions calls for an integrative ap-proach that combines adaptive signal processing, machine learning, and micropower VLSIdesign.This dissertation presents time-frequency feature extraction algorithms, inspired by bi-ological models of auditory processing, for robust feature extraction. The algorithms mapefficiently onto massive parallel VLSI hardware to provide real-time operation. Analogmodels of computation are combined with digital...,..tested for theQ1 PC1 bus cardBoth these projects mere sofixare des elopment efforts tonards contributing to dlfferentaspects of Roboucs and lZ1echatronics projects m the Controls and Roboucs Group..
Subject	:	Electericl tess
	:	برق
electronic file name	:	TL45245.pdf
Title and statement of responsibility and	:	Mixed-Signal VLSI Robust Time-Frequency Feature Extraction [Thesis]