Noise Enhanced Sensory Signal Processing
Abstract
Understanding and emulating sensory information systems is a challenging task. The goal of this project was to develop the theory of noise enhanced signal processing (NESP) where the performance of some nonlinear systems may be enhanced by adding a suitable amount of noise to the input signal. The main objective of this project was to explore the applicability of NESP based approaches to enhance the performance of ``source blind'' signal processing algorithms. During this effort, we have explored the NESP mechanism for signal detection and estimation problems in a non-stationary and dynamic environment and developed some iterative learning algorithms to apply NESP based procedure with incomplete knowledge. We investigated image enhancement algorithms based on stochastic resonance (SR) noise which improve the performance of suboptimal image enhancers. We further explored the recently developed Compressive Sensing based measurement scheme in performing detection, classification and estimation with sparse signals and derived achievable performance limits. Results obtained have been documented in a number of technical publications.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jan 31, 2012
- Accession Number
- ADA567093
Entities
People
- Pramod Varshney
Organizations
- Syracuse University