Adaptive multi-modal sensors

Item Type:	Book Section
Title:	Adaptive multi-modal sensors
Creators Name:	Harrington, K.I. and Siegelmann, H.T.
Abstract:	Compressing real-time input through bandwidth constrainedconnections has been studied within robotics, wireless sensor networks,and image processing. When there are bandwidth constraints on real-time input the amount of information to be transferred will always begreater than the amount that can be transferred per unit of time. Wepropose a system that utilizes a local diffusion process and a reinforcement learning-based memory system to establish a realtime predictionof an entire input space based upon partial observation. The proposedsystem is optimized for dealing with multi-dimension input spaces, andmaintains the ability to react to rare events. Results show the relationof loss to quality and suggest that at higher resolutions gains in qualityare possible.
Keywords:	Sensor Network, Wireless Sensor Network, Rare Event, Sensor Chemical, Bandwidth Constraint
Source:	Lecture Notes in Computer Science
Series Name:	Lecture Notes in Computer Science
Title of Book:	50 years of artificial intelligence
ISSN:	0302-9743
ISBN:	978-3-540-77295-8
Publisher:	Springer
Volume:	4850
Number:	4850
Page Range:	164-173
Number of Pages:	10
Date:	2007
Official Publication:	https://doi.org/10.1007/978-3-540-77296-5_16

Repository Staff Only: item control page