K
Kai-Yeung Siu
Researcher at University of California, Irvine
Publications - 34
Citations - 1529
Kai-Yeung Siu is an academic researcher from University of California, Irvine. The author has contributed to research in topics: Artificial neural network & Asynchronous Transfer Mode. The author has an hindex of 18, co-authored 34 publications receiving 1512 citations. Previous affiliations of Kai-Yeung Siu include Massachusetts Institute of Technology & Stanford University.
Papers
More filters
Journal ArticleDOI
Intelligent congestion control for ABR service in ATM networks
Kai-Yeung Siu,Hong-Yi Tzeng +1 more
TL;DR: A rate-based scheme that is now referred to by the ATM Forum as 'intelligent congestion control' and is currently considered as one of the most promising approaches to traffic management of available bit rate (ABR) service is described.
Book
Discrete Neural Computation: A Theoretical Foundation
TL;DR: 1. Computing Symmetric Functions 2. Depth Efficient Arithmetic Circuits 3. Rational Approximation and Optimal Size Circuits.
Journal ArticleDOI
On the Power of Threshold Circuits with Small Weights
Kai-Yeung Siu,Jehoshua Bruck +1 more
TL;DR: The following results are proved: (1) every LTE with big weights can be simulated by a depth-3, polynomial size network of LTEs with small weights; and (2) every depth-d, poynomial sizeNetwork of LTES with big weight can be simulate by a Depth-d + 1, depth-$( 2d - 1 + 1 )$, polynometric size networkof LTEsWith small weights.
Proceedings ArticleDOI
A Bluetooth scatternet formation algorithm
Ching Law,Kai-Yeung Siu +1 more
TL;DR: A new randomized distributed algorithm for Bluetooth scatternet formation is presented and it is proved that this algorithm achieves O(log n) time complexity and O(n) message complexity.
Proceedings ArticleDOI
Video-based freeway monitoring system using recursive vehicle tracking
TL;DR: An image processing and object tracking approach is proposed for the design of a video-based freeway traffic monitoring system that proper estimation of the traffic speed in different lanes of a freeway allows for timely detection of possible congestions.