Sciweavers

SDM
2007
SIAM

Load Shedding in Classifying Multi-Source Streaming Data: A Bayes Risk Approach

13 years 4 months ago
Load Shedding in Classifying Multi-Source Streaming Data: A Bayes Risk Approach
In many applications, we monitor data obtained from multiple streaming sources for collective decision making. The task presents several challenges. First, data in sensor networks, satellite transmissions, and many other fields are often of large volume, fast speed, and highly bursty nature. Second, because data are collected from multiple sources, it is impossible to offload classification decisions to individual data sources. Hence, the central classifier responsible for decision making is constantly under overloaded situations. In this paper, we study intelligent load shedding for classifying multi-source data. We aim at maximizing classification quality under resource (CPU and bandwidth) constraints. We use a Markov model to predict the distribution of feature values over time. Then, leveraging Bayesian decision theory, we use Bayes risk analysis to model the variances among different data sources in their contributions to classification quality. We adopt an Expected Observa...
Yijian Bai, Haixun Wang, Carlo Zaniolo
Added 30 Oct 2010
Updated 30 Oct 2010
Type Conference
Year 2007
Where SDM
Authors Yijian Bai, Haixun Wang, Carlo Zaniolo
Comments (0)