خط مشی دسترسیدرباره ماپشتیبانی آنلاین
ثبت نامثبت نام
راهنماراهنما
فارسی
ورودورود
صفحه اصلیصفحه اصلی
جستجوی مدارک
تمام متن
منابع دیجیتالی
رکورد قبلیرکورد بعدی
Document Type:Latin Dissertation
Language of Document:English
Record Number:53997
Doc. No:TL23951
Call number:‭3335978‬
Main Entry:Nithya Athreya Ramanathan
Title & Author:Improving data recovery from embedded networked sensing systems with fault detection and diagnosisNithya Athreya Ramanathan
College:University of California, Los Angeles
Date:2008
Degree:Ph.D.
student score:2008
Page No:162
Abstract:Unreliable collection systems result in missing data points; faulty or confusing sensor data further reduce the quantity of usable data recovered from a deployment. These problems lead to data gaps in space and time, which make it difficult to interpret results reliably. Unfortunately, compared with conventional systems, faults in ENS systems occur at a higher rate and are harder to find and fix. Sympathy and Confidence are new fault remediation systems that help users improve the quality and quantity of data recovered from embedded networked sensing (ENS) systems. Sympathy uses a high-level decision tree to analyze a small set of carefully chosen metrics that help it suggest actions users can take to fix data-flow disruptions in the network. Sympathy has been effective for managing network health in numerous real-world deployments since 2006, but its static algorithms proved insufficient for data faults. Our second system, Confidence, combines the successes of Sympathy with dynamic algorithms that more readily adapt to detecting data faults in new and unexplored environments. Confidence builds on three key ideas: (1) A flexible, multidimensional feature space that tends to group nodes and sensors that have similar fault states, and reduces fault detection and diagnosis to anomaly detection and other simple mechanisms; (2) a transparent system design that both aids and profits from the user's intuition; and (3) efficient incorporation of user feedback into fault detection and diagnosis algorithms. User feedback, in particular, makes Confidence quickly adapt to new deployment scenarios and previously unobserved types of faults. We have successfully deployed both Sympathy and Confidence alongside many ENS deployments in California and Bangladesh, including a long-term deployment at James Reserve of 130 sensors. Both Sympathy and Confidence are designed to simplify human response in the field by suggesting actions users can take to clarify or fix potential faults. However, Confidence's dynamic approach more easily adapts to a larger class of faults and deployment environments, making it preferable to Sympathy's static solution in most cases.
Subject:Applied sciences; Data recovery; Embedded sensors; Fault detection; Fault diagnosis; Sensor networks; Computer science; 0984:Computer science
Added Entry:D. Estrin
Added Entry:University of California, Los Angeles