Abstract

Reliable contextual information of remotely monitored patients should be generated to prevent hazardous situations and to provide pervasive services in home-based care. This is difficult for several reasons. First, low level data obtained from heterogeneous sensors have different degrees of uncertainty. Second, generated contexts can be corrupted or conflicted even if they are acquired by simultaneous operations. In this paper, we utilize Dezert-Smarandache theory (DSmT) as an evidence fusion approach to reduce ambiguous or imperfect information then to get higher belief levels in the data fusion process of contextual information. To analyze the improvement of DSmT fusion process, we compare DSmT with Dempster-Shafer theory (DST) using PCR5 rule of combination and Dempster's rule of combination respectively.

Highlights

  • A wide range of pervasive computing technologies aim to provide pervasive services to patients using intelligent embedded systems in smart home-based care

  • A higher confidence level in the generated contexts is difficult to produce, since multiple sensors may not provide reliable information due to faults, operational tolerance levels, or corrupted data even though they are acquired by simultaneous operations

  • Unpredictable malfunctions of sensors frequently happen in heterogeneous sensor environments

Read more

Summary

Introduction

A wide range of pervasive computing technologies aim to provide pervasive services to patients using intelligent embedded systems in smart home-based care. We aim to reduce ambiguous or imperfect contextual information using Dezert-Smarandache Theory (DSmT) [1] of evidence as a sensor data fusion technique to get a reliable activity recognition under uncertain or conflicting situations in smart home-based care applications. As a generalized probabilistic approach, DST, which considers upper and lower bounds of probability, has some distinct features when compared with Bayesian theory. This is because it represents the ignorance caused by the lack of information and aggregates the belief when new evidence is accumulated [2]. DSmT approach, which overcomes drawbacks of Dempster’s combination rule and extends the domain of application of the belief functions, is used as a sensor data fusion technique. We infer the activities of a patient based on the applied scenario compare DST approach with DSmT approach

Characteristics of Sensors
State-Space based Modeling
Quality of Data
Basics of Evidential Theory
Evidential Operations
DST Combination Rule
DSmT Combination Rule
Applied Scenario
Applying Dempster’s rule of combination
Applying PCR5 rule of combination
Compare DSmT with DST
Findings
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call