Online updating extended belief rule-based system for sensor-based activity recognition

نویسندگان

چکیده

• Propose an eigendecomposition-based method to select sensors in a high-efficiency way. domain division-based update rules online updating EBRBS for achieving activity recognition more efficiently. Experiments show the proposed has high accuracy and excellent response time. Sensor-based (AR) is core problem with research of smart environments. It has, however, potential provide solutions address problems associated growing size ageing profile global population. The work presented within this paper focuses on extended belief rule-based system (EBRBS), which offered promising performance compared popular benchmark AR models exhibited robustness situation sensor failure. Nevertheless, efficiency remains one major issues be improved determining rule base (EBRB) EBRBS. This critical further utilizing situations dynamic An selection firstly effective subset also enable efficient implementation facilitate AR. A novel generation generate EBRB efficiently when new data are available or some should included excluded EBRB. combination these two methods leads enhanced EBRBS, called . Two datasets (in balanced class situation) obtained from simulation actual environments studied detailed experimental analysis as preliminary study basis handle imbalanced real results demonstrate original models, terms effectiveness.

برای دانلود باید عضویت طلایی داشته باشید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Online Fault Detection and Isolation Method Based on Belief Rule Base for Industrial Gas Turbines

Real time and accurate fault detection has attracted an increasing attention with a growing demand for higher operational efficiency and safety of industrial gas turbines as complex engineering systems. Current methods based on condition monitoring data have drawbacks in using both expert knowledge and quantitative information for detecting faults. On account of this reason, this paper proposes...

متن کامل

Control Chart Recognition Patterns using Fuzzy Rule-Based System

Control Chart Patterns (CCPs) recognition is one the most important concepts in control chart application. Relating the patterns exhibited on the control chart to assignable causes is an ambiguous and vague task especially when multiple patterns co-exist. In this study, a fuzzy rule-based system is developed for X ̅ control charts to prioritize the control chart causes based on the accumulated e...

متن کامل

A Sensor-Based Scheme for Activity Recognition in Smart Homes using Dempster-Shafer Theory of Evidence

This paper proposes a scheme for activity recognition in sensor based smart homes using Dempster-Shafer theory of evidence. In this work, opinion owners and their belief masses are constructed from sensors and employed in a single-layered inference architecture. The belief masses are calculated using beta probability distribution function. The frames of opinion owners are derived automatically ...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: Expert Systems With Applications

سال: 2021

ISSN: ['1873-6793', '0957-4174']

DOI: https://doi.org/10.1016/j.eswa.2021.115737