A Belief Rule Based Expert System to Assess Clinical Bronchopneumonia Suspicion
Number of Authors: 5
2016 (English)In: Proceedings of Future Technologies Conference 2016 (FTC 2016) / [ed] Flavio Villanustre and Arjuna Chala, IEEE, 2016, 655-660 p.Conference paper (Refereed)
Bronchopneumonia is an acute or chronic inflammation of the lungs, in which the alveoli and/or interstitial are affected. Usually the diagnosis of Bronchopneumonia is carried out using signs and symptoms of this disease, which cannot be measured since they consist of various types of uncertainty. Consequently, traditional disease diagnosis, which is performed by a physician, cannot deliver accurate results. Therefore, this paper presents the design, development and application of an expert system for assessing the suspicion of Bronchopneumonia under uncertainty. The Belief Rule-Based Inference Methodology using the Evidential Reasoning (RIMER) approach was adopted to develop this expert system, which is named the Belief Rule-Based Expert System (BRBES). The system can handle various types of uncertainty in knowledge representation and inference procedures. The knowledge base of this system was constructed by using real patient data and expert opinion. Practical case studies were used to validate the system. The system-generated results are more effective and reliable in terms of accuracy than from the results generated by a manual system.
Place, publisher, year, edition, pages
IEEE, 2016. 655-660 p.
Belief Rule Base, Uncertainty, RIMER, Bronchopneumonia, Expert System, Inference
Engineering and Technology Media and Communication Technology
Research subject Mobile and Pervasive Computing; Enabling ICT (AERI)
IdentifiersURN: urn:nbn:se:ltu:diva-40083Local ID: f0fb4f08-c979-45a6-99ec-e522da70762fISBN: 978-1-5090-4171-8 (print)ISBN: 978-1-5090-4170-1 (print)OAI: oai:DiVA.org:ltu-40083DiVA: diva2:1013606
Future Technologies Conference 2016 (FTC 2016), San Francisco, 6-7 December 2016
ProjectsA belief-rule-based DSS to assess flood risks by using wireless sensor networks
FunderSwedish Research Council, 2014-4251
För godkännande; 2016; 20160701 (karand)2016-10-032016-10-032016-12-07