A Case-Based Classification for Drivers Alcohol Detection Using Physiological Signals
2016 (English)Conference paper (Refereed)
This paper presents a case-based classification system for alcohol detection using physiological parameters. Here, four physiological parameters e.g. Heart Rate Variability (HRV), Respiration Rate (RR), Finger Temperature (FT), and Skin Conductance (SC) are used in a Case-based reasoning (CBR) system to detect alcoholic state. In this study, the participants are classified into two groups as drunk or sober. The experimental work shows that using the CBR classification approach the obtained accuracy for individual physiological parameters e.g., HRV is 85%, RR is 81%, FT is 95% and SC is 86%. On the other hand, the achieved accuracy is 88% while combining the four parameters i.e., HRV, RR, FT and SC using the CBR system. So, the evaluation illustrates that the CBR system based on physiological sensor signal can classify alcohol state accurately when a person is under influence of at least 0.2 g/l of alcohol.
Place, publisher, year, edition, pages
2016. Vol. 187, 22-29 p.
Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST, ISSN 1867-8211 ; 187
Physiological signals, alcoholic detection, case-based reasoning.
Electrical Engineering, Electronic Engineering, Information Engineering
IdentifiersURN: urn:nbn:se:mdh:diva-33800OAI: oai:DiVA.org:mdh-33800DiVA: diva2:1048561
The 3rd EAI International Conference on IoT Technologies for HealthCare HealthyIoT'16, OCTOBER 18–19, 2016, VÄSTERÅS, SWEDEN
ProjectsSafeDriver: A Real Time Driver's State Monitoring and Prediction System