Classifying work rate from heart rate measurements using an adaptive neuro-fuzzy inference system. (May 2016)

• Record Type: Journal Article
• Authors: Kolus, Ahmet; Imbeau, Daniel; Dubé, Philippe-Antoine; Dubeau, Denise
• Is Part Of: Applied ergonomics. Volume 54(2016:May)
• Page Start: 158
• Page End: 168
• Publication Date: 2016-05
• Subjects: Work rate -- Heart rate -- Adaptive neuro-fuzzy inference system (ANFIS); Human engineering -- Periodicals; 620.82
• DOI: 10.1016/j.apergo.2015.12.006
• Languages: English
• ISSNs: 0003-6870

Abstract

Abstract: In a new approach based on adaptive neuro-fuzzy inference systems (ANFIS), field heart rate (HR) measurements were used to classify work rate into four categories: very light, light, moderate, and heavy. Inter-participant variability (physiological and physical differences) was considered. Twenty-eight participants performed Meyer and Flenghi's step-test and a maximal treadmill test, during which heart rate and oxygen consumption ( V ˙ O 2 ) were measured. Results indicated that heart rate monitoring (HR, HRmax, and HRrest ) and body weight are significant variables for classifying work rate. The ANFIS classifier showed superior sensitivity, specificity, and accuracy compared to current practice using established work rate categories based on percent heart rate reserve (%HRR). The ANFIS classifier showed an overall 29.6% difference in classification accuracy and a good balance between sensitivity (90.7%) and specificity (95.2%) on average. With its ease of implementation and variable measurement, the ANFIS classifier shows potential for widespread use by practitioners for work rate assessment. Highlights: We present a new fuzzy-based approach to classify work rate based on HR measurement. The proposed classifier accounts for participants' age, HR at rest and body weight. The proposed classifier has superior performance over Percent HR Reserve method.