Adaptive neuro-fuzzy inference systems with k-fold cross-validation for energy expenditure predictions based on heart rate. (September 2015)

• Record Type: Journal Article
• Authors: Kolus, Ahmet; Imbeau, Daniel; Dubé, Philippe-Antoine; Dubeau, Denise
• Is Part Of: Applied ergonomics. Volume 50(2015:Sep.)
• Page Start: 68
• Page End: 78
• Publication Date: 2015-09
• Subjects: Flex–HR method -- Physical workload -- Adaptive neuro-fuzzy inference system (ANFIS); Human engineering -- Periodicals; 620.82
• DOI: 10.1016/j.apergo.2015.03.001
• Languages: English
• ISSNs: 0003-6870

Abstract

Abstract: This paper presents a new model based on adaptive neuro-fuzzy inference systems (ANFIS) to predict oxygen consumption ( V ˙ O 2 ) from easily measured variables. The ANFIS prediction model consists of three ANFIS modules for estimating the Flex–HR parameters. Each module was developed based on clustering a training set of data samples relevant to that module and then the ANFIS prediction model was tested against a validation data set. Fifty-eight participants performed the Meyer and Flenghi step-test, during which heart rate (HR) and V ˙ O 2 were measured. Results indicated no significant difference between observed and estimated Flex–HR parameters and between measured and estimated V ˙ O 2 in the overall HR range, and separately in different HR ranges. The ANFIS prediction model (MAE = 3 ml kg −1 min −1 ) demonstrated better performance than Rennie et al.'s (MAE = 7 ml kg −1 min −1 ) and Keytel et al.'s (MAE = 6 ml kg −1 min −1 ) models, and comparable performance with the standard Flex–HR method (MAE = 2.3 ml kg −1 min −1 ) throughout the HR range. The ANFIS model thus provides practitioners with a practical, cost- and time-efficient method for V ˙ O 2 estimation without the need for individual calibration. Highlights: We present a practical approach based on neuro-fuzzy systems to estimate energy expenditure using heart rate monitoring. The proposed approach improves the standard Flex-HR method in that it does not require individual calibration. The proposed approach treats the uncertainty in human physiological systems and in various workplaces by using fuzzy logic.