Respiratory Effort Signal Based Sleep Apnea Detection System Using Improved Random Forest Classifier

Abstract

This work aims to develop a minimally obtrusive simple system for the automatic detection and classification of sleep apnea (SA) events using the single-channel abdomen respiratory effort signal (Abd RES) taken from the ISRUC sleep database. The discrete wavelet transform energy, time domain respiratory rate variability and the Shannon entropy features are extracted from the Abd RES to build a classifier system. The performance of linear multi-class support vector machine (SVM) and random forest (RF) classifiers is compared for the application. Furthermore, an improved random forest (IRF) classifier is proposed, which is a combination of data re-sampling, RF algorithm and threshold moving method. It is designed to deal with the imbalance in the input dataset for better classification results. Various systems are designed using individual feature sets, but classification accuracy increases when feature sets are combined. A maximum accuracy of 89.66% is achieved with the IRF based system using reduced feature set obtained by principal component analysis. Thus, the proposed method can provide an effective, economical and accessible screening tool for SA.

Keywords:

• Entropy triangle
• Improved random forest
• Multiclass
• PCA
• Random forest
• Respiratory effort signal
• ROC
• Sleep apnea
• SVM

Acknowledgements

This article does not contain any studies with human participants performed by any of the authors. This research work has been carried out using publicly available ISRUC – sleep database.

DISCLOSURE STATEMENT

No potential conflict of interest was reported by the authors.

Additional information

Notes on contributors

Anju Prabha

Anju Prabha received BTech degree in electronics and biomedical engineering from Govt Model Engineering College, Cochin University of Science and Technology, Cochin, Kerala in 2014 and MTech degree in biomedical engineering from Amrita School of Engineering, Amrita Vishwa Vidyapeetham University in 2017. She is pursuing PhD from Netaji Subhas Institute of Technology, University of Delhi, Delhi. Her research interests include sleep apnea, biomedical signal processing, biomedical instrumentation, artificial intelligence and image processing. instrumentation, biomedical transducers and sensors, and machine learning.

Jyoti Yadav

Jyoti Yadav received BTech degree in biomedical engineering from Guru Jambeshwer University, Hissar, Haryana in 2007 and MTech degree in process control from Netaji Subhas Institute of Technology, University of Delhi in 2011 and PhD from the same institute. Currently she is working as assistant professor in Division of Instrumentation and Control Engineering Division at Netaji Subhas Institute of Technology, Dwarka, New Delhi. Her research interests include spectroscopy, non-invasive glucose monitoring biomedical instrumentation, biomedical transducers and sensors, controlled drug delivery system. Email: [email protected]

Asha Rani

Asha Rani received her BTech in electrical engineering from Regional Engineering College (Now NIT), Hamir pur, Himachal Pradesh in 1998. She received ME degree in electrical engineering from IIT Roorkee in 2000 and PhD in 2013 from University of Delhi, Delhi. She has published many papers in international journals and conferences. She is working as professor in instrumentation and control engineering division at Netaji Subhas Institute of Technology, New Delhi, affiliated to University of Delhi, Delhi. Her areas of research are process control, microprocessor, artificial intelligence and control systems. Email: [email protected]

Vijander Singh

Vijander Singh received his BTech in electrical engineering from GB Pant University of Agriculture and Technology Pant Nagar in Uttarakhand in 1995. He received ME degree in electrical engineering in 2000 and PhD in electrical engineering in 2007 from IIT Roorkee. He has published many papers in international journals and conferences. He has chaired many international conferences. He is working as professor in Instrumentation and Control Engineering Division at Netaji Subhas Institute of Technology, New Delhi, affiliated to University of Delhi, Delhi. His area of research is process control. Email: [email protected]