Deep Learning Approach for Gait Detection for Precise Stimulation of FES to Correct Foot Drop

Abstract

Automatic detection of foot lift is one of the most important events of Functional Electrical Stimulation (FES). The FES system is used for the correction of Foot Drop (FD). FD is a condition where a person is unable to lift their foot from the ground due to complications that may arise after a stroke or spinal cord injury. It is crucial to accurately detect the patient’s foot lift event when correcting FD through FES as the pulse should only be applied when the person lifts their foot. The FES system applies the electrical pulse based on the input of the foot-lift detection sensor. A conventional FES system employs a sensor that is affixed on the heel to detect the lifting of the foot, but the connecting cables make the patient uncomfortable. To address this problem, IMU (Inertial Measurement Unit)-based sensors have been used, but they have some disadvantages, such as false triggering, low accuracy, and calibration. In this paper, we have presented an algorithm for detecting foot-lift events with high accuracy using a single IMU sensor through the application of deep learning techniques. We have recorded data from 10 healthy people and 10 foot drop patients. We have implemented Artificial Neural Network (ANN), K-Nearest Neighbour (KNN), and Convolutional Neural Network (CNN) models on these data and compared the results of these three models. The proposed algorithm aims to improve the precision of stimulation in the FES system.

KEYWORDS:

• Accelerometer
• Deep learning
• Functional electrical stimulation (FES)
• Foot drop
• Foot lift
• Gait detection
• IMU

ACKNOWLEDGMENT

We extend our sincere gratitude to the Department of Biomedical Engineering, Indian Institute of Technology Ropar for generously providing us with the essential infrastructure and support required to conduct this research. We are also grateful to the Department of Neurology at Dayanand Medical College and Hospital for their invaluable support in providing us with access to patient data and facilitating the clinical trials. We gratefully acknowledge the financial support (contingency fund) provided by the Prime Minister’s Research Fellowship (PMRF), which was instrumental in facilitating this research project.

Disclosure statement

No potential conflict of interest was reported by the authors.

Additional information

Notes on contributors

Bijit Basumatary

Bijit Basumatary is a PhD student in the department of biomedical engineering in the Indian Institute of Technology Ropar, Rupnagar, India. He received a BTech degree in instrumentation engineering from the Central Institute of Technology Kokrajhar, Assam, India in 2018 and MTech degree in biomedical engineering from the Indian Institute of Technology Ropar, India in 2021. His research area includes functional electrical stimulation, foot drop, EMG. Corresponding author. Email: [email protected]

Rajat Suvra Halder

Rajat Suvra Halder is currently pursuing PhD in the department of Biomedical Engineering, Indian Institute of Technology Ropar, Punjab, India. He has done an MTech in VLSI design and microelectronics from Jadavpur University, Kolkata, India. His research area includes VLSI, functional electrical stimulation, and biopotential amplifiers. Email: [email protected]

Chirag Singhal

Chirag Singhal is am MTech student in the department of Biomedical Engineering in the Indian Institute of Technology Ropar, Rupnagar, India. He received a BE degree in electronics (instrumentation and control) engineering from Thapar Institute of Engineering and Technology, Punjab, India in 2018. His research area includes functional electrical stimulation, and machine learning. Email: [email protected]

Adarsha Narayan Mallick

Adarsha Narayan Mallick is a PhD research scholar in the department of Biomedical Engineering (DBME) of Indian Institute of Technology, Ropar, Rupnagar, Punjab, India. He has completed his bachelor of technology from the College of Engineering and Technology, Bhubaneswar. His research area includes neonatology, soft robotics, and biomedical instrumentation. Email: [email protected]

Arun Khokhar

Arun Khokhar is working as a senior lab technician in the department of neurology, Dayanand Medical College, Ludhiana, India. He completed a bachelor of science (BSc) degree in medical laboratory technology (MLT) from Vinayaka Mission University, India in 2008. His research area includes EMG, EEG epilepsy, and neurological diseases. Email: [email protected]

Rajinder Bansal

Rajinder Bansal is working as a professor of neurology at Dayanand Medical College, Ludhiana, India. He has MBBS (Bachelor of Medicine and Surgery, 1989) and MD (Doctor of Medicine, Internal Medicine, 1992) from Dayanand Medical College and Hospital Ludhiana. He has a DM (Doctorate of Medicine) from Sanjay Gandhi Post-Graduate Institute, Medical Science & Research, Lucknow, UP (2000). His research area includes EMG, EEG, epilepsy, and neurological diseases. Email: [email protected]

Ashish Kumar Sahani

Ashish Kumar Sahani is working as an assistant professor in the department of Biomedical Engineering of the Indian Institute of Technology Ropar, India where he is heading the medical devices lab. He has a PhD from the Indian Institute of Technology Madras, India and postdoctoral training from Harvard Medical School and the University of Michigan, USA. His research area includes medical devices, instrumentation, machine learning, and signal processing. Email: [email protected]