Classification of lower limb rehabilitation exercises with multiple and individual inertial measurement units

Abstract

Straight leg raise rehabilitation exercises (for both lying and seated position) for lower limb injuries play a critical role in terms of stress on joints after the injury. The primary objective of the paper is to find how accurately and efficiently a single and a two IMU sensor-based system could classify SSLR (Seated straight leg raise) and LSLR (Lying straight leg raise) exercises using machine learning. Inertial Measurement Units (IMUs) that include accelerometer and gyroscope were calibrated and tested, individual and combined, for classified seating as well as lying exercise and for different demanded personalities. Individual IMUs achieved about 96 % accuracy in binary classification. However, the combined (two) IMUs achieved about 96.8 % accuracy. The merits of the proposed IMU based sensor system are that it is easy to install, cost effective and very useful for telemedical operations in pandemic situations like COVID19. On the basis of these results, it could be concluded that the accuracy of a single IMU sensor system and a two IMU sensor-based system is approximately 96% and both were efficiently able to classify SSLR and LSLR exercises as well as identify the individual performing the exercise.

Ataxic person prediction using feature optimized based on machine learning model

“…Motion disorders plays a key indicator in identifying many diseases as described in [1], [2] such as physical activity, rehabilitation, physical therapy, orthopedics, rheumatology, and neurology. As stated in [1], around 70% of neurological inpatients exhibit abnormal gait activity; thus, gait-based assessment model can be leveraged for early diagnosis [3] of neurological disorder as demonstrated in [4], [5]. The research work mainly focusses on identifying ataxic neurological disorder through gait analysis as demonstrated in [6].…”

Ataxia severity classification using enhanced feature selection and ranking optimization through machine learning model

“…There are several fields, including physiology, rehabilitation, physiotherapy, orthopedics, arthritis, and neuroscience, in which movement abnormalities serve [1] as crucial diagnostic indicators [2]. Approximately 70% of neurological hospitalized patients have abnormal gait activity, Alsaif et al [2], suggesting that the gait based evaluation method [3] can be used to make an earlier identification of neurological disease [4]. The primary goal of this study is to use gait analysis to diagnose ataxic neurologicaldisorder [5].…”