Automated Detection of Rehabilitation Exercise by Stroke Patients Using 3-Layer CNN-LSTM Model

Abstract

According to statistics, stroke is the second or third leading cause of death and adult disability. Stroke causes losing control of the motor function, paralysis of body parts, and severe back pain for which a physiotherapist employs many therapies to restore the mobility needs of everyday life. This research article presents an automated approach to detect different therapy exercises performed by stroke patients during rehabilitation. The detection of rehabilitation exercise is a complex area of human activity recognition (HAR). Due to numerous achievements and increasing popularity of deep learning (DL) techniques, in this research article a DL model that combines convolutional neural network (CNN) and long short-term memory (LSTM) is proposed and is named as 3-Layer CNN-LSTM model. The dataset is collected through RGB (red, green, and blue) camera under the supervision of a physiotherapist, which is resized in the preprocessing stage. The 3-layer CNN-LSTM model takes preprocessed data at the convolutional layer. The convolutional layer extracts useful features from input data. The extracted features are then processed by adjusting weights through fully connected (FC) layers. The FC layers are followed by the LSTM layer. The LSTM layer further processes this data to learn its spatial and temporal dynamics. For comparison, we trained CNN model over the prescribed dataset and achieved 89.9% accuracy. The conducted experimental examination shows that the 3-Layer CNN-LSTM outperforms CNN and KNN algorithm and achieved 91.3% accuracy.