Classification of physiotherapy exercise of stroke patients using deep transfer learning and fuzzy logic: A novel approach

Abstract

According to the world health organization (WHO), stroke stands as a significant contributor to mortality and adult disability, causing motor function impairment, paralysis, and intense back pain. In aiding stroke patients' mobility recovery, physiotherapists employ diverse therapeutic techniques. This research introduces an automated method for identifying distinct therapeutic exercises performed by stroke patients during their rehabilitation process. For detecting rehabilitation exercises, leveraging pre-trained neural networks like GoogLeNet, InceptionV3, ResNet-101, DenseNet-201, Xception, InceptionResNetV2, and DarkNet-53, all potent models trained on extensive datasets. The proposed models were trained on a dataset of 2250 diverse RGB images to classify eight rehabilitation exercises: Elbow Extension, Knee Flexion, Neck Exercise, Planter Flexion of Foot, Trunk Extension, Trunk Flexion, Wrist Extension, and Wrist Flexion. The resulting average validation accuracies are as follows: InceptionV3 (97.4%), Xception (97.3%), ResNet101 (97.3%), DarkNet53 (96.7%), GoogLeNet (95.9%), DenseNet201 (94.3%), and InceptionResNetV2 (93.4%). Fuzzy EDAS is then employed to rank the models. This ranking suggests that the inception-v3 model has high rank for most of the classes and is highly recommended for physiotherapy exercises classification.