Design and development of foot worn piezoresistive sensor for knee pain analysis with supervised machine learning algorithms based on gait pattern

Abstract

Gait monitoring and analysis have garnered more attention in gait analysis to verify the potential improvements of lower limb disorders like arthritis, trauma, and degenerative disorders. The irregularities in gait often manifest as knee pain or physical discomfort experienced by the patient. Existing vision and floor sensor-based systems have the limitations of operational complexity and high cost that make them uncomfortable for individual use. These limitations led to research interest in the design and development of insole embedded with 102 sensors to detect foot pressure distribution image for detecting lower limb disorder-based problems. The quality of these heat images is enhanced by a hybrid filter (RMSE = 2.748 and PSNR = 39.35) and feature extraction technique is utilized on the enhanced foot pressure images for classification. The KNN learner model yields accuracy of 99.4% in the detection of knee pain.