Feedback-Based Gait Identification Using Deep Neural Network Classification

Abstract

Identification of gait plays a major role in the healthcare industry, recognition of a gait having different angles, identification of abnormalities is a challenging task, to detect the abnormal person identification contains improper pattern style, human limbs, walking pattern, etc... A normal person has a correct pattern, an abnormal person has an irregular pattern. This paper provides the identification of the lean angle and ramp angle [19] of irregular patterns on three abnormalities such as Parkinson gait, Hemiplegic gait, and Neuropathic gait [18] by using deep neural network (DNN) without clinical observation by using DNN classification with feedback-based verification of trained features with query features of abnormal identification of trained features with query features. This paper concludes the gait abnormalities based on lean angle and ramp angle.

A comparative and comprehensive study of prediction of Parkinson’s disease

“…Viswanathan and Naib [61] have proposed as Performance parameters used by authors are true positive, true negative and accuracy. Authors make use of various semi-supervised classifiers for intrusion detection.…”

Survey of Human Gait Analysis and Recognition for Medical and Forensic Applications

“…They found that average stride length of control group is 37.2 cm which is greater than the stride length of PD group 22.38 cm but gait speed is almost equal in both cases. Early detection of Parkinson diseases (Kondragunta et al, 2019;Mallikarjuna et al,2020) can delay the effect of this disease. For early detection of this disease deep learning algorithms can be used to estimate 2D poses.…”