Journal of critical reviews 661 Journal of Critical Reviews ISSN- 2394-5125 Vol 7, Issue 4, 2020 Review Article FEEDBACK-BASED GAIT IDENTIFICATION USING DEEP NEURAL NETWORK CLASSIFICATION Basetty Mallikarjuna 1* , R. Viswanathan 2 and Bharat Bhushan Naib 3 School of Computing Science & Engineering, Galgotias University, Greater Noida, Uttar Pradesh, India 203201. 1 mallikarjuna.basetty@galgotiasuniversity.edu.in , 2rvnathan06@gmail.com, 3bharat.bhushan@galgotiasuniversity.edu.in Received: 22.12.2019 Revised: 24.01.2020 Accepted: 05.02.2020 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. Keywords: Human Gait, Deep Learning, Deep Neural Networks, Feedback-based etc.. © 2019 by Advance Scientific Research. This is an open-access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/) DOI: http://dx.doi.org/10.31838/jcr.07.04.125 INTRODUCTION: Gait plays a major role in health care applications to identify the walking style of the person and movements of the human, the normal gait refers to the correct walking style stance (pattern) [1], swing phases and sequence of the person, the abnormal gait refers to irregular pattern of a person walking style stance, swing phases and sequence of the person, in different situations. Several research has been done on human gait analysis, while human walking spending some energy conserved from the different parts of the body, some energy distributed from the body that depends on different parts of the body [2, 18]. The analysation of the body can be identified by the walking movements of the lean angle and ramp angle [18]. The purpose of the lean angle and ramp angle is to keep the balance of the person to provide the observation health condition as follows[3, 19]. • Lean Angle: While person walking lean angle is the leg position boot that forces to keep away from actual position, the boot ranges between the 13-17 ° [4], the walking position boot feels unbalanced, one leg position is behind the next step of leg position, the forcing of walking legs to bend from one position to another position [5]. • Ramp Angle: While person walking the height difference between the toes and heels inside the boot ranges between 4-7 ° [6], the forward lean of the left leg to right leg, the general body position unbalanced to adjust walking position [7]. The lean and ramp angle is most required to observe the walking position and identify the abnormality of a human [5, 6, 7, 8], it depends on the “actual position of walking” the observation towards the foot, and also depends on the strength of the person stability to walk [8]. The difference of angle between the two legs with a heel wedge under the liner, the people with excessive range of motion while walking with a boot of lower ramp angle is standing more upright [9]. Based on the human walking style, and pattern of leg movements derived from the kinematics, we observed the video sequence, abnormal person, it identifies the abnormal person by using gait cycles. The mainly gait cycles can be characterised as two groups i) Normal Gait ii) Abnormal Gait [10, 11]. Normal Gait Identification [2] The pattern occurs natural in gait cycles and it allows proper cycles while walking at least one foot can touch with the ground at one cycle of rotations, the recognition of human gait in healthcare industry plays a major role to identify normal or abnormal gait by identifying the walking style of the person movements which consist of the correct sequence of the stance and swing phases [4,19]. Abnormal Gait Identification [3] Abnormal gait is the improper pattern sequence, it identifies the visualizing the video sequence with sluggish observation, once it plays the video sluggish and improper stance of swing phases [5, 19]. This paper proposed the novel approach to identify the abnormal person by identifying the neurological disorders. The observation of video head, hip, heal and toe bidirectional analysis provides three major types of gaits as shown in figure 1. Figure 1: Types of Abnormal Gaits [18, 19].