Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{202059,
        author = {Mr. Abhishek Kumar Saxena and Mr. Mukesh Saini},
        title = {Smart Wearable Shoes for Deep Learning-Based Gait Analysis and Abnormal Walking Pattern Detection},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {12},
        pages = {8204-8208},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=202059},
        abstract = {Smart wearable shoes represent a significant advancement in healthcare-oriented product design by enabling continuous, real-time monitoring of human gait in everyday environments. This research focuses on the development of intelligent footwear integrated with sensor-based systems and deep learning algorithms to detect abnormal walking patterns with high precision. The proposed smart shoe incorporates multiple embedded sensors, including pressure sensors, accelerometers, and gyroscopes, strategically placed within the insole and sole structure to capture both spatial and temporal gait parameters such as foot pressure distribution, stride length, balance, and motion dynamics.
The collected data is transmitted to a processing unit where it is analyzed using a hybrid deep learning model that combines Convolutional Neural Networks (CNNs) for spatial feature extraction and Long Short-Term Memory (LSTM) networks for temporal sequence analysis. This integrated approach enhances the system’s ability to recognize subtle deviations in walking patterns. Unlike traditional gait analysis systems that rely on expensive laboratory-based equipment, this solution offers a portable, cost-effective, non-invasive, and user-friendly alternative.
The system enables early detection and continuous monitoring of disorders such as Parkinson’s disease, stroke-related impairments, musculoskeletal disorders, arthritis, and post-injury mobility conditions. Experimental findings indicate an overall classification accuracy of approximately 93–95%, highlighting the strong potential of smart wearable footwear in healthcare monitoring, rehabilitation support, and preventive diagnostics.},
        keywords = {Smart Wearable Shoes, Intelligent Footwear, Gait Analysis, Deep Learning, CNN-LSTM, Sensor-Based Footwear, Healthcare Wearables},
        month = {May},
        }