Convolutional neural network-based low-power wearable smart device for gait abnormality detection | |
| Author | Shakya, Sanjeev |
| Call Number | AIT Thesis no.IoT-22-01 |
| Subject(s) | Internet of Things Machine Learning Deep Learning Gait in humans |
| Note | A thesis submitted in partial fulfillment of the requirements for the degree of Master of Engineering in Internet of Things (IoT) Systems Engineering |
| Publisher | Asian Institute of Technology |
| Abstract | Gait analysis is often used to detect foot disorders and walking irregularities, such as prona tion, supination, unstable right foot, and unstable left foot. Detecting these abnormalities in their early stage could help us correct the walking posture, avoid getting injuries, and have a cortisone injection or surgery. The state-of-the-art gait analysis technology uses a camera-based motion-capture system and a combination of force plates. These systems are expensive and can only be used inside laboratories; therefore, emerging wearable technolo gies, such as the Artificial Intelligence (AI) and Internet of Things (IoT) based wearable devices, intelligent shoes, or insoles can potentially overcome this limitation. A novel ap proach using IoT, edge computing, and Tiny Machine Learning (TinyML) is proposed to predict the gait patterns of a person. The thesis discusses the overall architecture of col lecting, training, and deploying a data-driven solution on a microcontroller, the device is fitted onto a shoe of a person and classifies and predicts abnormal gait patterns. The solution makes use of an Inertial Measurement Unit (IMU) sensor, and a TinyML model deployed to Nordic semiconductor and an Advanced RISC Machines (ARM) chipset to infer from it. |
| Year | 2022 |
| Type | Thesis |
| School | School of Engineering and Technology (SET) |
| Department | Department of Information and Communications Technologies (DICT) |
| Academic Program/FoS | Internet of Things (IoT) Systems Engineering |
| Chairperson(s) | Attaphongse Taparugssanagorn |
| Examination Committee(s) | Chaklam Silpasuwanchai;Mongkol Ekpanyapong |
| Scholarship Donor(s) | Asian Institute of Technology Fellowship |
| Degree | Thesis (M. Eng.) - Asian Institute of Technology, 2022 |