Motion sensor interface for body activity monitoring

• Main Author: Ang, Deng
• Other Authors: Goh Wang Ling
• Format: Final Year Project
• Language: English
• Published: 2018
• Subjects: DRNTU::Engineering
• Online Access: http://hdl.handle.net/10356/74547
• Institution: Nanyang Technological University

Diabetic foot ulcer (DFU) is a debilitating complication of diabetes. It caused great vessels and foot nerve lesions, and lead to local tissue ulceration, infection, osteomyelitis, necrosis and so on. This diminishes the body’s natural protective mechanism. Foot pressure measurement devices have been used for adjusting footwear or alerting the patient of high pressure, but they are still in the infancy phase. The aim of this project is to develop a novel wearable intelligent foot pressure monitoring device. It will be able to perform comprehensive pressure, human activity analysis and real-time biofeedback. Meanwhile, this device is designed for miniaturization, ultra-low power consumption and low cost. In this project, a broad level foot pressure monitoring device and a digital signal processor system need be design. Therefore, a proper machine learning classifier need be chosen to perform in-device motion activity analysis. Moreover, to perform dynamic sensor monitoring system, a proper sensor inter-face circuit need to be designed. MATLAB is used to check the performance of random-forest (one of supervised classifier), in order to obtain the relationship between accuracy and processing time, power consumption of random-forest. Cadence Virtuoso Analog Design Environment is used to design the schematic of Op-amp inside sensor interface circuit, which use Op-amp AD8553 as reference. This Op-amp is used to amplify the signal captured from pressure sensors. In addition, testing on pressure sensors was also performed to determine several resistances value in the sensor interface circuit. It also used to find out the calibration methods for conducting pressure analysis.