Available at: https://digitalcommons.calpoly.edu/theses/3188
Date of Award
12-2025
Degree Name
MS in Biomedical Engineering
Department/Program
Biomedical Engineering
College
College of Engineering
Advisor
Long Wang
Advisor Department
Civil and Environmental Engineering
Advisor College
College of Engineering
Abstract
Lower limb amputees face significant challenges in maintaining a proper prosthetic fit, as improper fit can lead to slippage at the limb-socket interface, resulting in discomfort, pressure sores, and long-term musculoskeletal complications. To address this issue, a fully integrated slippage detection system was developed to monitor an amputee’s daily activities and slippage occurrences to understand their prosthetic fit over time. The system consists of a prosthetic sock embedded with Interlink 406 flexible piezoresistive force-sensing resistors (FSRs). The sock, worn directly on the residual limb, continuously measures pressure at the limb-socket interface. Sensor data from six FSRs is sampled at approximately 240 Hz and transmitted via Bluetooth to an iOS mobile application for real-time processing.
The mobile application implements a Temporal Convolutional Network (TCN) with dilated convolutions to classify amputee activity states and detect slippage events using the raw tensor of six FSR signals across a 5.28-second window. In parallel, a Random Forest classifier is trained on 48 statistical and structural features extracted from the same 5.28-second windows to validate the TCN model's performance and to confirm that relevant activity and slippage patterns are reliably captured by both feature-based and tensor-based approaches. Both the tensor data and classification results are stored in a cloud database to enable continuous tracking over time for each user.
Experimental results under controlled conditions show that the system combined with the TCN achieves 98% classification accuracy for activity states (such as walking, standing, sitting, transition) and 97% accuracy for slippage detection events. By tracking the amount and type of activity performed by an amputee and directly relating this to the frequency and characteristics of slippage occurrences, the system provides deep insights into prosthetic fit stability. Specifically, it enables early identification of deteriorating fit, assessment of whether recent prosthetic adjustments have led to lasting improvements, detection of increased slippage that may precede skin breakdown or injury, and longitudinal monitoring of limb volume changes or suspension system performance.
These findings suggest that the slippage detection system can be used daily by amputees to monitor the evolving interaction between their residual limb and prosthetic socket, offering feedback to users and clinicians that supports preventive care, prosthetic optimization, and overall user confidence during rehabilitation and long-term prosthetic use.