This study presents a new wearable insole pressure sensor (IPS), composed of fabric coated in a carbon nanotube-based composite thin film, and validates its use for quantifying ground reaction forces (GRFs) during human walking. Healthy young adults (n = 7) walked on a treadmill at three different speeds while data were recorded simultaneously from the IPS and a force plate (FP). The IPS was compared against the FP by evaluating differences between the two instruments under two different assessments: (1) comparing the two peak forces at weight acceptance and push-off (2PK) and (2) comparing the absolute maximum (MAX) of each gait cycle. Agreement between the two systems was evaluated using the Bland–Altman method. For the 2PK assessment, the group mean of differences (MoD) was −1.3 ± 4.3% body weight (BW) and the distance between the MoD and the limits of agreement (2S) was 25.4 ± 11.1% BW. For the MAX assessment, the average MoD across subjects was 1.9 ± 3.0% BW, and 2S was 15.8 ± 9.3% BW. The results of this study show that this sensor technology can be used to obtain accurate measurements of peak walking forces with a basic calibration and consequently open new opportunities to monitor GRF outside of the laboratory.

The development of wearable technology, which enables motion tracking analysis for human movement outside the laboratory, can improve awareness of personal health and performance. This study used a wearable smart sock prototype to track foot–ankle kinematics during gait movement. Multivariable linear regression and two deep learning models, including long short-term memory (LSTM) and convolutional neural networks, were trained to estimate the joint angles in sagittal and frontal planes measured by an optical motion capture system. Participant-specific models were established for ten healthy subjects walking on a treadmill. The prototype was tested at various walking speeds to assess its ability to track movements for multiple speeds and generalize models for estimating joint angles in sagittal and frontal planes. LSTM outperformed other models with lower mean absolute error (MAE), lower root mean squared error, and higher R-squared values. The average MAE score was less than 1.138° and 0.939° in sagittal and frontal planes, respectively, when training models for each speed and 2.15° and 1.14° when trained and evaluated for all speeds. These results indicate wearable smart socks to generalize foot–ankle kinematics over various walking speeds with relatively low error and could consequently be used to measure gait parameters without the need for a lab-constricted motion capture system.