Estimation of Knee Joint Angle Using Textile Capacitive Sensor and Artificial Neural Network Implementing with Three Shoe Types at Two Gait Speeds: A Preliminary Investigation

The lower limb joints might be affected by different shoe types and gait speeds. Monitoring joint angles might require skill and proper technique to obtain accurate data for analysis. We aimed to estimate the knee joint angle using a textile capacitive sensor and artificial neural network (ANN) implementing with three shoe types at two gait speeds. We developed a textile capacitive sensor with a simple structure design and less costly placing in insole shoes to measure the foot plantar pressure for building the deep learning models. The smartphone was used to video during walking at each condition, and Kinovea was applied to calibrate the knee joint angle. Six ANN models were created; three shoe-based ANN models, two speed-based ANN models, and one ANN model that used datasets from all experiment conditions to build a model. All ANN models at comfortable and fast gait provided a high correlation efficiency (0.75 to 0.97) with a mean relative error lower than 15% implement for three testing shoes. And compare the ANN with A convolution neural network contributes a similar result in predict the knee joint angle. A textile capacitive sensor is reliable for measuring foot plantar pressure, which could be used with the ANN algorithm to predict the knee joint angle even using high heel shoes.

Knee joint angle estimation by sequential correction of gyroscope bias

Compact and lightweight nine-axis motion sensors have come to be used for motion analysis in a variety of fields such as medical care, welfare, and sports. Nine-axis motion sensors include a three-axis gyroscope, a three-axis accelerometer, and a three-axis magnetometer and can estimate joint angles using the gyroscope outputs. However, the bias of the gyroscope is often unstable depending on the measurement environment and the accuracy of the gyroscope itself, causing error to accumulate in the angle obtained by integrating the gyroscope output. Although several sensor fusions have been proposed for pose estimation, such as using an accelerometer and a magnetometer, sequentially estimating and correcting the bias of the gyroscope are desirable for more accurate pose estimation. In addition, considering accelerations other than the acceleration due to gravity is important for a sensor fusion method that utilizes the accelerometer to correct the gyroscope output. Therefore, in this study, an extended Kalman filter algorithm was developed to sequentially correct both the gyroscope bias and the centrifugal and tangential acceleration of an accelerometer. The gait measurement results indicate that the proposed method successfully suppresses drift in the estimated knee joint angle over the entire measurement time of knee angle measurement during gait. The knee joint angles estimated using the proposed method were generally consistent with results obtained from an optical 3D motion analysis system. The proposed method is expected to be useful for estimating motion in medical care and welfare applications.