Objective: Powered assistive devices need improved control intuitiveness to enhance their clinical adoption. Therefore, the intent of individuals should be identified and the device movement should adhere to it. Skeletal muscles contract synergistically to produce defined lowerlimb movements so unique contraction patterns in lower-extremity musculature may provide a means of device joint control. Ultrasound (US) imaging enables direct measurement of the local deformation of muscle segments. Hence, the objective of this study was to assess the feasibility of using US to estimate human lower-limb movements. Methods: A novel algorithm was developed to calculate US features of the rectus femoris muscle during a non-weight-bearing knee flexion/extension experiment by 9 able-bodied subjects. Five US features of the skeletal muscle tissue were studied, namely, thickness, angle between aponeuroses, pennation angle, fascicle length, and echogenicity. A multiscale ridge filter was utilized to extract the structures in the image and a random sample consensus (RANSAC) model was used to segment muscle aponeuroses and fascicles. A localization scheme further guided RANSAC to enable tracking in an US image sequence. Gaussian process regression (GPR) models were trained using segmented features to estimate both knee joint angle and angular velocity. Results: The proposed segmentation-estimation approach could estimate knee joint angle and angular velocity with an average root mean square error value of 7.45 degrees and 0.262 rad/s, respectively. The average processing rate was 3-6 frames per second that is promising towards real-time implementation.

No abstract

No abstract

Population aging of the societies requires providing the elderly with safe and dependable assistive technologies in daily life activities. Improving the fall detection algorithms can play a major role in achieving this goal. This article proposes a real-time fall prediction algorithm based on the acquired visual data of a user with walking assistive system from a depth sensor. In the lack of a coupled dynamic model of the human and the assistive walker a hybrid "system identification-machine learning" approach is used. An autoregressive-moving-average (ARMA) model is fitted on the time-series walking data to forecast the upcoming states, and a hidden Markov model (HMM) based classifier is built on the top of the ARMA model to predict falling in the upcoming time frames. The performance of the algorithm is evaluated through experiments with four subjects including an experienced physiotherapist while using a walker robot in five different falling scenarios; namely, fall forward, fall down, fall back, fall left, and fall right. The algorithm successfully predicts the fall with a rate of 84.72%.

No abstract