Biomimetic Tendon-Based Mechanism for Finger Flexion and Extension in a Soft Hand Exoskeleton: Design and Experimental Assessment.

This study proposes a bioinspired exotendon routing configuration for a tendon-based mechanism to provide finger flexion and extension that utilizes a single motor to reduce the complexity of the system. The configuration was primarily inspired by the extrinsic muscle-tendon units of the human musculoskeletal system. The function of the intrinsic muscle-tendon units was partially compensated by adding a minor modification to the configuration of the extrinsic units. The finger kinematics produced by this solution during flexion and extension were experimentally evaluated on an artificial finger and compared to that obtained using the traditional mechanism, where one exotendon was inserted at the distal phalanx. The experiments were conducted on nine healthy subjects who wore a soft exoskeleton glove equipped with the novel tendon mechanism. Contrary to the traditional approach, the proposed mechanism successfully prevented the hyperextension of the distal interphalangeal (DIP) and the metacarpophalangeal (MCP) joints. During flexion, the DIP joint angles produced by the novel mechanism were smaller than the angles generated by the traditional approach for the same proximal interphalangeal (PIP) joint angles. This provided a flexion trajectory closer to the voluntary flexion motion and avoided straining the interphalangeal coupling between the DIP and PIP joints. Finally, the proposed solution generated similar trajectories when applied to a stiff artificial finger (simulating spasticity). The results, therefore, demonstrate that the proposed approach is indeed an effective solution for the envisioned soft hand exoskeleton system.

Sensor positioning for a human activity recognition system using a double layer classifier.

This paper describes the development of a human gait activity recognition system. A multi-sensor recognition system, which has been developed for this purpose, was reduced to a single sensor-based recognition system. A sensor election method was devised based on the maximum relevance minimum redundancy feature selector to determine the sensor's optimum position regarding activity recognition. The election method proved that the thigh has the highest contribution to recognize walking, stairs and ramp ascending, and descending activities. A recognition algorithm (which depends mainly on features that are classified by random forest, and selected by a combined feature selector using the maximum relevance minimum redundancy and genetic algorithm) has been modified to compensate the degradation that occurs in the prediction accuracy due to the reduction in the number of sensors. The first modification was implementing a double layer classifier in order to discriminate between the interfered activities. The second modification was adding physical features to the features dictionary used. These modifications succeeded to improve the prediction accuracy to allow a single sensor recognition system to behave in the same manner as a multi-sensor activity recognition system.