As a life-threatening disease, stroke can lead to long-term problems affecting the patients’ daily living ability. A common problem facing post-stroke patients is foot drop. An emerging modality of interest for correcting the foot drop is to combine both actuated ankle-foot orthosis (AAFO) and functional electrical stimulation (FES). Such hybrid assistive system not only ensure effective assistance but also can avoid fast muscular fatigue due to excessive muscular stimulation. Due to the significant changes in the ankle joint’s kinematics and kinetics with gait cycles, optimization control strategies for hybrid AAFO and FES systems are highly demanded. However, it is challenging to develop accurate gait phase detection algorithms to guide the control of AAFO and FES while ensuring robustness with respect to the diversity and variability of patients’ gaits. In this paper, we present a novel swing sub-phase detection algorithm based on a moving average convergence divergence (MACD) indicator. The proposed detection algorithm uses only information collected from the affected leg by means of two inertia measurement units (IMU) and the AAFO. Moreover, a gait-phase based control strategy is developed to optimize the assistive effect of a hybrid AAFO and FES system. Experimental results with five healthy show the potential of the proposed approaches in ensuring both satisfactory ankle joint trajectory tracking and effective reduction in stimulation intensity, compared to the use of conventional FES assistance.

Gesture recognition becomes a thriving research area in modern human motion recognition systems. The intensification of demands on efficient interactive human-machine-interface systems, commercial objectives, and many other factors contributes to fuel this revival dynamics. Understanding human gestures becomes essential for prevention and health monitoring applications. In particular, analyzing hand gestures is of paramount importance in personalized healthcare-related applications to help practitioners providing more qualitative assessments of subject's pathologies, such as Parkinson's diseases. This work proposes a novel deep neural network approach to forecast future gestures from a given sequence of hand motion using a wearable capacitance sensor of an innovative gesture recognition hardware system. To do this, we use an attention-based recurrent neural network to capture the temporal features of hand motion to unveil the underlying pattern between the gesture and these sequences. While the attention layers capture patterns from the weights of the short term, the gated recurrent unit (GRU) neural network layer learns the inherent interdependency of long-term hand gesture temporal sequences. The efficiency of the proposed model is evaluated with respect to cutting-edge work in the field using several metrics. Note to Practitioners-In this article, the problem of human hand gesture recognition is analyzed using deep learning techniques. The proposed model uses input historical motion sequences collected from a wearable capacitance sensor to predict hand gestures. The model leverages the intrinsic correlation of motion sequences and extracts the salient part of the sequences by taking into consideration their temporal, complex, and nonlinear features. The approach studies the effect of different lengths of historical motion sequences in prediction outcomes. This allows for avoiding using cumbersome data collection, heavy data treatment, and high computational cost. The model performance is trained and assessed on real-world data by performing comparisons with alternative approaches, including well-known classifiers. The model yields very encouraging results and demonstrates that the proposed approach is quite competitive as it can reproduce typical activity trends for important channels. The present findings could help in the development of intelligent wearable devices for predicting hand gestures using a limited number of channels. This work could also help practitioners to provide a more qualitative appraisal of patients suffering from different pathologies such as Parkinson's diseases to personalized healthcare-related applications and to develop wearable gesture recognition devices on a large scale.

In applications of human-robot interactions, accurate measurement of interactive forces between the human and the robot plays a significant role. Such sensors should not only be accurate and reliable, but also be soft enough to guarantee the safe and compliant human-robot interaction. In this aspect, pneumatic sensors with soft air chambers have often been utilized as a soft force measurement system. Although such a sensor system provides a good compliance and softness, however, it measures only a lumped force acting on the chamber, because the measurement of the pneumatic sensor is the pressure change in the air chamber. For the measurement of multi-dimensional interaction forces with high softness and compliance, a three-axis force measurement system is devised by arranging three air chambers in a radially symmetric pattern. Each air chamber embeds a pneumatic sensor, and the pressure changes in the three air chambers are measured in order to distinguish the direction of the applied force. By decoupling the sensor signals from the three pneumatic sensors, the three-dimensional force components can be calculated accurately. Consequently, the proposed sensor system is able to measure the three-axis forces while maintaining the great softness and compliance provided by the soft air chambers. The design, the fabrication method, and the verification of the proposed method are introduced in this paper.

Recognition of human gestures plays an important role in a number of human-interactive applications, such as mobile phones, health monitoring systems, and human-assistive robots. Electromyography (EMG) is one of the most common and intuitive methods used for detecting gestures based on muscle activities. The EMG, however, is in general, too sensitive to environmental disturbances, such as electrical noise, electromagnetic signals, humidity, and so on. In this paper, a new method for recognizing the muscular activities is proposed based on air-pressure sensors and air-bladders. The muscular activity is detected by measuring the change of the air pressure in an air-bladder contacting the interested muscle(s). Since the change of the air pressure can be more robustly measured compared with the change of electric signals appeared on the skin, the proposed sensing method is useful for mobile devices due to its great signal-to-noise ratio (SNR) and fast response time. The principle and applications of the proposed sensing method are introduced in this paper. The performance of the proposed method is evaluated in terms of linearity, repeatability, wear-comfort, etc., and is also verified by comparing it with an EMG signal and a motion sensor.

Motion capture systems play an important role in health-care and sport-training systems. In particular, there exists a great demand on a mobile motion capture system that enables people to monitor their health condition and to practice sport postures anywhere at any time. The motion capture systems with infrared or vision cameras, however, require a special setting, which hinders their application to a mobile system. In this paper, a mobile three-dimensional motion capture system is developed based on inertial sensors and smart shoes. Sensor signals are measured and processed by a mobile computer; thus, the proposed system enables the analysis and diagnosis of postures during outdoor sports, as well as indoor activities. The measured signals are transformed into quaternion to avoid the Gimbal lock effect. In order to improve the precision of the proposed motion capture system in an open and outdoor space, a frequency-adaptive sensor fusion method and a kinematic model are utilized to construct the whole body motion in real-time. The reference point is continuously updated by smart shoes that measure the ground reaction forces.