Sensor-based human activity recognition can benefit a variety of applications such as health care, fitness, smart homes, rehabilitation training, and so forth. In this paper, we propose a novel two-layer diversity-enhanced multiclassifier recognition method for single wearable accelerometer-based human activity recognition, which contains data-based and classifier-based diversity enhancement. Firstly, we introduce the kernel Fisher discriminant analysis (KFDA) technique to spatially transform the training samples and enhance the discrimination between activities. In addition, bootstrap resampling is utilized to increase the diversities of the dataset for training the base classifiers in the multiclassifier system. Secondly, a combined diversity measure for selecting the base classifiers with excellent performance and large diversity is proposed to optimize the performance of the multiclassifier system. Lastly, majority voting is utilized to combine the preferred base classifiers. Experiments showed that the data-based diversity enhancement can improve the discriminance of different activity samples and promote the generation of base classifiers with different structures and performances. Compared with random selection and traditional ensemble methods, including Bagging and Adaboost, the proposed method achieved 92.3% accuracy and 90.7% recall, which demonstrates better performance in activity recognition.

Sensor-based human activity recognition (HAR) has attracted interest both in academic and applied fields, and can be utilized in health-related areas, fitness, sports training, etc. With a view to improving the performance of sensor-based HAR and optimizing the generalizability and diversity of the base classifier of the ensemble system, a novel HAR approach (pairwise diversity measure and glowworm swarm optimization-based selective ensemble learning, DMGSOSEN) that utilizes ensemble learning with differentiated extreme learning machines (ELMs) is proposed in this paper. Firstly, the bootstrap sampling method is utilized to independently train multiple base ELMs which make up the initial base classifier pool. Secondly, the initial pool is pre-pruned by calculating the pairwise diversity measure of each base ELM, which can eliminate similar base ELMs and enhance the performance of HAR system by balancing diversity and accuracy. Then, glowworm swarm optimization (GSO) is utilized to search for the optimal sub-ensemble from the base ELMs after pre-pruning. Finally, majority voting is utilized to combine the results of the selected base ELMs. For the evaluation of our proposed method, we collected a dataset from different locations on the body, including chest, waist, left wrist, left ankle and right arm. The experimental results show that, compared with traditional ensemble algorithms such as Bagging, Adaboost, and other state-of-the-art pruning algorithms, the proposed approach is able to achieve better performance (96.7% accuracy and F1 from wrist) with fewer base classifiers.

The intelligent prosthesis driven by electromyography (EMG) signal provides a solution for the movement of the disabled. The proper position of EMG sensors can improve the prosthesis’s motion recognition ability. To exert the amputee’s action-oriented ability and the prosthesis’ control ability, the EMG spatial distribution and internal connection of the prosthetic wearer is analyzed in three kinds of movement conditions: appropriate angle, excessive angle, and angle too small. Firstly, the correlation characteristics between the EMG channels are analyzed by mutual information to construct a muscle functional network. Secondly, the network’s features of different movement conditions are analyzed by calculating the characteristic of nodes and evaluating the importance of nodes. Finally, the convergent cross-mapping method is applied to construct a directed network, and the critical muscle groups which can reflect the user’s movement intention are determined. Experiment shows that this method can accurately determine the EMG location and simplify the distribution of EMG sensors inside the prosthetic socket. The network characteristics of key muscle groups can distinguish different movements effectively and provide a new strategy for decoding the relationship between limb nerve control and body movement.

The multi‐camera calibration is an essential step for many spatially aware applications, such as robotic navigation, augmented reality, and 3D human pose estimation. Traditional calibration methods use off‐the‐shelf checkerboards or triangles as the known world coordinate system and their corresponding corners are set as control points, which heavily depends on specific calibration patterns and is not suitable for calibration pattern‐denied environments. In this paper, an automatic calibration method is proposed to calibrate the multi‐camera system without the aid of a known calibration pattern. The key idea of the proposed method is that the authors consider the human body, which is always available, as the counterpart of the calibration pattern. The authors’ approach starts with binocular camera calibration, in which the extrinsic and intrinsic parameters are calculated in order and followed by a joint optimisation. With the results of each pair of binocular camera calibration, the multi‐camera system calibration is carried out in three steps: (i) parameters initialisation, (ii) extrinsic parameters optimisation, and (iii) jointly optimising intrinsic and extrinsic parameters. Since the authors’ approach does not require additional calibration patterns except for one visible person, it is flexible and easy to be implemented. Real experiments are conducted in different scenes, camera angles, and camera settings. Human pose estimation with the multi‐camera system is additionally performed for exhaustive experiments. The experimental results demonstrate that the authors’ method shows superior performance than the traditional method with the aid of a specific calibration pattern.

The main joints of lower limb are hip, knee, ankle, and toe. Because of accidents or diseases, some people have to amputate. Wearing prosthesis can help them return to normal life. In the past, Active Knee joint and Active Knee-Ankle transfemoral prosthesis are studied. While in the stance phase, toe joint play an important role. In this article, the dynamic model and control method of Knee-Ankle-Toe Active Transfemoral Prosthesis are studied. The main contents are as follows: Firstly, according to the ground reaction force, the gait cycle is divided into three phases, Early and Middle Stance Phase (E&MSP), Late Stance Phase (LSP) and Swing Phase (SP), and the mechanical model of Knee-Ankle-Toe Active Transfemoral Prosthesis (KATATP) is established. Secondly, consider the cooperative movement of amputee and prosthesis, the kinematics model of prosthesis is established by Lie Groups and Lie Algebras, and the dynamic model of prosthesis is established by Lagrange equation. Thirdly, the whole gait cycle is a complete system and each phase is a different subsystem, switching rules and controllers of different subsystems are designed. Finally, experiments show that KATAP with the switching control enables amputee to have a biomechanically appropriate walking gait and achieve smooth transition between different gait phases.