Gait and posture are regular activities which are fully controlled by the sensorimotor cortex. In this study, fluctuations of joint angle and asymmetry of foot elevation in human walking stride records are analyzed to assess gait in healthy adults and patients affected with gait disorders. This paper aims to build a low-cost, intelligent and lightweight wearable gait analysis platform based on the emerging body sensor networks, which can be used for rehabilitation assessment of patients with gait impairments. A calibration method for accelerometer and magnetometer was proposed to deal with ubiquitous orthoronal error and magnetic disturbance. Proportional integral controller based complementary filter and error correction of gait parameters have been defined with a multi-sensor data fusion algorithm. The purpose of the current work is to investigate the effectiveness of obtained gait data in differentiating healthy subjects and patients with gait impairments. Preliminary clinical gait experiments results showed that the proposed system can be effective in auxiliary diagnosis and rehabilitation plan formulation compared to existing methods, which indicated that the proposed method has great potential as an auxiliary for medical rehabilitation assessment.

Gait analysis, as a common inspection method for human gait, can provide a series of kinematics, dynamics and other parameters through instrumental measurement. In recent years, gait analysis has been gradually applied to the diagnosis of diseases, the evaluation of orthopedic surgery and rehabilitation progress, especially, gait phase abnormality can be used as a clinical diagnostic indicator of Alzheimer Disease and Parkinson Disease, which usually show varying degrees of gait phase abnormality. This research proposed an inertial sensor based gait analysis method. Smoothed and filtered angular velocity signal was chosen as the input data of the 15-dimensional temporal characteristic feature. Hidden Markov Model and parameter adaptive model are used to segment gait phases. Experimental results show that the proposed model based on HMM and parameter adaptation achieves good recognition rate in gait phases segmentation compared to other classification models, and the recognition results of gait phase are consistent with ground truth. The proposed wearable device used for data collection can be embedded on the shoe, which can not only collect patients’ gait data stably and reliably, ensuring the integrity and objectivity of gait data, but also collect data in daily scene and ambulatory outdoor environment.

Driving behavior tracking and recognition are essential for traffic safety. This paper proposes a driving behavior monitoring and analysis method based on motion capture and artificial intelligence techniques. Different driving actions can be identified as normal or abnormal driving behaviors. The real-time motion is monitored bymultiple miniature inertial measurement units (IMUs). Gradient descent method is used to fuse the raw data and update the driver’s attitude information constantly. The body’s joint angle series can be obtained by the iteration operation of the consecutive segment under the assumption of rigid structure. In order to accurately identify two arms’ maneuvers under different traveling routes, we compare the traditional machine learning-based method with the proposed deep neural networkbased approach using joint angle series. The recognition rates of both methods are above 99% in the experiment, and the algorithm performance in real scenario is also satisfactory. These results show that joint angle-based driving behavior recognition is an effective method, and it can be applied for driving training or guiding the novice.

Gesture recognition has found widespread applications in various fields, such as virtual reality, medical diagnosis, and robot interaction. The existing mainstream gesture-recognition methods are primarily divided into two categories: inertial-sensor-based and camera-vision-based methods. However, optical detection still has limitations such as reflection and occlusion. In this paper, we investigate static and dynamic gesture-recognition methods based on miniature inertial sensors. Hand-gesture data are obtained through a data glove and preprocessed using Butterworth low-pass filtering and normalization algorithms. Magnetometer correction is performed using ellipsoidal fitting methods. An auxiliary segmentation algorithm is employed to segment the gesture data, and a gesture dataset is constructed. For static gesture recognition, we focus on four machine learning algorithms, namely support vector machine (SVM), backpropagation neural network (BP), decision tree (DT), and random forest (RF). We evaluate the model prediction performance through cross-validation comparison. For dynamic gesture recognition, we investigate the recognition of 10 dynamic gestures using Hidden Markov Models (HMM) and Attention-Biased Mechanisms for Bidirectional Long- and Short-Term Memory Neural Network Models (Attention-BiLSTM). We analyze the differences in accuracy for complex dynamic gesture recognition with different feature datasets and compare them with the prediction results of the traditional long- and short-term memory neural network model (LSTM). Experimental results demonstrate that the random forest algorithm achieves the highest recognition accuracy and shortest recognition time for static gestures. Moreover, the addition of the attention mechanism significantly improves the recognition accuracy of the LSTM model for dynamic gestures, with a prediction accuracy of 98.3%, based on the original six-axis dataset.

Coaches and athletes are constantly seeking novel training methodologies in an attempt to improve athletic performance. This paper proposes a method of rowing sport capture and analysis based on Inertial Measurement Units (IMUs). A canoeist’s motion was collected by multiple miniature inertial sensor nodes. The gradient descent method was used to fuse data and obtain the canoeist’s attitude information after sensor calibration, and then the motions of canoeist’s actions were reconstructed. Stroke quality was performed based on the estimated joint angles. Machine learning algorithm was used as the classification method to divide the stroke cycle into different phases, including propulsion-phase and recovery-phase, a quantitative kinematic analysis was carried out. Experiments conducted in this paper demonstrated that our method possesses the capacity to reveal the similarities and differences between novice and coach, the whole process of canoeist’s motions can be analyzed with satisfactory accuracy validated by videography method. It can provide quantitative data for coaches or athletes, which can be used to improve the skills of rowers.