(1) Background: In the case of quick picking and heavy lifting, the carrying action results in a much more active myoelectric signal in the lower back than in an upright stationary one, and there is a high risk of back muscle injury without proper handling skills and equipment. (2) Methods: To reduce the risk of LBP during manual handing tasks, a hip active exoskeleton is designed to assist human manual lifting. A power control method is introduced into the control loop in the process of assisting human transportation. The power curve imitates the semi-squat movement of the human body as the output power of the hip joint. (3) Results: According to the test, the torque can be output according to the wearer’s movement. During the semi-squat lifting process, the EMG (electromyogram) signal of the vertical spine at L5/S1 was reduced by 30–48% and the metabolic cost of energy was reduced by 18% compared the situation of without EXO. (4) Conclusion: The exoskeleton joint output torque can change in an adaptive manner according to the angular velocity of the wearer’s joint. The exoskeleton can assist the waist muscles and the hip joint in the case of the reciprocating semi-squat lifting movement.

To assist hemiplegic patients with the activities of daily life, many upper limb soft exoskeletons have been developed. In this paper, we propose the structure of upper limb soft exoskeleton for rehabilitation training based on human biomechanics. The soft driving structure based on Bowden cable is devised. Man-machine interaction force must be considered because it can damage on the joint and lead to arm discomfort. We focus on structural optimization to minimize man-machine interaction force. Human arm model is established to perform motion simulation in ADAMS. To summarize optimality conditions, the movements of elbow are simulated in ADAMS when the number and location of force bearing points are changed. This paper describes the movement of the shoulder skeletal system through a mathematical model based on the Bowden cable transmission and utilizes man-machine contact force sensor to detect human interaction forces for analysis of experimental data. The experimental results show that man-machine interaction force can be reduced when the number of bearing force points is increased and bearing force point is away from the elbow.

The classification of lower limb gait phase is very important for the control of exoskeleton robots. In order to enable the exoskeleton to determine gait phase and provide appropriate assistance to the wearer, we propose a compound network based on CNN-BiLSTM. The method uses data from inertial measurement units placed on the leg and pressure sensor arrays placed on the sole as inputs to the model. The convolutional neural network (CNN) is used to obtain the local key features of gait data, and then the bidirectional long short-term memory (BiLSTM) network is used to extract the serialized gait phase information from the local key features to obtain the high-level feature expression. Finally, the seven phases of both feet were obtained through the classification of the softmax layer. We designed a gait acquisition system and collected the gait data from seven subjects at varying walking speeds. In the test set, the highest gait phase classification accuracy can reach 95.09%. We compared the proposed model with the long short-term memory (LSTM) network and gated recurrent unit (GRU) network. The experimental results show that the average accuracy of CNN-BiLSTM network from seven subjects is 0.417% higher than that of the LSTM network and 0.596% higher than that of the GRU network. Therefore, the ability of the CNN-BiLSTM network to classify gait phases can be applied in designing exoskeleton controllers that can better assist for different gait phases correctly to assist the wearer to walk.

Coronavirus disease (COVID-19) is highly contagious and pathogenic. Currently, the diagnosis of COVID-19 is based on nucleic acid testing, but it has false negatives and hysteresis. The use of lung CT scans can help screen and effectively monitor diagnosed cases. The application of computer-aided diagnosis technology can reduce the burden on doctors, which is conducive to rapid and large-scale diagnostic screening. In this paper, we proposed an automatic detection method for COVID-19 based on spatiotemporal information fusion. Using the segmentation network in the deep learning method to segment the lung area and the lesion area, the spatiotemporal information features of multiple CT scans are extracted to perform auxiliary diagnosis analysis. The performance of this method was verified on the collected dataset. We achieved the classification of COVID-19 CT scans and non-COVID-19 CT scans and analyzed the development of the patients’ condition through the CT scans. The average accuracy rate is 96.7%, sensitivity is 95.2%, and F1 score is 95.9%. Each scan takes about 30 seconds for detection.

Robot-assisted interventional surgery can greatly reduce the radiation received by surgeons during the operation, but the lack of force detection and force feedback is still a risk in the operation which may harm the patient. In those robotic surgeries, the traditional force detection methods may have measurement losses and errors caused by mechanical transmission and cannot identify the direction of the force. In this paper, an interventional surgery robot system with a force detection device is designed and a new force detection method based on strain gauges is proposed to detect the force and infer the bending direction of the catheter in the vessel by using BP neural network. In addition, genetic algorithm is used to optimize the BP neural network, and the error between the calculated results and the actual results is reduced by 37%, which improves the accuracy of catheter bending recognition. Combining this new method with traditional force sensors not only reduces the error caused by the traditional mechanical transmission, but also can detect the bending direction of the catheter in the blood vessel, which greatly improves the safety of the operation.

Voice production occurs through vocal cord and vibration coupled to glottal airflow. Vocal cord lesions affect the vocal system and lead to voice disorders. In this paper, a pathological voice source analysis system is designed. This study integrates nonlinear dynamics with an optimized asymmetric two-mass model to explore nonlinear characteristics of vocal cord vibration, and changes in acoustic parameters, such as fundamental frequency, caused by distinct subglottal pressure and varying degrees of vocal cord paralysis are analyzed. Various samples of sustained vowel /a/ of normal and pathological voices were extracted from MEEI (Massachusetts Eye and Ear Infirmary) database. A fitting procedure combining genetic particle swarm optimization and a quasi-Newton method was developed to optimize the biomechanical model parameters and match the targeted voice source. Experimental results validate the applicability of the proposed model to reproduce vocal cord vibration with high accuracy, and show that paralyzed vocal cord increases the model coupling stiffness.