Rehabilitation robots play an increasingly important role in the recovery of motor function for stroke. To ensure a natural physical human-robot interaction (pHRI) and enhance the active participation of subjects, it is necessary for the robots to understand the human intention and cooperate actively with humanlike characteristics. This study proposed a hybrid active control algorithm with human motion intention detection. The motion intention was defined as the desired position and velocity, which were continuously estimated according to the human upper-limb model and minimum jerk model, respectively. The motion intention was then fed into a hybrid force and position controller of an upper-limb cable driven rehabilitation robot (CDRR). And a three-dimensional reaching task without predefined trajectory was employed to validate the effectiveness of the proposed control algorithm. Experimental results showed that the control algorithm could continuously recognize the human motion intention and enabled the robot better movement performance indicated as smaller offset error, smoother trajectory, and lower impact. The proposed method could guarantee a natural pHRI and improve the engagement of the subjects, which has great potential in clinical applications.

The major cities of China have experienced massive growth in the number and usage of dockless shared bicycle systems, such as Mobike and Ofo, which have replaced the traditional docked bicycle systems that are heavily regulated by local governments. However, docked bicycle systems are still in operation, especially in small and medium-sized cities that have docked shared bicycle systems run by the local government. This study aims to reveal the user choice behaviours for these two shared bicycle systems from the perspective of user experience and to find win-win strategies for the two systems, based on a case study of the Shunde district in Foshan city. The structural equation model and binary logit model are employed to identify the impact factors of the choice behaviours. It is found that user experience plays a key role in the use intention for two kinds of bicycles, including factors such as convenience, riding experience, and level of service. Age is the most important indicator distinguishing the user groups, as older people prefer docked bicycles while younger people prefer dockless ones. Docked and dockless shared bicycle systems operate together harmoniously in Shunde as they satisfy the demands of different user groups with little overlap. It is suggested that a new shared bicycle system, which combines the advantages of both docked and dockless shared bicycles, would be a better solution for small and mid-size cities.

In precision oncology, immune check point blockade therapy has quickly emerged as novel strategy by its efficacy, where programmed death ligand 1 (PD-L1) expression is used as a clinically validated predictive biomarker of response for the therapy. Automating pathological image analysis and accelerating pathology evaluation is becoming an unmet need. Artificial Intelligence and deep learning tools in digital pathology have been studied in order to evaluate PD-L1 expression in PD-L1 immunohistochemistry image. We proposed a Dual-scale Categorization (DSC)-based deep learning method that employed 2 VGG16 neural networks, 1 network for 1 scale, to critically evaluate PD-L1 expression. The DSC-based deep learning method was tested in a cohort of 110 patients diagnosed as non-small cell lung cancer. This method showed a concordance of 88% with pathologist, which was higher than concordance of 83% of 1-scale categorization-based method. Our results show that the DSCbased method can empower the deep learning application in digital pathology and facilitate computer-aided diagnosis.

To obtain an anthropomorphic performance in physical human-robot interaction during a reaching task, a variable impedance control (vIC) algorithm with human-like characteristics is proposed in this article. The damping value of the proposed method is varied with the target position as well as through the tracking error. The proposed control algorithm is compared with the impedance control algorithm with constant parameters (IC) and another vIC algorithm, which is only changed with the tracking error (vIC-e). The different control algorithms are validated through the simulation study, and are experimentally implemented on a cable-driven rehabilitation robot. The results show that the proposed vIC can improve the tracking accuracy and trajectory smoothness, and reduce the interaction force at the same time.

No abstract