As medical demands grow and machine learning technology advances, AI-based diagnostic and treatment systems are garnering increasing attention. Medication recommendation aims to integrate patients' long-term health records with medical knowledge, recommending accuracy and safe medication combinations for specific conditions. However, most existing researches treat medication recommendation systems merely as variants of traditional recommendation systems, overlooking the heterogeneity between medications and diseases. To address this challenge, we propose DGMed, a framework for medication recommendation. DGMed utilizes causal inference to uncover the connections among medical entities and presents an innovative feature alignment method to tackle heterogeneity issues. Specifically, this study first applies causal inference to analyze the quantified therapeutic effects of medications on specific diseases from historical records, uncovering potential links between medical entities. Subsequently, we integrate molecular-level knowledge, aligning the embeddings of medications and diseases within the molecular space to effectively tackle their heterogeneity. Ultimately, based on relationships at the entity level, we adaptively adjust the recommendation probabilities of medication and recommend medication combinations according to the patient's current health condition. Experimental results on a real-world dataset show that our method surpasses existing state-of-the-art baselines in four evaluation metrics, demonstrating superior performance in both accuracy and safety aspects. Compared to the sub-optimal model, our approach improved accuracy by 4.40%, reduced the risk of side effects by 6.14%, and increased time efficiency by 47.15%.
In response to the problems of mismatched human-robot motion and poor human-robot coupling (HRC) performance in ankle rehabilitation robots, this study proposes a cable-driven flexible ankle rehabilitation robot (FARR) based on biomimetic design and analyzes its HRC performance. Firstly, based on the motion characteristics and physiological structure of the ankle joint, an equivalent model of the ankle joint is proposed to solve the workspace of the ankle joint. Secondly, a design configuration of a cable-driven FARR with a flexible equivalent axis is proposed, and the structure of the FARR is designed. The robot's kinematics and dynamics are analyzed to solve the robot's workspace. By comparing the workspace of the ankle joint with the robot's workspace, the completeness of the robot's motion function is verified. Furthermore, the HRC dynamic theory model and the HRC dynamic simulation model are established to solve the HRC joint torque during the HRC system motion. The results show that the HRC joint torque is small in magnitude and stable in variation, indicating that the burden on the joint during robot motion is minimal. Finally, a prototype of the FARR is built, and motion function experiments of the HRC system are conducted to verify the matching between actual human motion and FARR motion under the HRC system.
In order to improve the dynamic tracking ability of adjusting system for the subreflector of 65 meters radio telescope, and lay the foundation for the calibration works, PID parameters were adjusted through parabolic speed response and ramp position response based on electrical control system.Circle tracking test were carried out using laser tracker, the result demonstrate that the dynamic tracking ability of subreflector control system is improved and calibration can carry out.
Dynamic modeling serves as the fundamental basis for dynamic performance analysis and is an essential aspect of the control scheme design of parallel manipulators. This report presents a concise and efficient solution to the dynamics of Stewart parallel manipulators based on the screw theory. The initial pose of these manipulators is described. Then the pose matrix of each link of the Stewart parallel mechanism is obtained using an inverse kinematics solution and an exponential product formula. Considering the constraint relationship between joints, the constraint matrix of the Stewart parallel manipulator is deduced. In addition, the Jacobian matrix and the twist of each link are obtained. Moreover, by deriving the differential form of the constraint matrix, the spatial acceleration of each link is obtained. Based on the force balance relationship of each link, the inverse dynamics and the general form of the dynamic model of the Stewart parallel manipulator is established and the process of inverse dynamics is summarized. The dynamic model is then verified via dynamic simulation using the ADAMS software. A numerical example is considered to demonstrate the feasibility and effectiveness of this model. The proposed dynamic modeling approach serves as a fundamental basis for structural optimization and control scheme design of the Stewart parallel manipulators.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)