Search

Large-scale medical equipment, extensively implemented in medical services, is of vital importance for diagnosis but vulnerable to various failures. Most of hospitals conduct regular maintenance for their medical equipment and have been suffering from medical-equipment-related incidents for years. Currently, the Internet of Medical Things (IoMT) has emerged as a crucial technology to monitor the real-time status of medical equipment. In this paper, we develop a IoMT system of Computed Tomography (CT) equipment in the West China Hospital of Sichuan University and meanwhile, select machine-learning algorithms to effectively store, preprocess and analyze the data. Specifically, a data-driven framework is proposed to predict the anomalies of CT equipment successfully. In this framework, the first step is data preprocessing, where we average the original non-uniform data and use linear interpolation to handle missing data. The second step is feature construction, where sliding time window is applied to fully reflect historical information. The third step is features selection, where the seven features that perform best are selected. Finally, we use two methods to split the training and test set, and apply random oversampling to deal with those imbalanced data before putting them into models. The results show that the prediction precision and recall of our method are 70% and 81%, respectively. The proposed method could distinguish the state of CT equipment and be used as a reference for practical maintenance by early prediction, where unexpected anomalies of medical equipment could be reduced. It also brings new insights about how to handle non-uniform and unbalanced time series data in the practical cases.

Peptidyl arginine deiminase (PAD) which mediates citrullination catalyzes the conversion of arginine residues of protein peptide chains to citrulline residues. Citrullination can be involved in the process of apoptosis, embryo development, regulation of myelin sheath function and other physiological processes. Besides, it can regulate the process of cell death, affect the formation of neutrophil extracellular traps (NETs) and produce anti-citrullinated protein antibody (ACPA) to participate in autoimmune diseases. In this manuscript, the regulatory effects of citrullination in normal physiology and autoimmune diseases are reviewed, and the effects of citrullination on immune cells in autoimmune diseases are discussed in detail.

The manufacturing industry has gradually developed from mass production to personalized customization, which requires a highly flexible robotic automated production line in manufacturing to deal with rapid retrofits of products. Industrial robots need to be taught the steps of completing tasks when dealing with new tasks. At present, the traditional robot teaching reproduction has many disadvantages, such as the complicated teaching system, the high cost, the waste of time, and the special training that operators need. In view of the above situation, a kind of teaching-playback based on machine vision and human hand demonstration was proposed in this paper. The position and orientation of the human fingertip during the execution of the mission were obtained by the Kinect sensor, and the pose information was transformed into the robot base coordinate system by coordinate transformation. The coordinate information was then transmit to the robot to enable the robot to quickly grab and place the target object. The feasibility and effectiveness of the teaching-playback system were proved by the experiment of picking and placing cylindrical workpiece.

In this paper, we propose a vision-based method to estimate the pose (position and orientation) of the palm. Two sub-problems were solved in this study. One is to obtain the correspondence of the four coplanar mark points on the target object. The other is to estimate the position and orientation of the palm in the camera coordinate system. The position and orientation of the palm in the camera coordinate system can be derived by the geometric relation, which can be transformed the pose estimation problem into a Perspective-n-Point (PnP) problem. Dog-Leg (DL) algorithm is adopted to solve the PnP problem to get a higher processing speed. An experiment is conducted to verify the effectiveness of the proposed methods. The experimental results demonstrate that proposed method can obtain the position and orientation accurately and the DL algorithm can be used to solve the P4P problem faster than an existing algorithm.

A general and comprehensive dynamics modeling of serial robot with clearance in joint is presented throughout this work. The key point in this paper is to treat the joint clearance as a massless link, which directly relate to the dynamics modeling of the mechanism. Using the massless link method, combined with the Lagrange method and the D’Alembert’s principle, a computational methodology for purpose of solving the clearance angle, is presented. With the clearance size calculated, the terminal position of robot manipulator can be derived, which provides a reference for subsequent robot control.