Search

This paper aims to utilize AI technology to solve the challenge of medicine compliance check. More specifically, we propose a Logic-BERT model to estimate whether certain medicine can be used in specific situations of a patient based on electronic medical record. We design a sentence level architecture that distill the text content by segmentation, selection and recombination to solve the length limitation of bidirectional encoder representations from transformers (BERT). We also apply data augmentation integrating logic rules to enhance the performance of our proposed model. Experiments based on real data have verified the effectiveness of our model.

Lane-changing is an important driving behavior and unreasonable lane changes can result in potentially dangerous traffic collisions. Advanced Driver Assistance System (ADAS) can assist drivers to change lanes safely and efficiently. To capture the stochastic time series of lane-changing behavior, this study proposes a temporal convolutional network (TCN) to predict the long-term lane-changing trajectory and behavior. In addition, the convolutional neural network (CNN) and recurrent neural network (RNN) methods are considered as the benchmark models to demonstrate the learning ability of the TCN. The lane-changing dataset was collected by the driving simulator. The prediction performance of TCN is demonstrated from three aspects: different input variables, different input dimensions and different driving scenarios. Prediction results show that the TCN can accurately predict the long-term lane-changing trajectory and driving behavior with shorter computational time compared with two benchmark models. The TCN can provide accurate lane-changing prediction, which is one key information for the development of accurate ADAS.

Based on the patient’s CT scanning data, a highly efficient and controllable porous element and a porous structure modeling method are studied, and the design structure and mechanical parameters are simulated and estimated. The porous titanium alloy implants are produced by laser selective melting, and the surface treatment is made by micro arc oxidation technique to prepare the precision. Less than 0.01 mm, the porous, controllable and active titanium alloy implanted with the thickness of the hydroxyl phosphor layer thickness >10 μm, the results of rational detection, comprehensive analysis and evaluation, forming the corresponding technical standards and technical standards, verifying the feasibility of the application of the technology in the application of titanium alloy materials in the Department of orthopedics, and the implantation of the porous titanium alloy. The application of body in the field of Department of orthopedics implantation provides material foundation and technical support.

Using laser scanning system for preparation of abutment body of data acquisition and accuracy analysis for the reconstruction of 3D laser scanner abutment preparations and by the method of reverse engineering established the 3D digital model of the simulated abutment, using professional software to simulation of abutment shape completes calculation machine aided design base crown. At the same time, the process parameters of laser rapid forming of pure titanium metal powder were tested by orthogonal design, and the process parameters were optimized by single pass multi-layer cladding forming experiment.

This paper researches the influence of laser rapid prototyping process for titanium metal crown. molding quality using the microstructure. The results show that laser rapid prototyping technology can form a uniform, defect-free titanium base crown. And than the thickness of choice is crucial, relatively speaking, other process parameters on material structure is weak.

Perimeter control is an emerging alternative for traffic signal control, which regulates the traffic flows on the periphery of a road network. Some model-based approaches have been suggested earlier for the optimization of perimeter control based on macroscopic fundamental diagrams (MFDs). However, there are several limitations when considering their application to a large-scale urban area because the model-based approaches may not be scalable to multiple regions and inappropriate for handling various effects caused by the shape change of MFDs. Therefore, we propose a model-free and data-driven approach that combines reinforcement learning (RL) with the macroscopic traffic simulation based on the recently developed network transmission model. First, we design four perimeter control models with different macroscopic traffic variables and parametrizations. Then, we validate the proposed models by evaluating their performances with the test demand scenarios at different levels. The validation results show that the model containing travel demand information adapts to a new demand scenario better than the model containing only density-related factors.