Search

As more and more patients choose online consultation, the information in the Question and Answering(Q&A) community is widely studied. Through automatic extraction of medical inquiry information entities, and establishing a neural network model, the input of basic patient information and disease information can be extracted. In order to provide an effective method for exploring medical named entity recognition in the medical community. Entity annotation is performed for the medical community Q&A pairs, and a BiLSTM-CRF network model is established for training to realize the identification of medical entities which are crawled from Q&A community. This paper introduces the principles and process of BiLSTM-CRF model, illustrates our experiment, including the data sources, experiment environment, evaluation index. This paper chooses four models of HMM, CRF, BiLSTM and BiLSTM-CRF for experiments. Finally, the experimental results are compared which verifies the effectiveness of the BiLSTM-CRF model. Realizing the recognition and extraction of diabetes-related entities in the medical field.

Recently, automatic visual data understanding from drone platforms becomes highly demanding. To facilitate the study, the Vision Meets Drone Object Detection in Image Challenge is held the second time in conjunction with the 17-th International Conference on Computer Vision (ICCV 2019), focuses on image object detection on drones. Results of 33 object detection algorithms are presented. For each participating detector, a short description is provided in the appendix. Our goal is to advance the state-of-the-art detection algorithms and provide a comprehensive evaluation platform for them. The evaluation protocol of the VisDrone-DET2019 Challenge and the comparison results of all the submitted detectors on the released dataset are publicly available at the website: http: //www.aiskyeye.com/. The results demonstrate that there still remains a large room for improvement for object detection algorithms on drones.

Video-based person re-identification (ReID) is an important task, which has received much attention in recent years due to its efficiency in the field of surveillance. Researchers have employed many effective approaches for video-based person ReID, but there are still two problems. Firstly, the same pedestrian in the video sequences differs in size. Secondly, traditional RNNs can only process one-dimension features, which are not suitable for dealing with video sequences. To solve above problems, we propose a new network called Multi-scale Spatial-Temporal Network (MSTN), which combines multi-scale feature extractor and CLSTM together to tackle the discrepant sizes of pedestrians and extract more representative temporal information for the video sequences. We conduct the experiments on the iLIDS-VID, PRID-2011 and MARS datasets, and our approach outperforms state-of-the-art methods by a large margin.

Taking chromium (Cr) in surface waters in Jiaozhou Bay in June 1982 as an example, this paper analyzed the horizontal loss processes of Cr, as well as the influence of tide on the horizontal loss. Results showed that the horizontal loss of Cr in coastal waters in the east of Jiaozhou Bay were calculated as 65.53×10-5 ?g L-1 m-1 and 6.50×10-5 m-1, or 65.53 YDFa and 6.50 YDFr, respectively. The horizontal loss of Cr in coastal waters in the north of Jiaozhou Bay were calculated as 55.03×10-5 µg L-1 m-1 and 5.63×10-5 m-1, or 55.03 YDFa and 5.63 YDFr, respectively. When the tide was out, the direction was from the northeast of the bay to the bay mouth and was parallel to the loss direction of Cr, and the dilution of Cr contents was enhancing, resulting in rapid settlement of Cr from surface waters to bottom waters. When the tide is out, the direction was from the northeast of the bay to the bay mouth and was perpendicular to the loss direction of Cr, and the dilution of Cr contents was limited, resulting in little settlement of Cr from surface waters to bottom waters.

This paper analyzed the settling process of Cd and the origin in Jiaozhou Bay based on investigation data during 1979 — 1983. Results showed that the distributions of Cd contents in bottom waters were determined by the spatialtemporal variations of the Cd source inputs, and the transports of Cd from land/atmosphere to ocean. The seasonal-spatial variations of the settling of Cd resulted in the variations of high Cd content regions in bottom waters. During 1979-1983, the source strengths of were increasing, and were extending the high Cd content regions and increasing the Cd contents in bottom waters.

We consider the problem of grasping concave objects, i.e., objects whose surface includes regions with negative curvature. When a multifingered hand is used to restrain these objects, these areas can be advantageously used to determine grasps capable of more robustly resisting to external disturbance wrenches. We propose a new grasp quality metric specifically suited for this case, and we use it to inform a grasp planner searching the space of possible grasps. Our findings are validated both in simulation and on a real robot system executing a bin picking task. Experimental validation shows that our method is more effective than those not explicitly considering negative curvature.