Search

Cross-modal pedestrian re-identification is a key technology to realize all-weather intelligent video surveillance system. This technology is designed to match the visible light image and infrared image of a pedestrian with a specific identity in a non-overlapping camera scene, so it faces huge intra-class changes and modal differences. Existing methods are difficult to solve these two difficulties, which is largely due to the lack of effective mining of feature discrimination and the full use of multi-source heterogeneous information. In view of the above shortcomings, a refined multi-source feature collaborative network is designed by the collaborative learning method, and multiple complementary features are extracted for information fusion, the learning ability of the network is improved. Multi-scale and multi-level features are extracted from the backbone convolutional network, and the refined feature collaborative learning is realized; the discriminative ability of features is enhanced to deal with intra-class changes. A modal sharing and unique feature collaboration module and a cross-modal human semantic self-supervision module are designed to achieve the purpose of multi-source feature collaborative learning, so as to improve the utilization of multi-source heterogeneous image information, and then modal differences are resolved. The validity and advancement of this method are verified on the SYSU-MM01 and RegDB data sets. [ABSTRACT FROM AUTHOR]

Concomitant drugs therapy is effective and inevitable for most patients. However, drug–drug adverse reactions (DDADRs) caused by combination drugs may bring about medical malpractices. Therefore, the accurate prediction of DDADRs is beneficial to human health and pharmaceutical researches. Currently, existing machine learning-based methods focus on a single feature. In this paper, we propose a novel method, MS-ADR, to extract multi-source features and predict DDADRs. First, we obtain four biomedical views by using four drug signed networks, respectively, namely enzyme view, indication view, side effect view, and transporter view. Then, different biomedical views are fed into graph convolutional neural networks (GCN) to extract multi-source features. Second, we propose an attention block to merge multi-source features from different biomedical views. Finally, a reconstructed drug–drug adverse reaction network is embedded to predict DDADR. The experiment shows that MS-ADR achieves better performance compared with other start-of-the-art baselines. [ABSTRACT FROM AUTHOR]

The auto-transformer rectifier unit (ATRU) is one of the most widely used avionic secondary power supplies. Timely fault identification and location of the ATRU is significant in terms of system reliability. A two-level fault diagnosis method for the ATRU using multi-source features (MSF) is proposed in this paper. Based on the topology of the ATRU, three key electrical signals are selected and analyzed to extract appropriate features for fault diagnosis. Mathematic expressions and simulation results of the feature signals under different fault modes are presented in the paper. Therefore, a unique MSF system is developed and a two-level fault diagnosis method based on radial basis function network groups is proposed. On the first level, the overall fault set is classified into three subsets and then on the second level, three radial basis function neural networks are constructed and trained to realize accurate fault localization. To verify the diagnosis performance of the proposed method, several comparative tests are implemented on a 12-pulse ATRU system, which shows that this method has a lower computational cost, better diagnostic accuracy and increased stability when compared with alternative methods. [ABSTRACT FROM AUTHOR]