Camouflaged Object Detection (COD) aims to identify and segment objects that blend into their surroundings. Since the color and texture of the camouflaged objects are extremely similar to the surrounding environment, it is super challenging for vision models to precisely detect them. Inspired by research on biology and evolution, we introduce depth information as an additional cue to help break camouflage, which can provide spatial information and texture-free separation for foreground and background. To dig clues of camouflaged objects in both RGB and depth modalities, we innovatively propose Depth-aided Camouflaged Object Detection (DaCOD), which involves two key components. We firstly propose the Multi-modal Collaborative Learning (MCL) module, which aims to collaboratively learning deep features from both RGB and depth channels via a hybrid backbone. Then, we propose a novel Cross-modal Asymmetric Fusion (CAF) strategy, which asymmetrically fuse RGB and depth information for complementary depth feature enhancement to produce accurate predictions. We conducted numerous experiments of the proposed DaCOD on three widely-used challenging COD benchmark datasets, in which DaCOD outperforms the current state-of-the-arts by a large margin. All resources are available at https://github.com/qingwei-wang/DaCOD.

The practical Byzantine fault-tolerant consensus algorithm reduces the operational complexity of Byzantine protocols from an exponential level to a polynomial level, which makes it possible to apply Byzantine protocols in distributed systems. However, it still has some problems, such as high communication overhead, low security, poor scalability, and difficulty in tracking. In this article, we propose a Byzantine fault-tolerant consensus algorithm based on dual administrator short group signatures (GPBFT). Firstly, the certification authority chooses the master node and group administrators based on the credit value. The group administrators organize the nodes into a group, and the members generate the signatures by applying the short group signatures scheme, in which any group member can represent the group during the GroupSign phase. Additionally, the GPBFT algorithm adds the Trace phase. According to member and client authentication information, the group administrator can track the true identity of the malicious node, identify the malicious node, and revoke it. The experimental results show that compared with the PBFT algorithm, the GPBFT algorithm can reduce the network communication overhead, reduce the consensus delay, and greatly improve the security and stability of the system. The algorithm can effectively manage member nodes and enable the tracking of identified malicious nodes while maintaining anonymity in terms of node tracking.

Background: Drug repositioning has caught the attention of scholars at home and abroad due to its effective reduction of the development cost and time of new drugs. However, existing drug repositioning methods that are based on computational analysis are limited by sparse data and classic fusion methods; thus, we use autoencoders and adaptive fusion methods to calculate drug repositioning. Results: In this study, a drug repositioning algorithm based on a deep autoencoder and adaptive fusion was proposed to mitigate the problems of decreased precision and low-efficiency multisource data fusion caused by data sparseness. Specifically, a drug is repositioned by fusing drug-disease associations, drug target proteins, drug chemical structures and drug side effects. First, drug feature data integrated by drug target proteins and chemical structures were processed with dimension reduction via a deep autoencoder to characterize feature representations more densely and abstractly. Then, disease similarity was computed using drug-disease association data, while drug similarity was calculated with drug feature and drug-side effect data. Predictions of drug-disease associations were also calculated using a top-k neighbor method that is commonly used in predictive drug repositioning studies. Finally, a predicted matrix for drug-disease associations was acquired after fusing a wide variety of data via adaptive fusion. Based on experimental results, the proposed algorithm achieves a higher precision and recall rate than the DRCFFS, SLAMS and BADR algorithms with the same dataset. Conclusion: The proposed algorithm contributes to investigating the novel uses of drugs, as shown in a case study of Alzheimer's disease. Therefore, the proposed algorithm can provide an auxiliary effect for clinical trials of drug repositioning.

In the field of electric power operation & inspection, a substantial amount of data are usually generated. However, these data are often unstructured and their expression is relatively complex. Nevertheless, these data contain great value. To address the problem of extracting valuable structured information from these unstructured power texts, A model specialized in identifying named entities in Chinese within the domain of electric power operation & inspection is proposed in this paper. It can effectively models the grammatical relationships between sentences and impoves how textual features are represented by adding grammatical information. At the same time, it uses bidirectional gated recurrent control units to capture temporal relationships and the interaction between multiple variables, thereby obtaining more effective local features. The experimental results show that the F1 score of the proposed model in the paper reaches 0.88646, and its performance is better than that of the traditional named entity recognition methods, which proves the effectiveness of the model.