Search

Remote sensing image classification (RSIC) is a classical and fundamental task in the intelligent interpretation of remote sensing imagery, which can provide unique labeling information for each acquired remote sensing image. Thanks to the potent global context information extraction ability of the multi-head self-attention (MSA) mechanism, visual transformer (ViT)-based architectures have shown excellent capability in natural scene image classification. However, in order to achieve powerful RSIC performance, it is insufficient to capture global spatial information alone. Specifically, for fine-grained target recognition tasks with high inter-class similarity, discriminative and effective local feature representations are key to correct classification. In addition, due to the lack of inductive biases, the powerful global spatial context representation capability of ViT requires lengthy training procedures and large-scale pre-training data volume. To solve the above problems, a hybrid architecture of convolution neural network (CNN) and ViT is proposed to improve the RSIC ability, called P 2 FEViT, which integrates plug-and-play CNN features with ViT. In this paper, the feature representation capabilities of CNN and ViT applying for RSIC are first analyzed. Second, aiming to integrate the advantages of CNN and ViT, a novel approach embedding CNN features into the ViT architecture is proposed, which can make the model synchronously capture and fuse global context and local multimodal information to further improve the classification capability of ViT. Third, based on the hybrid structure, only a simple cross-entropy loss is employed for model training. The model can also have rapid and comfortable convergence with relatively less training data than the original ViT. Finally, extensive experiments are conducted on the public and challenging remote sensing scene classification dataset of NWPU-RESISC45 (NWPU-R45) and the self-built fine-grained target classification dataset called BIT-AFGR50. The experimental results demonstrate that the proposed P 2 FEViT can effectively improve the feature description capability and obtain outstanding image classification performance, while significantly reducing the high dependence of ViT on large-scale pre-training data volume and accelerating the convergence speed. The code and self-built dataset will be released at our webpages. [ABSTRACT FROM AUTHOR]

An intruder of a company's network may use stolen login credentials to silently collect sensitive data. Such malicious user behavior is difficult to detect as long as it does not trigger access violation or data leak alert. In this paper, we propose to use an ensemble of three unsupervised anomaly detection algorithms, namely OCSVM, RNN and Isolation Forest, to detect abnormal user behavior patterns. Besides, an User Behavior Analytics (UBA) Platform is proposed to collect logs, extract features and conduct experiments. The experiment results indicate that our algorithm outperforms each individual algorithm with recall of 96.55% and precision of 91.24% on average, while both OCSVM and RNN suffer from anomalies in the training set, and i F o r e s t produces more false positives and false negatives in prediction. [ABSTRACT FROM AUTHOR]

The ubiquitous occurrence of microorganisms gives rise to continuous public concerns regarding their pathogenicity and threats to human environment, as well as potential engineering benefits in biotechnology. The development and wide application of environmental biotechnology, for example in bioenergy production, wastewater treatment, bioremediation, and drinking water disinfection, have been bringing us with both environmental and economic benefits. Strikingly, extensive applications of microscopic and molecular techniques since 1990s have allowed engineers to peep into the microbiology in 'black box' of engineered microbial communities in biotechnological processes, providing guidelines for process design and optimization. Recently, revolutionary advances in DNA sequencing technologies and rapidly decreasing costs are altering conventional ways of microbiology and ecology research, as it launches an era of next-generation sequencing (NGS). The principal research burdens are now transforming from traditional labor-intensive wet-lab experiments to dealing with analysis of huge and informative NGS data, which is computationally expensive and bioinformatically challenging. This study discusses state-of-the-art bioinformatics and statistical analyses of 16S ribosomal RNA (rRNA) gene high-throughput sequencing (HTS) data from prevalent NGS platforms to promote its applications in exploring microbial diversity of functional and pathogenic microorganisms, as well as their interactions in biotechnological processes. [ABSTRACT FROM AUTHOR]