DCFF-MTAD: A Multivariate Time-Series Anomaly Detection Model Based on Dual-Channel Feature Fusion.

The detection of anomalies in multivariate time-series data is becoming increasingly important in the automated and continuous monitoring of complex systems and devices due to the rapid increase in data volume and dimension. To address this challenge, we present a multivariate time-series anomaly detection model based on a dual-channel feature extraction module. The module focuses on the spatial and time features of the multivariate data using spatial short-time Fourier transform (STFT) and a graph attention network, respectively. The two features are then fused to significantly improve the model's anomaly detection performance. In addition, the model incorporates the Huber loss function to enhance its robustness. A comparative study of the proposed model with existing state-of-the-art ones was presented to prove the effectiveness of the proposed model on three public datasets. Furthermore, by using in shield tunneling applications, we verify the effectiveness and practicality of the model.

Unraveling the regulatory network of miRNA expression in Potato Y virus-infected of Nicotiana benthamiana using integrated small RNA and transcriptome sequencing.

Potato virus Y (PVY) disease is a global problem that causes significant damage to crop quality and yield. As traditional chemical control methods are ineffective against PVY, it is crucial to explore new control strategies. MicroRNAs (miRNAs) play a crucial role in plant and animal defense responses to biotic and abiotic stresses. These endogenous miRNAs act as a link between antiviral gene pathways and host immunity. Several miRNAs target plant immune genes and are involved in the virus infection process. In this study, we conducted small RNA sequencing and transcriptome sequencing on healthy and PVY-infected N. benthamiana tissues (roots, stems, and leaves). Through bioinformatics analysis, we predicted potential targets of differentially expressed miRNAs using the N. benthamiana reference genome and the PVY genome. We then compared the identified differentially expressed mRNAs with the predicted target genes to uncover the complex relationships between miRNAs and their targets. This study successfully constructed a miRNA-mRNA network through the joint analysis of Small RNA sequencing and transcriptome sequencing, which unveiled potential miRNA targets and identified potential binding sites of miRNAs on the PVY genome. This miRNA-mRNA regulatory network suggests the involvement of miRNAs in the virus infection process.