Search

Log information has become an important information resource in the rapid development of information systems. Through the analysis of logs, abnormal detection, fault diagnosis and performance diagnosis can be performed. The log-based anomaly detection technology was focused on. Firstly, the currently used log-based anomaly detection framework was introduced, and then the key link technologies such as log analysis and log anomaly detection were focused on. Finally, the current technology was summarized and suggestions for future research directions were given.

An ensemble K‐nearest neighbor model based on the double‐layer sampling method was proposed for the condition monitoring of wind turbine (WT) gearboxes. The distance function was improved to affinity distance, which helped overcome the limitation of obtaining local optimums. The feature priority was calculated based on the regularized mutual information, and a double‐layer sampling method combining data and feature sampling was designed. On the basis of the statistical process control technology, the warning threshold was designed and the real‐time residual was analyzed. The condition of the gearbox was monitored by combining the failure rate. Experimental results with real supervisory control and data acquisition (SCADA) data demonstrated that the proposed method improved the estimation accuracy of the model and could realize early fault warnings of a WT gearbox approximately 20 days earlier than the SCADA system. [ABSTRACT FROM AUTHOR]

The innate immune kinase TBK1 (TANK-binding kinase 1) responds to microbial-derived signals to initiate responses against viral and bacterial pathogens. More recent work implicates TBK1 in metabolism and tumorigenesis. The kinase mTOR (mechanistic target of rapamycin) integrates diverse environmental cues to control fundamental cellular processes. Our prior work demonstrated in cells that TBK1 phosphorylates mTOR (on S2159) to increase mTORC1 and mTORC2 catalytic activity and signaling. Here we investigate a role for TBK1-mTOR signaling in control of glucose metabolism in vivo. We find that mice with diet-induced obesity (DIO) but not lean mice bearing a whole-body "TBK1-resistant" Mtor S2159A knock-in allele (MtorA/A) display exacerbated hyperglycemia and systemic insulin resistance with no change in energy balance. Mechanistically, Mtor S2159A knock-in in DIO mice reduces mTORC1 and mTORC2 signaling in response to insulin and innate immune agonists, reduces anti-inflammatory gene expression in adipose tissue, and blunts anti-inflammatory macrophage M2 polarization, phenotypes shared by mice with tissue-specific inactivation of TBK1 or mTOR complexes. Tissues from DIO mice display elevated TBK1 activity and mTOR S2159 phosphorylation relative to lean mice. We propose a model whereby obesity-associated signals increase TBK1 activity and mTOR phosphorylation, which boost mTORC1 and mTORC2 signaling in parallel to the insulin pathway, thereby attenuating insulin resistance to improve glycemic control during diet-induced obesity. [ABSTRACT FROM AUTHOR]