Multivariate Time Series Anomaly Detection Based on Spatial-Temporal Network and Transformer in Industrial Internet of Things

In the Industrial Internet of Things(IIoT),sensors generate time series data to reflect the working state.When the systems are attacked,timely identification of outliers in time series is critical to ensure security.Although many anomaly detection methods have been proposed,the temporal correlation of the time series over the same sensor and the state(spatial)correlation between different sensors are rarely considered simultaneously in these methods.Owing to the superior capability of Transformer in learning time series features.This paper proposes a time series anomaly detection method based on a spatial-temporal network and an improved Transformer.Additionally,the methods based on graph neural networks typically include a graph structure learning module and an anomaly detection module,which are interdependent.However,in the initial phase of training,since neither of the modules has reached an optimal state,their performance may influence each other.This scenario makes the end-to-end training approach hard to effectively direct the learning trajectory of each module.This interdependence between the modules,coupled with the initial instability,may cause the model to find it hard to find the optimal solution during the training process,resulting in unsatisfactory results.We introduce an adaptive graph structure learning method to obtain the optimal model parameters and graph structure.Experiments on two publicly available datasets demonstrate that the proposed method attains higher anomaly detection results than other methods.

Surgical timing and long-term outcomes in patients with severe haemorrhagic spinal cord cavernous malformations

Background Surgical resection of the lesions remains the main treatment method for most symptomatic spinal cord cavernous malformations(SCCMs)to eliminate the occupation and associated subsequent lifelong haemorrhagic risk.However,the timing of surgical intervention remains controversial,especially for patients in the acute stage after severe haemorrhage.Methods Patients diagnosed with SCCMs who were surgically treated between January 2002 and December 2021 were selected and retrospectively reviewed.The Modified McCormick Scale(MMS)was used to evaluate neurological and disability status.All medical information was reviewed,and all patients were followed up for at least 6 months.Results A total of 279 patients were ultimately included.With regard to long-term outcomes,110(39.4%)patients improved,159(57.0%)remained unchanged and 10(3.6%)worsened.For patients with an MMS score of 2–5 on admission,in univariate and multivariate analyses,a≤6 weeks period between onset and surgery(adjusted OR 3.211,95%CI 1.504 to 6.856,p=0.003)was a significant predictor of improved MMS.Among 69 patients who first presented with severe haemorrhage,undergoing surgery within 6 weeks of the onset of severe haemorrhage(adjusted OR 4.901,95%CI 1.126 to 21.325,p=0.034)was significantly associated with improvement of MMS score.Conclusion Surgical timing can influence the long-term outcome of SCCMs.For patients with symptomatic SCCMs,especially those with severe haemorrhage,early surgical intervention within 6 weeks can provide more benefit.

Novel PIO Algorithm with Multiple Selection Strategies for Many-Objective Optimization Problems

With the increase of problem dimensions,most solutions of existing many-objective optimization algorithms are non-dominant.Therefore,the selection of individuals and the retention of elite individuals are important.Existing algorithms cannot provide sufficient solution precision and guarantee the diversity and convergence of solution sets when solving practical many-objective industrial problems.Thus,this work proposes an improved many-objective pigeon-inspired optimization(ImMAPIO)algorithm with multiple selection strategies to solve many-objective optimization problems.Multiple selection strategies integrating hypervolume,knee point,and vector angles are utilized to increase selection pressure to the true Pareto Front.Thus,the accuracy,convergence,and diversity of solutions are improved.ImMAPIO is applied to the DTLZ and WFG test functions with four to fifteen objectives and compared against NSGA-III,GrEA,MOEA/D,RVEA,and many-objective Pigeon-inspired optimization algorithm.Experimental results indicate the superiority of ImMAPIO on these test functions.