Log Sequence Anomaly Detection Method Based on Contrastive Adversarial Training and Dual Feature Extraction

The log messages generated in the system reflect the state of the system at all times. The realization of autonomous detection of abnormalities in log messages can help operators find abnormalities in time and provide a basis for analyzing the causes of abnormalities. First, this paper proposes a log sequence anomaly detection method based on contrastive adversarial training and dual feature extraction. This method uses BERT (Bidirectional Encoder Representations from Transformers) and VAE (Variational Auto-Encoder) to extract the semantic features and statistical features of the log sequence, respectively, and the dual features are combined to perform anomaly detection on the log sequence, with a novel contrastive adversarial training method also used to train the model. In addition, this paper introduces the method of obtaining statistical features of log sequence and the method of combining semantic features with statistical features. Furthermore, the specific process of contrastive adversarial training is described. Finally, an experimental comparison is carried out, and the experimental results show that the method in this paper is better than the contrasted log sequence anomaly detection method.

Design of System Level Architecture of Multi-Core with Array Mapping Based on Floating Processing Factor-Fast Fourier Transform for Health Informatics Application

In FFT algorithms memory access patterns prevent multiple architectures from achieving high machine use, particularly when parallel processing is needed to achieve the desired efficiency rates. Beginning with the extremely powerful FFT heart, the on-chip memory hierarchy for the multicored FFT processor, is co-designed and linked on-chip. We have shown that the Floating Processing Factor (FPPE) proposed achieves greater operating rate and lower power for the application of health informatics. This test mechanism aids in omission of faulty cores and autonomous detection also makes elegant multi-core architecture degradation feasible. Experimental results illustrate that the anticipated design is scalable widely in terms of performance overhead and hardware overhead which makes it appropriate to many-cores with more than a thousand processing cores through Low Power and High Speed.

A Review of Vision-Based On-Board Obstacle Detection and Distance Estimation in Railways

This paper provides a review of the literature on vision-based on-board obstacle detection and distance estimation in railways. Environment perception is crucial for autonomous detection of obstacles in a vehicle’s surroundings. The use of on-board sensors for road vehicles for this purpose is well established, and advances in Artificial Intelligence and sensing technologies have motivated significant research and development in obstacle detection in the automotive field. However, research and development on obstacle detection in railways has been less extensive. To the best of our knowledge, this is the first comprehensive review of on-board obstacle detection methods for railway applications. This paper reviews currently used sensors, with particular focus on vision sensors due to their dominant use in the field. It then discusses and categorizes the methods based on vision sensors into methods based on traditional Computer Vision and methods based on Artificial Intelligence.