Anomaly detection is a very important step in building a secure and trustworthy system. Manually it is daunting to analyze and detect failures and anomalies. In this paper, we proposed an approach that leverages the pattern matching capabilities of Convolution Neural Network (CNN) for anomaly detection in system logs. Features from log files are extracted using a windowing technique. Based on this feature, a one-dimensional image (1×n dimension) is generated where the pixel values of an image correlate with the features of the logs. On these images, the 1D Convolution operation is applied followed by max pooling. Followed by Convolution layers, a multi-layer feed-forward neural network is used as a classifier that learns to classify the logs as normal or abnormal from the representation created by the convolution layers. The model learns the variation in log pattern for normal and abnormal behavior. The proposed approach achieved improved accuracy compared to existing approaches for anomaly detection in Hadoop Distributed File System (HDFS) logs.

Most works on SRGMs in a unified multi release approach has been done using calendar time. Not much heed is given to consumption pattern of various testing resources. Due to stiff market rivalry, developers need to develop latest versions of software in multiple releases. Apart from being beneficial, it also turns to be challengeable as revision in the code creates hindrances in updating the software. Testers may find it difficult to rectify a detected fault resulting in imperfect debugging or error generation. Testing phase is affected by many factors which may change at any time, a concept called as change point. In this work, we propose detection and correction-based general scheme for modelling multi-release of software under the realistic environment of imperfect debugging, error generation, change point and testing effort. Parameter estimation has been done on Tandem data and SRGMs have been ranked using distance-based approach.