English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

As stability testing execution logs can be very long, software engineers needhelp in locating anomalous events. We develop and evaluate two models forscoring individual log-events for anomalousness, namely an N-Gram model and aDeep Learning model with LSTM (Long short-term memory). Both are trained onnormal log sequences only. We evaluate the models with long log sequences ofAndroid stability testing in our company case and with short log sequences fromHDFS (Hadoop Distributed File System) public dataset. We evaluate next eventprediction accuracy and computational efficiency. The LSTM model is moreaccurate in stability testing logs (0.848 vs 0.865), whereas in HDFS logs theN-Gram is slightly more accurate (0.904 vs 0.900). The N-Gram model has farsuperior computational efficiency compared to the Deep model (4 to 13 secondsvs 16 minutes to nearly 4 hours), making it the preferred choice for our casecompany. Scoring individual log events for anomalousness seems like a good aidfor root cause analysis of failing test cases, and our case company plans toadd it to its online services. Despite the recent surge in using deep learningin software system anomaly detection, we found limited benefits in doing so.However, future work should consider whether our finding holds with differentLSTM-model hyper-parameters, other datasets, and with other deep-learningapproaches that promise better accuracy and computational efficiency than LSTMbased models.

Pinpointing Anomaly Events in Logs from Stability Testing -- N-Grams vs. Deep-Learning