TY - GEN
T1 - Literature Review on Log Anomaly Detection Approaches Utilizing Online Parsing Methodology∗
AU - Lupton, Scott
AU - Washizaki, Hironori
AU - Yoshioka, Nobukazu
AU - Fukazawa, Yoshiaki
N1 - Publisher Copyright:
© 2021 IEEE.
PY - 2021
Y1 - 2021
N2 - The use of anomaly detection for log monitoring requires parsing model input features from raw, unstructured data. Log parsing methods come in many forms, but are generally categorized as being either offline or online. In this study, a systematic literature review of anomaly detection approaches utilizing online parsing methods is performed. An inventory of these approaches is taken, research gaps are explored, and suggestions for future exploration and study are presented.
AB - The use of anomaly detection for log monitoring requires parsing model input features from raw, unstructured data. Log parsing methods come in many forms, but are generally categorized as being either offline or online. In this study, a systematic literature review of anomaly detection approaches utilizing online parsing methods is performed. An inventory of these approaches is taken, research gaps are explored, and suggestions for future exploration and study are presented.
KW - Log parsing
KW - anomaly detection
KW - log template extraction
KW - online algorithms
UR - http://www.scopus.com/inward/record.url?scp=85126216831&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85126216831&partnerID=8YFLogxK
U2 - 10.1109/APSEC53868.2021.00068
DO - 10.1109/APSEC53868.2021.00068
M3 - Conference contribution
AN - SCOPUS:85126216831
T3 - Proceedings - Asia-Pacific Software Engineering Conference, APSEC
SP - 559
EP - 563
BT - Proceedings - 2021 28th Asia-Pacific Software Engineering Conference, APSEC 2021
PB - IEEE Computer Society
T2 - 28th Asia-Pacific Software Engineering Conference, APSEC 2021
Y2 - 6 December 2021 through 9 December 2021
ER -