The topic of my doctoral research is Lightweight Approaches to Software Log Anomaly Detection. I have finished writing the dissertation and my doctoral defense is October 23rd in University of Helsinki. I started to work on this topic in 2022 in the University of Oulu and moved to University of Helsinki in 2023.
The main topics of my thesis along with the included publications are summarized in the table below.
| Topic | Paper | Title |
|---|---|---|
| Optimizing event prediction How to best configure next-event prediction methods for detecting anomalies in logs |
I | How to Configure Masked Event Anomaly Detection on Software Logs? |
| II | Event-level Anomaly Detection on Software Logs: Role of Algorithm, Threshold, and Window Size | |
| Lightweight vs. deep learning methods How unsupervised, parserless methods perform against deep learning in terms of speed and accuracy |
III | Speed and Performance of Parserless and Unsupervised Anomaly Detection Methods on Software Logs |
| IV | Fast Unsupervised Anomaly Detection Methods on Software Logs: An Empirical Study | |
| Microservice datasets The challenges microservice systems pose for log anomaly detection, and new datasets to study them |
V | LO2: Microservice API Anomaly Dataset of Logs and Metrics |
| VI | An Improved Microservice Dataset of Logs and Metrics (LO2v2) | |
| Tools and reproducibility Building tools for the research community, and assessing how usable existing academic tools are in practice |
VII | LogLead: Fast and Integrated Log Loader, Enhancer, and Anomaly Detector |
| VIII | VisualLogAnalyzer: An Interactive Web Application for Multi-Level Log Analysis | |
| IX | Towards LLM Accelerated Rapid Reviews for Software Tool Discovery: Case for Log Analysis |
Original publications
- J. Nyyssölä, M. Mäntylä, and M. Varela, “How to configure masked event anomaly detection on software logs?” in 2022 IEEE International Conference on Software Maintenance and Evolution (ICSME), 2022, pp. 414–418. https://doi.org/10.1109/ICSME55016.2022.00050.
- J. Nyyssölä and M. Mäntylä, “Event-level Anomaly Detection on Software Logs: Role of Algorithm, Threshold, and Window Size,” in 2024 IEEE 24th International Conference on Software Quality, Reliability and Security (QRS), 2024, pp. 649–656. https://doi.org/10.1109/QRS62785.2024.00070.
- J. Nyyssölä and M. Mäntylä, “Speed and Performance of Parserless and Unsupervised Anomaly Detection Methods on Software Logs,” in 2024 IEEE 24th International Conference on Software Quality, Reliability and Security (QRS), 2024, pp. 657–666. https://doi.org/10.1109/QRS62785.2024.00071.
- J. Nyyssölä, Y. Wang, and M. Mäntylä, “Fast Unsupervised Anomaly Detection Methods on Software Logs – An Empirical Study,” submitted for publication.
- A. Bakhtin, J. Nyyssölä, Y. Wang, N. Ahmad, K. Ping, M. Esposito, M. Mäntylä, and D. Taibi, “LO2: Microservice API Anomaly Dataset of Logs and Metrics,” in Proceedings of the 21st International Conference on Predictive Models and Data Analytics in Software Engineering, 2025, pp. 1–10. https://dl.acm.org/doi/10.1145/3727582.3728682.
- A. Bakhtin, J. Nyyssölä, M. Esposito, M. Mäntylä, and D. Taibi, “Descriptor: An Improved Microservice Dataset of Logs and Metrics (LO2v2),” IEEE Data Descriptions, vol. 3, pp. 507–518, 2026. https://doi.org/10.1109/IEEEDATA.2026.3701668.
- M. Mäntylä, Y. Wang, and J. Nyyssölä, “LogLead – Fast and Integrated Log Loader, Enhancer, and Anomaly Detector,” in 2024 IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER), 2024, pp. 395–399. https://doi.org/10.1109/SANER60148.2024.00046.
- J. Nyyssölä, S. Sipilä, and M. Mäntylä, “VisualLogAnalyzer: An Interactive Web Application for Multi-Level Log Analysis,” in Proceedings of the IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER), 2026. (To appear)
- J. Nyyssölä, H. Bin Mazhar, A. Bakhtin, M. Esposito, N. Reinikainen, Y. Wang, Y. Song, D. Taibi, and M. Mäntylä, “Towards LLM Accelerated Rapid Reviews for Software Tool Discovery – Case for Log Analysis,” in Euromicro Conference on Software Engineering and Advanced Applications, 2026. (To appear)