Advancing Anomaly Detection in Time Series Data: A Knowledge Distillation Approach with LSTM Model

Arsan, TanerKilinc,S.Camlidere,B.Yildiz,E.Guler,A.K.Alsan,H.F.Arsan,T.2024-06-232024-06-2320230979-835030659-0https://doi.org/10.1109/ASYU58738.2023.10296674https://hdl.handle.net/20.500.12469/5856This paper focuses on enhancing anomaly detection in time series data using deep learning techniques. Particularly, it investigates the integration of knowledge distillation with LSTM-based models for improved precision, efficiency, and interpretability. The study outlines objectives such as dataset preprocessing, developing a novel LSTM-knowledge distillation framework, incorporating Grafana, InfluxDB, Flask API with Docker, performance assessment, and practical implications. Results highlight the efficacy of knowledge distillation in enhancing student model performance. The proposed approach enhances anomaly detection, offering a viable solution for real-world applications. © 2023 IEEE.eninfo:eu-repo/semantics/closedAccessAnomaly DetectionDeep LearningKnowledge DistillationLSTMNetwork TrafficTime SeriesAdvancing Anomaly Detection in Time Series Data: A Knowledge Distillation Approach with LSTM ModelConference Object10.1109/ASYU58738.2023.102966742-s2.0-85178280287N/AN/A