Encoder-Decoder based Time Series Anomaly Prediction

The Hong Kong University of Science and Technology
Department of Computer Science and Engineering

Final Year Thesis Oral Defense

Title: "Encoder-Decoder based Time Series Anomaly Prediction"

by

TSUI Hok Wai

Abstract:

My research on anomaly prediction is at the junction of two areas: anomaly 
detection and time-series forecasting. The proposed approach utilizes deep 
learning techniques to enhance anomaly forecasting, enabling proactive and 
timely implementation of preventive or corrective measures. Such novel 
approaches in my project would extend the application of autoencoder structures 
to perform anomaly prediction.


Date            : 26 April 2024 (Friday)

Time            : 15:00 - 15:40

Venue           : Room 5506 (near lifts 25/26), HKUST

Advisor         : Prof. YEUNG Dit-Yan

2nd Reader      : Prof. ZHANG Nevin Lianwen