Collaborative thesis opportunity

In this thesis, supervised by Hao Dong, we seek to develop a tool for Multimodal Fusion for Time-Series Representation Learning. 
*Hao is ia dcotral student with the SMM group at ETH Zurich, co-supervised by Prof. E. Chatzi (ETHZ) and Prof. Olga Fink (EPFL), and working under support of the ETH Mobility project SENTINEL.

Time-series data is increasingly prevalent across various domains, including finance, healthcare, and environmental monitoring. The ability to extract meaningful information from time-series data is crucial for prediction, classification, and anomaly detection. This project focuses on exploring different time-series representations and their impact on machine learning tasks.

Objectives

Benchmarking Time-Series Representations: Investigate the performance of various time-series representations including Fast Fourier Transform (FFT), Recurrence Plot (RP), Gramian Angular Field (GAF), and Markov Transition Field (MTF) in the context of machine learning tasks.

Design of Fusion Method: Develop a novel method to fuse information from these representations, aiming to leverage their combined strengths.

Evaluation on Diverse Datasets: Assess the effectiveness of the proposed method on a variety of datasets pertaining to Time-Series Classification, Forecasting, and Anomaly Detection.

Methodology

Literature Review: Conduct a comprehensive review of existing literature on time-series representation methods and their applications.

Implementation of Representations: Implement and fine-tune FFT, RP, GAF, and MTF, ensuring a fair and consistent basis for comparison.

Benchmarking: Evaluate each representation method across multiple datasets, using standard metrics relevant to classification, forecasting, and anomaly detection.

Fusion Method Development: Design a fusion algorithm to integrate the different representations, potentially using techniques like feature concatenation, ensemble methods, or deep learning architectures.

Experimental Evaluation: Test the fusion method across the same datasets used for benchmarking, comparing its performance against the individual representation methods.

References

[1]Garcia GR, Michau G, Ducoffe M, Gupta JS, Fink O. Temporal signals to images: Monitoring the condition of industrial assets with deep learning image processing algorithms. Proceedings of the Institution of Mechanical Engineers, Part O: Journal of Risk and Reliability. 2022;236(4):617-627. doi:10.1177/1748006X21994446

[2]Yang, L. and Hong, S., 2022, June. Unsupervised time-series representation learning with iterative bilinear temporal-spectral fusion. In International Conference on Machine Learning (pp. 25038-25054). PMLR.

Goal
A detailed comparative analysis of FFT, RP, GAF, and MTF in the context of time-series machine learning tasks.

A robust fusion method capable of integrating the strengths of individual time-series representations.

Empirical evidence demonstrating the effectiveness of the fusion method in improving the performance of time-series classification, forecasting, and anomaly detection tasks.


Contact Details

Apply on the Sirop platform:

external page https://sirop.org/app/e3dfc2dd-8c81-4009-a77f-6901d887f3a6?_k=re7bU9jP7LHjSvO-