Publication Date
Fall 2024
Degree Type
Master's Project
Degree Name
Master of Science in Computer Science (MSCS)
Department
Computer Science
First Advisor
Saptarshi Sengupta
Second Advisor
Navrati Saxena
Third Advisor
Fabio Di Troia
Keywords
Frequency domain, time series forecasting, fourier transform, deep learning, comparative analysis, resource utilization
Abstract
Time series forecasting influences our lives on a daily basis, being a versatile tool in various application areas like environmental studies, finance, medicine and much more. While there are many established statistical and deep learning approaches to model time series data, each implementation comes with their own set of drawbacks or areas of improvements. Most of the existing deep learning architectures and research have focused on modeling time series data in the time-domain exclusively. However training deep learning models in the time-domain has some drawbacks, mainly due to the inherent temporal dependence of each time-step on the time-steps before it, which causes the model training process to be more sequential and hence can potentially limit efficiency. The idea of converting the time-domain data representation into the less sequential frequency-domain data is being explored in recent years. Using the frequency domain to represent time series data has multiple benefits including a temporally independent data representation and more options for effective data preprocessing like noise removal, dimensionality reduction, etc. This study explores the existing literature, implementation and performance of Frequency-informed neural networks and how they fare in comparison to existing established deep learning models like LSTMs.
Recommended Citation
Suresh, Avinash Mangalore, "COMPARITIVE ANALYSIS OF TIME SERIES FORECASTING USING FREQUENCY INFORMED DENSE NEURAL NETWORKS AND LSTM" (2024). Master's Projects. 1427.
https://scholarworks.sjsu.edu/etd_projects/1427
