Theses and Dissertations

Date of Award

12-2023

Document Type

Thesis

Degree Name

Master of Science (MS)

Department

Computer Science

First Advisor

Yifeng Gao

Second Advisor

Emmett Tomai

Third Advisor

Dong-Chul Kim

Abstract

Deep hashing has been widely used for efficient retrieval and classification of high-dimensional data like images and text. However, its application to time series data is still challenging due to the data’s temporal nature. To tackle this issue, a new deep hashing method has been proposed that generates efficient hash codes and enhances the time series hashing performance using a ResNet model with Orthohash (Cosine Similarity Loss). The proposed method uses one loss architecture while using ResNet model for efficient hashing. It uses the Character Trajectories dataset to extract discriminative features from the time series data. These features are then converted into binary codes using a quantization function to produce hash codes that can be easily stored and compared. The study evaluated the performance of the hash codes using t-SNE (t-Distributed Stochastic Neighbor Embedding) technique. The classification performance of the time series data are evaluated using accuracy and F1 score. The experimental results show improved deep hashing performance with significantly better distinct clusters for each class within the dataset. The proposed method outperformed other state-of-the-art methods in terms of accuracy and efficiency.

Comments

Copyright 2023 Mahmudul Hasan Robin. All Rights Reserved.

https://go.openathens.net/redirector/utrgv.edu?url=https://www.proquest.com/pqdtglobal1/dissertations-theses/enhancing-time-series-hashing-performance-via/docview/2928517186/sem-2?accountid=7119

Download

Share

COinS