Title page for etd-0612118-160809


[Back to Results | New Search]

URN etd-0612118-160809
Author Wei-Hao Kau
Author's Email Address acps90137@gmail.com
Statistics This thesis had been viewed 5358 times. Download 0 times.
Department Applied Mathematics
Year 2017
Semester 2
Degree Master
Type of Document
Language English
Title Time series prediction using LSTM Network Models
Date of Defense 2018-07-05
Page Count 55
Keyword
  • prediction
  • LSTM
  • time series model
  • Abstract As recent computing hardware technology has undergone rapid and significant advances, complex methods that require a lot of computing power have been realized, which has led to the development of more machine learning methods and neural network models. This paper discusses the Long short-term memory (LSTM) network model of recurrent neural networks. The first part of this paper introduces the basic concept of LSTM and its training method. The second part discusses short- and long-term prediction, and compares their differences with the conventional time series model. The third part compares the prediction performance of the conventional time series model and LSTM by analysing simulated data. In the empirical study, a Long short-term memory network model is fitted for bicycle rental data in Kaohsiung, and predictive analysis is performed.
    Advisory Committee
  • Mong-Na Lo Huang - chair
  • Chung Chang - co-chair
  • Liang-Ching Lin - co-chair
  • Huang, Shih-Feng - co-chair
  • Mei-Hui Guo - advisor
  • Files
  • etd-0612118-160809.pdf
  • Indicate in-campus at 5 year and off-campus access at 5 year.
    Date of Submission 2018-07-19

    [Back to Results | New Search]


    Browse | Search All Available ETDs

    If you have more questions or technical problems, please contact eThesys