Abstract

Factor impact analysis is one of the preprocessing procedures required to improve forecasting. Several methods' performance depends on the input data quality. Earlier studies are missing from the factor ranking and selection procedures. This study aims to look at the impact of temporal-based spatial factors on forecasting performance while considering the entire factor set. We propose a multilevel analysis that uses an RReliefF technique to rank factor subsets and a deep learning method to evaluate how the ranking factors affect the forecasting performance. Experiments are run on seven situations and eighteen datasets on three terrains. This study found that involving time lag and the number of cases in areas directly adjacent to it proved to have a substantial effect on forecasting results. The proposed approach has the lowest RMSE average compared to the prior strategy.

Original languageEnglish
Title of host publicationIST 2022 - IEEE International Conference on Imaging Systems and Techniques, Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781665481021
DOIs
Publication statusPublished - 2022
Event2022 IEEE International Conference on Imaging Systems and Techniques, IST 2022 - Virtual, Online, Taiwan, Province of China
Duration: 21 Jun 202223 Jun 2022

Publication series

NameIST 2022 - IEEE International Conference on Imaging Systems and Techniques, Proceedings

Conference

Conference2022 IEEE International Conference on Imaging Systems and Techniques, IST 2022
Country/TerritoryTaiwan, Province of China
CityVirtual, Online
Period21/06/2223/06/22

Keywords

  • Deep Learning
  • RReliefF
  • forecasting
  • impact factor
  • ranking

Fingerprint

Dive into the research topics of 'Multilevel Analysis of Temporal-Based Spatial Factors Impact in Dengue Fever Forecasting using RReliefF - Deep Learning'. Together they form a unique fingerprint.

Cite this