Optimizing Neural Network for Parameter Estimation of Highly Multivariate Log Gaussian Cox Process Using Dropout Training

Ekky Rino Fajar Sakti, Achmad Choiruddin, Tintrim Dwi Ary Widhianingsih

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Analyzing highly multivariate spatio-temporal point pattern data is very challenging, especially using the standard procedure since it cannot handle huge data volume, complex spatio-temporal model, and expensive computation. Meanwhile, neural networks have shown their ability to handle complex problems. This study uses a robust neural network model with dropout layers to estimate parameters of highly multivariate spatio-temporal log Gaussian Cox processes. We employ our model to assess the distributional patterns of 25 tree species within Barro Colorado Island dataset, observed at 4 different timestamps. We achieved an accuracy improvement of more than 2.5% over previous state-of-the-art work, demonstrating that our network is better to handle highly multivariate spatio-temporal data.

Original languageEnglish
Title of host publication2024 ASU International Conference in Emerging Technologies for Sustainability and Intelligent Systems, ICETSIS 2024
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages604-608
Number of pages5
ISBN (Electronic)9798350372229
DOIs
Publication statusPublished - 2024
Event2024 ASU International Conference in Emerging Technologies for Sustainability and Intelligent Systems, ICETSIS 2024 - Manama, Bahrain
Duration: 28 Jan 202429 Jan 2024

Publication series

Name2024 ASU International Conference in Emerging Technologies for Sustainability and Intelligent Systems, ICETSIS 2024

Conference

Conference2024 ASU International Conference in Emerging Technologies for Sustainability and Intelligent Systems, ICETSIS 2024
Country/TerritoryBahrain
CityManama
Period28/01/2429/01/24

Keywords

  • dropout
  • lgcp
  • neural network
  • point process
  • tree

Fingerprint

Dive into the research topics of 'Optimizing Neural Network for Parameter Estimation of Highly Multivariate Log Gaussian Cox Process Using Dropout Training'. Together they form a unique fingerprint.

Cite this