Logo

Spatial Multi-Layer Perceptron Model for Predicting Dengue Fever Outbreaks in Surabaya

Halim, Siana and Handojo, Andreas and WIDODO, IVAN ENRICO and Felecia, and Octavia, Tanti (2020) Spatial Multi-Layer Perceptron Model for Predicting Dengue Fever Outbreaks in Surabaya. [UNSPECIFIED]

[img]
Preview
PDF
Download (1887Kb) | Preview
    [img] PDF
    Download (2029Kb)
      [img]
      Preview
      PDF (peer review)
      Download (1882Kb) | Preview
        [img]
        Preview
        PDF (paper - Siana H)
        Download (1892Kb) | Preview
          [img]
          Preview
          PDF (korespondensi - Siana H)
          Download (933Kb) | Preview

            Abstract

            Dengue fever (DF) is a tropical disease spread by mosquitoes of the Aedes type. Therefore, a DF outbreak needs to be predicted to minimize the spread and death caused by it. The spread of dengue fever is a spatial problem. In this paper, we adopted the Multi Linear Perceptron (MLP) to solve the spatial problem, and we called it a spatial multi-layer perceptron model (Spatial MLP). In this proposed model, we consider two types of input neurons in the Spatial MLP, a region and the neighbourhood of that region. The spatial inputs dynamically change to the region. Additionally, the neighbourhood numbers of a region are also varied. So, the spatial inputs are changed in terms of the number of inputs and the neighbourhoods. As a result, the proposed model is outperformed the traditional MLP since it can adapt to the neighbourhoods. We can conclude the spatial MLP model can manage the information and predict the dengue fever outbreak in Surabaya

            Item Type: UNSPECIFIED
            Uncontrolled Keywords: Multilayer Perceptron; Spatial; Dengue Fever Outbreak
            Subjects: H Social Sciences > HA Statistics
            Divisions: Faculty of Industrial Technology > Industrial Engineering Department
            Depositing User: Admin
            Date Deposited: 14 Sep 2020 15:22
            Last Modified: 07 Mar 2024 10:30
            URI: https://repository.petra.ac.id/id/eprint/18882

            Actions (login required)

            View Item