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

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

Spatial connectivity in mosquito-borne disease models: a systematic review of methods and assumptions

“…Five papers included spatial covariates as inputs for their machine learning algorithms. These spatial covariates included cases from neighbouring regions [233][234][235], the number of people travelling between regions based on air travel [234], public transportation networks [20] or a gravity model that aimed to replicate human commuting behaviour [236], and the distance between countries [236]. The inclusion of spatial covariates as inputs is compatible with all machine learning models and, if the data are available, does not require any additional computation.…”