A novel model for malaria prediction based on ensemble algorithms

Abstract

Background and objectiveMost previous studies adopted single traditional time series models to predict incidences of malaria. A single model cannot effectively capture all the properties of the data structure. However, a stacking architecture can solve this problem by combining distinct algorithms and models. This study compares the performance of traditional time series models and deep learning algorithms in malaria case prediction and explores the application value of stacking methods in the field of infectious disease prediction.MethodsThe ARIMA, STL+ARIMA, BP-ANN and LSTM network models were separately applied in simulations using malaria data and meteorological data in Yunnan Province from 2011 to 2017. We compared the predictive performance of each model through evaluation measures: RMSE, MASE, MAD. In addition, gradient-boosting regression trees (GBRTs) were used to combine the above four models. We also determined whether stacking structure improved the model prediction performance.ResultsThe root mean square errors (RMSEs) of the four sub-models were 13.176, 14.543, 9.571 and 7.208; the mean absolute scaled errors (MASEs) were 0.469, 0.472, 0.296 and 0.266 and the mean absolute deviation (MAD) were 6.403, 7.658, 5.871 and 5.691. After using the stacking architecture combined with the above four models, the RMSE, MASE and MAD values of the ensemble model decreased to 6.810, 0.224 and 4.625, respectively.ConclusionsA novel ensemble model based on the robustness of structured prediction and model combination through stacking was developed. The findings suggest that the predictive performance of the final model is superior to that of the other four sub-models, indicating that stacking architecture may have significant implications in infectious disease prediction.

A Review on Spatial Technologies for Enhancing Malaria Control: Concepts, Tools, and Challenges

“…Deep learning algorithms, such as LSTM and stacking algorithms (ensemble) are shown to be more superior in predicting Malaria outbreak with RMSE of 0.072 and 0.068 using meteorological data [15]. The findings also indicate that the ensemble stacking architecture produced promising results in predicting malaria disease prediction as different architecture produces different prediction results.…”

“…3) Data Analysis, Modelling and Processing Phase: In the data modeling and visualization phase, data were analyzed or modeled in order to predict and detect the occurrence of the malaria disease outbreak. Machine learning algorithms can be used to analyzed non-spatial and temporal data [14], [15], [24], [25], [38], and the mapping and modeling of malaria risk can also be performed by using GIS spatial and temporal models [13]. Image processing can be used to process the imageries captured using remote sensing devices [26].…”

Hybrid Machine Learning Model Coupled with School Closure For Forecasting COVID-19 Cases in the Most Affected Countries

“…An artificial neural network (ANN), which is especially capable of solving nonlinear problems, is a mathematical model designed to solve complex problems especially nonlinear problems [11]. In this regard, BP based neural networks (BP-ANN) are one of the most broadly employed neural network types, as they improve the accuracy of predictions [28]. Backpropagation (BP) networks use the method of returning the error amount in a feedforward network to the neurons in the hidden layer, thereby increase the success of its training.…”

“…In this study, a BP-ANN with a single hidden layer is used to forecast the number of Covid-19 cases as it is one of the best training algorithm improving prediction accuracy, consistent with the expression elsewhere [28]. Forecasting is performed with the BP-ANN algorithm developed in C sharp visual studio environment.…”

Covid-19 Containment: Demystifying the Research Challenges and Contributions Leveraging Digital Intelligence Technologies

“…In [15], and influenza prediction platform has been proposed as a reference architecture to estimate future flu-like epidemics with sufficient accuracy. In [16], deep learning algorithm is integrated with traditional time series models with a stacking ensemble approach in order to improve the prediction of malaria. In the survey work [17], the authors have reviewed and analyzed that Artificial Neural Network (ANN) when combined with different neural network techniques produced improved accuracy of predicting epidemics such as Ebola, Zika, Middle East Respiratory Syndrome (MERS), and Lassa.…”