Deep Learning Algorithms for predicting the geographical locations of Pandemic Disease Patients from Global Positioning System (GPS) Trajectory Datasets

Background and aim: The successful isolation of the Covid-19 virus in Wuhan, China in December 2019 provided empirical/scientific proof of the existence of the Covid 19 virus and marked the beginning of a pandemic of great proportions. Although localized and moderate at inception, the Covid-19 pandemic has proceeded to overwhelm the health authorities in several countries of the world. Concerted efforts to monitor the spread of the virus had been undertaken since the advent of the Covid-19 pandemic. The attempt to flatten the curve of the Covid-19 pandemic initially relied on contact tracing of persons who made contacts with infected persons. Presently, owing to the dynamics of the pandemic, scientists appear more preoccupied with the higher task of geographical location prediction of pandemic disease patients. Accordingly, the aim of this study is to carry out a comparative analysis of six deep learning algorithms for predicting the geographical locations of Covid-19 patients from Big GPS trajectory datasets. Method: The methodology for this study, proposes to design and apply selected deep learning algorithms for predicting the location of infected Covid-19 patients under monitoring. Among the deep learning algorithms include Recurrent Neural networks (RNN), Long-Short Term Memory (LSTM), Bidirectional LSTM (BiLSTM), Convolutional Neural Networks (CNN), Gated Recurrent Unit (GRU), Multilayer perceptron (MLP). The distinctive quality of the models is efficiency and effectiveness with regards to time saving, minimal use of computer resources, smart design, and development. Result: The result of this study showed that with application of the above mentioned deep learning models, it is possible to predict the location of infected Covid-19 patients. Thus, the predictive ability of these models is not in doubt. The GRU algorithm outperformed the other algorithms (i.e., RNN, LSTM, BiLSTM, CNN, and MLP) based on Key Performance Indicators (KPIs) metrics applied such as Mean Absolute Error (MAE), Mean Squared Error (MSE), Mean Absolute Percentage Error (MAPE), and Root Mean Squared Logarithmic Error (RMSLE) using uniform geographical location data. The result further revealed that location prediction of Covid-19 patients is more optimally executed using the deep learning models. Based on the findings in this paper, it is recommended that the deep learning models be applied in other jurisdictions for location prediction problems. Conclusion: The result of this study recommends the deep learning models for location prediction problems of not only Covid-19 patients but all other pandemic disease situations around the globe.