Spatio-temporal COVID-19 Spread Prediction: Comparing SVM with Time-Expanded Features and RNN Models
-
Raden Aria Gusti Aji
*
Telkom University, Bandung,
Indonesia
- Sri Suryani Prasetiyowati Telkom University, Bandung, Indonesia
- Yuliant Sibaroni Telkom University, Bandung, Indonesia (*) Corresponding Author
Abstract
Covid-19 which spread in early 2020, still needs to be observed, considering the high growth rate of the pandemic at that time. The right prediction model is needed, because it can estimate the speed and extent of its spread for some time to come. This study develops a prediction model for the classification of the spread of Covid-19 in the future using SVM with time-based feature expansion and RNN. The scenario developed to determine the effect of time-based feature expansion and kernel function on classification performance using time series and spatial data. The results obtained show that SVM with time-based feature expansion achieves the most optimal performance using a polynomial kernel with an accuracy of 96.23%, a precision of 96.48%, a recall of 96.23%, and an F1-score of 96.21%. The performance of the SVM is superior to RNN which achieves an accuracy of 93.55%, a precision of 87.51%, a recall of 93.55%, and an F1-score of 90.43. Spatial prediction using Kriging interpolation can provide an overview of the spread of COVID-19 in all villages in Bandung City. The contribution of this research can provide much-needed information for policy makers and the community in managing future pandemic predictions and management strategies in the field of public health.
Downloads
References
M. Muñoz-Organero and P. Queipo-Álvarez, "Deep Spatiotemporal Model for COVID-19 Forecasting," Sensors, vol. 22, no. 9, p. 3519, 2022, doi: 10.3390/s22093519.
B. Vahedi, M. Karimzadeh, and H. Zoraghein, "Spatiotemporal prediction of COVID-19 cases using inter- and intra-county proxies of human interactions," Nat. Commun., vol. 12, p. 6440, 2021, doi: 10.1038/s41467-021-26742-6.
A. Ghozi, A. Aprianti, A. Dimas, and R. Fauzi, "Analisis Prediksi Data Kasus Covid-19 di Provinsi Lampung Menggunakan Recurrent Neural Network (RNN)," Indonesian Journal of Applied Mathematics, vol. 2, no. 1, pp. 25-32, 2022, doi: 10.35472/indojam.v2i1.763.
A. Kaddar, A. Abta, and H. T. T. Alaoui, "A comparison of delayed SIR and SEIR epidemic models," NAMC, vol. 16, no. 2, pp. 181–190, Apr. 2011, doi: 10.15388/NA.16.2.14104.
F. Ravenda, M. Cesarini, S. Peluso, et al., "A probabilistic spatio-temporal neural network to forecast COVID-19 counts," Int. J. Data Sci. Anal., 2024, doi: 10.1007/s41060-024-00525-w.
K. E. ArunKumar, D. V. Kalaga, C. M. Sai Komar, M. Kawaji, and T. M. Breza, "Forecasting of COVID-19 using deep layer Recurrent Neural Networks (RNNs) with Gated Recurrent Units (GRUs) and Long Short-Term Memory (LSTM) cells," Chaos, Solitons & Fractals, vol. 146, 2021, doi: 10.1016/j.chaos.2021.110861.
B. Safa and M. Kdayem, "Deep Learning for COVID-19 prediction," in Proc. 2020 Int. Conf. on Advances in Science, Engineering and Technology (IC_ASET), 2020, pp. 406-411, doi: 10.1109/IC_ASET49463.2020.9318297.
R. K. Pathan, M. Biswas, and M. U. Khandaker, "Time series prediction of COVID-19 by mutation rate analysis using recurrent neural network-based LSTM model," Chaos, Solitons & Fractals, vol. 138, p. 110018, 2020, doi: 10.1016/j.chaos.2020.110018.
Z. Ahmed and M. K. Faisal, "Advancements in Support Vector Machines for Environmental Modeling," J. Environ. Informatics, vol. 47, no. 1, pp. 40–55, 2021, doi: 10.3808/jei.2021.47.1.40.
E. Zhao and P. Tan, "Integration of Machine Learning and Kriging for Spatial Data Analysis: A Review," Comput. Geosci., vol. 151, pp. 104–117, 2021, doi: 10.1016/j.cageo.2021.104117.
Y. Wang, M. Xu, and X. Zhao, "Comparative analysis of kriging interpolation and support vector machine regression for spatial data," Environ. Earth Sci., vol. 78, no. 3, p. 81, 2019.
J. Park, J. Kim, and S. Lee, "Application of machine learning techniques for flood prediction in urban areas: A review," Water (Basel), vol. 12, no. 1, p. 352, 2020, doi.org/10.3390/w12010352
N. Ali, M. B. Rahman, and H. U. Ahmed, "Hybrid Models of SVM and Kriging for Improved Spatial Predictions," Environ. Monit. Assess., vol. 196, no. 9, pp. 1–15, 2024, doi: 10.1007/s10661-024-11628-0.
J. Sun, T. Wu, and Q. Li, "Recent Developments in Kriging Methods for Accurate Spatial Data Modeling," Spat. Stat., vol. 40, p. 100546, 2024, doi: 10.1016/j.spasta.2024.100546.
L. Cheng, Y. Zhang, and Y. Wu, "Predicting extreme weather events using hybrid machine learning models," J. Environ. Manage., vol. 325, no. 116401, 2023, doi: 10.1016/j.jenvman.2022.116401
R. J. Hyndman and G. Athanasopoulos, Forecasting: Principles and Practice, OTexts, 2018, doi: 10.1016/C2012-0-03732-9
G. P. Zhang, "Time series forecasting using a hybrid ARIMA and neural network model," Neurocomputing, vol. 50, pp. 159–175, 2003, doi: 10.1016/S0925-2312(01)00702-0
K. Shin, J. Han, and S. Kang, "MI-MOTE: Multiple imputation-based minority oversampling technique for imbalanced and incomplete data classification," Inf. Sci. (N.Y.), vol. 575, pp. 80–89, 2021, doi: 10.1016/j.ins.2021.06.042
A. Smith and B. Johnson, "Efficient parameter tuning for support vector machines in large-scale datasets," IEEE Trans. Neural Netw. Learn. Syst., vol. 30, no. 8, pp. 2404–2415, 2019.
J. Lee, H. Park, and S. Kim, "Enhanced support vector machines using adaptive kernel functions," Pattern Recognit. Lett., vol. 131, pp. 123–130, 2020.
K. Ousmane et al., "Novel Classification Method of Spikes Morphology in EEG Signal Using Machine Learning," Procedia Comput. Sci., vol. 148, pp. 70–79, Jul. 2019, doi: 10.1016/j.procs.2019.01.010.
Bila bermanfaat silahkan share artikel ini
Berikan Komentar Anda terhadap artikel Spatio-temporal COVID-19 Spread Prediction: Comparing SVM with Time-Expanded Features and RNN Models
Pages: 2251-2263
Copyright (c) 2025 Raden Aria Gusti Aji, Sri Suryani Prasetiyowati, Yuliant Sibaroni
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under Creative Commons Attribution 4.0 International License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (Refer to The Effect of Open Access).
