Research Article
Time Series Forecasting Using the LSTM Model as a Sequential Ensemble Method
@INPROCEEDINGS{10.1007/978-3-032-05832-4_8, author={Alioum Abdoulaye and Apollinaire Batoure Bamana and Richard Guiem and Shadi Attala and Kaladzavi Guidedi}, title={Time Series Forecasting Using the LSTM Model as a Sequential Ensemble Method}, proceedings={Safe, Secure, Ethical, Responsible Technologies and Emerging Applications. Second EAI International Conference, SAFER-TEA 2024, Dubai, United Arab Emirates, December 9--10, 2024, Proceedings}, proceedings_a={SAFER-TEA}, year={2026}, month={11}, keywords={Malaria Time Series Time Series Forecasting Sequential Ensemble Method (SEM) Long-Short Term Memory (LSTM) Limited data volume}, doi={10.1007/978-3-032-05832-4_8} }- Alioum Abdoulaye
Apollinaire Batoure Bamana
Richard Guiem
Shadi Attala
Kaladzavi Guidedi
Year: 2026
Time Series Forecasting Using the LSTM Model as a Sequential Ensemble Method
SAFER-TEA
Springer
DOI: 10.1007/978-3-032-05832-4_8
Abstract
Forecasting in time series remains a challenge despite numerous proposed models. There is a constant desire to improve the rates obtained, depending on the data available, especially in the context of quantity-limited data, which is the main challenge to overcome in this work. An approach based on sequential ensemble methods, with LSTM as a basic model called SEM-LSTM, is proposed to achieve this. The approach is based on the analysis of local autocorrelations, exploring temporal dependencies in specific segments of the series under study. A lag value d is deduced and taken as the sliding window size. The model is applied to Malaria data collected weekly in the Health Districts of the Adamawa Region of Cameroon to be assessed. The performance of SEM-LSTM is then compared with ARIMA and simple LSTM models using RMSE, MAE and R metrics. The results highlight the superiority of the SEM-LSTM model for predicting complex time series, such as Malaria cases, in the context of a limited quantity of data.