Trang chủ    Giới thiệu    Danh mục công bố    Thống kê công bố    Liên hệ   
Trang chủ Công bố quốc tế • Giới thiệu     • Tài liệu hướng dẫn
  • Chỉ mục bởi
  • Năm xuất bản
LIÊN KẾT WEBSITE

COVID-19 cases prediction by using hybrid machine learning and beetle antennae search approach

Zivkovic Singidunum University, Danijelova 32, Belgrade, 11000, Serbia|
Fadi (20336944100) | Ivana (57191590910); Al-Turjman | Aleksandar (57221288967); Strumberger | Anand (55201442200); Djordjevic Research Centre for AI and IoT, Department of Artificial Intelligence Engineering, Near East University, Nicosia, Mersin 10, 99138, Turkey| K. (57213001965); Nayyar Faculty of Information Technology, Duy Tan University, Da Nang, Viet Nam| Nebojsa (37028223900); Venkatachalam Graduate School, Duy Tan University, Da Nang, 550000, Viet Nam| Miodrag (57208755936); Bacanin School of Computer Science and Engineering, VIT Bhopal University, Bhopal, India|

Sustainable Cities and Society Số , năm 2021 (Tập 66, trang -)

ISSN: 22106707

ISSN: 22106707

DOI: 10.1016/j.scs.2020.102669

Tài liệu thuộc danh mục:

Article

English

Từ khóa: Biomimetics; Forecasting; Fuzzy inference; Fuzzy neural networks; Fuzzy systems; Predictive analytics; Swarm intelligence; Time series; Time series analysis; Viruses; Adaptive neuro-fuzzy inference system; Benchmark functions; Comparative analysis; Hybrid machine learning; Nature inspired algorithms; State-of-the-art approach; Time series prediction; World Health Organization; artificial intelligence; computer simulation; COVID-19; epidemic; fuzzy mathematics; machine learning; Machine learning
Tóm tắt tiếng anh
The main objective of this paper is to further improve the current time-series prediction (forecasting) algorithms based on hybrids between machine learning and nature-inspired algorithms. After the recent COVID-19 outbreak, almost all countries were forced to impose strict measures and regulations in order to control the virus spread. Predicting the number of new cases is crucial when evaluating which measures should be implemented. The improved forecasting approach was then used to predict the number of the COVID-19 cases. The proposed prediction model represents a hybridized approach between machine learning, adaptive neuro-fuzzy inference system and enhanced beetle antennae search swarm intelligence metaheuristics. The enhanced beetle antennae search is utilized to determine the parameters of the adaptive neuro-fuzzy inference system and to improve the overall performance of the prediction model. First, an enhanced beetle antennae search algorithm has been implemented that overcomes deficiencies of its original version. The enhanced algorithm was tested and validated against a wider set of benchmark functions and proved that it substantially outperforms original implementation. Afterwards, the proposed hybrid method for COVID-19 cases prediction was then evaluated using the World Health Organization's official data on the COVID-19 outbreak in China. The proposed method has been compared against several existing state-of-the-art approaches that were tested on the same datasets. The proposed CESBAS-ANFIS achieved R2 score of 0.9763, which is relatively high when compared to the R2 value of 0.9645, achieved by FPASSA-ANFIS. To further evaluate the robustness of the proposed method, it has also been validated against two different datasets of weekly influenza confirmed cases in China and the USA. Simulation results and the comparative analysis show that the proposed hybrid method managed to outscore other sophisticated approaches that were tested on the same datasets and proved to be a useful tool for time-series prediction. � 2020 Elsevier Ltd

Xem chi tiết