Development of Computer State Identification Method Based on Boosting Ensemble
Keywords:computer system state identification, data processing, decision tree boosting ensembles
This work is about developing a modification of boosting method by using a special preprocessing procedure to improve the accuracy of computer system state identification. The aim of the research is to develop method for detection computer threats, malware, etc. Experimental research have confirmed the effectiveness of the proposed method, which makes it possible to recommend it for practical use in order to improve the accuracy of identifying the state of the computer system. Prospects for further research may be to develop an ensemble of fuzzy decision trees based on the proposed method, optimizing their software implementation.
Inter American Development Bank and Organization of American States, "Cybersecurity Risks, Progress, and the Way Forward in Latin America and the Caribbean", July 2020, pp. 19-38, doi: http://dx.doi.org/10.18235/0002513.
J. Dutta, Y. W. Kim and D. Dominic, "Comparison of Gradient Boosting and Extreme Boosting Ensemble Methods for Webpage Classification," 2020 Fifth International Conference on Research in Computational Intelligence and Communication Networks (ICRCICN), Bangalore, India, 2020, pp. 77-82, doi: 10.1109/ICRCICN50933.2020.9296176.
A. H. Mirza, "Online boosting algorithm for regression with additive and multiplicative updates," 2018 26th Signal Processing and Communications Applications Conference (SIU), Izmir, 2018, pp. 1-4, doi: 10.1109/SIU.2018.8404455.
Z. Li and D. Wang, "Classification on Point-cloud of Shoe-last Curvature using Weight-updated Boosting based Ensemble Learning," 2020 IEEE 9th Joint International Information Technology and Artificial Intelligence Conference (ITAIC), Chongqing, China, 2020, pp. 2073-2077, doi: 10.1109/ITAIC49862.2020.9338947.
P. Kumkar, I. Madan, A. Kale, O. Khanvilkar and A. Khan, "Comparison of Ensemble Methods for Real Estate Appraisal," 2018 3rd International Conference on Inventive Computation Technologies (ICICT), Coimbatore, India, 2018, pp. 297-300, doi: 10.1109/ICICT43934.2018.9034449.