{"title":"Classification Algorithms Analysis in the Forest Fire Detection Problem","authors":"M. D. Molovtsev, I. Sineva","doi":"10.1109/IT&QM&IS.2019.8928398","DOIUrl":null,"url":null,"abstract":"The development of information technology allows applying complex mathematical algorithms. For example, machine learning (ML) procedures are used in almost all humans life areas: smart home systems, online recommendation systems intelligent chatbots and so on. This creates a huge demand for specialists in data analysis and ML. Modern data analysis packages often do not require deep knowledge from a specialist, which allows to apply all ML algorithms without a deep understanding of their work. However, the main problem is that the data is not suitable for the algorithm and as a result, the algorithm cannot detect all the patterns or does it incorrectly. This situation can be acceptable in pet projects and is completely unacceptable in cases where the algorithm error costs a lot of money or human lives. In this paper the analysis of ML algorithms and the possibility of their application to forest fires data are done.","PeriodicalId":285904,"journal":{"name":"2019 International Conference \"Quality Management, Transport and Information Security, Information Technologies\" (IT&QM&IS)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"7","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2019 International Conference \"Quality Management, Transport and Information Security, Information Technologies\" (IT&QM&IS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/IT&QM&IS.2019.8928398","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 7
Abstract
The development of information technology allows applying complex mathematical algorithms. For example, machine learning (ML) procedures are used in almost all humans life areas: smart home systems, online recommendation systems intelligent chatbots and so on. This creates a huge demand for specialists in data analysis and ML. Modern data analysis packages often do not require deep knowledge from a specialist, which allows to apply all ML algorithms without a deep understanding of their work. However, the main problem is that the data is not suitable for the algorithm and as a result, the algorithm cannot detect all the patterns or does it incorrectly. This situation can be acceptable in pet projects and is completely unacceptable in cases where the algorithm error costs a lot of money or human lives. In this paper the analysis of ML algorithms and the possibility of their application to forest fires data are done.