Senthilkumar Mohan, John A, Ahed Abugabah, Adimoolam M, Shubham Kumar Singh, Ali Kashif Bashir, Louis Sanzogni
{"title":"An approach to forecast impact of Covid-19 using supervised machine learning model.","authors":"Senthilkumar Mohan, John A, Ahed Abugabah, Adimoolam M, Shubham Kumar Singh, Ali Kashif Bashir, Louis Sanzogni","doi":"10.1002/spe.2969","DOIUrl":null,"url":null,"abstract":"<p><p>The Covid-19 pandemic has emerged as one of the most disquieting worldwide public health emergencies of the 21st century and has thrown into sharp relief, among other factors, the dire need for robust forecasting techniques for disease detection, alleviation as well as prevention. Forecasting has been one of the most powerful statistical methods employed the world over in various disciplines for detecting and analyzing trends and predicting future outcomes based on which timely and mitigating actions can be undertaken. To that end, several statistical methods and machine learning techniques have been harnessed depending upon the analysis desired and the availability of data. Historically speaking, most predictions thus arrived at have been short term and country-specific in nature. In this work, multimodel machine learning technique is called EAMA for forecasting Covid-19 related parameters in the long-term both within India and on a global scale have been proposed. This proposed EAMA hybrid model is well-suited to predictions based on past and present data. For this study, two datasets from the Ministry of Health & Family Welfare of India and Worldometers, respectively, have been exploited. Using these two datasets, long-term data predictions for both India and the world have been outlined, and observed that predicted data being very similar to real-time values. The experiment also conducted for statewise predictions of India and the countrywise predictions across the world and it has been included in the Appendix.</p>","PeriodicalId":49504,"journal":{"name":"Software-Practice & Experience","volume":"52 4","pages":"824-840"},"PeriodicalIF":2.6000,"publicationDate":"2022-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8250688/pdf/SPE-52-824.pdf","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Software-Practice & Experience","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1002/spe.2969","RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2021/4/1 0:00:00","PubModel":"Epub","JCR":"Q2","JCRName":"COMPUTER SCIENCE, SOFTWARE ENGINEERING","Score":null,"Total":0}
引用次数: 0
Abstract
The Covid-19 pandemic has emerged as one of the most disquieting worldwide public health emergencies of the 21st century and has thrown into sharp relief, among other factors, the dire need for robust forecasting techniques for disease detection, alleviation as well as prevention. Forecasting has been one of the most powerful statistical methods employed the world over in various disciplines for detecting and analyzing trends and predicting future outcomes based on which timely and mitigating actions can be undertaken. To that end, several statistical methods and machine learning techniques have been harnessed depending upon the analysis desired and the availability of data. Historically speaking, most predictions thus arrived at have been short term and country-specific in nature. In this work, multimodel machine learning technique is called EAMA for forecasting Covid-19 related parameters in the long-term both within India and on a global scale have been proposed. This proposed EAMA hybrid model is well-suited to predictions based on past and present data. For this study, two datasets from the Ministry of Health & Family Welfare of India and Worldometers, respectively, have been exploited. Using these two datasets, long-term data predictions for both India and the world have been outlined, and observed that predicted data being very similar to real-time values. The experiment also conducted for statewise predictions of India and the countrywise predictions across the world and it has been included in the Appendix.
期刊介绍:
Software: Practice and Experience is an internationally respected and rigorously refereed vehicle for the dissemination and discussion of practical experience with new and established software for both systems and applications.
Articles published in the journal must be directly relevant to the design and implementation of software at all levels, from a useful programming technique all the way up to a large scale software system. As the journal’s name suggests, the focus is on practice and experience with software itself. The journal cannot and does not attempt to cover all aspects of software engineering.
The key criterion for publication of a paper is that it makes a contribution from which other persons engaged in software design and implementation might benefit. Originality is also important. Exceptions can be made, however, for cases where apparently well-known techniques do not appear in the readily available literature.
Contributions regularly:
Provide detailed accounts of completed software-system projects which can serve as ‘how-to-do-it’ models for future work in the same field;
Present short reports on programming techniques that can be used in a wide variety of areas;
Document new techniques and tools that aid in solving software construction problems;
Explain methods/techniques that cope with the special demands of large-scale software projects. However, software process and management of software projects are topics deemed to be outside the journal’s scope.
The emphasis is always on practical experience; articles with theoretical or mathematical content are included only in cases where an understanding of the theory will lead to better practical systems.
If it is unclear whether a manuscript is appropriate for publication in this journal, the list of referenced publications will usually provide a strong indication. When there are no references to Software: Practice and Experience papers (or to papers in a journal with a similar scope such as JSS), it is quite likely that the manuscript is not suited for this journal. Additionally, one of the journal’s editors can be contacted for advice on the suitability of a particular topic.