Bhanu Pratap Singh Bankoti, C. Gupta, O. Bandyopadhyay, Mallika Banerjee
{"title":"Analysis of Multitasking in Divided Attention using Machine Learning","authors":"Bhanu Pratap Singh Bankoti, C. Gupta, O. Bandyopadhyay, Mallika Banerjee","doi":"10.1109/CICT48419.2019.9066233","DOIUrl":null,"url":null,"abstract":"Evaluation of cognitive functionality plays an important role in the career choice of students as well as for the selection of employee for the employer. Divided attention is one such cognitive ability that deals with allocation of attention to multiple tasks simultaneously. An accurate analysis of divided attention would help us to identify cognitive decline, as well as provides a quantifiable indicator of a salient feature viz., vigilance which is highly relevant for defence personnel as well as pilots in air, water and road. The close observation of divided attention in home or classroom environment is an essential component for early detection of cognitive problems. It also helps in assessing the effectiveness of learning patterns. This work proposes a new method to determine the ability of relative divided attention through unobtrusive monitoring of use of a software game. The process measures the performance of a user (college student) on a multi-task cognitive software by computing the scores as part of the test for divided attention. This metric indicates the user's ability of multitasking in divided attention, i.e whether user is efficiently paying attention to all the tasks at once, or is primarily attending to one task at a time (sacrificing optimal performance). The data set is labelled based on statistical analysis. After classifying the data using machine learning model (random forest), the academic performance of the user is analysed against the divided attention levels to establish a correlation among them.","PeriodicalId":234540,"journal":{"name":"2019 IEEE Conference on Information and Communication Technology","volume":"37 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2019 IEEE Conference on Information and Communication Technology","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CICT48419.2019.9066233","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
Evaluation of cognitive functionality plays an important role in the career choice of students as well as for the selection of employee for the employer. Divided attention is one such cognitive ability that deals with allocation of attention to multiple tasks simultaneously. An accurate analysis of divided attention would help us to identify cognitive decline, as well as provides a quantifiable indicator of a salient feature viz., vigilance which is highly relevant for defence personnel as well as pilots in air, water and road. The close observation of divided attention in home or classroom environment is an essential component for early detection of cognitive problems. It also helps in assessing the effectiveness of learning patterns. This work proposes a new method to determine the ability of relative divided attention through unobtrusive monitoring of use of a software game. The process measures the performance of a user (college student) on a multi-task cognitive software by computing the scores as part of the test for divided attention. This metric indicates the user's ability of multitasking in divided attention, i.e whether user is efficiently paying attention to all the tasks at once, or is primarily attending to one task at a time (sacrificing optimal performance). The data set is labelled based on statistical analysis. After classifying the data using machine learning model (random forest), the academic performance of the user is analysed against the divided attention levels to establish a correlation among them.