Yunbiao Wang, Chenyang Zhang, Chenglin Liu, Kun Liu, Fang Xu, Jixue Yuan, Chaozhe Jiang, Chuang Liu, Weiwei Cao
{"title":"Analysis on pulse rate variability for pilot workload assessment based on wearable sensor","authors":"Yunbiao Wang, Chenyang Zhang, Chenglin Liu, Kun Liu, Fang Xu, Jixue Yuan, Chaozhe Jiang, Chuang Liu, Weiwei Cao","doi":"10.1002/hfm.21053","DOIUrl":null,"url":null,"abstract":"<p>The workload levels of pilots directly affect their flight performance and the safety of the whole flight. To explore the real-time workload of pilots in different flight phases (takeoff, cruise, and landing), this paper leveraged National Aeronautics and Space Administration Task Load Index (NASA-TLX), a subjective evaluation scale, and PhotoPlethysmoGraphy (PPG) signals of 21 participants using a flight simulator and a wearable sensor. First, the workloads of pilots under different phases were explored by the NASA-TLX scales; secondly, the pulse rate variability (PRV) features were selected by variance analysis and random forest importance evaluation; finally, the performances of the k-nearest neighbor (KNN), random forest (RF), and support vector machine (SVM) were compared for workload levels identification. It is shown that the workloads are ranked as follows: landing > takeoff > cruise. SDNN, CVCD, CVNNI, LF, TP, SD2, and SD2/SD1 were used as selected features with significant differences in different flight phases. In addition, machine learning models can effectively identify pilot workloads, and feature selection enhances the performance of both KNN and RF classifiers. The best identification of workload was achieved using the selected PRV features as inputs to the KNN classifier, with an average accuracy of 88.9%. Our results indicate that the KNN classifier and PRV features are suitable for identifying pilot workload. The pilot workload is highest during the landing phase, which provides a reference for flight safety management. The findings from this research could contribute to developing a robust pilot workload detection system and improve current flight operation safety regulations.</p>","PeriodicalId":55048,"journal":{"name":"Human Factors and Ergonomics in Manufacturing & Service Industries","volume":null,"pages":null},"PeriodicalIF":2.2000,"publicationDate":"2024-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Human Factors and Ergonomics in Manufacturing & Service Industries","FirstCategoryId":"5","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1002/hfm.21053","RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"ENGINEERING, MANUFACTURING","Score":null,"Total":0}
引用次数: 0
Abstract
The workload levels of pilots directly affect their flight performance and the safety of the whole flight. To explore the real-time workload of pilots in different flight phases (takeoff, cruise, and landing), this paper leveraged National Aeronautics and Space Administration Task Load Index (NASA-TLX), a subjective evaluation scale, and PhotoPlethysmoGraphy (PPG) signals of 21 participants using a flight simulator and a wearable sensor. First, the workloads of pilots under different phases were explored by the NASA-TLX scales; secondly, the pulse rate variability (PRV) features were selected by variance analysis and random forest importance evaluation; finally, the performances of the k-nearest neighbor (KNN), random forest (RF), and support vector machine (SVM) were compared for workload levels identification. It is shown that the workloads are ranked as follows: landing > takeoff > cruise. SDNN, CVCD, CVNNI, LF, TP, SD2, and SD2/SD1 were used as selected features with significant differences in different flight phases. In addition, machine learning models can effectively identify pilot workloads, and feature selection enhances the performance of both KNN and RF classifiers. The best identification of workload was achieved using the selected PRV features as inputs to the KNN classifier, with an average accuracy of 88.9%. Our results indicate that the KNN classifier and PRV features are suitable for identifying pilot workload. The pilot workload is highest during the landing phase, which provides a reference for flight safety management. The findings from this research could contribute to developing a robust pilot workload detection system and improve current flight operation safety regulations.
期刊介绍:
The purpose of Human Factors and Ergonomics in Manufacturing & Service Industries is to facilitate discovery, integration, and application of scientific knowledge about human aspects of manufacturing, and to provide a forum for worldwide dissemination of such knowledge for its application and benefit to manufacturing industries. The journal covers a broad spectrum of ergonomics and human factors issues with a focus on the design, operation and management of contemporary manufacturing systems, both in the shop floor and office environments, in the quest for manufacturing agility, i.e. enhancement and integration of human skills with hardware performance for improved market competitiveness, management of change, product and process quality, and human-system reliability. The inter- and cross-disciplinary nature of the journal allows for a wide scope of issues relevant to manufacturing system design and engineering, human resource management, social, organizational, safety, and health issues. Examples of specific subject areas of interest include: implementation of advanced manufacturing technology, human aspects of computer-aided design and engineering, work design, compensation and appraisal, selection training and education, labor-management relations, agile manufacturing and virtual companies, human factors in total quality management, prevention of work-related musculoskeletal disorders, ergonomics of workplace, equipment and tool design, ergonomics programs, guides and standards for industry, automation safety and robot systems, human skills development and knowledge enhancing technologies, reliability, and safety and worker health issues.