{"id":201,"date":"2016-12-12T21:39:21","date_gmt":"2016-12-12T20:39:21","guid":{"rendered":"http:\/\/liacs.leidenuniv.nl\/~kraaijw\/?p=201"},"modified":"2016-12-12T21:47:27","modified_gmt":"2016-12-12T20:47:27","slug":"detecting-work-stress-offices-combining-unobtrusive-sensors","status":"publish","type":"post","link":"https:\/\/liacs.leidenuniv.nl\/~kraaijw\/index.php\/2016\/12\/12\/detecting-work-stress-offices-combining-unobtrusive-sensors\/","title":{"rendered":"Detecting work stress in offices by combining unobtrusive sensors"},"content":{"rendered":"<p>Saskia Koldijk, Mark A. Neerincx, and Wessel Kraaij.<\/p>\n<p>Detecting work stress<br \/>\nin offices by combining unobtrusive sensors.<\/p>\n<p>IEEE Transactions on Affective Computing<\/p>\n<p>&nbsp;<\/p>\n<p><strong>Abstract:<\/strong><\/p>\n<div class=\"abstract-text ng-binding\">Employees often report the experience of stress at work. In the SWELL project we investigate how new context aware pervasive systems can support knowledge workers to diminish stress. The focus of this paper is on developing automatic classiers to infer working conditions and stress related mental states from a multimodal set of sensor data (computer logging, facial expressions, posture and physiology). We address two methodological and applied machine learning challenges: 1) Detecting work stress using several (physically) unobtrusive sensors, and 2) Taking into account individual dierences. A comparison of several classication approaches showed that, for our SWELL-KW dataset, neutral and stressful working conditions can be distinguished with 90% accuracy by means of SVM. Posture yields most valuable information, followed by facial expressions. Furthermore, we found that the subjective variable `mental eort&#8217; can be better predicted from sensor data than e.g. `perceived stress&#8217;. A comparison of several regression approaches showed that mental eort can be predicted best by a decision tree (correlation of 0.82). Facial expressions yield most valuable information, followed by posture. We nd that especially for estimating mental states it makes sense to address individual dierences. When we train models on particular subgroups of similar users, (in almost all cases) a specialized model performs equally well or better than a generic model.<\/div>\n<p><!-- end ngIf: ::vm.details.abstract --> <!-- ngIf: ::vm.details.scope --> <!-- ngIf: ::vm.details.purpose --> <!-- end ngIf: ::vm.details.impactStatement || vm.details.abstract || vm.details.scope || vm.details.purpose || vm.details.previewImage --> <!-- ngIf: ::vm.jwpOptions && vm.details.graphicalAbstract --> <!-- ngIf: ::vm.details.xploreNote --> <!-- ngIf: ::vm.details.publicationTitle && vm.details.isJournal --><\/p>\n<div class=\"u-pb-1 stats-document-abstract-publishedIn ng-scope\" data-tealium_data=\"{&quot;docType&quot;: &quot;Journal&quot;}\"><strong>Published in: <\/strong> <a class=\"stats-document-abstract-publishedIn ng-binding\" href=\"http:\/\/ieeexplore.ieee.org\/xpl\/RecentIssue.jsp?punumber=5165369\"><u><span style=\"color: #0066cc;\">IEEE Transactions on Affective Computing<\/span><\/u><\/a> <!-- ngIf: (vm.details.volume || vm.details.issue) --><span class=\"ng-scope\"> ( <!-- ngIf: ::vm.details.volume --><span class=\"ng-binding ng-scope\">Volume: PP<\/span><!-- end ngIf: ::vm.details.volume --><!-- ngIf: ::vm.details.issue -->, <a class=\"stats-document-abstract-publishedIn-issue ng-binding\" href=\"http:\/\/ieeexplore.ieee.org\/xpl\/tocresult.jsp?isnumber=5520654\"><u><span style=\"color: #0066cc;\">Issue: 99<\/span><\/u><\/a><!-- ngIf: ::vm.details.chronOrPublicationDate --><!-- end ngIf: ::vm.details.issue --> ) <\/span><!-- end ngIf: (vm.details.volume || vm.details.issue) --> <!-- ngRepeat: x in vm.details.virtualJournals --><\/div>\n<p><!-- end ngIf: ::vm.details.publicationTitle && vm.details.isJournal --> <!-- ngIf: ::vm.details.publicationTitle && vm.details.isConference --><\/p>\n<div class=\"pure-g u-pt-1\">\n<div class=\"pure-u-1-2\">\n<p><!-- ngIf: ::vm.details.externalId --> <!-- ngIf: ::vm.details.startPage && vm.details.isJournal && !vm.details.externalId --><\/p>\n<div class=\"u-pb-1 ng-binding ng-scope\"><strong>Page(s): <\/strong> 1 <!-- ngIf: ::vm.details.endPage --><span class=\"ng-binding ng-scope\">&#8211; 1<\/span><!-- end ngIf: ::vm.details.endPage --><\/div>\n<p><!-- end ngIf: ::vm.details.startPage && vm.details.isJournal && !vm.details.externalId --> <!-- ngIf: ::vm.details.isJournal == true --><\/p>\n<div class=\"u-pb-1 ng-binding ng-scope\"><strong>Date of Publication:<\/strong> 20 September 2016 <i class=\"doc-abs-pubdate-help\"><\/i><u> <\/u><\/div>\n<p><!-- end ngIf: ::vm.details.isJournal == true --> <!-- ngIf: ::vm.details.isStandard == true --> <!-- ngIf: ::vm.details.isConference == true --> <!-- ngIf: ::vm.details.isConference == true --> <!-- ngIf: ::vm.details.ISSN --> <!-- ngIf: ::vm.details.isbn --> <!-- ngIf: ::vm.details.issn --><\/p>\n<div class=\"u-pb-1 ng-scope\">\n<div class=\"ng-hide\" tabindex=\"0\"><strong><i class=\"icon-caret-down\"><\/i> ISSN Information: <\/strong><\/div>\n<div>\n<p><!-- ngRepeat: issn in ::vm.details.issn --><\/p>\n<div class=\"ng-binding ng-scope\"><strong class=\"ng-binding\">Print ISSN:<\/strong> 1949-3045<\/div>\n<p><!-- end ngRepeat: issn in ::vm.details.issn --><\/p>\n<\/div>\n<\/div>\n<p><!-- end ngIf: ::vm.details.issn --> <!--\n\n\n<div class=\"u-pb-1\" ng-if=\"::vm.details.citationCount\">\n\t\t\t\t<strong>References Cited: <\/strong>\n{{::vm.details.citationCount}}<\/div>\n\n\n--> <!-- ngIf: ::vm.details.pubMedId --><\/p>\n<\/div>\n<div class=\"pure-u-1-2\">\n<p><!-- ngIf: ::vm.details.accessionNumber --> <!-- ngIf: ::vm.details.doi --><\/p>\n<div class=\"u-pb-1 stats-document-abstract-doi ng-scope\"><strong>DOI: <\/strong> <a class=\"ng-binding\" href=\"http:\/\/dx.doi.org\/10.1109\/TAFFC.2016.2610975\" target=\"_blank\"><u><span style=\"color: #0066cc;\">10.1109\/TAFFC.2016.2610975<\/span><\/u><\/a><\/div>\n<p><!-- end ngIf: ::vm.details.doi --> <!-- ngIf: ::vm.details.icsCodes --> <!-- ngIf: ::(vm.details.isStandard && vm.details.persistentLink) --> <!-- ngIf: ::vm.details.year --> <!-- ngIf: ::(!vm.details.isStandard && vm.details.publisher) --><\/p>\n<div class=\"u-pb-1 ng-binding ng-scope\"><strong>Publisher: <\/strong> IEEE<\/div>\n<\/div>\n<\/div>\n","protected":false},"excerpt":{"rendered":"<p>Saskia Koldijk, Mark A. Neerincx, and Wessel Kraaij. Detecting work stress in offices by combining unobtrusive sensors. IEEE Transactions on Affective Computing &nbsp; Abstract: Employees often report the experience of stress at work. In the SWELL project we investigate how new context aware pervasive systems can support knowledge workers to diminish stress. The focus of [&hellip;]<\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[7],"tags":[],"class_list":["post-201","post","type-post","status-publish","format-standard","hentry","category-publication"],"_links":{"self":[{"href":"https:\/\/liacs.leidenuniv.nl\/~kraaijw\/index.php\/wp-json\/wp\/v2\/posts\/201","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/liacs.leidenuniv.nl\/~kraaijw\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/liacs.leidenuniv.nl\/~kraaijw\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/liacs.leidenuniv.nl\/~kraaijw\/index.php\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/liacs.leidenuniv.nl\/~kraaijw\/index.php\/wp-json\/wp\/v2\/comments?post=201"}],"version-history":[{"count":2,"href":"https:\/\/liacs.leidenuniv.nl\/~kraaijw\/index.php\/wp-json\/wp\/v2\/posts\/201\/revisions"}],"predecessor-version":[{"id":212,"href":"https:\/\/liacs.leidenuniv.nl\/~kraaijw\/index.php\/wp-json\/wp\/v2\/posts\/201\/revisions\/212"}],"wp:attachment":[{"href":"https:\/\/liacs.leidenuniv.nl\/~kraaijw\/index.php\/wp-json\/wp\/v2\/media?parent=201"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/liacs.leidenuniv.nl\/~kraaijw\/index.php\/wp-json\/wp\/v2\/categories?post=201"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/liacs.leidenuniv.nl\/~kraaijw\/index.php\/wp-json\/wp\/v2\/tags?post=201"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}