{"id":{"repo_id":"de-montfort","oai_identifier":"oai:dora.dmu.ac.uk:2086/24507"},"canonical_url":"https://search.dev.ndltd.org/etd/de-montfort/oai:dora.dmu.ac.uk:2086/24507","repository":{"repo_id":"de-montfort","name":"De Montfort University","base_url":"https://dora.dmu.ac.uk/server/oai/request"},"display":{"title":"An Analysis of Grey Theory for Personal Affective Computing","abstract":"Affective computing, the study of artificial intelligence for computing with mood and emotion, has been rapidly growing since its inception in the late 1990s, however model-based affective computing remains limited. This thesis proposes grey theory, in particular grey systems analysis, as a potential model for affective computing. This gives the novel advantage among affective computing methods of being able to apply grey incidence analysis, which returns important contributing factors to a given sequence. Grey modelling is applied to a novel affective dataset, collected using behavioural and mood data from 7 different participants. Grey incidence analysis is performed on this dataset using two different mood sequences (a series of emotion categories, and a series of valence values) alongside the behavioural factors. This gives each participant in the dataset a unique set of contributing behavioural factors to their mood, with the sequence of valence values providing better overall system performance. These unique contributing behavioural factors are compared to two other methods of measuring similarity; three correlation measures (including two non-parametric), and two spatial distance measures (cosine and Euclidean distance). This comparison proves grey incidence analysis capable of finding contributing factors where correlations and spatial distance measures are unable to, including with flag-type data used to represent missing values. This thesis is successful in proving grey systems modelling, and grey incidence analysis, can be applied to affective data and that useful insights into the contributing factors to a person's mood can be extracted. The next step from this research would be creating \"behavioural prescriptions\", where a person could be told to modify their contributing behaviours to have a positive effect on their mood. It was found in this thesis that this is not currently possible, given the lack of directionality in grey incidence analysis' degrees of incidence, however this is an avenue for further research.","abstract_html":"Affective computing, the study of artificial intelligence for computing with mood and emotion, has been rapidly growing since its inception in the late 1990s, however model-based affective computing remains limited. This thesis proposes grey theory, in particular grey systems analysis, as a potential model for affective computing. This gives the novel advantage among affective computing methods of being able to apply grey incidence analysis, which returns important contributing factors to a given sequence. Grey modelling is applied to a novel affective dataset, collected using behavioural and mood data from 7 different participants. Grey incidence analysis is performed on this dataset using two different mood sequences (a series of emotion categories, and a series of valence values) alongside the behavioural factors. This gives each participant in the dataset a unique set of contributing behavioural factors to their mood, with the sequence of valence values providing better overall system performance. These unique contributing behavioural factors are compared to two other methods of measuring similarity; three correlation measures (including two non-parametric), and two spatial distance measures (cosine and Euclidean distance). This comparison proves grey incidence analysis capable of finding contributing factors where correlations and spatial distance measures are unable to, including with flag-type data used to represent missing values. This thesis is successful in proving grey systems modelling, and grey incidence analysis, can be applied to affective data and that useful insights into the contributing factors to a person's mood can be extracted. The next step from this research would be creating "behavioural prescriptions", where a person could be told to modify their contributing behaviours to have a positive effect on their mood. It was found in this thesis that this is not currently possible, given the lack of directionality in grey incidence analysis' degrees of incidence, however this is an avenue for further research.","abstract_has_math":false,"creators":["Felton, Elizabeth"],"institution":"De Montfort University","degree_name":"PhD","degree_level":"Doctoral","degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2024,"date_issued":"2024-08","date_published":"2024-08","updated_at":"2026-07-24T06:18:47Z","subjects":[],"languages":[],"rights":[],"rights_urls":["https://dora.dmu.ac.uk/bitstreams/fe0558c6-2caf-428a-8f59-3a5c46c0cd5a/download"],"identifier_entries":[]},"links":{"outbound_url":null,"outbound_label":null,"outbound_source":null},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:creator","label":"Author","values":["Felton, Elizabeth"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.issued","label":"Date","values":["2024-08"]},{"key":"dc:publisher.department","label":"Dc Publisher Department","values":["Faculty of Computing, Engineering and Media"]},{"key":"dc:publisher.institution","label":"Dc Publisher Institution","values":["De Montfort University"]},{"key":"dc:relation.isreferencedby","label":"Dc Relation Isreferencedby","values":["https://hdl.handle.net/2086/24507"]},{"key":"dc:type","label":"Dc Type","values":["Thesis or dissertation"]},{"key":"dc:type.qualificationlevel","label":"Dc Type Qualificationlevel","values":["Doctoral"]},{"key":"dc:type.qualificationname","label":"Dc Type Qualificationname","values":["PhD"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["https://dora.dmu.ac.uk/bitstreams/fe0558c6-2caf-428a-8f59-3a5c46c0cd5a/download"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://dora.dmu.ac.uk/bitstreams/4cbd5314-1ee5-448d-982a-ec6173b4aad6/download"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Affective computing, the study of artificial intelligence for computing with mood and emotion, has been rapidly growing since its inception in the late 1990s, however model-based affective computing remains limited. This thesis proposes grey theory, in particular grey systems analysis, as a potential model for affective computing. This gives the novel advantage among affective computing methods of being able to apply grey incidence analysis, which returns important contributing factors to a given sequence. Grey modelling is applied to a novel affective dataset, collected using behavioural and mood data from 7 different participants. Grey incidence analysis is performed on this dataset using two different mood sequences (a series of emotion categories, and a series of valence values) alongside the behavioural factors. This gives each participant in the dataset a unique set of contributing behavioural factors to their mood, with the sequence of valence values providing better overall system performance. These unique contributing behavioural factors are compared to two other methods of measuring similarity; three correlation measures (including two non-parametric), and two spatial distance measures (cosine and Euclidean distance). This comparison proves grey incidence analysis capable of finding contributing factors where correlations and spatial distance measures are unable to, including with flag-type data used to represent missing values. This thesis is successful in proving grey systems modelling, and grey incidence analysis, can be applied to affective data and that useful insights into the contributing factors to a person's mood can be extracted. The next step from this research would be creating \"behavioural prescriptions\", where a person could be told to modify their contributing behaviours to have a positive effect on their mood. It was found in this thesis that this is not currently possible, given the lack of directionality in grey incidence analysis' degrees of incidence, however this is an avenue for further research."]},{"key":"dc:format.checksum.md5","label":"Dc Format Checksum Md5","values":["9ec966657d7bba71c352701591a067b1","bd41181d9a4c38b5ebacc69a027024d9","f56a62951124d7c6da3cb59bbbf22f89"]},{"key":"dc:title","label":"Title","values":["An Analysis of Grey Theory for Personal Affective Computing"]}]}],"canonical_facts":{"dc:creator":["Felton, Elizabeth"],"dc:date.issued":["2024-08"],"dc:description.abstract":["Affective computing, the study of artificial intelligence for computing with mood and emotion, has been rapidly growing since its inception in the late 1990s, however model-based affective computing remains limited. This thesis proposes grey theory, in particular grey systems analysis, as a potential model for affective computing. This gives the novel advantage among affective computing methods of being able to apply grey incidence analysis, which returns important contributing factors to a given sequence. Grey modelling is applied to a novel affective dataset, collected using behavioural and mood data from 7 different participants. Grey incidence analysis is performed on this dataset using two different mood sequences (a series of emotion categories, and a series of valence values) alongside the behavioural factors. This gives each participant in the dataset a unique set of contributing behavioural factors to their mood, with the sequence of valence values providing better overall system performance. These unique contributing behavioural factors are compared to two other methods of measuring similarity; three correlation measures (including two non-parametric), and two spatial distance measures (cosine and Euclidean distance). This comparison proves grey incidence analysis capable of finding contributing factors where correlations and spatial distance measures are unable to, including with flag-type data used to represent missing values. This thesis is successful in proving grey systems modelling, and grey incidence analysis, can be applied to affective data and that useful insights into the contributing factors to a person's mood can be extracted. The next step from this research would be creating \"behavioural prescriptions\", where a person could be told to modify their contributing behaviours to have a positive effect on their mood. It was found in this thesis that this is not currently possible, given the lack of directionality in grey incidence analysis' degrees of incidence, however this is an avenue for further research."],"dc:format.checksum.md5":["9ec966657d7bba71c352701591a067b1","bd41181d9a4c38b5ebacc69a027024d9","f56a62951124d7c6da3cb59bbbf22f89"],"dc:identifier.uri":["https://dora.dmu.ac.uk/bitstreams/4cbd5314-1ee5-448d-982a-ec6173b4aad6/download"],"dc:publisher.department":["Faculty of Computing, Engineering and Media"],"dc:publisher.institution":["De Montfort University"],"dc:relation.isreferencedby":["https://hdl.handle.net/2086/24507"],"dc:rights":["https://dora.dmu.ac.uk/bitstreams/fe0558c6-2caf-428a-8f59-3a5c46c0cd5a/download"],"dc:title":["An Analysis of Grey Theory for Personal Affective Computing"],"dc:type":["Thesis or dissertation"],"dc:type.qualificationlevel":["Doctoral"],"dc:type.qualificationname":["PhD"]},"updated_at":"2026-07-24T06:18:47Z"}