2026-09-19T07:29:01Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/1554832024-07-09T04:02:37Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023
Hu, Tony
Jacobs Luengo, Daniel Alberto
System Design and Management Program.
2024-07-08T18:54:17Z
2024-07-08T18:54:17Z
2024-05
2024-06-11T19:47:01.052Z
https://hdl.handle.net/1721.1/155483
Insomnia—difficulty in initiating and maintaining sleep—affects a significant portion of the global population. The mainstream adoption of wearable computing presents a unique opportunity to study and aid sleep at an individual level. Here we introduce Zzzonic, a smart sleep-aid application designed for smartwatches that leverages cognitive psychology and human-computerinteraction (HCI) to facilitate sleep onset by engaging users in audio tasks as a formof intrusive thought control. A significant aspect of Zzzonic's functionality is its adaptive control system, which estimates sleep onset latency in realtime by monitoring indicators such as motion anduser response. The system then progressively modifies the characteristics of the audio tasks to minimize sleep onset latency. This thesis evaluates Zzzonic through a series of user trials conducted throughout the development of the app, accessing the capacity to predict and control sleep onset. The results indicate accurately predicting sleep onset latency in realtime as a control signal is possible but there was no evidence indicating the system could minimize slope onset latency. The inclusion of more indicator signals and machine learning techniques is likely to significantly improve realtime sleep onset latency prediction. Future work on computer-modulated intrusive thought control would benefit from the evaluation of task design, intrusive thought indicators and identifying an adequate control framework.
S.M.
Massachusetts Institute of Technology
In Copyright - Educational Use Permitted
Copyright retained by author(s)
https://rightsstatements.org/page/InC-EDU/1.0/
Harnessing Intelligent Audio-Gesture Interfaces For Wearables As A Sleep Aid
Thesis
application/pdf
Master
Master of Science in Engineering and Management
Publication
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="0d85a49f-e4df-41f1-a09c-a0ef038acb5a">
<Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type>
<Title>Harnessing Intelligent Audio-Gesture Interfaces For Wearables As A Sleep Aid</Title>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2024-05</PublicationDate>
<Authors>
<Author>
<DisplayName>Jacobs Luengo, Daniel Alberto</DisplayName>
<Affiliation>
<OrgUnit>
</OrgUnit>
</Affiliation>
</Author>
</Authors>
<Editors>
</Editors>
<Publishers>
<Publisher>
<DisplayName>Massachusetts Institute of Technology</DisplayName>
<OrgUnit />
</Publisher>
</Publishers>
<License>https://rightsstatements.org/page/InC-EDU/1.0/</License>
<Abstract>Insomnia—difficulty in initiating and maintaining sleep—affects a significant portion of the global population. The mainstream adoption of wearable computing presents a unique opportunity to study and aid sleep at an individual level. Here we introduce Zzzonic, a smart sleep-aid application designed for smartwatches that leverages cognitive psychology and human-computerinteraction (HCI) to facilitate sleep onset by engaging users in audio tasks as a formof intrusive thought control. A significant aspect of Zzzonic's functionality is its adaptive control system, which estimates sleep onset latency in realtime by monitoring indicators such as motion anduser response. The system then progressively modifies the characteristics of the audio tasks to minimize sleep onset latency. This thesis evaluates Zzzonic through a series of user trials conducted throughout the development of the app, accessing the capacity to predict and control sleep onset. The results indicate accurately predicting sleep onset latency in realtime as a control signal is possible but there was no evidence indicating the system could minimize slope onset latency. The inclusion of more indicator signals and machine learning techniques is likely to significantly improve realtime sleep onset latency prediction. Future work on computer-modulated intrusive thought control would benefit from the evaluation of task design, intrusive thought indicators and identifying an adequate control framework.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>