The Impact of Domain Shift on Predicting Perceived Sleep Quality from Wearables
Machine learning models for personal informatics systems are typically trained offline on <i>records of a specific population of users</i>, resulting in <i>population models.</i> These models may suffer performance degradation in real-world settings due to <i>domain shi...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-06-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/25/13/4012 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850115430801211392 |
|---|---|
| author | Nouran Abdalazim Leonardo Alchieri Lidia Alecci Pietro Barbiero Silvia Santini |
| author_facet | Nouran Abdalazim Leonardo Alchieri Lidia Alecci Pietro Barbiero Silvia Santini |
| author_sort | Nouran Abdalazim |
| collection | DOAJ |
| description | Machine learning models for personal informatics systems are typically trained offline on <i>records of a specific population of users</i>, resulting in <i>population models.</i> These models may suffer performance degradation in real-world settings due to <i>domain shift</i>, i.e., differences in data distributions across users and contexts. Domain adaptation techniques can address this <i>issue</i> by, <i>e.g.,</i> personalizing models with user-specific data. <i>In this paper, we quantify the impact of domain shift</i> on <i>the performance</i> of both population and personalized models <i>in a specific scenario:</i> sleep quality recognition. <i>To this end, we also collect and make available to the research community the new BiheartS dataset</i>. Our analysis shows <i>that</i> domain shift <i>causes the</i> accuracy of population models <i>to decrease</i> by up to 18.54 percentage points, when <i>used</i> on <i>new data</i>. Personalized models, <i>instead</i>, show robust performance across datasets. However, <i>crafting personalized models typically requires using new data or user-provided labels</i>, limiting their <i>applicability in real settings</i>. To <i>mitigate</i> the limitations <i>of both population and personalized models</i>, we propose a novel unsupervised domain adaptation approach: the cluster-based population model (CBPM). CBPM achieves accuracy improvements of up to 13.45 percentage points <i>w.r.t. population model</i> without requiring <i>the use of</i> user-specific records or <i>labels</i>. |
| format | Article |
| id | doaj-art-b6e9d8bdf8634788bbde93bfbb899b57 |
| institution | OA Journals |
| issn | 1424-8220 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj-art-b6e9d8bdf8634788bbde93bfbb899b572025-08-20T02:36:34ZengMDPI AGSensors1424-82202025-06-012513401210.3390/s25134012The Impact of Domain Shift on Predicting Perceived Sleep Quality from WearablesNouran Abdalazim0Leonardo Alchieri1Lidia Alecci2Pietro Barbiero3Silvia Santini4Faculty of Informatics, Università della Svizzera Italiana, 6900 Lugano, SwitzerlandFaculty of Informatics, Università della Svizzera Italiana, 6900 Lugano, SwitzerlandFaculty of Informatics, Università della Svizzera Italiana, 6900 Lugano, SwitzerlandFaculty of Informatics, Università della Svizzera Italiana, 6900 Lugano, SwitzerlandFaculty of Informatics, Università della Svizzera Italiana, 6900 Lugano, SwitzerlandMachine learning models for personal informatics systems are typically trained offline on <i>records of a specific population of users</i>, resulting in <i>population models.</i> These models may suffer performance degradation in real-world settings due to <i>domain shift</i>, i.e., differences in data distributions across users and contexts. Domain adaptation techniques can address this <i>issue</i> by, <i>e.g.,</i> personalizing models with user-specific data. <i>In this paper, we quantify the impact of domain shift</i> on <i>the performance</i> of both population and personalized models <i>in a specific scenario:</i> sleep quality recognition. <i>To this end, we also collect and make available to the research community the new BiheartS dataset</i>. Our analysis shows <i>that</i> domain shift <i>causes the</i> accuracy of population models <i>to decrease</i> by up to 18.54 percentage points, when <i>used</i> on <i>new data</i>. Personalized models, <i>instead</i>, show robust performance across datasets. However, <i>crafting personalized models typically requires using new data or user-provided labels</i>, limiting their <i>applicability in real settings</i>. To <i>mitigate</i> the limitations <i>of both population and personalized models</i>, we propose a novel unsupervised domain adaptation approach: the cluster-based population model (CBPM). CBPM achieves accuracy improvements of up to 13.45 percentage points <i>w.r.t. population model</i> without requiring <i>the use of</i> user-specific records or <i>labels</i>.https://www.mdpi.com/1424-8220/25/13/4012personal informatics systemssleep behaviour monitoringsleep quality recognitiondataset biasdomain shiftcovariate shift |
| spellingShingle | Nouran Abdalazim Leonardo Alchieri Lidia Alecci Pietro Barbiero Silvia Santini The Impact of Domain Shift on Predicting Perceived Sleep Quality from Wearables Sensors personal informatics systems sleep behaviour monitoring sleep quality recognition dataset bias domain shift covariate shift |
| title | The Impact of Domain Shift on Predicting Perceived Sleep Quality from Wearables |
| title_full | The Impact of Domain Shift on Predicting Perceived Sleep Quality from Wearables |
| title_fullStr | The Impact of Domain Shift on Predicting Perceived Sleep Quality from Wearables |
| title_full_unstemmed | The Impact of Domain Shift on Predicting Perceived Sleep Quality from Wearables |
| title_short | The Impact of Domain Shift on Predicting Perceived Sleep Quality from Wearables |
| title_sort | impact of domain shift on predicting perceived sleep quality from wearables |
| topic | personal informatics systems sleep behaviour monitoring sleep quality recognition dataset bias domain shift covariate shift |
| url | https://www.mdpi.com/1424-8220/25/13/4012 |
| work_keys_str_mv | AT nouranabdalazim theimpactofdomainshiftonpredictingperceivedsleepqualityfromwearables AT leonardoalchieri theimpactofdomainshiftonpredictingperceivedsleepqualityfromwearables AT lidiaalecci theimpactofdomainshiftonpredictingperceivedsleepqualityfromwearables AT pietrobarbiero theimpactofdomainshiftonpredictingperceivedsleepqualityfromwearables AT silviasantini theimpactofdomainshiftonpredictingperceivedsleepqualityfromwearables AT nouranabdalazim impactofdomainshiftonpredictingperceivedsleepqualityfromwearables AT leonardoalchieri impactofdomainshiftonpredictingperceivedsleepqualityfromwearables AT lidiaalecci impactofdomainshiftonpredictingperceivedsleepqualityfromwearables AT pietrobarbiero impactofdomainshiftonpredictingperceivedsleepqualityfromwearables AT silviasantini impactofdomainshiftonpredictingperceivedsleepqualityfromwearables |