Wearable Sleep Computing

=== Funded by JSPS KAKENHI ===

Objective

To develop automatic sleep apnea detection models for wearable devices that can be used at home.

Method

Machine learning + chaos theory.

Contributors

Nhung Hoang, Hannah Jayen (intern from WPI), Alena Lukovnikova (intern from WPI)  

Selected Publications

• [Q1] ​ Liang Z. (2024) Developing Probabilistic Ensemble Machine Learning Models for Home-Based Sleep Apnea Screening using Overnight SpO2 Data at Varying Data Granularity. Sleep and Breathing.  Doi: 10.1007/s11325-024-03141-x. [SCI/Scopus/PubMed] 

• [Q1] ​​Nhung, H. H., Liang Z. (2023) Knowledge discovery in ubiquitous and personal sleep-tracking: a scoping review. JMIR mHealth and uHealth 11:e42750 [PubMed/SCI/Scopus]

• Hoang HN, Liang Z. (2024) Apnea hypopnea index estimation from low-granularity overnight oxymetry data. In Proceedings of the 17th International Conference on Health Informatics (HEALTHINF 2024), Rome, Italy.  [Scopus]

• Nhung H. H., Liang Z. (2023) Contrast set mining for actionable insights into associations between sleep and glucose in a normoglycemic population. In Proceedings of the 16th International Conference on Health Informatics (HEALTHINF 2023), Lisbon, Portugal. [SCI/Scopus]  

• Jayen H, Lukovnikova A, Nhung HH, Liang Z. (2023) Mining Contrast Rules in a Sleep Apnea Dataset. In Proceedings of the 2023 IEEE 12th Global Conference on Consumer Electronics (GCCE 2023), Nara, Japan. [Scopus] 

=== Funded by JSPS KAKENHI ===

Objective

To develop new sleep staging algorithms that achieves better accuracy with Fitbit processed physiological signals.

Method

Two-stage classification with cascading machine learning.

Contributors

• Dr. Zilu Liang

• Dr. Mario Alberto Chapa-Martell (Silver Egg Technology, Japan)

Selected Publications

• Liang Z, Chapa-Martell MA. (2021) A Multi-level Classification Approach for Sleep Stage Prediction with Processed Data Derived from Consumer Wearable Activity Trackers. Frontiers in Digital Health (Section: Machine Learning and Wearable Technology in Sleep Medicine).

• Liang Z. (2021) Not just a matter of accuracy: a fNIRS pilot study into discrepancy between sleep data and subjective sleep experience in quantified-self sleep tracking. In Proceedings of the 8th EAI International Conference on IoT Technologies for HealthCare (HealthyIoT 2021), Cyberspace. 

• Liang Z, Chapa-Martell MA. (2019) Achieving accurate ubiquitous sleep sensing with consumer wearable activity wristbands using multi-class imbalanced classification. In Proceedings of IEEE Int Conf on Pervasive Intelligence and Computing (PICOM '19). p.768-775, Fukuoka, Japan. [SCI/Scopus] 

• Liang Z, Chapa-Martell MA. (2019) Combining resampling and machine learning to improve sleep-wake detection of Fitbit wristbands. In Proceedings of IEEE Int Conf on Healthcare Informatics (ICHI '19). Xi'an, China.  [Scopus] 

• Liang Z, Chapa-Martell MA. (2019) Accuracy of Fitbit wristbands in measuring sleep stage transitions and the effect of user-specific factors. JMIR mHealth and uHealth 7(6):e13384, DOI:10.2196/13384. 【Highly cited / web of Science 94th percentile in 2019 (top 6%) 】

• Liang Z, Chapa-Martell MA. (2019) Combining numerical and visual approaches in validating sleep data quality of consumer wearable wristbands. In Proceedings of IEEE PerCom Workshops (IQ2S Workshop), p.777-782, Kyoto, Japan.  [SCI/Scopus] 

• Liang Z, Chapa-Martell MA. (2019) Not all errors are created equal: influence of user characteristics on measuring errors of consumer wearable devices for sleep tracking. EAI Endorsed Transactions on Pervasive Health and Technology 18(15):e4. 

• Liang Z, Chapa-Martell MA. (2018) Validity of consumer activity wristbands and wearable EEG for measuring overall sleep parameters and sleep structure in free-living conditions. Journal of Healthcare Informatics Research 2 (1-2): 152-178.【Highly cited / Web of Science 91th percentile in 2018 (top 9%)】

• Liang Z, Chapa-Martell MA. (2017) Are wearable EEG devices more accurate than fitness wristbands for home sleep tracking? Comparison of consumer sleep trackers with clinical devices. IEEE 6th Global Conference on Consumer Electronics (GCCE 2017), Nagoya, Japan. [SCI/Scopus] 

• Liang Z, Chapa-Martell MA. (2017) Considering interpersonal differences in validating wearable sleep-tracking technologies. The 10th International Conference on Mobile Computing and Ubiquitous Networking, Toyama, Japan. [SCI/Scopus] 

=== Funded by JSPS KAKENHI ===

Objective

To develop new sleep staging algorithms that achieves better accuracy with Apple Watch processed physiological signals.

Method

Machine learning.

Contributors

Ms. Pataranit Sirithummarak

Selected Publications

• Sirithummarak P, Liang Z. (2021) Investigating the effect of feature distribution shift on the performance of sleep stage classification with consumer sleep trackers. In Proceedings of the IEEE 10th Global Conference on Consumer Electronics (GCCE 2021), Kyoto, Japan.