Semi-Supervised Learning and Data Augmentation in Wearable-based Momentary Stress Detection in the Wild

Han, Yu; Sano, Akane

doi:10.48550/arxiv.2202.12935

Cited by 2 publications

(2 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, caregivers needed to label moments of stress and relaxation during the reference period (first month of use) to train a personalized stress detection model. The number of labels given by caregivers could be limited and placed at the wrong moment in time, whereas unlabelled data collection is enormous [51]. Moreover, during moments of escalation, the caregiver was occupied with mitigating the situation rather than labelling the stress.…”

Section: Study Limitationsmentioning

confidence: 99%

Effect of stress-based interventions on the quality of life of people with an intellectual disability and their caregivers

Hesselmans,

Meiland,

Adam

et al. 2023

Disability and Rehabilitation: Assistive Technology

View full text Add to dashboard Cite

Purpose: People with intellectual disabilities often show challenging behaviour, which can manifest itself in self-harm or aggression towards others. Real-time monitoring of stress in clients with challenging behaviour can help caregivers to promptly deploy interventions to prevent escalations, ultimately to improve the quality of life of client and caregiver. This study aimed to assess the impact of real-time stress monitoring with HUME, and the subsequent interventions deployed by the care team, on stress levels and quality of life. Materials and methods: Real-time stress monitoring was used in 41 clients with intellectual disabilities in a long-term care setting over a period of six months. Stress levels were determined at the start and during the deployment of the stress monitoring system. The quality of life of the client and caregiver was measured with the Outcome Rating Scale at the start and at three months of use. Results:The results showed that the HUME-based interventions resulted in a stress reduction. The perceived quality of life was higher after three months for both the clients and caregivers. Furthermore, interventions to provide proximity were found to be most effective in reducing stress and increasing the client's quality of life. Conclusions:The study demonstrates that real-time stress monitoring with the HUME and the following interventions were effective. There was less stress in clients with an intellectual disability and an increase in the perceived quality of life. Future larger and randomized controlled studies are needed to confirm these findings. h IMPLICATIONS FOR REHABILITATION• Assistive technology such as real-time stress monitoring enables caregivers to timely intervene and contributes to the reduction of challenging behaviour. • Real-time stress monitoring contributes to the quality of life of clients and caregivers in healthcare.• There is a reduction in the levels of stress of people with an intellectual disability by using stress-monitoring technology. Challenging behaviourPeople with an intellectual disability have deficits in cognitive abilities, such as reasoning, problem-solving, learning, and understanding. These limitations can significantly affect individuals' daily

show abstract

Section: Study Limitationsmentioning

confidence: 99%

Effect of stress-based interventions on the quality of life of people with an intellectual disability and their caregivers

Hesselmans,

Meiland,

Adam

et al. 2023

Disability and Rehabilitation: Assistive Technology

View full text Add to dashboard Cite

show abstract

“…In addition to physical health, deep models have also been used for mental health. Yu and Sano [3] applied semi-supervised learning on leveraging unlabeled data to estimate wearablebased momentary stress. Radhika et al [4], [5] proposed the frameworks that investigate the effectiveness of transfer This work is supported by NSF #2047296 and #1840167.…”

Section: Introductionmentioning

confidence: 99%

PiRL: Participant-Invariant Representation Learning for Healthcare Using Maximum Mean Discrepancy and Triplet Loss

Cao¹,

Han²,

Hu³

et al. 2023

Preprint

View full text Add to dashboard Cite

Due to individual heterogeneity, person-specific models are usually achieving better performance than generic (one-size-fits-all) models in data-driven health applications. However, generic models are usually preferable in real-world applications, due to the difficulties of developing person-specific models, such as new-user-adaptation issues and system complexities. To improve the performance of generic models, we propose a Participant-invariant Representation Learning (PiRL) framework, which utilizes maximum mean discrepancy (MMD) loss and domain-adversarial training to encourage the model to learn participant-invariant representations. Further, to avoid trivial solutions in the learned representations, a triplet loss based constraint is used for the model to learn the label-distinguishable embeddings. The proposed framework is evaluated on two public datasets (CLAS and Apnea-ECG), and significant performance improvements are achieved compared to the baseline models.

show abstract

Semi-Supervised Learning and Data Augmentation in Wearable-based Momentary Stress Detection in the Wild

Cited by 2 publications

References 38 publications

Effect of stress-based interventions on the quality of life of people with an intellectual disability and their caregivers

Effect of stress-based interventions on the quality of life of people with an intellectual disability and their caregivers

PiRL: Participant-Invariant Representation Learning for Healthcare Using Maximum Mean Discrepancy and Triplet Loss

Contact Info

Product

Resources

About