MétaCan
Menu
Back to cohort
Record W4405113355 · doi:10.1016/j.procs.2024.11.119

SereniSens: a Multimodal AI Framework with LLMs for Stress Prediction through Sleep Biometrics

2024· article· en· W4405113355 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

VenueProcedia Computer Science · 2024
Typearticle
Languageen
FieldComputer Science
TopicContext-Aware Activity Recognition Systems
Canadian institutionsUniversité du Québec à Rimouski
Fundersnot available
KeywordsComputer scienceBiometricsStress (linguistics)Sleep (system call)Speech recognitionArtificial intelligenceOperating system

Abstract

fetched live from OpenAlex

Stress is a physiological and psychological response to threatening, challenging, or demanding situations. It can have profound effects on both mental and physical health such as anxiety and depression. Thus, managing stress levels in mental healthcare is crucial for maintaining overall well-being. In this work, we introduce SereniSens, a multimodal AI framework with conversational agent integration to predict stress levels during sleep using physiological data. We evaluated the performance of four machine learning models - Decision Tree, Support Vector Machines, Multilayer Perceptron, and XGBoost - on the SaYoPillow dataset containing physiological signals recorded during sleep. Our models achieve high accuracy in predicting fve stress levels, with SVM obtaining 99.37% accuracy, outperforming previous implementations. We also propose an architecture integrating these predictive models with a Large Language Model to create a context-aware chatbot for stress monitoring and management. This framework demonstrates the potential of AI in mental healthcare, particularly for personalized stress assessment and intervention.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow), Scholarly communication
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.983
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0010.007
Science and technology studies0.0000.000
Scholarly communication0.0020.004
Open science0.0020.001
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.023
GPT teacher head0.286
Teacher spread0.263 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it