AI Science Tracker
EN

Università Politecnica delle Marche

2 discoveries from 2023 to 2026

Discoveries

Machine learning relates personal and environmental measurements to thermal-comfort votes

Source check: Source checked. Not independent scientific confirmation.

Finding: Participants’ comfort votes were compared with measurements collected under controlled temperature conditions using leave-one-subject-out evaluation. Transfer to other populations, buildings or uncontrolled settings and improved comfort from using the models are not established.

Technology: Machine-learning models related environmental and physiological sensor measurements and personal characteristics to participants’ thermal-comfort votes.

Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.

AI contribution
Machine-learning models related environmental and physiological sensor measurements and personal characteristics to participants’ thermal-comfort votes.
Test and result
Participants’ comfort votes were compared with measurements collected under controlled temperature conditions using leave-one-subject-out evaluation.
Limitation / still unknown
Transfer to other populations, buildings or uncontrolled settings and improved comfort from using the models are not established.
Evidence sources and annotation context

Evidence context (descriptions follow the cited sources; test type is a catalog classification):

Evidence sources: https://pmc.ncbi.nlm.nih.gov/articles/PMC13766517/

Source checked · editorial details

The source page was checked against this entry. Independent confirmation is not assessed by this label.

Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.

Review date: 22 Nov 2026. Review scope: Primary result-bearing material for the stated method, result and evaluation, with bibliographic version information..

No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.

Editorial assessment: Impact 2/5 · Validation 2/5 · Novelty 2/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.

A Method for Stress Detection Using Empatica E4 Bracelet and Machine-Learning Techniques.

Source check: Source checked. Not independent scientific confirmation.

Finding: Random-forest classification of Empatica E4-derived PPG/EDA features distinguished induced stress-task from rest segments in 29 laboratory participants, with reported accuracy of 76.5%. Random segment-level cross-validation was not subject-independent, so the result is preliminary and does not establish real-world stress detection. External replication and prospective utility were not established in the reviewed material.

Technology: Random forest, SVM and logistic regression classify features from Empatica E4 PPG and electrodermal signals.

Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.

AI contribution
Random forest, SVM and logistic regression classify features from Empatica E4 PPG and electrodermal signals.
Test and result
Random-forest classification of Empatica E4-derived PPG/EDA features distinguished induced stress-task from rest segments in 29 laboratory participants, with reported accuracy of 76.5%. Random segment-level cross-validation was not subject-independent, so the result is preliminary and does not establish real-world stress detection.
Limitation / still unknown
External replication, causal effects and prospective utility were not established in the reviewed material.
Evidence sources and annotation context

Evidence context (descriptions follow the cited sources; test type is a catalog classification):

Evidence sources: https://doi.org/10.3390/s23073565

Source checked · editorial details

The source page was checked against this entry. Independent confirmation is not assessed by this label.

Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.

Review date: 22 Nov 2026. Review scope: Primary result-bearing material for the stated method, result and evaluation, with bibliographic version information..

No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.

Editorial assessment: Impact 2/5 · Validation 2/5 · Novelty 2/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.

Open the interactive profile for the timeline, or browse all organizations and model families.