Human-Perception-Aligned Machine Learning for Indoor-Outdoor Classification
Mahfoud, D.; Tang, Z.; Najjar, R. P.
Show abstract
Daylight is vital for eye, brain, and overall health, yet misperceptions of what constitutes true outdoor daylight exposure can lead to poor behavioural choices and weaken public health recommendations. We developed InNOut, a perception-aligned machine learning model trained on 73,879 minutes of multispectral light data to classify environments as indoor or outdoor, and benchmarked against public (n = 383) and expert (n = 17) judgments across 183 scenes. InNOut achieved excellent performance (AUC = 0.92 [95% CI, 0.92-0.93], sensitivity 73.9%, specificity 94.5%), closely aligning with expert (83.5%) and public (80.8%) judgments. Clear outdoor and indoor scenes were reliably classified, whereas ambiguous settings (e.g., windowed rooms, vehicles) were often judged indoor by participants but outdoor by the model, consistent with their spectral light profiles. InNOut bridges perception and measurement, offering a scalable means to map light environments and inform digital interventions in medicine and public health.
Matching journals
The top 6 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Spectral dependency of the human pupillary light reflex. Influences of pre-adaptation and chronotype. 93%
- Methodological issues in visible LED therapy dermatological research and reporting 93%
- Abrupt light transitions in illuminance and CCT result in different temporal dynamics and interindividual variability for sensation, comfort and alertness 92%
Similar papers in this journal
- Macroscopic waves, biological clocks and morphogenesis driven by light in a giant unicellular green alga 90%
- Novel subthreshold retinal laser treatment with ERG-based thermal dosimetry activates hormetic heat response in pig RPE in vivo 89%
- SARS-CoV-2 and other respiratory pathogens are detected in continuous air samples from congregate settings 89%
Similar papers in this journal
Similar papers in this journal
- Classification of daily crop phenology in PhenoCams using deep learning and hidden markov models 90%
- A satellite-based spatio-temporal machine learning model to reconstruct daily PM2.5 concentrations across Great Britain 89%
- Individual tree-crown detection in RGB imagery using semi-supervised deep learning neural networks 87%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.