# MultiMental-IAS: A Multimodal Driver Mental State Analysis Dataset for Context-Aware Non-IID Evaluation

DevFeed: [MultiMental-IAS: A Multimodal Driver Mental State Analysis Dataset for Context-Aware Non-IID Evaluation](<https://devfeed.tech/articles/multimental-ias-a-multimodal-driver-mental-state-analysis-dataset-for-context-aware-non-iid-evaluation-115375.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.02790>)

Author: Baran Can G\\"ul, Nagendra Pal Singh, Anjana Arvind Naik

Published: 2026-11-03T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Dataset development](<https://devfeed.tech/topics/dataset-development.md>), [scikit-learn](<https://devfeed.tech/topics/scikit-learn.md>), [AI-Ready Data](<https://devfeed.tech/topics/ai-ready-data.md>), [benchmark overfitting machine learning](<https://devfeed.tech/topics/benchmark-overfitting-machine-learning.md>)

Tags: [acquisition](<https://devfeed.tech/tags/acquisition.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-hc](<https://devfeed.tech/tags/cs-hc.md>), [dataset](<https://devfeed.tech/tags/dataset.md>), [driver](<https://devfeed.tech/tags/driver.md>), [driving](<https://devfeed.tech/tags/driving.md>), [eeg](<https://devfeed.tech/tags/eeg.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [federated](<https://devfeed.tech/tags/federated.md>), [federated-learning](<https://devfeed.tech/tags/federated-learning.md>), [fusion](<https://devfeed.tech/tags/fusion.md>), [monitoring](<https://devfeed.tech/tags/monitoring.md>), [multimodal](<https://devfeed.tech/tags/multimodal.md>), [personalization](<https://devfeed.tech/tags/personalization.md>), [simulation](<https://devfeed.tech/tags/simulation.md>), [state](<https://devfeed.tech/tags/state.md>), [telemetry](<https://devfeed.tech/tags/telemetry.md>), [testbed](<https://devfeed.tech/tags/testbed.md>), [training](<https://devfeed.tech/tags/training.md>), [validation](<https://devfeed.tech/tags/validation.md>), [video](<https://devfeed.tech/tags/video.md>)

## AI overview

Multimental-IAS is a CARLA cockpit simulation dataset for studying driver mental states and cross-driver generalization. It combines vehicle telemetry and scenario context, four-channel EEG and three-channel PPG from a Muse 2 headband, and cabin-facing video from 23 participants across 148 trials (11.6 hours) and six induced states. Its benchmark uses chronological within-subject splits, participant-disjoint cross-subject folds, validation-based model selection, and modality, context, and normalization ablations. Multimodal fusion achieves macro-F1 0.94 for drivers seen in training. For unseen drivers, driving dynamics fused with per-window normalized EEG/PPG reaches 0.485 versus 0.408 for telemetry alone, consistently across five folds. The authors present the performance gap between protocols as evidence of inter-driver heterogeneity relevant to personalization and federated learning.

## Source excerpt

arXiv:2611.02790v1 Announce Type: cross Abstract: Robust driver-state modelling requires synchronized physiological, behavioural, and contextual signals, yet existing open resources typically target a single cognitive state, omit continuous vehicle context, or do not define evaluation protocols that expose inter-subject heterogeneity. We present Multimental-IAS, a multimodal driver mental-state dataset collected in a cockpit-in-the-loop simulation built on CARLA. It contains vehicle telemetry with scenario-context channels, four-channel EEG and three-channel PPG from a Muse 2 headband, and cabin-facing video from 23 participants, recorded in 148 trials (11.6 hours) under six induced states: Normal, Distracted, Alerted, Stressed, Relaxed, and Drowsy. We document the acquisition pipeline in detail and provide a benchmark with one protocol for all models: chronological within-subject splits, participant-disjoint cross-subject folds, validation-based model selection, and ablations over modalities, scenario-context channels, and signal normalization. Multimodal fusion reaches a macro-F1 of 0.94 for drivers seen during training. For unseen drivers, fusing driving dynamics with per-window normalized EEG/PPG raises macro-F1 from 0.408 (telemetry alone) to 0.485, consistently across all five folds, while the gap between the two protocols quantifies the inter-driver heterogeneity that personalized models must address. Multimental-IAS thus provides a concrete testbed for non-IID generalization, personalization, and federated learning in driver monitoring.