{"slug": "tempest-temporal-embeddings-for-scalable-driver-identification-via-angular", "title": "TEMPEST: Temporal Embeddings for Scalable Driver Identification via Angular Margin Learning", "summary": "Researchers introduced TEMPEST, a Temporal Convolutional Network embedding model trained with an additive angular margin (ArcFace) loss that maps 60-second multimodal driving windows to 96-dimensional embeddings for scalable driver identification without retraining. On a 45-driver dataset under rigorous temporal evaluation, TEMPEST reached 91.71% Rank-1 accuracy, beating the best classical model by 17.9 percentage points and the strongest triplet-loss baseline by 58.4 percentage points, and it degraded only 4.3 percentage points when the subject pool grew from 10 to 45 drivers versus 22 and 32.5 points for supervised and unsupervised triplet-loss baselines. The model has 720K parameters, a 2.80 MB footprint, and 50-epoch convergence, and on the public KIA Soul dataset it outperformed the best classical model by 7.3 percentage points within-session and 14.3 percentage points cross-session.", "body_md": "arXiv:2610.06855v1 Announce Type: new \nAbstract: Scalable driver identification requires embedding models that maintain discriminative performance as fleet size grows, yet existing triplet-loss formulations degrade rapidly with driver pool size and overfit to session-specific patterns under rigorous temporal evaluation. We introduce TEMPEST, a Temporal Convolutional Network embedding model trained with an additive angular margin (ArcFace) loss that enforces global class-level separation in a normalized angular space. TEMPEST maps 60-second multimodal driving windows to compact 96-dimensional embeddings, supporting truly dynamic enrollment without any retraining or classifier refitting. Under rigorous temporal evaluation on a 45-driver dataset, TEMPEST achieves 91.71% Rank-1 accuracy, outperforming the best classical model by 17.9 pp and the strongest triplet-loss baseline by 58.4 pp. TEMPEST degrades by only 4.3 pp when growing the subject pool from 10 to 45 drivers, compared to 22 pp and 32.5 pp for supervised and unsupervised triplet-loss baselines, and its cross-session advantage is corroborated on the public KIA Soul dataset, where it outperforms the best classical model by 7.3 pp within-session and 14.3 pp cross-session. With 720K parameters, a 2.80 MB footprint, and 50-epoch convergence, TEMPEST establishes a rigorous, reproducible baseline for scalable behavioral driver biometric identification.", "url": "https://wpnews.pro/news/tempest-temporal-embeddings-for-scalable-driver-identification-via-angular", "canonical_source": "https://arxiv.org/abs/2610.06855", "published_at": "2026-10-07 04:00:00+00:00", "updated_at": "2026-10-07 04:16:34.315133+00:00", "lang": "en", "topics": ["machine-learning", "ai-research", "neural-networks"], "entities": ["TEMPEST", "ArcFace", "Temporal Convolutional Network", "KIA Soul"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/tempest-temporal-embeddings-for-scalable-driver-identification-via-angular", "markdown": "https://wpnews.pro/news/tempest-temporal-embeddings-for-scalable-driver-identification-via-angular.md", "text": "https://wpnews.pro/news/tempest-temporal-embeddings-for-scalable-driver-identification-via-angular.txt", "jsonld": "https://wpnews.pro/news/tempest-temporal-embeddings-for-scalable-driver-identification-via-angular.jsonld"}}