# Modified TSception for Analyzing Driver Drowsiness and Mental Workload from EEG

arXiv: https://arxiv.org/abs/2512.21747 · HTML: https://mlsanity.com/paper/2512.21747/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 34 references that are in the map.
- First posted on arXiv 25 Dec 2025.

## Builds on (most cited first, 9 of 9)

- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [EEGNet: A Compact Convolutional Network for EEG-based Brain-Computer Interfaces](https://mlsanity.com/paper/1611.08024/) (2016)
- [Deep learning-based electroencephalography analysis: a systematic review](https://mlsanity.com/paper/1901.05498/) (2019)
- [TSception: Capturing Temporal Dynamics and Spatial Asymmetry from EEG for Emotion Recognition](https://mlsanity.com/paper/2104.02935/) (2021)
- [A Multimodal Approach to Estimating Vigilance Using EEG and Forehead EOG](https://mlsanity.com/paper/1611.08492/) (2016)
- [A Compact and Interpretable Convolutional Neural Network for Cross-Subject Driver Drowsiness Detection from Single-Channel EEG](https://mlsanity.com/paper/2106.00613/) (2021)
- [Efficacy of Transformer Networks for Classification of Raw EEG Data](https://mlsanity.com/paper/2202.05170/) (2022)
- [Enhancing EEG Signal-Based Emotion Recognition with Synthetic Data: Diffusion Model Approach](https://mlsanity.com/paper/2401.16878/) (2024)
- [Challenges of Driver Drowsiness Prediction: The Remaining Steps to Implementation](https://mlsanity.com/paper/2109.08355/) (2021)

## Built on by (most cited first, 1 of 1)

- [Bidirectional Temporal Dynamics Modeling for EEG-based Driving Fatigue Recognition](https://mlsanity.com/paper/2602.14071/) (2026)

## Abstract (arXiv)

Driver drowsiness is a leading cause of traffic accidents, necessitating real-time, reliable detection systems to ensure road safety. This study proposes a Modified TSception architecture for robust assessment of driver fatigue and mental workload using Electroencephalography (EEG). The model introduces a five-layer hierarchical temporal refinement strategy to capture multi-scale brain dynamics, surpassing the original TSception's three-layer approach. Key innovations include the use of Adaptive Average Pooling (ADP) for structural flexibility across varying EEG dimensions and a two-stage fusion mechanism to optimize spatiotemporal feature integration for improved stability. Evaluated on the SEED-VIG dataset, the Modified TSception achieves 83.46% accuracy, comparable to the original model (83.15%), but with a significantly reduced confidence interval (0.24 vs. 0.36), indicating better performance stability. The architecture's generalizability was further validated on the STEW mental workload dataset, achieving state-of-the-art accuracies of 95.93% and 95.35% for 2-class and 3-class classification, respectively. These results show that the proposed modifications improve consistency and cross-task generalizability, making the model a reliable framework for EEG-based safety monitoring.