Journal
IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE
Volume 5, Issue 4, Pages 583-594Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TETCI.2020.2997031
Keywords
Electroencephalography; Safety; Reinforcement learning; Fatigue; Brain modeling; Automobiles; Brain-computer interface (BCI); deep Q-learning; driving safety; electroencephalogram (EEG); reinforcement learning
Categories
Funding
- Australian Research Council (ARC) [DP180100670, DP180100656]
- Australia Defence Innovation Hub [P18-650825]
- US Office of Naval Research Global [ONRG -NICOP -N62909-19-1-2058]
- NSW Defence Innovation Network [DINPP2019 S1-03/09]
- NSW State Government of Australia [DINPP2019 S1-03/09]
Ask authors/readers for more resources
This paper proposes using deep Q-learning to study the correlation between drowsiness and driving performance, based on analyzing EEG data and designing a deep Q network to indirectly estimate drowsiness. The results demonstrate that this method performs well in tracking variations in mental state, outperforming supervised learning and confirming the feasibility and practicality of this new computational paradigm.
Fatigue is the most vital factor of road fatalities, and one manifestation of fatigue during driving is drowsiness. In this paper, we propose using deep Q-learning to study the correlation between drowsiness and driving performance. This study is carried out by analyzing an electroencephalogram (EEG) dataset captured during a simulated endurance driving test. Driving safety research using EEG data represents an important brain-computer interface (BCI) paradigm from an application perspective. To formulate the drowsiness estimation problem as an optimization of a Q-learning task, we adapt the terminologies in the driving test to fit the reinforcement learning framework. Based on that, a deep Q-network (DQN) is tailored by referring to the latest DQN technologies. The designed network merits the characteristics of the EEG data and can generate actions to indirectly estimate drowsiness. The results show that the trained model can trace the variations of mind state in a satisfactory way against the testing EEG data, which confirms the feasibility and practicability of this new computation paradigm. By comparison, it also reveals that our method outperforms the supervised learning counterpart and is superior for real applications. To the best of our knowledge, we are the first to introduce the deep reinforcement learning method to this BCI scenario, and our method can potentially be generalized to other BCI cases.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available