AUTHOR=Cui Yujie , Xie Songyun , Xie Xinzhou , Zhang Xiaowei , Liu Xianghui 

TITLE=Dynamic probability integration for electroencephalography-based rapid serial visual presentation performance enhancement: Application in nighttime vehicle detection

JOURNAL=Frontiers in Computational Neuroscience

VOLUME=Volume 16 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/computational-neuroscience/articles/10.3389/fncom.2022.1006361

DOI=10.3389/fncom.2022.1006361

ISSN=1662-5188

ABSTRACT=Background: Rapid serial visual presentation (RSVP) has become a popular target detection method by decoding electroencephalography (EEG) signals, owing to its sensitivity and effectiveness. Most current research of EEG based RSVP task focused on feature extraction algorithms developing to deal with non-stationarity and low signal-to-noise ratio (SNR) of EEG signals. However, these algorithms cannot handle the problem of no ERP component or miniature ERP components caused by the attention lapses of human vision. The fusion of human–computer vision can obtain complementary information, making it a promising way to become an efficient and general way to detect objects, especially in attention lapses.
Methods: Dynamic probability integration (DPI) was proposed in this study to fuse human vision and computer vision. A novel probability assignment method was included, which can fully consider the classification capabilities of different heterogeneous information sources for targets and non-targets, and constructs the detection performance model for the weight generation based on classification capabilities. Furthermore, a spatial-temporal hybrid common spatial pattern-principal component analysis (STHCP) algorithm was designed to decode EEG signals in RSVP task. It is a simple and effective method to distinguish target and non-target by using spatial-temporal feature.
Results: A nighttime vehicle detection based RSVP task was performed to evaluate the performance of DPI and STHCP, which is one of the conditions of attention lapses because of its decrease in visual information. The average AUC of DPI was 0.912±0.041 and increased 11.5%, 5.2%, 3.4% and 1.7% compared with human vision, computer vision, naive Bayesian fusion and dynamic belief fusion, respectively. A higher average balanced accuracy of 0.845±0.052 was also achieved using DPI, which representing that DPI have balanced detection capacity of target and non-target. Moreover, STHCP obtained the highest AUC of 0.818±0.06 compared with other two baseline method and increased by 15.4% and 23.4%.
Conclusion: Experimental results indicated that the average AUC and balanced accuracy of the proposed fusion method were higher than individual detection methods used for fusion as well as any of the baseline fusion methods. It is a promising way to improve the detection performance in RSVP task.