Advanced Ensemble Deep Random Vector Functional Link for Eye-Tracking-based Situation Awareness Recognition

被引：2
|
作者：
Li, Ruilin [1 ,2 ]
Gao, Ruobin [3 ]
Cui, Jian [4 ]
Suganthan, P. N. [1 ,5 ]
Sourina, Olga [2 ]
机构：
[1] Nanyang Technol Univ, Sch Elect & Elect Engn, Singapore, Singapore
[2] Fraunhofer Singapore, Singapore, Singapore
[3] Nanyang Technol Univ, Sch Civil & Environm Engn, Singapore, Singapore
[4] Zhejiang Lab, Artificial Intelligence Res Inst, Res Ctr AI Adv Theory, Hangzhou, Zhejiang, Peoples R China
[5] Qatar Univ, Coll Engn, KINDI Ctr Comp Res, Doha, Qatar
来源：
2022 IEEE SYMPOSIUM SERIES ON COMPUTATIONAL INTELLIGENCE (SSCI) | 2022年
关键词：
Conditionally automated driving; situation awareness (SA); eye-tracking (ET); ensemble deep random vector functional link (edRVFL); pruning; weighting;
D O I：
10.1109/SSCI51031.2022.10022019
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
Situation awareness (SA) plays a significant role in takeover transitions from autonomous to manual driving. Previous researchers have shown that eye movement signals can be used for SA recognition. Moreover, ensemble deep random vector functional link (edRVFL) has demonstrated its superiority in different applications. Therefore, this work proposes an advanced edRVFL (AedRVFL) to perform eye-tracking (ET)based SA recognition, including improvements in two aspects. Specifically, pruning in the direct links is implemented to improve the efficiency of linear features. Then, a weighting method based upon the regression errors of samples is developed. The experiment was conducted on a public conditionally automated driving dataset. Results showed that the proposed AedRVFL outperformed the baseline methods, demonstrating the effectiveness of using AedRVFL for ET-based SA recognition. Ablation studies were conducted to validate the improvements in the edRVFL.
引用
收藏
页码：300 / 307
页数：8
相关论文
共 50 条
  • [31] SAR Target Recognition with Modified Convolutional Random Vector Functional Link Network
    Dai, Qijun
    Zhang, Gong
    Fang, Zheng
    Xue, Biao
    IEEE Geoscience and Remote Sensing Letters, 2022, 19
  • [32] SAR Target Recognition With Modified Convolutional Random Vector Functional Link Network
    Dai, Qijun
    Zhang, Gong
    Fang, Zheng
    Xue, Biao
    IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2022, 19
  • [33] Representation learning using deep random vector functional link networks for clustering
    Hu, Minghui
    Suganthan, P. N.
    PATTERN RECOGNITION, 2022, 129
  • [34] Recurrent ensemble random vector functional link neural network for financial time series forecasting
    Bhambu, Aryan
    Gao, Ruobin
    Suganthan, Ponnuthurai Nagaratnam
    APPLIED SOFT COMPUTING, 2024, 161
  • [35] An ensemble of decision trees with random vector functional link networks for multi-class classification
    Katuwal, Rakesh
    Suganthan, P. N.
    Zhang, Le
    APPLIED SOFT COMPUTING, 2018, 70 : 1146 - 1153
  • [36] Travel time prediction for highway network based on the ensemble empirical mode decomposition and random vector functional link network
    Li, Linchao
    Qu, Xu
    Zhang, Jian
    Li, Hanchu
    Ran, Bin
    APPLIED SOFT COMPUTING, 2018, 73 : 921 - 932
  • [37] A robust variational mode decomposition based deep random vector functional link network for dynamic system identification
    Pattanaik, Rakesh Kumar
    Rout, Susanta Kumar
    Sahani, Mrutyunjaya
    Narayan, Mihir
    COMPUTERS & ELECTRICAL ENGINEERING, 2025, 122
  • [38] Utilization of ensemble random vector functional link network for freshwater prediction of active solar stills with nanoparticles
    Abd Elaziz, Mohamed
    Essa, F. A.
    Elsheikh, Ammar H.
    SUSTAINABLE ENERGY TECHNOLOGIES AND ASSESSMENTS, 2021, 47
  • [39] Assessing situation awareness in an unmanned vehicle control task A case for eye tracking based metrics
    Coyne, Joseph T.
    Sibley, Ciara M.
    Monfort, Samuel S.
    ADVANCES IN AVIATION PSYCHOLOGY, VOL 2: USING SCIENTIFIC METHODS TO ADDRESS PRACTICAL HUMAN FACTORS NEEDS, 2017, : 217 - 236
  • [40] Heteroscedastic ensemble deep random vector functional link neural network with multiple output layers for High Frequency Volatility Forecasting and Risk Assessment
    Bhambu, Aryan
    Suganthan, Ponnuthurai Nagaratnam
    Natarajan, Selvaraju
    Neurocomputing, 2025, 638
12345