Feature Selection for Prediction of Railway Disruption Length

被引：0
|
作者：
Fan, Menglin [1 ,2 ]
Zheng, Wei [1 ,2 ]
机构：
[1] Beijing Jiaotong Univ, Natl Res Ctr Railway Safety Assessment, Beijing, Peoples R China
[2] Beijing Jiaotong Univ, Beijing Key Lab Intelligent Traff Data Secur & Pr, Beijing, Peoples R China
来源：
2019 IEEE INTELLIGENT TRANSPORTATION SYSTEMS CONFERENCE (ITSC) | 2019年
基金：
中国国家自然科学基金;
关键词：
D O I：
暂无
中图分类号：
U [交通运输];
学科分类号：
08 ; 0823 ;
摘要：
Disruptions such as accidents, facility failures and power outage occur frequently during daily railway operation, which can disrupt the railway timetable and cause financial cost in terms of lost patronage. Recent study indicates that skilled dispatchers can estimate the disruption length based on the analysis of related features. To select the significant features of railway disruption length (RDL), in this study, bidirectional gated recurrent unit with focal loss (FL-BiGRU) and maximal information coefficient (MIC) were applied to analyze the Chinese railway accident reports. FL-BiGRU was proposed to classify the disruption causes into seven categories and MIC algorithm was applied to select the related RDL features. Experiment results showed that the FL-BiGRU model outperforms rest models and can provide good accuracy especially on categories with fewer samples. Moreover, the set of predictors built by the maximum information coefficient can significantly improve the accuracy of the prediction model.
引用
收藏
页码：351 / 356
页数：6
相关论文
共 50 条
  • [1] Improved feature selection based on genetic algorithms for real time disruption prediction on JET
    Ratta, G. A.
    Vega, J.
    Murari, A.
    FUSION ENGINEERING AND DESIGN, 2012, 87 (09) : 1670 - 1678
  • [2] Feature selection for disruption prediction from scratch in JET by using genetic algorithms and probabilistic predictors
    Pereira, Augusto
    Vega, Jesus
    Moreno, Raul
    Dormido-Canto, Sebastian
    Ratta, Giuseppe A.
    Pavon, Fernando
    FUSION ENGINEERING AND DESIGN, 2015, 96-97 : 907 - 911
  • [3] Feature Selection for Link Prediction
    Xu, Ye
    Rockmore, Dan
    PROCEEDINGS OF THE 5TH PH.D. WORKSHOP ON INFORMATION AND KNOWLEDGE, 2012, : 25 - 32
  • [4] Feature selection in bankruptcy prediction
    Tsai, Chih-Fong
    KNOWLEDGE-BASED SYSTEMS, 2009, 22 (02) : 120 - 127
  • [5] Feature extraction for improved disruption prediction analysis at JET
    Ratta, G. A.
    Vega, J.
    Murari, A.
    Johnson, M.
    REVIEW OF SCIENTIFIC INSTRUMENTS, 2008, 79 (10):
  • [6] Dynamic feature selection for hardware prediction
    Fern, A
    Givan, R
    Falsafi, B
    Vijaykumar, TN
    JOURNAL OF SYSTEMS ARCHITECTURE, 2006, 52 (04) : 213 - 234
  • [7] Feature Selection for Wheat Yield Prediction
    Russ, Georg
    Kruse, Rudolf
    RESEARCH AND DEVELOPMENT IN INTELLIGENT SYSTEMS XXVI: INCORPORATING APPLICATIONS AND INNOVATIONS IN INTELLIGENT SYSTEMS XVII, 2010, : 465 - 478
  • [8] Feature selection and the prediction of corporate failure
    Lin, FY
    McClean, S
    IC-AI'2000: PROCEEDINGS OF THE INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 1-III, 2000, : 787 - 793
  • [9] Feature Selection in Supervised Saliency Prediction
    Liang, Ming
    Hu, Xiaolin
    IEEE TRANSACTIONS ON CYBERNETICS, 2015, 45 (05) : 900 - 912
  • [10] Age Prediction Based on Feature Selection
    Wang, Yanhong
    Song, Wei
    Liu, Lizhen
    2017 2ND IEEE INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE AND APPLICATIONS (ICCIA), 2017, : 359 - 363
12345