Continuous Conditional Random Fields in Predicting High-Dimensional Data

被引:0
|
作者
Purbarani, Sumarsih Condroayu [1 ]
Sanabila, H. R. [1 ]
Wibisono, Ari [1 ]
Jatmiko, Wisnu [1 ]
机构
[1] Univ Indonesia, Fac Comp Sci, Depok, Indonesia
关键词
Traffic flow; traffic congestion; prediction; time series; probabilistic graphical model; REGRESSION;
D O I
暂无
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
The increase of vehicle in highways may cause traffic congestion as well as in the normal roadways. Predicting the traffic flow in highways especially, is demanded to solve this congestion problem. Predictions on time-series multivariate data, such as in the traffic flow dataset, have been largely accomplished through various approaches. The approach with conventional prediction algorithms, such as with Support Vector Machine (SVM), is only capable of accommodating predictions that are independent in each time unit. Hence, the sequential relationships in this time series data is hardly explored. Continuous Conditional Random Field (CCRF) is one of Probabilistic Graphical Model (PGM) algorithms which can accommodate this problem. The neighboring aspects of sequential data such as in the time series data can be expressed by CCRF so that its predictions are more reliable. In this article, CCRF is implemented to increase the prediction ability of different baseline regressors, i.e. SVM and Extreme Learning Machine (ELM). Both algorithms are examined in two different datasets. The result shows that CCRF is superior in performance when examined using high-dimensional dataset. This is validated by the increasing of the coefficient of correlation of the baseline up to 7.3% of significance.
引用
收藏
页码:427 / 432
页数:6
相关论文
共 50 条
  • [1] Preliminary Research on Continuous Conditional Random Fields in Predicting High-Dimensional Data
    Purbarani, Sumarsih Condroayu
    Sanabila, H. R.
    Wibisono, Ari
    Jatmiko, Wisnu
    [J]. 2017 INTERNATIONAL CONFERENCE ON ADVANCED COMPUTER SCIENCE AND INFORMATION SYSTEMS (ICACSIS), 2017,
  • [2] High-Dimensional Random Fields and Random Matrix Theory
    Fyodorov, Y. V.
    [J]. MARKOV PROCESSES AND RELATED FIELDS, 2015, 21 (03) : 483 - 518
  • [3] Dimensional Affect Recognition using Continuous Conditional Random Fields
    Baltrusaitis, Tadas
    Banda, Ntombikayise
    Robinson, Pete
    [J]. 2013 10TH IEEE INTERNATIONAL CONFERENCE AND WORKSHOPS ON AUTOMATIC FACE AND GESTURE RECOGNITION (FG), 2013,
  • [4] A New Feature Sampling Method in Random Forests for Predicting High-Dimensional Data
    Thanh-Tung Nguyen
    Zhao, He
    Huang, Joshua Zhexue
    Thuy Thi Nguyen
    Li, Mark Junjie
    [J]. ADVANCES IN KNOWLEDGE DISCOVERY AND DATA MINING, PART II, 2015, 9078 : 459 - 470
  • [5] Random forests for high-dimensional longitudinal data
    Capitaine, Louis
    Genuer, Robin
    Thiebaut, Rodolphe
    [J]. STATISTICAL METHODS IN MEDICAL RESEARCH, 2021, 30 (01) : 166 - 184
  • [6] On conditional moments of high-dimensional random vectors given lower-dimensional projections
    Steinberger, Lukas
    Leeb, Hannes
    [J]. BERNOULLI, 2018, 24 (01) : 565 - 591
  • [7] Estimation of Conditional Average Treatment Effects With High-Dimensional Data
    Fan, Qingliang
    Hsu, Yu-Chin
    Lieli, Robert P.
    Zhang, Yichong
    [J]. JOURNAL OF BUSINESS & ECONOMIC STATISTICS, 2022, 40 (01) : 313 - 327
  • [8] ROBOUT: a conditional outlier detection methodology for high-dimensional data
    Farne, Matteo
    Vouldis, Angelos
    [J]. STATISTICAL PAPERS, 2024, 65 (04) : 2489 - 2525
  • [9] Converting high-dimensional regression to high-dimensional conditional density estimation
    Izbicki, Rafael
    Lee, Ann B.
    [J]. ELECTRONIC JOURNAL OF STATISTICS, 2017, 11 (02): : 2800 - 2831
  • [10] Interaction Detection with Random Forests in High-Dimensional Data
    Winham, Stacey
    Wang, Xin
    de Andrade, Mariza
    Freimuth, Robert
    Colby, Colin
    Huebner, Marianne
    Biernacka, Joanna
    [J]. GENETIC EPIDEMIOLOGY, 2012, 36 (02) : 142 - 142