Prediction of multivariate probabilistic systems based on predictive state representation

doi:10.3724/SP.J.1087.2012.03044

Journal of Computer Applications ›› 2012, Vol. 32 ›› Issue (11): 3044-3046.DOI: 10.3724/SP.J.1087.2012.03044

Previous Articles Next Articles

Prediction of multivariate probabilistic systems based on predictive state representation

WANG Qing-miao¹,²,JU Shi-guang¹,²

1. School of Computer Science and Technology，Soochow University, Suzhou Jiangsu 215006,China
2. School of Computer Science and Telecommunication Engineering, Jiangsu University, Zhenjiang Jiangsu 212013,China

Received:2012-05-22 Revised:2012-06-28 Online:2012-11-12 Published:2012-11-01
Contact: WANG Qing-miao

基于预测状态表示的多变量概率系统预测

汪庆淼¹,²,鞠时光¹,²

1. 江苏大学计算机科学与通信工程学院, 江苏镇江 212013
2. 苏州大学计算机科学与技术学院，江苏苏州 215006

通讯作者: 汪庆淼
作者简介:汪庆淼（1977-），男，浙江绍兴人，实验师，博士研究生，主要研究方向：模式识别、系统建模；鞠世光（1955-），男，江苏南通人，教授，博士生导师，主要研究方向：信息安全、模式识别、空间数据库管理。
基金资助:
国家自然科学基金资助项目（11102124）

Abstract

Abstract: In this paper, a new method based on Predictive State Representation (PSR) was proposed to solve high complexity of multivariate probability system. The paper introduced a new concept about general multivariate process in the first, and then described the multivariate system with the concept. Furthermore, the authors imported MultiVariate (MV)PSR as prediction model for multivariate system. The model was based on observable information and could realize the multivariate prediction in the finite dimensions. The experimental result shows that the approximate model effectively reduces the complexity of the system prediction.

Key words: multivariate, Predictive State Representation (PSR), common random process, observable information, core query

摘要： 针对由于多变量概率系统预测高复杂度而导致的建模困难问题，提出了一种基于预测状态表示（PSR）的系统建模新方法，首先介绍一种通用多变量过程概念，并进一步用此概念描述多变量系统。在此基础上，引入了针对多变量系统的预测模型MVPSR，模型基于可观测信息，可在有限维实现对多变量的预测。实验结果表明，该近似模型有效降低了系统预测的复杂度。

关键词: 多变量, 预测状态表示, 通用随机过程, 可观测信息, 核查询

CLC Number:

TP18

WANG Qing-miao JU Shi-guang. Prediction of multivariate probabilistic systems based on predictive state representation[J]. Journal of Computer Applications, 2012, 32(11): 3044-3046.

汪庆淼鞠时光. 基于预测状态表示的多变量概率系统预测[J]. 计算机应用, 2012, 32(11): 3044-3046.

References

［1］ SINGH S, MICHAEL R J, RUDARY M R. Predictive state representations: A new theory for modeling dynamical systems［C］// Proceedings of the Twentieth Conference on Uncertainty in Artificial Intelligence. New York:ACM, 2004:512–519. ［2］ WINGATE D, SINGH S. Efficiently learning linearlinear exponential family predictive representations of state［C］// Proceedings of the Twentieth International Conference on Machine Learning. New York:ACM, 2008:1128-1135. ［3］ MURPHY K P.An introduction to graphical models［EB/OL］.［2012-03-01］.http://www.cs.ubc.ca/~murphyk/Papers/intro_gm.pdf. ［4］ LOWD D, DOMINGOS P. Naive Bayes models for probability estimation［C］// Proceedings of the TwentySecond International Conference on Machine Learning. New York: ACM,2005:964-971. ［5］ WOLFE, B, JAMES, M R, SINGH S.Approximate predictive state representations［C］// Proceedings of the 7th International Joint Conference on Autonomous Agents and Multiagent Systems. New York:ACM,2008:2035-2042. ［6］ WOLFE B,JAMES M,SINGH S. Learning predictive state representations in dynamical systems without reset［C］// Proceedings of the TwentySecond International Conference on Machine Learning. New York:ACM, 2005: 980-987. ［7］ BOOTS B, GORDON G J. An online spectral learning algorithm for partially observable nonlinear dynamical systems［C］// Proceedings of the 25th National Conference on Artificial Intelligence. New York:ACM, 2011:564-571. ［8］ DINCULESCU M, PRECUP D. Approximate predictive representations of partially observable systems［C］// Proceedings of 27th International Conference on Machine Learning. New York:ACM, 2010:888-895. ［9］ BOOTS B, SIDDIQI S, GORDON G J. Closing the learningplanning loop with predictive state representations［C］// Proceedings of Robotics: Science and Systems V. New York:ACM,2010: 1377-1384. ［10］ TALVITIE E,SINGH S. Simple local models for complex dynamical systems［C］// TwentySecond Annual Conference on the Neural Information Processing Systems. New York:ACM, 2008:1421-1428. ［11］ TALVITIE E,SINGH S. Maintaining predictions over time without a model［C］// Proceedings of the TwentyFirst International Joint Conference on Artificial Intelligence. New York:ACM, 2009:733-740. ［12］ BLAKE C L, MERZ C J.UCI repository of machine learning databases［EB/OL］.［2012-03-15］.http://www.ics.uci.edu/- _mlearn/MLRepository.html.

[1]	Liting LI, Bei HUA, Ruozhou HE, Kuang XU. Multivariate time series prediction model based on decoupled attention mechanism [J]. Journal of Computer Applications, 2024, 44(9): 2732-2738.
[2]	Zixuan YUAN, Xiaoqing WENG, Ningzhen GE. Early classification model of multivariate time series based on orthogonal locality preserving projection and cost optimization [J]. Journal of Computer Applications, 2024, 44(6): 1832-1841.
[3]	Hongtao SONG, Jiangsheng YU, Qilong HAN. Industrial multivariate time series data quality assessment method [J]. Journal of Computer Applications, 2024, 44(6): 1743-1750.
[4]	Siyi ZHOU, Tianrui LI. Visual analysis of multivariate spatio-temporal data for origin-destination flow [J]. Journal of Computer Applications, 2024, 44(2): 452-459.
[5]	Yiyang FAN, Yang ZHANG, Shang ZENG, Yu ZENG, Maoli FU. Multivariate long-term series forecasting model based on decomposition and frequency domain feature extraction [J]. Journal of Computer Applications, 2024, 44(11): 3442-3448.
[6]	Pei ZHAO, Yan QIAO, Rongyao HU, Xinyu YUAN, Minyue LI, Benchu ZHANG. Multivariate time series anomaly detection based on multi-domain feature extraction [J]. Journal of Computer Applications, 2024, 44(11): 3419-3426.
[7]	Hui JIANG, Qiuyan YAN, Zhujun JIANG. Symmetric positive definite autoencoder method for multivariate time series anomaly detection [J]. Journal of Computer Applications, 2024, 44(10): 3294-3299.
[8]	Bin LIU, Qian ZHANG, Yaqin WEI, Xueying CUI, Hongying ZHI. Graph to equation tree model based on expression layer-by-layer aggregation and dynamic selection [J]. Journal of Computer Applications, 2023, 43(8): 2390-2395.
[9]	Xingheng TANG, Qiang GUO, Tianhui XU, Caiming ZHANG. Stock return prediction via multi-scale kernel adaptive filtering [J]. Journal of Computer Applications, 2023, 43(5): 1385-1393.
[10]	Weikang CHEN, Qiqing ZHAI, Youguo WANG. Multivariate communication system based on discrete bidirectional associative memory neural network [J]. Journal of Computer Applications, 2023, 43(3): 848-852.
[11]	KONG Lingxu, WU Haifeng, ZENG Yu, LU Xiaoling. Diagnosis of mild cognitive impairment using deep learning and brain functional connectivities with different frequency dimensions [J]. Journal of Computer Applications, 2021, 41(2): 590-597.
[12]	WANG Min, WU Yubo, MIN Fan. Multi-category active learning algorithm based on multiple clustering algorithms and multivariate linear regression [J]. Journal of Computer Applications, 2020, 40(12): 3437-3444.
[13]	LUO Xiaoshuang, YANG Xiaoyuan, LI Cong, WANG Xu'an. Publicly verifiable outsourced computation scheme for multivariate polynomial based on two-server model [J]. Journal of Computer Applications, 2018, 38(2): 321-326.
[14]	HUO Weigang, CHENG Zhen, CHENG Wenli. Improved clustering algorithm for multivariate time series with unequal length [J]. Journal of Computer Applications, 2017, 37(12): 3477-3481.
[15]	MAO Yingchi, QI Hai, JIE Qing, WANG Longbao. M-TAEDA: temporal abnormal event detection algorithm for multivariate time-series data of water quality [J]. Journal of Computer Applications, 2017, 37(1): 138-144.

Prediction of multivariate probabilistic systems based on predictive state representation

基于预测状态表示的多变量概率系统预测

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics