摘要
海量规则并行处理是一个新兴研究课题,它涉及语义计算、规则处理、数据库、模式识别、人工智能、数据挖掘、模式识别、知识发现、并行计算、图论以及数据结构等多个学科,给目前信息科学和技术领域的研究带来了巨大的挑战。该技术的研究突破可以解决海量规则的有效、即时处理问题,并具有非常广阔的应用前景。规则描述模型、海量规则网优化理论与海量规则网的有效划分是海量规则并行处理研究的最核心的重难点问题,其研究受到了国内外学者越来越多的关注。
本文对海量规则并行处理的几个关键性技术进行了研究,其内容主要包括以下几个方面：
(1)规则描述模型
本文研究了一种可以表示各种粒度(大粒度、中粒度以及小粒度)规则的规则描述模型。主要包括规则节点表示方法、规则节点流量以及规则节点可计算代价等。
(2)海量规则网及其优化方法
本文研究了基于规则合并及其基于规则模块等价替换的海量规则网优化方法。论文通过研究规则,将不同规则中有重复规则节点的进行合并,达到规则完全合并或者部分合并目的；同时,论文通过那些计算功能等价的规则模块,将计算代价小的规则模块替换掉计算代价大的规则模块。
(3)海量规则模式匹配处理模型以及运行时处理算法
本文在分析现有的各种规则模式匹配处理算法的基础上,针对现有规则模式匹配处理算法的缺陷,提出了一种适合于海量规则的海量规则模式匹配处理模型以及运行时处理算法。
(4)海量规则网并行处理机制
本文提出并研究了一种海量规则并行处理机制GAPCM。研究了将海量规则生成互相独立的规则子网方法；研究了任务预分配方法；研究了规则子网的合理划分方法；研究了规则子网内部通信以及处理机之间的外部通信；最后研究了将任务具体映射到所对应处理机的方法。
(5)海量规则网分割算法
针对海量规则的并行处理,研究了海量规则子网的分割问题,本文设计了：1)规则子网平衡分割算法,该算法考虑处理机处理代价平衡分布,不考虑处理机等待(依赖)消耗也不考虑处理机通信消耗问题；2)规则子网平衡最小依赖分割算法,该算法考虑处理机处理代价平衡分布,考虑处理机等待(依赖)消耗,但是不考虑处理机通信消耗问题；3)规则子网平衡最小依赖与通信分割算法,该算法考虑处理机处理代价平衡分布,考虑处理机等待(依赖)消耗,同时也在考虑处理机等待消耗基础上考虑处理机通信消耗。
Processing of massive number of rules is a research problem that has attracted more attention in recently years. It involves many research disciplines such as semantic computing, rule processing, database, pattern recognition, artificial intelligence, data mining, knowledge mining, parallel computing, graph theory, data structure and so on, and presents a huge challenge. The key problems involved in this field includes description and modelling of rules, optimal sharing among multiple rules, partitioning of a rule network, and parallelization.
This dissertation considers the above key problems:
(1) Description and Modelling of Rules
We propose a rule description language that can express rules of different granularities. We also propose a model to capture massive number of rules and their processing costs.
(2) Optimization of a Rule Network
We propose several optimization methods given a large rule network based on common sub-expression sharing and rule equalence.
(3) Partioning of a Rule Network
We propose a parallel rule processing algorithm GAPCM that includes a method to generate mutually independent rule subnets given a large rule network, several methods to partion a rule subnet, a method to compute the internal as well as external communication costs between rule subnets, and a method that maps the subnets to the processors.
(4) GAPCM
This article proposed and studied a kind of very large scale rules parallel processing mechanism GAPCM.
(5) Parrellization We propose three algorithms to support parallelization:
a) Balanced Cutting Algorithm, that considers load balancing but not the processor waiting time due to the dependencies among rule;
b) Balanced and Minimal Dependency Cutting Algorithm, that considers both load balancing and processor waiting time, but not the communication costs among processors;
c) Balanced, Minimal Dependeny and Minimal Communication Algorithm, that considers load balancing, processor waiting time, and the communication costs among processors;
引文
[1]S. Fujii, A. M. K. Cheng. "Bounded-Response-Time Self-Stabilizing Real-Time Rule Systems," submitted for publication,1999.
[2]P.-Y. Lee, A. M. K. Cheng. "HAL:A New Match Algorithm with Low Match-Time Variance," submitted to IEEE Transactions on Knowledge and Data Engineering, Sept.1998.
[3]J. Considine, F. Li, G. Kollios, J. Byers. Approximate aggregation techniques for sensor databases. In Proc. International Conference onData Engineering (ICDE), Mar.2004.
[4]J. M. Hellerstein, R. Avnur, A. Chou, C. Hidber, C. Olston, V. Raman, T. Roth, and P. J. Haas. Interactive data analysis with CONTROL. IEEE Computer,32(8), August 1999.
[5]Y.-H. Lee, A. M. K. Cheng. "Run-time Dynamic Optimization of Real-Time Rule-Based Systems," submitted to Proc. IEEE-CS Real-Time Technology and Applications Symposium, Vancouver, Canada, June 1999.
[6]Ceri S, Fraternali P, Paraboschi S, Letizia T. Constraint enforcement through production rules: putting active databases at work. IEEE Data Engineering bulletin, Vol.15,No.1-4, Dec. ]992.PP.10-14.
[7]C. Guestrin, R. Thibaux, P. Bodik, M. A. Paskin, and S. Madden. Distributed regression:An efficient framework for modeling sensor network data. In Proc.3rd International Symposium on Information Processing in Sensor Networks (IPSN),2004.
[8]Date.C.J. An Introduction to Database Systems. Vol.1, Fourth Edition. Addison Wesley Publishing Computer, Inc,1986.
[9]Date.C.J., An Introduction to Database Systems. Vol.1. Addison Wesley Publishing Computer, Inc.,1983
[10]Astrahan M. M., et. al. System R:Relational Approach to Database Management, ACM Transactions on Database Systems, Vol.1, No.2, June 1976. pp:97-137.
[[11]O.P.Buchmann, A.Deutsch.The REACH Active OODBMS. In Proc. Of the ACM SIFMOD intl. Conf. on Mangagemeng of Data, May 1995.
[12]Morgenstern M. Active Databases as a Paradigm for Enhanced Computing Environments,Proc. 9th VLDB conf., Florence, Nov.1983.
[13]Dayal U., McCarthy D. The architecture of an Active Database Management System.ACM SIGMOD conf.,1989.PP:215-224.
[14]Chakravarthy S., et. al. HiPAC:A Research Project in Active Time-Constrained DatabaseManagement, Xerox Advanced Information Technology, Cambridge, Mass., July 1989.
[15]Fahl G., Risch T., Skold M. AMOS-An Architecture for Active Mediators, Intl. Workshop on Next Generation Information Technologies and Systems (NGITS'93) Haifa, Israel, June 1993. PP:47-53
[16]Buchman A. P, Branding H, Kudrass T, Zimmermann J. REACH:a REal-time, ACtive and Heterogeneous mediator system. IEEE Data Engineering bulletin, Vol.15,No.1-4, Dec.1992. PP:44-47.
[17]Wiederhold G. Mediators in the Architecture of Future Information Systems. IEEE Computer, March 1992.
[18]Fishman D. et. Al. Overview of the Iris DBMS, Object-Oriented Concepts, Databases, and Applications. ACM press, Addison-Wesley Publ. Comp,1989.
[19]Litwin W, Risch T. Main Memory Oriented Optimization of OO Queries using Typed Datalog with Foreign Predicates.IEEE Transactions on Knowledge and Data Engineering Vol.4, No.6, December 1992.
[20]Beech D. Collections of Objects in SQL3.VLDB conf, Dublin 1993. PP:244-255.
[21]Stonebraker M,Row L. The Design of POSTGRES, ACM SIGMOD conf. Washington,D.C., May 1986.PP:340-355.
[22]Lohman G. M., Lindsay B., Pirahesh H., Schiefer K. B. Extensions to Starburst:Objects, Types, Functions and Rules. Communications of the ACM, oct.1991, vol.34,no.10. PP:94-109.
[23]Hanson, E. Rule condition testing and action execution in ariel. Proceedings of ACM SIGMOD Conference,1992.PP:171
[24]E.N. Hanson, S. Bodagala, M. Hasan, G. Kulkarni, J. Rangarajan. Optimized Rule Condition Testing in Ariel using Gator Networks. Technical report, CISE Department, University of Florida, October 1995.
[25]Hanson E. N. Rule Condition Testing and Action Execution in Ariel.ACM SIGMOD conf, 1992.PP:49-58.
[26]Hanson Eric N. Design and implementation of the Ariel active database rule system. IEEE Transactions on Knowledge and Data Engineering, v 8, n 1.PP:157-172.
[27]Gehani N, Jagadish H. V. Ode as an Active Database:Constraints and Triggers, Proc.95.
[28]Gatziu S, Dittrich K. R. SAMOS:an Active Object-Oriented Database System.IEEE Data Engineering bulletin, Vol.15, No.1-4, Dec.1992.PP:23-26.
[29]Perraju T.S, Prasad B.E.Interference analysis in multiple rule firing systems. Knowledge-Based Systems, v 13, n 4. PP:171-176.
[30]P. C.-Y. Sheu, H. Yu, C.V. Ramamoorthy, A. Joshi, L.A. Zadeh (eds.) Semantic Computing, IEEE. Press/Wiley,2008.
[31]P. C-Y. Sheu, "Semantic Web Service Synthesis," in Semantic Computing, IEEE Press/Wiley, 2008.
[32]P. C.-Y. Sheu, H. Yu, C.V. Ramamoorthy, A. Joshi, L.A. Zadeh (eds.). "Semantic Languages," in Semantic Computing, IEEE Press/Wiley,2008
[33]P. C-Y. Sheu, Editorial Preface, International Journal of Semantic Computing, Vol 1.1,2007, pp.1-9.
[34]H. Gong, S. Wang, Q. Wang, P. C-Y. Sheu, "Synthesis of Relational Web Services based on SCDL," Proceedings, International Conference on Tools with Artificial Intelligence, November, 2008, Dayton, Ohio, USA.
[35]Q. Wang and P. C-Y. Sheu, "An Approach to Relational Web Service Composition," Proceedings, International Conference on Tools with Artificial Intelligence, November,2008, Dayton, Ohio, USA.
[36]P. C.-Y. Sheu and Atsushi Kitazawa."From SemanticObjects to Semantic Software Engineering," International Journal of Semantic Computing, Vol.1, No.1,2007, pp.11-28.
[37]Tieyun Qian, Phillip C-Y Sheu, Shijun Li, Lina Wang, "A Scientific Theme Emergence Detection Approach based on Citation Graph Analysis," Proceedings, International Conference on Tools with Artificial Intelligence, November,2008, Dayton, Ohio, USA.
[38]C. Chubb, Y. Inagaki, P. C-y Sheu."BioVision:An Application for the Automated Image Analysis of Histological Sections," Neurobiology of Aging, Vol.27, No.10,2006, pp.1462-1476.
[39]H. Yu, P.C-Y. Sheu, S. Ying."A Method of Establishing Semantic Information Space Model Based On WSDL4S Documents," Proceedings IEEE International Workshop on Semantic Computing and Systems, June,2008, Huangshan, China.
[40]Chen, E., Li, T. and P. C-y Sheu. "A General Effective Framework for Monotony and Tough Constraint Based Sequential Pattern Mining," Lecture Notes in Computer Science 3589, Springe Verlagr,458-467,2005.
[41]E. Chen, S. Wang, P. C-y Sheu."A Novel Approach to Table Detection and Analysis for Semantic Annotation," International Journal on Tools for Artificial Intelligence, Vol.15, No.3, 2006, pp.465-480.
[42]F. Xie, P. C-Y Sheu. "Semantic Synthesis and Analysis of Complex Biological Systems,", International Journal on Software Engineering & Knowledge Engineering*, Vol.15, No.3,2005, pp.547-569.
[43]C. Chubb, Y. Inagaki, C. Cotman. "Semantic Biological Image Management and Analysis," International Journal on Tools for Artificial Intelligence, Vol.13, No.4,2004, pp.881-896.
[44]Deng, D. and P. C-y Sheu. "DPSSEE:A Distributed Proactive Semantic Software Engineering Environment,"in Advances in Machine Learning Applications in Software Engineering, Du Zhang, Jeffery J -P Tsai (eds.),2006, pp.409-438.
[45]Donghua Deng, Guigang Zhang, Phillip C-y Sheu. "Semantic Programming of Web-Enabled Database Applications," Proceedings IEEE International Workshop on Semantic Computing and Applications, June,2008, Inchon, Korea.
[46]Zhang Guigang, Shu Wang,, Xu ChengZhi(etls). "A Semantic Programming Language SPL+-A Preliminary Report," Proceedings, International Conference on Tools with Artificial Intelligence, November,2008, Dayton, Ohio, USA.
[47]S. Wang, R.M. Hu, D. Hecht, R.M. Chen(etls). "Using SCDL for Integrating Tools and Data for Integrating Complex Biomedical Applications," to appear, International Journal of Semantic Computing, Vol.2.2, June,2008.
[48]B.Huang, G. Zhang, P. C-Y Sheu. "A Natural Language Database Interface based on a Probabilistic Context Free Grammar,". Proceedings IEEE International Workshop on Semantic Computing and Systems, June,2008, Huangshan, China.
[49]W. Ying, Y. Li, and P. C-Y Sheu. "A GA-based Approach to Optimizing Combinatorial Queries in SCDL," to appear, International Journal of Semantic Computing, Vol.2.2, June,2008.
[50]Nayak, P., Gupta, A., Rosenbloom, P. Comparison of the Rete and Treat production matchers for Soar (A summary). In Proceedings of the Seventh National Conference on Artificial Intelligence,1988. PP:693-698.
[51]D. P. Miranker. TREAT:A better match algorithm for AI production systems. In proceedings of AAAI 87 conference on Artificial Intelligence, August 1987. PP:42-47.
[52]Miranker, D. P. Treat:A better match algorithm for AI production systems. In Proceedings of the Sixth National Conference on Artificial Intelligence,1987.PP:42-47.
[53]Rete II.http://www.pst.com/rete2.htm.
[54]Forgy, C.L. Rete:A Fast Algorithm for the Many Pattern/Many Object Pattern Match Problem. Artificial Intelligence.19(1982).PP:17-37.
[55]N. Alex Rupp. The logic of the bottom line:An Introduction to the Drools Project.May 2004.
[56]P.-Y. Lee, A. M. K. Cheng. "Reducing Match Time Variance in Production Systems with HAL," Proc.6th Intl. ACM Conf. on Information and Knowledge Management, Las Vegas, Nevada, Nov.1997.
[57]http://www.lsiinc.com/univercd/cc/td/doc/product/rtrmgmt/ana/3_5_1/admin/admin/ruleseng.h tm.
[58]http://rools.rubyforge.org.
[59]Dehne Frank, Eavis Todd, Hambrusch Susanne, Rau-Chaplin.Parallelizing the data cube. Andrew Source:Distributed and Parallel Databases, v 11, n 2, March 2002.PP:p 181-201.
[60]Kulkarni Milind, Pingali Keshav, Ramanarayanan Ganesh, Walter Bruce, Bala Kavita, Chew L. Paul. Optimistic parallelism benefits from data partitioning. International Conference on Architectural Support for Programming Languages and Operating Systems-ASPLOS,2008.PP:p 233-243.
[61]O'Nils Mattias.Data partitioning for parallel implementation of real-time video processing systems. Proceedings of the 2005 European Conference on Circuit Theory and Design, v 1, 2005.PP:p 213-216.
[62]Jendrsczok J, Ediger P. Hoffmann, R. A scalable configurable architecture for the massively parallel GCA model. IPDPS Miami 2008-Proceedings of the 22nd IEEE International Parallel and Distributed Processing Symposium, Program and CD-ROM,2008, IPDPS Miami 2008.
[63]Heenes Wolfgang, Hoffmann Rolf, Kanthak Sebastian.FPGA implementations of the massively parallel GCA model. Proceedings-19th IEEE International Parallel and Distributed Processing Symposium, IPDPS 2005.
[64]王永杰；孟令奎；赵春宇；基于Hilbert空间排列码的海量空间数据划分算法研究.武汉大学学报(信息科学版),2007年07期
[65]孟令奎；黄长青；赵春宇；林志勇;An Improved Hilbert Curve for Parallel Spatial Data Partitioning,地球空间信息科学字报(英文版),2007年04期.
[66]Jie W, Cai W, Turner S.J. Dynamic load-balancing in a data parallel object-oriented system. Proceedings of the Internatoinal Conference on Parallel and Distributed Systems-ICPADS, 2001.PP:p 279-286.
[67]杨小虎；王新宇；毛明；基于数据划分的分布式模型及其负载均衡算法.浙江大学学报(工学版),2008年04期.
[68]T Yan Baoqiang, Rhodes Philip J.oward automatic parallelization of spatial computation for computing clusters.Proceedings of the 17th International Symposium on High Performance Distributed Computing 2008, HPDC'08.PP:45-54.
[69]Gutierrez Eladio, Plata Oscar, Zapata Emilio L. Data partitioning-based parallel irregular reductions.Concurrency Computation Practice and Experience, v 16, n 2-3, February/March 2004. PP:155-172.
[70]Kamel, Nabil N. Using SIMD parallelism to support rule-based systems. PARBASE 90 Int Conf Databases Parallel Archit Appl,1990, PARBASE 90. PP:544.
[71]Wu Shiow-Yang, Miranker Daniel P, Browne James C.Decomposition abstraction in parallel rule languages. IEEE Transactions on Parallel and Distributed Systems, v 7, n 11. PP:116.4-1184.
[72]Miller Michael I, Roysam Badrinath, Smith Kurt R., O'Sullivan Joseph A. Representing and computing regular languages on massively parallel networks.IEEE Transactions on Neural Networks, v 2, n 1.PP:56-72.
[73]Widom J., Finkelstein S.J. Set-oriented production rules in relational database system.ACM SIGMOD conf, Atlantic City, New Jersey 1990.PP:259-270.
[74]Gonzales Eloy, Shimada Kaoru, Mabu Shingo, Hirasawa Kotaro Hu, Genetic network programming with parallel processing for association rule mining in large and dense databases. Proceedings of GECCO 2007:Genetic and Evolutionary Computation Conference.PP:1512.
[75]B. Zupan,A. M. K. Cheng. "Optimization of Rule-Based Systems Using State Space Graphs," IEEE Transactions on Knowledge and Data Engineering, April 1998.
[76]M. K. Cheng,J.-C Wang. "Applying a Modified EQL Optimization Method to MRL Rule-Based Programs," Proc. IEEE Workshop on Application-Specific Software Engineering and Technology, Richardson, TX, Mar.1998.
[77]M. K. Cheng. "Optimization of Real-Time MRL Rule-Based Systems with the EQL Optimizer," Proc. WIP Session,18th IEEE-CS Real-Time Systems Symposium, San Francisco, CA, Dec.1997.
[78]S. Avery,A. M. K. Cheng. "Optimizing OPS5 Rule-Based Programs by Rule-Splitting," Proc. Intl. Conf. on Software Engineering, San Francisco, CA, Nov.1997.
[79]Abraham Silberschatz,Henry F.Korth,S.Sudarshan.Database System Conceps(Fifth Edition), 2006.9.PP:P378-P383.
[80]Moldovan Dan I. RUBIC:A multiprocessor for rule-based systems. IEEE Transactions on Systems, Man and Cybernetics, v 19, n 4, Jul-Aug.PP:p 699-706.
[81]Zhou Jiayi,Yu Kun-Ming.Tidset-based parallel FP-tree algorithm for the frequent pattern mining problem on PC clusters. Lecture Notes in Computer Science, v 5036 LNCS,2008.PP: 18-28.
[82]Aref Mostafa M, Tayyib Mohammed A. Lana-Match algorithm:A parallel version of the Rete-Match algorithm.Parallel Computing, v 24, n 5-6. PP:763-775.
[83]Gaudiot Jean-Luc, Sohn Andrew.Data-driven parallel production systems. IEEE Transactions on Software Engineering, v 16, n 3.PP:281-293.
[84]Wolfson Ouri, Ozeri Aya. Parallel and distributed processing of rules by data-reduction. Source:IEEE Transactions on Knowledge and Data Engineering, v 5, n 3. PP:523-530.
[85]Walzer Karen, Breddin Tino, Groch Matthias.Relative temporal constraints in the Rete algorithm for complex event detection. Proceedings of the 2nd International Conference on Distributed Event-Based Systems, DEBS 2008,2008.PP:147-155.
[86]Matsuzawa, Kazumitsu.Parallel execution method of production systems with multiple worlds. IEEE Int Workshop Tools Artif Intell Archit Lang Algorithms,1989, IEEE Int Workshop Tools Artif Intell Archit Lang Algorithms.PP:339-344.
[87]Gordin D.N., Pasik A.J. Set-oriented constructs. From rete rule bases to database systems. Proceedings of the 1991 ACM SIGMOD International Conference on Management of Data, 1991.PP:60.
[88]Chen Ken, Yu Fei; Xu Cheng. Liu Yan. Intrusion detection for high-speed networks based on producing system. Proceedings-1st International Workshop on Knowledge Discovery and Data Mining, WKDD,2008. PP:532-537.
[89]Sellis Timos,Lin Chih-Chen. Performance of DBMS implementations of production systems. Proc 2 Int IEEE Conf Tools Artif Intell,1990. PP:393-399.
[90]Butler P.L, Allen Jr., J.D, Bouldin D.W. PARALLEL ARCHITECTURE FOR OPS5. IEEE, 1988.PP:452-457.
[91]Cheng Albert Mo Kim,Chen Jeng-Rung.Response time analysis of OPS5 production systems. IEEE Transactions on Knowledge and Data Engineering, v 12, n 3,2000. PP:391-409.
[92]Kang J.A, Cheng A.M.K. Reducing matching time for OPS5 production systems. Proceedings-IEEE Computer Society's International Computer Software and Applications Conference,2001. PP:429-434.
[93]Kang Jeong A, Cheng Albert. Mo Kim.Shortening matching time in OPS5 production systemsl. Source:IEEE Transactions on Software Engineering, v 30, n 7, July 2004.PP:p 448-457.
[94]Cheng Albert,Mo Kim. Fujii Seiya.Self-stabilizing real-time OPS5 production systemsl. Source:IEEE Transactions on Knowledge and Data Engineering, v 16, n 12, p 1543-1554, December 2004.
[95]Liu Faguf, Hu Wei. Rule match-an important issue in RFID middleware.2007 IEEE International Workshop on Anti-counterfeiting, Security, Identification, ASID,2007.PP:p 394-397.
[96]Nambo Hidetaka, Kimura Haruhiko, Hirose Sadaki. High-speed production system using dynamic two-way switching of match algorithm. Systems and Computers in Japan, v 32, n 9, August 2001.PP:61-70.
[97]Rychtyckyj Nestor, Reynolds Robert G. Using cultural algorithms to re-engineer large-scale semantic networksl. International Journal of Software Engineering and Knowledge Engineering, v 15, n 4, August 2005.PP:p 665-693.
[98]Gupta Anoop, Forgy Charles. Newell, Allen.High-speed implementations of rule-based systems. ACM Transactions on Computer Systems, v 7, n 2.PP:119-146.
[99]Mahanti, Anirban; Eager, Derek L.Adaptive data parallel computing on workstation clusters. Source:Journal of Parallel and Distributed Computing, v 64, n 11,, November 2004.PP: p1241-1255.
[100]Jin Dejiang, Ziavras Sotirios G. A super-programming approach for mining association rules in parallel on PC clusters. IEEE Transactions on Parallel and Distributed Systems, v 15, n 9, September 2004. PP:783-794.
[101]Kai Zheng,Zhiyong Liang, Yi Ge. Parallel packet classification via policy table pre-partitioning. GLOBECOM-IEEE Global Telecommunications Conference, v 1,2005. pPP:73-78.
[102]Zhang Weining, Wang Ke, Chau Siu-Cheung.Data partition and parallel evaluation of datalog programs. Source:IEEE Transactions on Knowledge and Data Engineering, v 7, n 1. PP:163-176.
[103]Kejariwal, Arun; Nicolau, Alexandru. An efficient load balancing scheme for grid-based high performance scientific computing. Source:ISPDC 2005:4th International Symposium on Parallel and Distributed Computing, v 2005,PP:217-225.
[104]Yu Kun-Ming, Zhou Jia-Ling.A weighted load-balancing parallel apriori algorithm for association rule mining. IEEE International Conference on Granular Computing, GRC 2008. PP:756-761.
[105]Ou, Chao-Wei; Ranka, Sanjay. Parallel incremental graph partitioning. Source:IEEE Transactions on Parallel and Distributed Systems, v 8, n 8, Aug.PP:p 884-896.
[106]陈国良.并行计算—结构.算法.编程[M].2005年.
[107]Pasik Alexander J.A. Source-to-source transformation for increasing rule-based system parallelism. Source:IEEE Transactions on Knowledge and Data Engineering, v 4, n 4, Aug.PP:p 336-343.
[108]Eshera M.A., Barash S.C. Parallel rule-based fuzzy inference on mesh-connected systolic arrays.IEEE Expert, v 4, n 4, Winter. PP:27-35.
[109]严蔚敏,吴伟民.数据结构[M].1998年第2版.
[110]Liu, Lei; Zhang, Dingfei,Li Hengjie,Chen Li.Automatic implementation of multi-partitioning using global tiling. Source:Proceedings of the International Conference on Parallel and Distributed Systems-ICPADS,2008, ICPADS'08.PP:p 673-680.
[111]Martinez Tony R, Campbell Douglas M.A. self-organizing binary decision tree for incrementally defined rule-based systems. IEEE Transactions on Systems, Man and Cybernetics, v 21, n 5, Sep-Oct. PP:1231-1238.
[112]Paul Sujni, Saravanan, V.Hash.Partitioned Apriori in parallel and distributed data mining environment with dynamic data allocation approach. Source:Proceedings of the International Conference on Computer Science and Information Technology, ICCSIT 2008.PP:p 481-485.
[113]Hui, K.C.; Kan, Y.M. Data partitioning for parallel solid modelling. Source:Visual Computer, v 11.n 10,1995.PP:p 526-541
[114]Palomo M., Martin-Mateos F.J, Alonso J.A. Rete algorithm applied to robotic soccer. Lecture Notes in Computer Science, v 3643 LNCS,2005.PP:p 571-576.
[115]Derks E.P.P., Beckers M.L.M., Melssen W.J. Buydens, L.M.C. Parallel processing of chemical information in a local area network-Ⅱ. A parallel cross-validation procedure for artificial neural networks. Computers and Chemistry, v 20, n 4, Aug 23.PP:439-448.