A new method of mapping relations from data based on artificial neural network

详细信息    查看全文

• 作者：Yunpeng Li (1)
  Jie Liu (1)
  Qiuchen Bao (1)
  Wenxiao Xu (1)
  Rehan Sadiq (2)
  Yong Deng (1) (3)
  
• 关键词：Artificial neural network ; Relation map ; Machine learning ; Data mining ; Knowledge discovery ; Weather forecast
• 刊名：International Journal of Systems Assurance Engineering and Management
• 出版年：2014
• 出版时间：December 2014
• 年：2014
• 卷：5
• 期：4
• 页码：544-553
• 全文大小：462 KB
• 参考文献：1. Ahn B, Cho S, Kim C (2000) The integrated methodology of rough set theory and artificial neural network for business failure prediction. Expert Syst Appl 18(2):65-4 CrossRef
  2. Augasta MG, Kathirvalavakumar T (2012a) Reverse engineering the neural networks for rule extraction in classification problems. Neural Process Lett 35(2):131-50 CrossRef
  3. Augasta MG, Kathirvalavakumar T (2012b) Rule extraction from neural networks a comparative study. In: International conference on pattern recognition, informatics and medical engineering (PRIME), IEEE, pp 404-08
  4. Awan MSK, Awais MM (2011) Predicting weather events using fuzzy rule based system. Appl Soft Comput 11(1):56-3 CrossRef
  5. Azam S, Sadiq R (2006) Evaluation of slurry settling rate using fuzzy rule-based modeling. Acta Geotechnica 1(3):149-56 CrossRef
  6. Bell JE, Palecki MA, Baker CB et al (2013) US climate reference network soil moisture and temperature observations. J Hydrometeorol 14:977-88
  7. Betrie GD, Tesfamariam S, Morin KA, Sadiq R (2012) Predicting copper concentrations in acid mine drainage: a comparative analysis of five machine learning techniques. Environ Monit Assess 185(5):4171-182 CrossRef
  8. Buckley JJ, Hayashi Y, Czoga?a E (1993) On the equivalence of neural nets and fuzzy expert systems. Fuzzy Sets Syst 53(2):129-34 CrossRef
  9. Coulibaly P, Evora N (2007) Comparison of neural network methods for infilling missing daily weather records. J Hydrol 341(1C2):27-1 CrossRef
  10. Craven MW, Shavlik JW (1991) Visualizing learning and computation in artificial neural networks. Int J Artif Intell Tools 1(3):399-25 CrossRef
  11. Craven MW, Shavlik JW (1994) Using sampling and queries to extract rules from trained neural networks. In: Proceedings of the 11th international conference on machine learning, Citeseer, pp 37-5
  12. Detienne KB, Detienne DH, Joshi SA (2003) Neural networks as statistical tools for business researchers. Organ Res Methods 6(2):236-65 CrossRef
  13. Diamond HJ, Karl TR, Palecki MA et al (2013) US climate reference network after one decade of operations: status and assessment. B Am Meteorol Soc 94:485-98
  14. Elsner J, Tsonis A (1992) Nonlinear prediction, chaos, and noise. Bull Am Meteorol Soc 73:49-44 CrossRef
  15. Fu LM (1991) Rule learning by searching on adapted nets. In: Proceedings of the ninth national conference on artificial intelligence, pp 590-95
  16. Funahashi KI (1989) On the approximate realization of continuous mappings by neural networks. Neural Netw 2(3):183-92 CrossRef
  17. Giorgi MGD, Ficarella A, Tarantino M (2011) Assessment of the benefits of numerical weather predictions in wind power forecasting based on statistical methods. Energy 36(7):3968-978 CrossRef
  18. Hagan MT, Demuth HB, Beale MH et?al. (1996) Neural network design. PWS Publishing, Boston
  19. Hecht-Nielsen R (1989) Theory of the backpropagation neural network. In: Proceedings of the international joint conference on neural networks (IJCNN), IEEE, New York, pp 593-05
  20. Hornik K, Stinchcombe M, White H (1989) Multilayer feedforward networks are universal approximators. Neural Netw 2(5):359-66 CrossRef
  21. Huang SH, Endsley MR (1997) Providing understanding of the behavior of feedforward neural networks. IEEE Trans Syst Man Cybern
• 作者单位：Yunpeng Li (1)
  Jie Liu (1)
  Qiuchen Bao (1)
  Wenxiao Xu (1)
  Rehan Sadiq (2)
  Yong Deng (1) (3)
  
  1. School of Computer and Information Science, Southwest University, Chongqing, 400715, China
  2. School of Engineering, University of British Columbia Okanagan, 3333, University Way, Kelowna, BC, Canada
  3. School of Engineering, Vanderbilt University, Nashville, TN, 37235, USA
  

文摘

Many methods have been proposed to derive patterns and correlations from data, such as artificial neural network (ANN) and support vector machine. They successfully learned the pattern from data but failed to illustrate them to human. In this paper, a new method which reveals the influences between factors and identifies key correlations among them from ANN is proposed. The method extracts the relations as relation maps, which is a perceptive illustration to interpret the actual logic beneath the neuron matrices. In this paper, we propose some definitions, express our method in mathematics, and develop a simplified practical algorithm of our method. Then we apply our algorithm to weather forecast problems. The algorithm successfully excavates the relations among weather factors, maps the relations to explicit graph, identifies the key relations, and thus used to reduces the inputs of predicting ANNs by 60?%. Generally, the pruned ANNs performed effectively. Of all the 14 predicting ANNs, when pruned, 10 have prediction errors no more than 16?% greater than the original ANNs, and 5 of the 10 have even lower prediction errors than before. Such result shows that our method successfully identifies key relations among factors. This is a justification for the reliability of our method on extracting relations encoded in ANNs. This promising method can be widely applied in the field of data mining and knowledge discovery.