Journal of Applied Sciences ›› 2018, Vol. 36 ›› Issue (3): 515-523.doi: 10.3969/j.issn.0255-8297.2018.03.011

• Computer Science and Applications • Previous Articles     Next Articles

Agricultural Drought Vulnerability Evaluation of Gansu Province

DAI Yong-qiang1,2, WANG Lian-guo1, HU Bin2   

  1. 1. College of Information Science & Technology, Gansu Agricultural University, Lanzhou 730070, China;
    2. College of Information Science and Engineering, Lanzhou University, Lanzhou 730000, China
  • Received:2017-09-01 Revised:2017-09-29 Online:2018-05-31 Published:2018-05-31

Abstract:

Address to the multidimensionality and the uncorrelation of agricultural drought vulner-ability evaluation indicators a new method, projection pursuit based on the improved shufed frog leaping algorithm, is used to evaluate the agricultural drought vulnerability. By combining the chemotaxis operation of bacteria foraging algorithm with the shufed frog leaping algorithm, the method enhances the individual refnement searching ability within solution domain and improves the optimizing accuracy and stability of the projection pursuit model. The proposed method searches for the optimal projection direction and acquires evaluation index weights basing on characteristics of sample data, accordingly, reducing the interference of artifcial empowerment with evaluation results of objectivity. The feasibility and validity of the method are verifed by the analyzing and evaluating the agricultural drought vulnerability data in 14 regions of Gansu province.

Key words: projection pursuit, projection value, hufed frog leaping algorithm, agricultural drought vulnerability

CLC Number: