Optimal Pattern Mining from Time-Series Cultivation Data of Soybeans for Knowledge Discovery

被引:2
作者
Umejima, Kohei [1 ]
Arimitsu, Fumihito [1 ]
Ozawa, Seiichi [1 ]
Murakami, Noriyuki [2 ]
Tsuji, Hiroyuki [2 ]
Ohkawa, Takenao [1 ]
机构
[1] Kobe Univ, Kobe, Hyogo, Japan
[2] NARO Hokkaido Agr Res Ctr, Sapporo, Hokkaido, Japan
来源
PROCEEDINGS OF THE WORKSHOP ON TIME SERIES ANALYTICS AND APPLICATIONS (TSAA'16) | 2016年
关键词
frequent pattern; optimal pattern; time-series data; smart agriculture; soybean; knowledge discovery;
D O I
10.1145/3014340.3014344
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
Recently, we can analyze and store big data by high performance computers. In this paper, we present a method of optimal pattern mining from soybean cultivation data for knowledge discovery by introducing an evaluation function based on differences in the frequency of high-yields and low-yields. We can discover factors affecting the growth of soybeans by analyzing optimal patterns extracted using evaluation functions. In our proposed method, optimal patterns are enumerated by eliminating elements that decrease the value of evaluation functions from frequent closed patterns. As a result, our experiment showed the efficiency of the proposed method. In addition, we can observe both general and new knowledge by analyzing extracted optimal pattern groups.
引用
收藏
页码:19 / 24
页数:6
相关论文
共 9 条
[1]  
Agrawal R., 1993, SIGMOD Record, V22, P207, DOI 10.1145/170036.170072
[2]  
Fehr W. R., 1977, COOPERATIVE EXTENSIO
[3]  
Japan Agricultural Development And Extension Association (JADEA), 2012, SOYB MAK IMPR YIELD, P2
[4]  
Nakamura S., 1996, WEATHER YIELD GROWTH, P81
[5]  
Ohyama T., 2000, AGR TECHNOLOGY OUTLI, V6, P3
[6]   Simulation of soybean growth and yield in near-optimal growth conditions [J].
Setiyono, T. D. ;
Cassman, K. G. ;
Specht, J. E. ;
Dobermann, A. ;
Weiss, A. ;
Yang, H. ;
Conley, S. P. ;
Robinson, A. P. ;
Pedersen, P. ;
De Bruin, J. L. .
FIELD CROPS RESEARCH, 2010, 119 (01) :161-174
[7]  
Uno T, 2004, LECT NOTES COMPUT SC, V3245, P16
[8]  
Xin D., 2006, Proceedings of the 12th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD'06), P444, DOI DOI 10.1145/1150402.1150452
[9]  
Yumoto S., 2013, TOHOKU AGR RES CTR, V64, P39