International Journal of Engineering Research in Electronics and Communication Engineering

Classification of Business Crop Disease by Data Analytics

Author : Chintha Sireesha ¹ Dr.M.S.S.Sai ²

Date of Publication :20th April 2018

Abstract: Due to automation, the term, data is large in amount so it is transformed as big data in many fields. Rapid advancements in the robotics cause floricultural data to participate in the era of big data. Traditional tools and techniques are side-lined to store and to determine this process on the part of data. To save and resolve this type of data is comparable in computing and in figuring out the need of model. Big data problem-solving is used as a quick solution to fix the problem.. To reach this solution we use Hadoop and Hive tools. The data is poised, cleansed and distribute. Data is encrypted from research laboratory reports and web sites etc. then cleansing of data is done i.e. necessary information which is extracted from disorderly unnecessary data. In the next step, we finish the normalization process. Later, Normalized data is uploaded on HDFS and save in a file placed hive. Havel is a SQL like interrogate sound which identifies some crop contamination symptoms like plague and so. And benefit an explanation occupying on evince from historical data. Result is picturized in the model graphs. That will compare the result with other with other diseases of the crop

Reference :

1. F. C. Heilbron and J. C. Niebles, “Collecting and annotating human activities in web videos,” in Proc. Int. Conf. Multimedia Retrieval, 2014, p. 377.
2. N. Hung, et al., “On leveraging crowdsourcing techniques for schema matching networks,” in Proc. Int. Conf. Database Syst. Adv. Appl., 2013, pp. 139–154. [15] P. G. Ipeirotis, et al., “Quality management on amazon mechanical turk,” in Proc. SIGKDD Workshop Human Comput., 2010, pp. 64–67.
3. P. G. Ipeirotis and E. Gabrilovich, “Quizz: Targeted crowdsourcing with a billion (potential) users,” in Proc. 23rd Int. Conf. World Wide Web, 2014, pp. 143–154.
4. K. J€arvelin and J. Kek€al€ainen, “Cumulated gainbased evaluation of ir techniques,” ACM Trans. Inf. Syst., vol. 20, no. 4, pp. 422–446, 2002.
5. M. Joglekar, et al., “Comprehensive and reliable crowd assessment algorithms,” in Proc. Int. Conf. Data Eng., 2015.
6. H. Kaplan, I. Lotosh, T. Milo, and S. Novgorodov, “Answering planning queries with the crowd,” Proc. VLDB Endowment, vol. 6, no. 9, pp. 697–708, 2013.