At present, due to the unavailability of natural resources, society should take the maximum advantage of data, information, and knowledge to achieve sustainability goals. In today’s world condition, the existence of humans is not possible without the essential proliferation of plants. In the photosynthesis procedure, plants use solar energy to convert into chemical energy. This process is responsible for all life on earth, and the main controlling factor for proper plant growth is soil since it holds water, air, and all essential nutrients of plant nourishment. Though, due to overexposure, soil gets despoiled, so fertilizer is an essential component to hold the soil quality. In that regard, soil analysis is a suitable method to determine soil quality. Soil analysis examines the soil in laboratories and generates reports of unorganized and insignificant data. In this study, different big data analysis machine learning methods are used to extracting knowledge from data to find out fertilizer recommendation classes on behalf of present soil nutrition composition. For this experiment, soil analysis reports are collected from the Tata soil and water testing center. In this paper, Mahoot library is used for analysis of stochastic gradient descent (SGD), artificial neural network (ANN) performance on Hadoop environment. For better performance evaluation, we also used single machine experiments for random forest (RF), K-nearest neighbors K-NN, regression tree (RT), support vector machine (SVM) using polynomial function, SVM using radial basis function (RBF) methods. Detailed experimental analysis was carried out using overall accuracy, AUC–ROC (receiver operating characteristics (ROC), and area under the ROC curve (AUC)) curve, mean absolute prediction error (MAE), root mean square error (RMSE), and coefficient of determination (R2) validation measurements on soil reports dataset. The results provide a comparison of solution classes and conclude that the SGD outperforms other approaches. Finally, the proposed results support to select the solution or recommend a class which suggests suitable fertilizer to crops for maximum production.

No abstract

No abstract

In the current world scenario, the existence of human is impossible without the necessary proliferation of plants. Health of plant depends on water and soil nutrition that help plants to produce energy. Apply appropriate recommended fertilizer quantity is necessary for a healthy plant. However, due to overexposure, soil sometimes gets degraded, so fertilizer is an important element to retain the soil quality. Now a days decision support system plays a vital role in the recommendation. These recommendation systems are based on historical data. In this respect, soil analysis is an appropriate approach to determine the soil quality. Soil analysis generates a report of unstructured and unperceivable data by testing soil in laboratories that make it agriculture big data. This type of systems generally has been implemented in the banking and health care sector for fraud detection and patient recommendations, respectively. In this paper, we have been proposed fertilizer recommendation system based on present nutrition quantity in the soil. In this system, the useful data is extracted from soil analysis reports and save into two files: 1) first file save soil nutrition composition and solution number that act as the label in 2) second file save solution number and recommended fertilizer quantity. Soil composition encoded into vector use by classification system to trained system. In this research work, SGD big data analysis machine learning techniques are applied to identify the fertilizer recommendation classes based on present soil nutrition composition. Here, SGD classification system is used to train the system. Our proposed system obtained 64.08% total average accuracy. The proposed model can also be used by agriculture experts to recommend fertilizer quantity according to crop type and present nutrition composition.

Web data mining is a field that has gained popularity in the recent time with the advancement in web mining technologies. Web data mining is the extraction of data on web. The term Web Data Mining is a technique used to crawl through various web resources to collect required information, which enables an individual or a company to promote business, understanding marketing dynamics, new promotions floating on the Internet, etc. The data on web is unstructured, irregular and lacks a fixed unified pattern as it is presented in HTML format that represents data in the presentation format and is unable to handle semi-structured or unstructured data . These difficulties lead to the emergence of XML based web data mining. XML was created so that richly structured documents could be used over the web.XML provides a standard for the data exchange and data storage .This paper presents a web data mining model based on XML. In this model first of all unstructured data is transformed to XML and then XML document is stored in database in the form of the string tree, then specific records are searched using a LINQ query. If record does not exist in the database then check the updates of specific website and repeat the same steps. At last data selected by LINQ Query is displayed on web browser. The feature that helped to increase the speed of data extraction and that also reduces the time of extraction is the presence of database that stores the data that have been extracted earlier by a user and can be used by other users by passing a LINQ query .In this model there is no need to create an extra separate XSL file because this model stores xml document in the database in the form of the string tree. This model is implemented using C# with XML.