Applying Data Mining Techniques on Soil Fertility Prediction

Baskar, S.; Arockiam, L.; Charles, Stephen P.

doi:10.7753/ijcatr0206.1005

Cited by 22 publications

(12 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…and Charles, S "Soil Classification Using Data Mining Techniques A Comparative Study" used classification techniques called JRip & J48, Naive Bayes which are acted on the data sets of the soil. Skyline shrewd examples were gathered and portrayed for significant physical and concoction following standard strategies [4]. To identify the fertility prediction of the soil Bhuvaneswari, S., Pramananda Perumal, T., Jagadhesan, B.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Classification of Soil Based on Fuzzy Logics

M.H¹,

kumari²

2019

International Journal of Advanced Research in Computer and Comm

View full text Add to dashboard Cite

The quick height in innovation has made information in plenty which has both required just as undesirable. So as to truncate the undesirable information and order, plentiful of data mining methods has been actualized. The primary objective of information mining is to gather, pre-process and order the information dependent on specific highlights of soil, for ex, PH, Nitrogen, Oxygen and Carbon percent of soil and foresee the harvests developed for the particular soil type. The application provides a deep insight of the behaviour of the soil in a particular region. It provides a feature extraction method to sort the data set according to the users need and thereby determining the necessary values of certain attributes. The decision makers can easily focus on the content they are interested on under certain context in the sub-classifications by grouping the attributes. Information from different nations are assembled and broke down and were determined based predefined Fuzzy Rules which has returned the precise and recall as result at the end of an output. fuzzy principles so as to diminish the number of fuzzy guidelines. At that point, we compute the heaviness of each info variable showing up in the produced fuzzy standards by the connections of information factors. Weighted fuzzy principles strategy gets a higher normal characterization exactness rate than the ones. This is benevolent for the researchers to help them estimate the type of soil required for cultivation of crops on the different varieties of land. ACKNOWLEDGEMENTThe satisfaction of completing any task would be incomplete without mentioning the people without whom this endeavor would have been a difficult one to accomplish. I would like to extend heartfelt gratitude to Dr. M. Sharmila Kumari, HOD, Department of Computer Science and Engineering for her continuous guidance and support in every stage of this main project. I would like to thank our Principal Dr. Abdul Sharif for his support and encouragement during the process of this main project. I am indebted to the entire faculties Department of CSE for their help and cooperation. It is a great pleasure for me to acknowledge the valuable suggestions, help, and ideas of all my friends. Most importantly I thank the Almighty and my family for their blessings and continuous support.

show abstract

Section: Related Workmentioning

confidence: 99%

“…Arrangement and bunching is the real procedure in information mining to settle AI process. Information from different nations are assembled and investigated and were determined dependent on pre-characterized Fuzzy Rules which restored the exact result toward the end as a yield [4].…”

Section: Introductionmentioning

confidence: 99%

Classification of Soil Based on Fuzzy Logics

M.H¹,

kumari²

2019

International Journal of Advanced Research in Computer and Comm

View full text Add to dashboard Cite

show abstract

“…This work [15] uses the techniques of data mining to analyze soil datasets. These data mining algorithms are used for classification purposes to test the soil datasets.…”

Section: Literature Reviewmentioning

confidence: 99%

Applications of FP Growth and Apriori Algorithm for Mining Fuzzified Spatial Dataset

Matapurkar,

Shrivastava

2019

IJEAT

View full text Add to dashboard Cite

Spatial data, also called geospatial data, is term needed to describe data linked to or containing knowledgeable data about a particular location on Earth’s surface. Spatial data mining's primary goal is to uncover hidden complicated information from spatial & non-spatial information in spite of their enormous quantity and find the spatial relations density. Spatial Data Mining techniques, however, continue to be an expansion of individuals utilized in standard data mining. Spatial Data is an extremely challenging area since enormous quantities of spatial data have been obtained from the remote sensed to the GIS (Geographic Information Systems), ecological estimation, computer cartography, planning and many more. In a given paper, we only focus on an essential type of spatial vagueness termed as spatial fuzziness. Spatial fuzziness intakes the property of several spatial objects in certainty which don’t contain boundaries of sharp type and interiors or whose boundaries as well as interiors can't be determined in precise form. This paper provides the method for finding fuzzy spatial data of association rule. Association rules provided valuable data in the assessment of important correlations observed in big databases. Compared to the previous research work, the current approach for there search highlights the superiority over the same dataset in terms of time taken and generated rules. The rules generated tell about the occurrence of attributes. The results show that the current research is more efficient than that of the previous work and also less time-consuming.

show abstract

“…These data mining techniques also analyse the factors that are responsible for the cause of disease this include type of food, living conditions, availability of pure water, etc. Health care organization develops an extensive data which is found difficult to analyse and to make a proper decision regarding patient health, treatment costs and other details of hospitals; in this case, data mining tool is helpful [4]. Kidney disease is increasing, and its prevailing seeks public attention, the high cost of treatment for this illness and the negligence may lead to cardiovascular [5].…”

Section: Introductionmentioning

confidence: 99%

Performance Comparison of Some Classifier for Chronic Kidney Disease

Nasuha¹

2019

International Journal of Advanced Research in Computer and Comm

View full text Add to dashboard Cite

Nearly 10 percent of the world's population is affected by a major chronic kidney disease health issue. However, systematic and automatic methodologies are evidently used to predict chronic kidney disease. Machine training is one of the very kind methodologies. The classifier in the machine learning algorithms can provide known features and unknown class to the test samples with class labels. Existing works with machine learning algorithms do not provide the predictive accuracy to the extent required. To satisfy the gap, this initiative offers a new approach for the classification of acute renal illness with environmental variables from the medical dataset. The goal of this initiative is to forecast renal illness through the use of machine learning algorithm that supports vector machine (SVM). The primary goal of this study is to forecast renal disease using classification algorithms such as closest neighbour Optimal Fuzzy-K and Support-Vector-Machine. This study work concentrates primarily on discovering the finest classification algorithm based on the precise classification and output time variables. It is noted from the experimental outcomes that the SVM's output is a lot productive than the closest neighbouring machine Optimal Fuzzy-K. The precision is regarded to be the main measure for quality evaluation, and it is proven that the suggested technique offers greater precision in classification.Here the accuracy produced by KNN is 33.33 and accuracy produced by SVM is 6.666.as SVM produced higher accuracy than KNN we can say that SVM is more efficient than KNN. Figure 5 shows the graphical representation of KNN and SVM accuracy comparison. Figure 5 : Graphical Representation ACKNOWLEDGMENTThe satisfaction of completing any task would be incomplete without mentioning the people without whom this endeavour would have been a difficult one to accomplish. I would like to extend heartfelt gratitude to Dr. M. Sharmila kumari , HOD, Department of Computer Science and Engineering for her continuous guidance and support in every stage of this main project. I would like to thank our Principal Dr. Abdul Sharif for his support and encouragement during the process of this main project. I am indebted to the entire faculties Department of CSE for their help and cooperation. It is a great pleasure for me to acknowledge the valuable suggestions, help, and ideas of all my friends. Most importantly I thank the Almighty and my family for their blessings and continuous support.

show abstract

Applying Data Mining Techniques on Soil Fertility Prediction

Cited by 22 publications

References 6 publications

Classification of Soil Based on Fuzzy Logics

Classification of Soil Based on Fuzzy Logics

Applications of FP Growth and Apriori Algorithm for Mining Fuzzified Spatial Dataset

Performance Comparison of Some Classifier for Chronic Kidney Disease

Contact Info

Product

Resources

About