| Autor: |
Reddy, S. Venkatramana, Saheb, S. Hussain, Reddy, N. Konda, Sarojamma, B. |
| Předmět: |
|
| Zdroj: |
AIP Conference Proceedings; 5/11/2023, Vol. 2707 Issue 1, p1-6, 6p |
| Abstrakt: |
Outlier means points lie outside the normal data. Outlier plays an important role in model fitting. If outlier is involved in data, models may be over fitted or under fitted. Detection of outlier is important for fitting the best model to data. In data mining techniques for detection of outliers DBSCAN Clustering method, Isolation Forest etc. are used. In this paper for rainfall data for detection of outliers DBSCAN clustering method is used. After detecting outliers we removed that and we run regression models of data mining techniques such as Linear Regression(LR), k-Nearest Neighbors(k-NN), Decision Tree(DT), Support Vector Machines(SVM) and Multi-Layer Perceptron(MLP) using WEKA software. Using the accuracy measures such as Mean absolute error(MAE), Root mean square error(RMSE) criterion, we choose the best model among five regression algorithm of data mining techniques for rainfall data. [ABSTRACT FROM AUTHOR] |
| Databáze: |
Complementary Index |
| Externí odkaz: |
|
