rnn appraoch for machine learning with datamining.pptx

sadas

1. A Recurrent Neural Network Approach for Feature Selection using Cloud Database

2. Introduction Combination of Cloud Computing, Neural Network and Feature Selection. Datasets stored in the cloud database are retrieved from the cloud environment train the data sets using feed-back neural network by applying proposed feature selection method to achieve the target concepts. better than the Conventional models handles noisy data and removes redundant, irrelevant features while considering feature interaction.

3. Data Mining Nontrivial extraction of implicit, previously unknown and potentially useful information from data in databases. Also known as KDD ( Knowledge Discovery in Databases )

4. Steps in KDD Data cleaning Data integration Data selection Data transformation Data mining Pattern evaluation Knowledge representation

5. Architecture of a typical Data mining System

6. Data Mining Techniques Association Classification Clustering Prediction Decision Trees Neural Networks

7. Data Preprocessing Incomplete, noisy, and inconsistent data are commonplace properties of large real world databases and data warehouses. Duplicate tuples also require data cleaning Need for data reduction A database/data warehouse may store terabytes of data Complex data analysis/mining may take a very long time to run on the complete data set

8. Data reduction strategies Data cube aggregation Dimensionality reduction — e.g., remove unimportant attributes Data Compression Numerosity reduction — e.g., fit data into models Discretization and concept hierarchy generation

9. Dimensionality Reduction Technique Principal component analysis Singular value decomposition Supervised and nonlinear techniques ( e.g., Feature Selection )

10. Feature Selection pre-processing step in data mining process which selects the most “relevant” subset of attributes according to some selection criteria. Two Commonly used approaches followed in feature selection are Wrapper approach Filter approach Wrapper approach is generally more accurate but also more computationally expensive.

11. Feature Selection Algorithm General Algorithm for Feature Selection Input: S- data sample with features X, |X| = n J – Evaluation measure to be Maximized GS – Successor generation Operator Output: Solution – (Weighted) feature subset L := Start_Point (X); Solution = { best of L according to J}; repeat L:= Search_Strategy ( L, GS(J),X); X ’ := { best of L according to J}; if J(X’)>=J(Solution) or (J(X’) = J(Solution) and |X’|< |Solution|) then Solution := X’; until Stop(J,L)