Data Mining

Data Mining

EG 3212 CT

	Total:   7 hour /week
Year:            III	Lecture:   3 hours/week
Semester:    VI	Tutorial: 1 hours/week
	Practical:  3 hours/week

Course Introduction

Data Mining studies algorithms and computational paradigms that allow computers to find patterns and regularities in databases, perform prediction and forecasting, and generally improve their performance through interaction with data. The course will cover all these issues and will illustrate the whole process by examples. 

Objectives   

The general objectives of this course are as follows:

•       To introduce concept of data preprocessing and data mining 

•       To discuss multi-dimensional data representation and OLAP operations

•       To provide skill of illustrating clustering, classification, and association rule mining algorithms

•       To introduce advanced concept of data mining

Course Contents: 

Unit	Topics	Contents	Hours	Methods/ Media	Marks
1	Introduction to Data Mining	1.1 Data Mining Concepts, KDD vs Data Mining, Data Mining System Architecture 1.2 Data Mining Functionalities, Kinds of Data on which Data Mining is Performed 1.3 Applications of Data Mining,	(5Hrs)
2	Data Warehouse and OLAP	2.1 Data Warehouse definition and Characteristics, DBMS vs Data Warehouse, Multi-dimensional Data, Data Cube, Cube Materialization 2.2 Data Warehouse Schemas: Star, Snowflake and Fact Constellation Schema 2.3 OLAP Operations: Roll-up, Drill, Down, Slice & Dice, and Pivot Operations	(6Hrs)

Unit	Topics	Contents	Hours	Methods/ Media	Marks
		2.4 OLAP       Servers:          ROLAP, MOLAP,        HOLAP,         Data Warehouse Architecture
3	Data Preprocessing and DMQL	3.1 Data Pre-processing Concepts 3.2 Data Cleaning, Data Integration, Data        Transformation,                  Data Reduction 3.3 Data        Discretization        and Concept Hierarchy Generation 3.4 DMQL, Syntax of DMQL, Full Specification of DMQL	(6Hrs)
4	Clustering	4.1 Introduction to Clustering, Distance Measures, Categories of Clustering algorithms 4.2 K-means, and K-medoid algorithms 4.3 Agglomerative Clustering, Concept of Divisive Clustering	(6Hrs)
5	Classification and Prediction	5.1 Concept of Classification and Clustering, Evaluating Classification Algorithms 5.2 Bayesian Classification, Decision Tree Classification, Concept of Entropy 5.3 Linear Regression, Concept of Non-linear regression	(8Hrs)
6	Association Rule Mining	6.1 Frequent Patterns, Association Rule, Concept of Support and Confidence 6.2 Apriori Property, Apriori algorithm, Generating Association Rules 6.3 FP-growth algorithm, FP-tree, Generating Association Rules	(8Hrs)
Unit	Topics	Contents	Hours	Methods/ Media	Marks
7	Advanced Data Mining	7.1 Information Retrieval, Measuring Effectiveness of Information Retrieval 7.2 Concept of Time-Series Data and Analysis, Image and Video Retrieval 7.3 Concept of Support Vector Machine and Deep Learning	(6Hrs)
8	Laboratory Work	Perform the following: 1      Design data warehouse by using SQL Server or Oracle 2      Implement OLAP operations 3      Implement clustering algorithms K-means and Kmedoid by using Weka 4      Implement classification algorithms Naïve-Bayes and decision trees by using Weka 5      Implement regression algorithms by using Weka 6      Implement association mining algorithms by using Weka	45hrs

Recommended Books

1. Jiawei Han, MichelineKamber, Jian Pei; Data Mining: Concepts and Techniques, Morgan Kaufman Publication, 3^rd Edition, 2011

References

2.     Pang-Ning Tan, Michael Steinbach, AnujKarpatne, Vipin Kumar, Introduction to Data Mining, Pearson Publication, First Edition, 2013

3.     Charu C. Agrawal, Data Mining: The Textbook, Springer Nature Publication, First Edition,

2015