Semester:4

Credit: 2

Program:Computer Science

Course Module:Specialized Optional

Responsible: Yu Mei

E-mail: yumei@tju.edu.cn

Department:College of Intelligence and Computing, Tianjin University

Time Allocation (1 credit hour = 45 minutes)

0

4

28

0

0

12

Prerequisite

Ÿ Mathematical statistics and analysis: concepts and methods

Ÿ Data structure: data storage and query method

Course Objectives

This coursediscusses basic concepts ofdata mining to help studentsfind potential knowledge. After this course, students should be able to:

Ÿ Understand what data mining is and how to cope with the actual problem with data mining method.

Ÿ Master the related algorithms about on-line analytical processing (OLAP), classification, clustering, prediction and so on.

Ÿ Identify several data mining strategies and the application environment of each strategy.

Ÿ Comprehensively understand how to establish a model through data mining technology to solve an actual problem.

Course Syllabus

Ÿ Data mining overview: definition, task, mining object.

Ÿ Data: attributes, basic statistical description, similarity and dissimilarity.

Ÿ Data preprocessing: data, data quality issues, data preprocessing.

Ÿ Data warehousing and OLAP: design, implement, OLPA, metadata model.

Ÿ Regression analysis: basic concepts, univariate linear regression, multiple linear regression, Polynomial regression.

Ÿ Association analysis: definition, task, Apriori algorithm, FP- tree algorithm.

Ÿ Clustering: definition, main method.

Ÿ Classify: definition, decision tree, Naive Bayesian.

Ÿ Classification methods, such as decision tree, naive bayesian, and neural network.

Ÿ Exception Mining: definition, application, exception data generation causes, solutions.

Textbooks & References

Ÿ Yu Mei, Yu Jian. Data Analysis and Data Mining (2nd Edition). Tsinghua University Press, 2020.

Ÿ Jiawei Han and Micheline Kamber, Data Mining: Concepts and Techniques, China Machine Press,2006.

Ÿ D. Hand, H.Mannila and P. Smith, Principle of Data Mining, Springer, 2004.

Ÿ Pang-Ning Tan,Michael Steinbach andVipin Kumar, Introduction to Data Mining, Addison Wesley, 2005.

Ÿ Te-Ming Huang, Vojislav Kecman and Ivica Kopriva, Kernel Based Algorithms for Mining Huge Data Sets: Supervised, Semi-supervised and Unsupervised Learning, Springer, 2006.

Capability Tasks

CT1: Tounderstand the concept of data analysis and data mining, master the data types of analysis and mining, be able to apply the methods of data analysis and data mining

CT2: Be able to explain the properties of the data, master the basic statistical description of the data, and explain the similarities and differences of the data.

CT3: Understand the problems existing in data, master the concepts and methods of data cleaning, and be able to implement data integration and data reduction.

CS1:To master the basic concepts of data warehouse, implement data warehouse design, master the implementation method of data warehouse, understand online analytical processing, and be able to describe metadata models.

CS2:Be able to describe the concept of frequent patterns, master Apriori algorithm and FP-growth algorithm, understand compression frequent itemsets and association pattern evaluation.

Achievements

Ÿ To understand the application scenarios of data analysis and mining-Level: N

Ÿ To Master the properties of the data and how to describe them, the design and implementation of a data warehouse and three types of regression analysis methods. -Level: M

Ÿ To apply data mining technology to solve practical problems. -Level: M

Ÿ To master the methods of various types of data classification, data clustering and exceptionmining. -Level: M

Students: Computer Science，Year 1, Year2, Year3; Smart Medicine Year 2

Assessment：

Exam

Assignment

Report

Term Paper

Presentation

Others

√

√

Language of assessment：Chinese

Attendance： 0 % Homework: 30 %

Mid-term report/test：0 % Final report/test： 70 %