COMPUTATIONAL INTELLIGENCE FOR DATA ANALYTICS

CSE5CI

2018

Credit points: 15

Subject outline

Quantitative analysis plays an important role in business analytics and knowledge engineering, thus it is very useful to develop computing skills for data regression and classification. This subject covers some fundamentals of computational intelligence techniques, including linear regression analysis, fuzzy inference systems, neural networks and hybrid neuro-fuzzy systems. The subject is designed with a focus on solving time-series forecasting problems using fuzzy inference systems, where fuzzy inference mechanisms and fuzzy rule extraction from numerical data are addressed. Some advanced learning techniques for training neural networks will also be highlighted. In labs and assignment students will work with business datasets for time-series prediction using a fuzzy system and neural networks with advanced learning algorithms, which help to consolidate the knowledge taught in the lectures and gain a hands-on experience on computational intelligence applications in business.

SchoolSchool Engineering&Mathematical Sciences

Credit points15

Subject Co-ordinatorJustin Wang

Available to Study Abroad StudentsYes

Subject year levelYear Level 5 - Masters

Exchange StudentsYes

Subject particulars

Subject rules

Prerequisites CSE4DBF or admission into one of the following courses: SMIT, SMICT,SMITCN SMCSC, SGIT, SGCS or SMDS.

Co-requisitesN/A

Incompatible subjects CSE3CI and CSE4CI

Equivalent subjectsN/A

Special conditions Students in the following courses are not permitted to enrol: SBCS, SBIT, SBCSGT, SVCSE, SZCSC, SBITP and SBBIY.

Readings

Resource TypeTitleResource RequirementAuthor and YearPublisher
Discipline SpecificArtificial intelligence-a guide to intelligent systemsPreliminaryM. NegnevitskyAddison Wesley; 3 edition (November 9, 2011)
ReadingsNeural fuzzy systems-a neuro-fuzzy synergism to intelligent systemsRecommendedC. T. Lin, C. S. LeePrentice-Hall. 1996

Graduate capabilities & intended learning outcomes

01. Explain the technologies and applications of computational intelligence systems (CIS) for data analytics.

Activities:
Lecture 1 is on the introduction of computational intelligence systems and its applications in data analytics.
Related graduate capabilities and elements:
Inquiry/ Research
Critical Thinking
Creative Problem-solving

02. Describe the major components and system design in developing computational intelligence systems for data modelling i.e., data regression and classification.

Activities:
Lectures 2, 3, 4, 5 are on linear regression analysis, fuzzy logic and fuzzy inference systems. Lectures 6, 7, 8 are on how to build predictive models using neural networks.
Related graduate capabilities and elements:
Critical Thinking
Creative Problem-solving
Quantitative Literacy/ Numeracy
Inquiry/ Research

03. Apply learnt knowledge and skills to analyse data, design, implement and evaluate computational intelligence systems for real world problem solving

Activities:
Lecture 9 and 10 give some case studies, demonstrating the value and usefulness of computational intelligence systems for data analytics.
Related graduate capabilities and elements:
Critical Thinking
Creative Problem-solving

04. Implement a fuzzy expert system and a neural network for time-series forecasting with real world data from industry.

Activities:
Lab 1 to Lab 6 are on fuzzy expert system implementation, where students will learn how to use Matlab tools to implement a computational intelligence system for resolving a time-series forecasting problem. Lab 7 and Lab 8 are on neural network modeling and applications.
Related graduate capabilities and elements:
Quantitative Literacy/ Numeracy
Ethical Awareness
Critical Thinking
Teamwork
Creative Problem-solving
Inquiry/ Research
Discipline-specific GCs

Subject options

Select to view your study options…

Start date between: and    Key dates

Melbourne, 2018, Semester 1, Blended

Overview

Online enrolmentYes

Maximum enrolment sizeN/A

Enrolment information

Subject Instance Co-ordinatorJustin Wang

Class requirements

Lecture Week: 10 - 22
One 2.0 hours lecture per week on weekdays during the day from week 10 to week 22 and delivered via face-to-face.

Laboratory Class Week: 11 - 22
One 2.0 hours laboratory class per week on weekdays during the day from week 11 to week 22 and delivered via face-to-face.

Assessments

Assessment elementComments% ILO*
Assignment 1 - Fuzzy expert system design (equiv to 750-1500 words)20 04
Assignment 2 - Neural networks modeling (Group project) (equiv to 750-2000 words)A 30-40 pages presentation slide20 04
3 hour Exam60 01, 02, 03