Knowledge Discovery
Code
10287
Academic unit
Faculdade de Ciências e Tecnologia
Department
Departamento de Engenharia Electrotécnica
Credits
6.0
Teacher in charge
Pedro Alexandre da Costa Sousa
Weekly hours
4
Total hours
56
Teaching language
Português
Objectives
Knowledge:
Knowledge Discovery
Datamining
ETL
Datawarehouse
Do:
Algorithm specification.
Assembly programming
Specification, Development and implementation of datamining
Non-Technical:
Written and oral communication skills
Demonstration skills
Produce reports of analysis, design and implementation of a solution
Work management, time management and delivery deadlines
Teamwork and tem participation
Delivery
Honesty
Prerequisites
Not defined
Subject matter
Introduction
• Bussiness inteligence
• Inteligent systems
• Data «warehouse»
Anexo A – Ficha da unidade curricular – 2012/13 Pág.4 - 6
• Knowledge discovery
Managing Knowledge discovery projects
• CRISP-DM, SEMMA
• Knowledge discovery
• Typical problems
• Techniques
• Input/output data
• Preprocessing data
• Data Quality
• Results Quality
Learning
• Classification/regression
Statistic approach
Decision tress
Rules
Error
• Segmentation
• Association
•Ethics and privacy
Bibliography
Data Mining from Eibe Frank, Christopher Pal, Mark Hall e Ian H. Witten
ISBN: 9780128042915,Edition: 11-2016 Editor: ELSEVIER SCIENCE & TECHNOLOGY
Advances In Knowledge Discovery And Data Mining from Padhraic Smyth, Ramasamy Uthurusamy, Gregory Piatetsky-Shapiro e Usama M. Fayyad ISBN: 9780262560979Edition: 03-1996 Editor: MIT PRESS LTD
Teaching method
The course is divided into theoretical classes and theoretical-practical classes.
In the theoretical the subjects are introduced and practical problems are formulated that the students have to solve in the respective pratical classes.
In the theoretical-practical classes the execution of the problems (implementation) is carried out.
All the work that the students develop in practice is part of a larger work (integration) that students have to deliver in a defined time frame, together with a report of analysis, design and implementation.
Evaluation method
Theoretical component (weight of 34%) - NT:
===========================================
Can be performed through 1 test or exam;
It is necessary to have a grade (of exam or average of the tests) of not less than 9.5 values.
Theoretical Practical component (weight of 66%) - NTP:
=========================================
2 Work. Delivery through Moodle. Evaluation based on implemented functionalities.
It is necessary to have average grade of not less than 9.5 values.
NOTE: Approvals from the previous two semesters can be used this semester.
Calculation of final grade - NF:
====================
NF = 34% * NT + 66% * NTP