Data Mining

Jing-Doo Wang, jdwang@asia.edu.tw, ext: 1847.
Time: Monday, 9:10am~12:00am,
Room: I533

Discussion Group :Facebook DataMining_AsiaUniversity
Instead of theoretical proof, this data mining course aims to have students learn from hands-on experiments such that they can get impressive experiences when handling different types of data. First of all, this course introduces fundemental data mining technigues based on Weka, one well-known data mining sofeware in Java, to show the concepts of classication techniques, such as decision tree, k-Nearest nieghbor and navie bayes classifiers. To emphasize the importance of data preprocessing, the "Python" (Anacoda) is required as one of programming language to have data ETL(extracting, transformation and loading). The middle project is based on the prediction of NBA game winnner with on-line open source data. To learn the techniques of AI topic "deep neuron network"(DNN), some image classifcaiton experiments with CIFAR&Minist dataset using DNN on Keras are introduced. One homework for images classification, furthermore, using students' personal photos as resources is proposed. The final project, finally, is designed to have students practice with their own data using those data mining techniques learned in this course.
Introduction to Data Mining and Machine Learning Techniques (8 Feb, 2018 in Data Mining Tutorials by Data Flair)
Grade

Score (Report (upload to Moodle) + YouTube (Demo what you have done)()>
  1. On-Line Test& HW1 :(15%)(2018/3/26)
    Install&Practice Data Mining with your own data (small testing set)
    Weka
    WekaPractice
    Data Sets for Data Mining
    Decision Tree (J48(java version of C4.5)) with "iris.arff"
    Learning Data Mining with Python (Second Edition)
    (Chapter 3. Predicting Sports Winners with Decision Trees(Nearest Neighbor Classification (Aconda:Python))

  2. Middle Project:(25%)(Only one ? two as one Group?)(presentation:2018/4/16, Report(Moodle):2018/4/23)
    Decision Tree Project: Predicting Sports Winners (NBA)
    InterActive Scoring and Comments

  3. HW2:(15%)(2018/6/8)
    Image Classification (Deep Learning with Keras + Tensorflow)

  4. Final Project:(40%)(2018/6/11:presentation,2018/6/25:report:moodle)
    Problem-Based Learning ( Weka or RapidMiner or Your own code )(Deep Learning?)
    (2018/5/7) Give a brief description of what you plan to do
    (2018/5/28) Present the proposal of your final project
    (2018/6/11) Final project: Presentation (PPT)
    (2018/6/18) (Off) Dragon Boat Festival
    http://time.com/4797048/dragon-boat-festival-duanwu-tuen-ng/
    (2018/6/25) Final project: Report to Moodle

    IEEE 18th International Conference on BioInformatics and BioEngineering (Taichung, Taiwan from October 29-31, 2018)
    CPF BIBE 2018
    Paper Submission June 30, 2018
    Acceptance Notification July 31, 2018
    Camera-ready Submission August 31, 2018

    5. 2018/6/11
Content Data Mining: Practical Machine Learning Tools and Techniques (4th Edition),
  1. From: Machine Learning Group at the University of Waikato
    Free online courses on data mining with machine learning techniques in Weka

  2. What is the difference between data mining, statistics, machine learning and AI?
  3. Chapter 1. What’s it all about?
    What's the Weka?
    Downloading and installing Weka
  4. Chapter 2. Input: concepts, instances, attributes
    What do you know about the "input" of data mining?
  5. Chapter 3. Output: Knowledge representation
    What do you know about the "output" of data mining?
  6. Chapter 4. Algorithms: the basic methods
    What do you know about the "Algorithm" of data mining?
  7. Chapter 5. Credibility: Evaluating what’s been learned
    What do you evaluate the performance or efficience of one data mining algorithm
  8. Chapter 6. Trees and rules
    DecisionTree_jdwang