Other Applications: Sequential Dependence Modelling and Data Mining - On Statistical Pattern Recognition in Independent Component Analysis Mixture Modelling - page 163

Sources

0

-0.5

-1

0 100 200 300 400 500 600 700 800 900 1000

0

-0.5

-1

0 100 200 300 400 500 600 700 800 900 1000

1

-1

0 100 200 300 400 500 600 700 800 900 1000

0.5

0

-0.5

0 100 200 300 400 500 600 700 800 900 1000

- 0

-10

0 100 200 300 400 500 600 700 800 900 1000

0.5

0

-0.5

0 100 200 300 400 500 600 700 800 900 1000

0.5

0

-0.5

0 100 200 300 400 500 600 700 800 900 1000

0.5

0

-0.5

0 100 200 300 400 500 600 700 800 900 1000

0.5

0

-0.5

0 100 200 300 400 500 600 700 800 900 1000

0.5

-0. 0

0 100 200 300 400 500 600 700 800 900 1000

0.5

-0. 0

0 100 200 300 400 500 600 700 800 900 1000

0.5

0

-0.5

0 100 200 300 400 500 600 700 800 900 1000

Fig. 7.7 Sources calculated by the Mixca algorithm for the data of the graduate courses with

grades

Table 7.4 ICA mixing matrix

LSD a

Sorted web activity contribution

2 Chat Forum News Email Access Exercises

1 0.82283 0.30755 0.16476 0.14756 0.14231

Wg-doc b

4 Email Content Exercises Forum Chat

1 0.34189 0.32297 0.28768 0.22548 0.20078

3 Wg-doc News Achieve Content Chat Email

1 0.80531 0.4122 0.39987 0.39421 0.31666

5' Achieve Content Agenda Access Forum News

1 0.45124 0.2117 0.21116 0.20087 0.18239

5 Access Agenda Content Achieve Email Chat

1 0.95776 0.85549 0.7143 0.5832 0.49774

a

Learning style dimension

b

Workgroup documents

emphasis of educational strategies did not favour highlighting that dimension. The
relationship between learning style dimensions and web activities can be made
using Table 7.4 . Table 7.5 shows the association detected by ICA between
learning styles and web activities (we have added a possible web activity com-
bination for learning dimension 1).