Given temperature data record for five working days. The hourly temperature measurements for a complete working day are stored in a file in random order. That is, for five working days we have 5 files and each file has 8 temperature measurements (that are normalized).

Given data record:

File1=[0.1, 0.2 ,0.8, 0.4, 0.5, 0.5, 0.6, 0.5];

File2=[0.1, 0.3, 0.3, 0.3, 0.4, 0.7, 0.6, 0.7];

File3=[0.5, 0.6, 0.7,0.8, 0.1, 0.8, 0.8, 0.9 ];

File4=[0.5, 0.6, 0.7,0.8, 0.1, 0.8, 0.8, 0.9 ];

File5=[0.5, 0.6, 0.7,0.8, 0.1, 0.8, 0.8, 0.9 ];

a) Perform Feature extraction from the given record.

1) Compute maximum value feature.

2) Compute minimum value feature.

3) Compute mean value feature.

Note: all four feature values must be written in tabular form (i.e., Max | Min| Mean)

b) Perform feature reduction.

The features extracted from the above tasks are three:

5) Reduce the feature set to two features using the low variance filter technique.

6) Write reduced feature set (of two features) in a table and the variance of each feature at the end of the table.

c) Perform visualization and determine feature similarity.

7) Using the reduced data set of two features compute correlation coefficient.

8) Draw the reduced feature set in 2-D and label each dimension.