4 CST.2005.12.7 5 Computer Graphics and Image Processing (a) Explain why display devices appear to be able to reproduce (almost) all the colours of the spectrum using only red, green and blue light. [4 marks] (b) Describe an algorithm (other than thresholding) which will convert a greyscale image (8 bits per pixel) to a bi-level black and white image (1 bit per pixel), with the same number of pixels, while retaining as much detail as possible. In the two activities being executed? Explain the difference between 'qy' and "qxy" when used as constants in C. Describe the memory representation of both values. [4 marks] 12 Complexity TheoryA You are to create data mining processes where you are predicting US Life Satisfaction (Q49) from the remaining predictors for the World Value Survey (WVS) Wave 7. I would like the process in R to do the following: 1) Read the SPSS file (alternatively you can a csv file) 2) Regroup Q287 into 3 groups: 1&2, 3, 4&5. Afterwards create hot-encoded variables to represent these three levels. 3) Choose the most important variables for life satisfaction - again 5-10 variables are sufficient. Use a random forest to determine importance. Also add the hot-encoded variable for Q287. *Make sure to look at your variables; you don't want proxies of life satisfaction like happiness. The neural network wants numeric variables as categorical ones would require hot encoding as well. 4) Remove all records which have negative values for Q49. This process is only for files that are not representing missing values that are recognized as such in R. 5) Replace missing values in the predictors with their most frequent value (mode). 6) Hot-encode Q49 for two groups of values 1-7 and 8-10. 7) Use a random number seed so that the results can replicated 8) Run a neural network to predict the hot-encoded Q49 variable. 9) For this model, a PMML file 10) Report the confusion matrix and accuracy a java program to an abstract class named Shape that contains two integers and an empty method named printArea(). (b) The method for processing any given position's worth is to include the numbers to the position's both ways in the previous column. For example, to process the center number in the third column, you add 1 and 1; the sides of the triangle are consistently 1 since you just add the number to the upper left or the upper not too far off (being no second number on the opposite side)