Results

**11 - 14**of**14**### Table 2: Optimal Homogeneous Con#0Cgurations: Type

"... In PAGE 5: ... In all tables, the optimal values of S a , C 1 , C 2 , and F a as well as the correspond- ing optimal value of the consumed power are tabulated for each of the four cases considered. Notice that optimal values of S a and F a given in Table2 are substantially less than those in Table 3. This is logical considering that the memory to pro- cessor ratio for the type 2 card is much higher than that for the type 1 card, and memory requirements grow linearly with the value of S a #28refer to Eq.... ..."

### Table 4. The Bayesian decision with the minimum risk Risk ratio CCR Std T1ERR T2ERR

"... In PAGE 9: ... As a comparison, we also employ the Bayesian decision with the minimum risk to build a quality prediction model. The results are shown in Table4 , where the first column is the risk ratio of Type I error versus Type II error. We can observe that SVM with risk is superior to the Bayesian decision based on the minimum risk in the classification performance.... ..."

### Table 2 shows the ratio of the energies of coe cients with q = 1 and q = 2,

in and

2002

"... In PAGE 16: ...method B yc x y Is Iq 0:0 0:01 0:01 0 3:43 1:14 0:95 0:01 0:01 0 3:25 5:4 0:0 0:01 0:1 0 0:41 21:0 0:95 0:01 0:1 0 0:23 57:5 0:0 0:1 0:01 0 19:45 0:06 0:95 0:1 0:01 0 18:45 0:23 0:0 0:1 0:01 45 1:36 1:24 0:95 0:1 0:01 45 0:88 26:0 Table2 : Global index for the aspect ratio Is and type-speci c coe cient energy ratio Iq for the example of the two-dimensional Gaussian bump (40). The transform was performed with N = 256.... ..."

### Table 6{1):

"... In PAGE 8: ... The results are shown below: ANOVA Table Degrees Sum of of Mean Source squares freedom square Ratio Type 10 684 2 5 342 7:9114 Temperature 39 119 2 19 559 28:9677 Interaction 9 614 4 2 403 3:5595 Error 18 231 27 675 TOTAL 77 647 35 A program in R to carry out the example is given below. Note that in the program a * is used instead of a + to ensure that an interaction term is allowed for: cat( quot;\nData from D C Montgomery, Design and Analysis of \n quot;) cat( quot;Experiments, (4th edn), Wiley 1997, Table6 -1. \n\n quot;) dat lt;- c(130, 155, 34, 40, 20, 70, 74, 180, 80, 75, 82, 58, 150, 188, 136, 122, 25, 70, 159, 126, 106, 115, 58, 45, 138, 110, 174, 120, 96, 104, 168, 160, 150, 139, 82, 60) temp lt;- gl(3,2,36,labels=c(15,70,125)) type lt;- gl(3,12,36) mod lt;- lm(dat ~ type*temp) print(anova(mod)) References D G Lewis, The Analysis of Variance, Manchester University Press 1971 (SF 2.... ..."

**11 - 14**of

**14**