### Table 1. The perturbed results arising from the deletion of each point estimated to a rst order approximation using Equation 5.

1997

"... In PAGE 14: ... It can be seen that points 1 and 7 lie furthest from the centre of the ellipses. Z = V U gt; which on inserting values is 2 6 6 6 6 6 4 ?3:28 ?2:00 ?2:28 ?1:00 ?1:28 0:00 ?0:28 0:00 ?0:28 1:00 0:71 2:00 6:71 0:00 3 7 7 7 7 7 5 = 2 6 6 6 6 6 4 0:48 ?0:44 0:20 ?0:30 ?0:08 ?0:15 ?0:017 ?0:03 ?0:36 ?0:01 ?0:64 0:13 0:41 0:81 3 7 7 7 7 7 5 h 8:08 0:00 0:00 2:86 i h 0:18 ?0:98 0:98 0:18 i: Using Equation (5) with these values gives the the perturbed results (u11(i); u12(i)) which are given in Table1 and plotted in Figure 6. Also shown in Figure 6 are concentric ellipses corresponding to increasing values of the in uence measure Ti determined from the covariance matrix of the parameter estimate.... ..."

Cited by 156

### Table 2: N-point crossover: best amount of disruptiveness for di erent combinations of the selection and deletion schedules on Schwefel function (#Xp. = number of crossover points).

1995

"... In PAGE 7: ... Table 1 contains a brief summary of results obtained when optimizing the Schwefel function using the modi ed diagonal crossover. Table2 contains the same summary for a GA using the n-point crossover. When using a random deletion schedule, which most closely corresponds to a generational GA, a large tournament size is needed to in order to nd the global optimum.... ..."

Cited by 5

### Table 2: N-point crossover: best amount of disruptiveness for di erent combinations of the selection and deletion schedules on Schwefel function (#Xp. = number of crossover points).

in Raising GA Performance by Simultaneous Tuning of Selective Pressure and Recombination Disruptiveness

1995

"... In PAGE 6: ...Table 1 contains a brief summary of results obtained when optimizing the Schwefel function using the modi ed diagonal crossover. Table2 contains the same summary for a GA using the n-point crossover. When using a random deletion schedule, which most closely corresponds to a generational GA, a large tournament size is needed to in order to nd the global optimum.... ..."

Cited by 5

### Table 4: N-point crossover: best amount of disruptiveness for di erent combinations of the selection and deletion schedules on Griewangk function (#Xp. = number of crossover points).

1995

"... In PAGE 9: ... = number of parents). when applying the modi ed diagonal crossover and Table4 shows the results when applying the n-point crossover. Again we see that a low selective pressure combined with reasonably high disruptiveness of the recombination operator seems the appropriate setting.... ..."

Cited by 5

### Table 4: Storage overhead correlated to the average number of \outlying quot; points in each bounding box. (Algorithm-B, polynomial t of degree 6, and quot; = 0:05) As expected, we observe that the number of bounding boxes decreases as we increase the capacity of the over ow arrays. The resulting curves can be used for interpolation, but the storage overhead associated with this algorithm is still unacceptable. Algorithm-C: Table 5 shows data points distributions with respect to the relative error levels, when tting the synthetic data set with a 6-degree polynomial using Algorithm-C. One can observe that there is a limit to deleting \bad quot; points. If this limit is exceeded, the performance will degrade. For example consider the number of points whose relative error is with 0.05. Deleting points whose relative errors are greater than 0:1 (iteration 4), results in a 522 points instead of the 544 points when deleting the points with relative error greater than 0.2 (iteration 3). Algorithm-C adjusts by picking the best t (iteration 5). Furthermore, due to the 10

### Table 6: List of 2 DF in distinct solutions obtained after deleting undetermined parameters; NExp = 411 experimental points. (To save the space only the best unphysical solutions of the \DRNbior quot; variant are shown.)

"... In PAGE 24: ...ameters had no influence on the above conclusions 1.{4. whereas the number of parameters in e ect had been considerably reduced. The new inferences derived from the Table6 read: 5. The considered data base requires a complicated model for its description.... In PAGE 26: ... The parameter g1 of the paper [21] is found to be relatively important, the D{waves parameters g2, g3 being much less necessary. For illustrations we have chosen the solution from the \DRNbior quot; variant with 2 DF =1:16 (see Table6 ). The data on total cross sections and the theoretical curves in terms of the quasi{amplitude (15) are drawn in Fig.... In PAGE 32: ...quantities D1 and D2 found in the solution with 2 DF =1:16 (see the variant \DRNbior quot; of the Table6 for values of scattering lengths). We also quote here the predictions of papers [12, 57, 13] and the results ALL and TRI of the linear t from the Table 7 for an easy comparison.... ..."

### Table 3. Results for Manual 1 data with deletions

2002

"... In PAGE 8: ... To test how well the algorithms perform on more difficult data, we applied both the method based only on sentence length and the hybrid method to versions of the Manual 1 data, from which single blocks of 50, 100, and 300 sentences had been deleted from one side of the corpus at a randomly chosen point. The results of this experiment are shown in Table3 , for the 0.5 probability threshold.... ..."

Cited by 13

### Table 4.1: Comparison of [26] and the Proposed Method on TIMIT and SWITCHBOARD. I - number of Insertions, D - number of Deletions F-female, M-male, CPs - Change Points

2005

### Table 4.2: Comparison of conventional GMM evaluation and voting on SWITCHBOARD. I - number of Insertions, D - number of Deletions F-female, M-male, CPs - Change Points

2005