### Table 2. Trajectory Outlier Limits

"... In PAGE 6: ... The limits are a function of phase of flight. Trajectory segments with a calculated error outside of any one of the limits shown in Table2 were excluded from all segment statistics. The majority of the exclusions were due to large cross track errors.... In PAGE 7: ...head times of fifteen minutes, calculated with the baseline trajectory prediction algorithm, are shown in Fig. 4. The total number of level flight segments with data for a look-ahead time of fifteen minutes was 813, including outliers. Approximately 17 percent of the segments were excluded from the statistics based on the limits defined in Table2 . The mean and standard deviation for the along track error of the remaining 672 segments were -1.... In PAGE 9: ... 10. Climb data outliers were excluded from the statistical segments based on the limits defined in Table2 . All but two outliers were attributed to excessive cross track error.... ..."

### Table 4: Time spent on queries with the trajectory operator.

"... In PAGE 10: ... This operation is even simpler, it just scans the array containing the units, because the complete spatial information of the movement is contained in this array. Table4 shows the time spent to perform the following query with the trajectory operator: SELECT trajectory(trip) FROM R This is another operation that takes advantage of the com- pact representation proposed in this paper for data with pe- riodicity. Again, for the data set without periodicity, the performance of both approaches is still similar.... ..."

### Table 1: The computation time for the multi-stage op- timization of the sequences in Fig. 7.

2003

"... In PAGE 6: ... From the trajectories tracked throughout the sequence, we removed outlier trajectories using the method of Sugaya and Kanatani [16]. Table1 lists the number of frames, the number of inlier trajectories, and the computation time for our multi-stage optimization. We reduced the com- putation time by compressing the trajectory data into 8-dimensional vectors [14].... ..."

Cited by 9

### Table 1: Heteroscedastic pbM and pbM-Real data Inliers Outliers

"... In PAGE 6: ... To get an estimate of the ground truth the cor- rect point matches were extracted by inspection, and were used to estimate the true fundamental matrix using HEIV [7]. The results with 500 elemental subsets of pbM and het- eroscedastic pbM are shown in Table1 . The outliers classi- fied as inliers were found to be points whose epipolar lines passed close to the mismatched points in the other image.... ..."

### Table C.1: Wall-clock times for cluster identi cation with cut-and-stack data mapping on the MasPar MP-2 (all times are in seconds).

### Table C.2: Wall-clock times for cluster identi cation with hierarchical data mapping on the MasPar MP-2 (all times are in seconds).

### Table 1: Arti cial time series data without outliers.

"... In PAGE 3: ... Consider the outlier-contaminated time series shown in Figure 1. The outlier-free data consist of a random realization of n = 50 observations given in Table1 and generated from the AR(3) model, xt = 8 gt; lt; gt; : at t = 1, 2, 3 2:1xt?1 ? 1:46xt?2 + 0:336xt?3 + at t = 4; : : : ; 50; where fatg is a sequence of independent and identically distributed Gaussian variates with mean zero and variance 2 a = 1: The roots of the autoregressive polynomial are 0.... ..."

### Table Table 1. CPU time and the acceleration ratio of O(N) sorting algorithms Algorithm N

1993

Cited by 1

### Table Table 1. CPU time and the acceleration ratio of O(N) sorting algorithms Algorithm N

1993

Cited by 1

### Table 1. Time performance data for tests of distributing integer arrays on a 10-node cluster. The first row gives the size of the integer array. The second, third and fourth rows give the execution times in seconds for FastPara, LAM/MPI and MPICH implementations respectively. Array Size

"... In PAGE 6: ... The networks connecting these nodes are Ethernet at 100 Mbps. Table1 and table 2 give the raw program execution times in seconds with three implementations in two tests respectively. In test 1, when the array size is n, the size the data involved in transmission is about n*4*2 (It is multiplied by 2 since the data are first distributed and then collected).... ..."