### Table 5 Discretization Scheme - Age Interval

"... In PAGE 15: ... The Mortality Dataset contains two continuous attributes: Age and Month. The discretization schemes of these attributes are shown in Table5 and Table 6 below. Each interval in these tables represents a consistent set of patterns (association rules).... In PAGE 15: ... A new interval is generated by the information- theoretic procedure, when there is a change in the rules explaining the target attribute. Thus, the death causes of infants (Age = 0) are different from children between the ages of one to three (see Table5 ). From looking at interval no.... ..."

### Table III. Proportion of Rule Episodes in which the Role of Deciding

1995

Cited by 3

### Table 1. Parameters of the equivalent discrete system representation (16) and the solutions to the discrete Riccati equations (61) and (82) for three values of .

"... In PAGE 24: ...ot change sign in the interval [0; h), cf. Theorem 5.4 and Remark 5.1. Table1 shows the parameters of the equivalent discrete system representations. It is interesting to note that for the values of shown in the example, the discrete systems are unsta- ble, although the continuous-time system (104) is stable.... ..."

### Table 3. Underlying illnesses of 246 patients who died during 1998-2005 after ingesting a lethal dose of medication, compared with 74,967 Oregonians dying from the same underlying diseases.

2006

"... In PAGE 3: ...Table 2..................................................................................................... 21 Table3 .... In PAGE 12: ... These include people age 85 or older, people who did not graduate from high school, people who are married or widowed, and Oregon residents living east of the Cascade Range. Patients with certain terminal illnesses were more likely to use PAS ( Table3 ). The ratio of DWDA deaths to all deaths resulting from the same underlying illness was highest for three conditions: amyotrophic lateral sclerosis (ALS) (269.... ..."

### Table 7. Comparison of results for R = 10000 by using the adaptive algorithm

1998

"... In PAGE 11: ... Numerical computations show that this adaptive MQ o ers much better results near the peak of the shock wave. Compared with FEM with moving nodes, this adaptive MQ is much easier to implement and, as shown in Table7 , o ers much better numerical results. 4.... ..."

Cited by 14

### Table 15 The discretization scheme of randomly selected attribute from the dataset thy by CACC: (a) three intervals; (b) five intervals Class Interval Total

2007

"... In PAGE 17: ...orm one interval [0.0098,0.041]. The corresponding discretization schemes containing three and five intervals are illustrated in Table15 . In summary, we can conclude from this experiment that CACC can, on the average, generate a good discretization scheme even if it uses a greedy approach.... ..."

### Table 1. When the slice (with parameter all, for example) is applied on the temporal role-node JOB, a new role-node r is created whose related classes are JOB All, EMPLOYEE, PROJECT, SALARY-VALUE and the class ALL (according to the given parameter) representing the time intervals. So, the tabular representation of the interpretation for the role-node r is shown in Table 2.

"... In PAGE 3: ... In short, we share with the majority of temporal data models the notion that the time domain is linearly ordered, discrete, bounded in the past and unbounded in the future (Morris amp; Khatib 1997). An example of using the Graph Model, in order to model the information concerning employment agencies is presented in Figure 1 and Table1 . Figure 1 shows the typed graph g with the constraints.... In PAGE 3: ... Figure 1 shows the typed graph g with the constraints. Table1 contains a possible interpretation m for g. For the sake of simplicity, the interpretation is listed only for a subset of the nodes.... In PAGE 4: ...m(Person) = fho1;o2;o3;o4ig m(Name) = fhPerson : o1;String : Maryi; hPerson : o2;String : Peteri, hPerson : o3;String : Johni;hPerson : o4;String : Annig m(Job) = fhEmployee : o1; Salary ? V alue : 5000; Project : p1;fh1; 5i;h8;10igi hEmployee : o1;Salary ? V alue : 6000; Project : p2;fh6; 7igi hEmployee : o2;Salary ? V alue : 10 000;Project : p3;fh3;5igi hEmployee : o3;Salary ? V alue : 8000; Project : p2;fh2; 7igig m(Level) = fhEmployee : o1;Integer : 1; fh1;5i;h8;10igi, hEmployee : o1;Integer : 2;fh6; 7igi, hEmployee : o2;Integer : 6;fh3; 5igi, hEmployee : o3;Integer : 4;fh2; 7igig m(Integer) = Z m(String) = fa :: :z;1 :::0g Table1 An Interpretation m for g The details of the Graph Model and its temporal extension is out of the scope of this paper. The interested reader can refer to (Catarci et al.... ..."

### Table 4. The mean number of intervals produced by different discretization methods

"... In PAGE 6: ... This accuracy is usually higher on the test (unseen) data, in comparison to the accuracy based on decision trees with no pruning. Table4 shows the mean number of intervals produced by CloNI, PKID, and Entropy discretization methods. ... In PAGE 8: ... From both Table 2 and 3, it is apparent that even though CloNI is not a winning method for every single dataset, it gives improvement on accuracies over PKID on all datasets, and gives the best classification accuracies on larger datasets. In addition, from Table4 , we can see that the number of intervals produced by CloNI is about 3 times fewer than what PKID would produce, and yet give higher accuracies that PKID. And even though the number of intervals produced by the Entropy method is relatively small, it does not always guarantee high classification accuracy.... ..."

### Table 2: Initial rules

"... In PAGE 1: ... Initially, every age forms an interval of its own and each row maps to an associ- ation rule. See Table2 . If we merge ages [40; 40] and [45; 45] into interval [40,45], there is an information loss... ..."

### Table 2. The Representation of the Interval Information of Orientations and the Ratio Information of Distances Methods Interval Information Ratio Information

1997

"... In PAGE 10: ... Representation of interval informa- tion. Table2 shows the representation of the interval and ratio information for the five methods. In the VOR method (Figure 6A), the interval relation (the angular dif- ference) between the heading and the north is represented externally in the heading indicator because it is perceptu- ally available.... In PAGE 12: ... This is because the amount of cognitive processing that can take place in working memory is limited by the lim- ited capacity of working memory. If we use the amount of information repre- sented in external representations as a measure of representational efficiency (see Table2 ), we can get a representa- tional efficiency order, from most efficient to least efficient: Modified Map = Map gt; RMI gt; ADF gt; VOR. The more direct is the reading of numerical values, the more efficient is the display, because a more direct reading re- quires less mental computation.... ..."

Cited by 7