Tree methods

CBDTM Cause Based Decision Tree Method Singh et al, 1993... 

The SCB distribution (SCBD) has been extensively studied by fractionation based on compositional difference as well as molecular size. The analysis by cross fractionation, which involves stepwise separation of the molecules on the basis of composition and molecular size, has provided information of inter- and intramolecular SCBD in much detail. The temperature-rising elution fractionation (TREE) method, which separates polymer molecules according to their composition, has been used for HP LDPE it has been found that SCB composition is more or less uniform [24,25]. It can be observed from the appearance of only one melt endotherm peak in the analysis by differential scanning calorimetry (DSC) (Fig. 1) [26]. Wild et al. [27] reported that HP LDPE prepared by tubular reactor exhibits broader SCBD than that prepared by an autoclave reactor. The SCBD can also be varied by changing the polymerization conditions. From the cross fractionation of commercial HP LDPE samples, it has been found that low-MW species generally have more SCBs [13,24]. 

Eisenberg JNS, McKone TE. 1998. Decision tree method for the classification of chemical pollutants Incorporation of across-chemical pollutants Incorporation of across-chemical variability and within-chemical uncertainty. Environ Sci Technol 32 3396-3404. 

Mokashi, S. D. and A. Kokossis. The Maximum Order Tree Method A New Approach for the Optimal Scheduling of Product Distribution Lines. Comput Chem Eng 21 S679-684 (1997). 

Causal Trees were developed in an effort to use the principles of deductive logic found in Fault Tree but make it more user-friendly. Originally, private companies developed the Causal Tree Method (CTM) for safety, process safety, and environmental incident investigations applications. Rhone-Poulenc, for example, was an early user.<20.21) Multiple-Cause Systems Oriented Incident Investigation (MCSOfl) is another name for the CTM. At this time, most companies use simplified versions of fault trees for complex incident investigations. 

Causal tree methods rely on group discussion among experts from different fields, including workers, witnesses, supervisors, and process safety specialists. Starting at the end event, and working one level of the tree at a time, the group asks three questions ... 

Figure 9-1, the two flowcharts describing root cause determinations using Methods A and B, presents general frameworks for root cause determination. Method A focuses on the logic tree method using a simplified fault tree approach. Method B focuses on the predefined tree method. 

Root Cause Determination Using Logic Trees—Method A... 

Next the team develops a chronology of events based on the available known times and sequences. This document is usually referred to as a timeline. (See the detailed description of timeline development in Section 9.3.) Unconfirmed assumptions regarding chronology should be clearly identified as unconfirmed, and action should be initiated to verify assumptions. Many investigators use relatively simple timelines (instead of sequence diagrams) with the logic tree methods because the logic tree itself shows the interactions of events and conditions. 

Root Cause Determination Using Predefined Trees— Method B... 

The decision tree method of Cramer et al. (1978) was based on the toxicological data then available and used a series of 33 questions, each leading either to another question or to classification into one of three classes of presumptive toxicity. The questions were primarily based on chemical stmcmre, but namral occurrence in body tissues or fluids as well as natural occurrence in traditional foods was also considered. The three classes of substances were defined as follows ... 

The spherical parametrization (1) can be graphically exhibited by the tree method [13] (see Fig. 1(a)). To compare the volume element in momentum space ... 

Recursive partitioning was originally called the decision tree method (31) the goal of this method is to divide the dataset up using a series of simple rules,... 

The orthogonality of a set of molecular descriptors is a very desirable property. Classification methodologies such as CART (11) (or other decision-tree methods) are not invariant to rotations of the chemistry space. Such methods may encounter difficulties with correlated descriptors (e.g., production of larger decision trees). Often, correlated descriptors necessitate the use of principal components transforms that require a set of reference data for their estimation (at worst, the transforms depend only on the data at hand and, at best, they are trained once from some larger collection of compounds). In probabilistic methodologies, such as Binary QSAR (12), approximation of statistical independence is simplified when uncorrelated descriptors are used. In addition,... 

In chemoinformatics research, partitioning algorithms are applied in diversity analysis of large compound libraries, subset selection, or the search for molecules with specific activity (1-4). Widely used partitioning methods include cell-based partitioning in low-dimensional chemical spaces (1,3) and decision tree methods, in particular, recursive partitioning (RP) (5-7). Partitioning in low-dimensional chemical spaces is based on various dimension reduction methods (4,8) and often permits simplified three-dimensional representation of... 

Descriptor requirements present a significant difference between MP and decision tree methods such as RP. Whereas two-state descriptors are not suitable for MP, these types of descriptors are typically required for decision tree algorithms because at each branch the presence or absence of specific feature(s) must be detected in order to recursively divide a molecular dataset. 

Topliss Decision Tree Method. This method is quicker and easier to use than the Hansch method. The Topliss scheme is an empirical method in which each compound is tested before an analog is planned, and is compared in terms of its physical properties with analogs already planned. Like the Free-Wilson method, the Topliss decision tree is no longer extensively used. The 2D- and 3D-QSAR methods are gradually supplanting the ID methods. 

The methodology that was selected for this taxonomy of pretreatment processes is the objectives-tree method developed by Swager (7) Lipinsky (8), Janstch (9), and others (10) for presentation of alternatives in a systematic structure. 

Phylogenetic analysis is the means of inferring or estimating evolutionary relationships. Nucleotide sequences of DNA or RNA and amino acid sequences of proteins are the most popular data used to construct phylogenetic trees. Methods of phylogenetic analysis using sequence data are introduced and performed with a software package, PHYLIP locally and online. 

In addition to cell-based partitioning, statistical partitioning methods are widely used for compound classification. One of the most popular approaches is recursive partitioning (Rusinko et al. 1999), a decision tree method, as illustrated in Figure 1.8. Recursive partitioning divides data sets along decision trees formed by sequences of molecular descriptors. At each node of the tree, a descriptor-based decision is made and the molecular data set is subdivided. For example, a chosen descriptor could simply detect the presence or absence of a structural fragment in a molecule. Alternatively, the... 

This phase classifies chemicals passing from the previous phase into active and inactive categories. Three structural alerts (Section IV.B), seven pharmacophore queries (Section IV.C), and the Decision Tree classification model (Section IV.D) were used in parallel to discriminate active from inactive chemicals. To ensure the lowest false negative rate in this phase, a chemical predicted to be active by any of these 11 models is subsequently evaluated in Phase III, whereas only those predicted to inactive by all these models are eliminated for further evaluation. Since structural alert, pharamacophore and Decision Tree methods incorporate and weight differently the various structural features that endow a chemical with the ability to bind the ER the combined outputs derived... 

Finally, the example given here shows the possibilities of the Incident Production Tree method to go beyond the single near miss originally reported, by adding alternative failure (or recovery) elements if these seem realistic according to the sourcc(s) describing the near miss backgrounds. 

Traps compared to Trap Trees. Trap-trees have been used in Europe for more than 200 years to control the spruce bark beetle (14). One reason for developing pheromone traps is to replace the trap-tree method, which has become more and more expensive. An average trap-tree (20 cm d.b.h.) will be occupied by about 6500 beetles (12). Average trap-catches in 1980 were 7406 beetles. Within 2-3 weeks parent beetles occupying a trap-tree have utilized the phloem suitable for breeding so most of them emerge to attack another tree. After 3-4 weeks only 10-20% of the beetles are left. Trap-trees therefore have to be removed from the forest... 

Monothetic divisive clustering has largely been ignored, although there have been applications and development of a classification method closely related to monothetic divisive clustering. This classification is recursive partitioning, a type of decision tree method. 

---