scispace - formally typeset
Search or ask a question
Topic

Decision tree model

About: Decision tree model is a research topic. Over the lifetime, 2256 publications have been published within this topic receiving 38142 citations.


Papers
More filters
Patent
07 Sep 2016
TL;DR: In this paper, a matched relationship retrieval method and system is proposed, which comprises the steps of after a retrieval request signal is received, obtaining a first actual unit required to be retrieved currently from the retrieval request signals, and locating a current node of the first actual units in a free tree model; and by taking the current node as a root node, retrieving associated nodes associated with the root node level by level according to a connection path of the free-tree model based on a first configuration file corresponding to the current vertex, and obtaining a matched actual unit associated with a current vertex
Abstract: The invention discloses a matched relationship retrieval method and system The method comprises the steps of after a retrieval request signal is received, obtaining a first actual unit required to be retrieved currently from the retrieval request signal, and locating a current node of the first actual unit in a free tree model; and by taking the current node as a root node, retrieving associated nodes associated with the root node level by level according to a connection path of the free tree model based on a first configuration file corresponding to the current node, and obtaining a matched actual unit associated with the first actual unit from the associated nodes According to the method and system, based on the pre-established free tree model, actual unit sets are represented with nodes in the free tree model, an associative relationship among the actual unit sets is represented with the connection path in the free tree model, and the retrieval is carried out level by level according to the connection path of the free tree model, so that an automated chain type retrieval effect is achieved; and finally the problem of low efficiency of a conventional manual form query mode is solved

2 citations

Journal Article
TL;DR: A new algorithm for classification rules extraction by choosing attributes of importance of attributes and dependance based on rough set is presented, which can extract crisp rules from classification information system.
Abstract: The decision tree is a usual method of classification in data mining.In the process of constructing a decision tree,the criteria of selecting attributes to split will influence the efficiency of classification directly.The decision tree algorithm traditionally is based on information theory measure.Presented a new algorithm for classification rules extraction by choosing attributes of importance of attributes and dependance based on rough set.Using this algorithm,can extract crisp rules from classification information system.Compared with the traditional ID3 algorithm,it's simpler in the structure,and can improve the efficiency of classification.

2 citations

Journal ArticleDOI
01 Dec 2011
TL;DR: This study proposes a new model named Real Option Decision Tree Model which is a conceptual combination form of ROA and DTA and it is possible for the decision-makers to simulate the project value applying the uncertainties onto the decision making nodes.
Abstract: RD they are based on traditional methods such as Discounted Cash Flow (DCF), Decision Tree Analysis (DTA) and Real Option Analysis (ROA) or some fusion forms of the traditional methods. However, almost of the models have constraints in practical use owing to limits on application, procedural complexity and incomplete reflection of the uncertainties. In this study, to make the constraints minimized, we propose a new model named Real Option Decision Tree Model which is a conceptual combination form of ROA and DTA. With this model, it is possible for the decision-makers to simulate the project value applying the uncertainties onto the decision making nodes.

2 citations

Book ChapterDOI
09 Jul 2009
TL;DR: This work proposes a new alignment, taking in account the homeomorphism between trees, rather than the isomorphism, as in prior works, and develops several computationally efficient algorithms for reaching real-time motion capture.
Abstract: Motion capture, a currently active research area, needs estimation of the pose of the subject. For this purpose, we match the tree representation of the skeleton of the 3D shape to a pre-specified tree model. Unfortunately, the tree representation can contain vertices that split limbs in multiple parts, which do not allow a good match by usual methods. To solve this problem, we propose a new alignment, taking in account the homeomorphism between trees, rather than the isomorphism, as in prior works. Then, we develop several computationally efficient algorithms for reaching real-time motion capture.

2 citations

Book
14 Jun 2009
TL;DR: Numerical results are obtained for several difficult test data sets indicating that GA-based instance selection can often reduce the size of the decision tree by an order of magnitude while still maintaining good prediction accuracy.
Abstract: This book describes theoretical and experimental studies of instance selection to improve data mining model. Data preparation is one of the most important and time consuming phases in knowledge discovery. Preparation tasks often determine the success of data mining engagements. The importance of instance selection is the primary focus because the size of current and future databases often exceeds the amount of data which current data mining algorithms can handle properly. Instance selection thus can be used to improve scalability of data mining algorithms as well as improve the quality of the data mining results. This book presents a new optimization-based approach for instance selection that uses a genetic algorithm to select a subset of instances to produce a simpler decision tree model with acceptable accuracy. The resultant trees are easier to comprehend and interpret by the decision maker and hence more useful in practice. Numerical results are obtained for several difficult test data sets indicating that GA-based instance selection can often reduce the size of the decision tree by an order of magnitude while still maintaining good prediction accuracy.

2 citations


Network Information
Related Topics (5)
Cluster analysis
146.5K papers, 2.9M citations
80% related
Artificial neural network
207K papers, 4.5M citations
78% related
Fuzzy logic
151.2K papers, 2.3M citations
77% related
The Internet
213.2K papers, 3.8M citations
77% related
Deep learning
79.8K papers, 2.1M citations
77% related
Performance
Metrics
No. of papers in the topic in previous years
YearPapers
202310
202224
2021101
2020163
2019158
2018121