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
Journal Article
TL;DR: The prediction for the properties of traditional Chinese medicine components with a decision tree model could reflect the theoretical connotation of the property of traditionalChinese medicine components to some extent and provide a new method for studying the properties.
Abstract: OBJECTIVE To study the relationship between pharmacological effects and properties of traditional Chinese medicine by the decision tree algorithm METHOD Based on of pharmacological effects of traditional Chinese medicine, the decision tree algorithm was applied in the study on the relationship between pharmacological effects and properties of traditional Chinese medicines A model was established with the decision tree algorithm for the purpose of predicting the properties of traditional Chinese medicine components RESULT The established model was reliable and stable, and could be used to predict the properties of traditional Chinese medicine components CONCLUSION The prediction for the properties of traditional Chinese medicine components with a decision tree model could reflect the theoretical connotation of the properties of traditional Chinese medicine components to some extent and provide a new method for studying the properties of traditional Chinese medicine components

1 citations

Proceedings ArticleDOI
01 Dec 2010
TL;DR: The results indicate that the built decision tree model through NDVI, K-T transformation and principal component analysis is reasonable; the overall accuracy is higher than that of K-Mean and maximum likelihood and can provide scientific basis for the ecological health dynamic monitoring and regional sustainable development of Ejina oasis.
Abstract: The accuracy improvement of remote sensing images has been always one of preceding issues in the filed of remote sensing. maximum likelihood to new decision tree, neural networks, wavelet transform and fuzzy recognition system, the classification accuracy has been improved. In this work, based on 3S technology and Landsat ETM data, using 3 classification methods (K-Mean, maximum likelihood and decision tree), Ejina oasis landscape is classified into 6 types: farmland, forestland, grassland, waters, saline land and desert; and the accuracies of the classification results are analyzed. The results indicate that the built decision tree model through NDVI, K-T transformation and principal component analysis is reasonable; the overall accuracy is up to 93.28%, higher than that of K-Mean (86.32%) and maximum likelihood (85.82%) obviously. It can provide scientific basis for the ecological health dynamic monitoring and regional sustainable development of Ejina oasis.

1 citations

Patent
15 Dec 2020
TL;DR: In this paper, a business rule generation method and device, equipment and a storage medium were described, which relates to the artificial intelligence technology, and the method comprisesthe steps: obtaining a tree model matching a business demand, adjusting a model parameter of an initial business model according to the business demand parameter; extracting a text structure of the tree model, and performing format conversion on the text structure, to obtain a treemodel structure in a view format; extracting passing paths of all leaf nodes from the treeModel structure in the view format, and screening all the extracted passing paths
Abstract: The embodiment of the invention discloses a business rule generation method and device, equipment and a storage medium, and relates to the artificial intelligence technology, and the method comprisesthe steps: obtaining a tree model matching a business demand by obtaining a business demand parameter and adjusting a model parameter of an initial business model according to the business demand parameter; extracting a text structure of the tree model, and performing format conversion on the text structure of the tree model to obtain a tree model structure in a view format; extracting passing paths of all leaf nodes from the tree model structure in the view format; and screening all the extracted passing paths according to the business requirements to obtain all the service rules meeting theservice requirements. In addition, the invention further relates to blockchain technology, and the business rules meeting the business requirements can be stored in the blockchain. According to the business rule generation method disclosed by the invention, the business rule generation process is simpler and more efficient.

1 citations

Patent
21 Aug 2020
TL;DR: In this paper, the authors proposed a prediction method for the survival probability of an infectious disease, and a training method and device for a prediction model, which comprises the steps of acquiring diagnosis and treatment data of an infected disease patient to be diagnosed and treated, and extracting a plurality of data features of the diagnosis and treating data; encoding the plurality of feature vectors to obtain feature vectors, and determining a target decision tree model in a trained decision tree set according tothe data features; and inputting the feature vectors into the target decisiontree model to enable the target prediction model to output the
Abstract: The invention belongs to the technical field of data processing, and relates to a prediction method for the survival probability of an infectious disease, and a training method and device for a prediction model. The prediction method comprises the steps of acquiring diagnosis and treatment data of an infectious disease patient to be diagnosed and treated, and extracting a plurality of data features of the diagnosis and treatment data; encoding the plurality of data features to obtain feature vectors, and determining a target decision tree model in a trained decision tree model set according tothe data features; and inputting the feature vectors into the target decision tree model to enable the target decision tree model to output the survival probability of the infectious disease patientto be diagnosed and treated. According to the invention, the problem that accurate estimation cannot be carried out due to lack of data characteristics in clinical practice is solved; the applicationscenarios for predicting the survival probability of infectious disease patients are enriched, inaccurate manual estimation is abandoned in the automatic and intelligent processing process, targeted treatment measures can be conveniently, efficiently and accurately taken for different infectious disease patients, and the situation of medical resource waste caused by missed examination and wrong examination is avoided.

1 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