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 published on a yearly basis
Papers
More filters
••
01 Dec 2020TL;DR: In this article, a preliminary power prediction model is proposed for building power-efficient GPU applications, which combines the information derived from static analysis of a CUDA program and a machine learning-based model.
Abstract: Graphics Processing Unit (GPU) has emerged as a popular computing device to achieve Exa-scale performance in High-Performance Computing (HPC) applications. While the power-performance ratio is relatively high for a GPU, it still draws a significant amount of power during computation. In this paper, we propose a preliminary power prediction model which can be used by developers for building power-efficient GPU applications. Using this proposed work, developers can estimate the power consumption of a GPU application during implementation without having to execute it on actual hardware. Our model combines the information derived from static analysis of a CUDA program and a machine learning-based model. We have utilised decision tree technique to validate results across three different GPU architectures: Kepler, Maxwell and Volta. Observed $R^{2}$ score value using the decision tree model is 0.8973 for Volta architecture.
••
29 Apr 2023TL;DR: Wang et al. as discussed by the authors used decision tree classification algorithm the employment situation of college students based on their past educational background and work experience, and took the enrollment, student status management and employment data of Yunnan Institute of Mechanical and Electrical Technology as samples, analyzed the employment factors of students through learning decision tree classifier, and obtains the scores of student enrollment, comprehensive quality evaluation
Abstract: Decision tree is a data analysis method that can be used to predict the future behavior of individuals based on their past behavior. This technology is very effective in predicting the future employment situation of students, because it takes into account all relevant factors that affect a person's job prospects. In this paper, I will use decision tree classification algorithm the employment situation of college students based on their past educational background and work experience. This paper is based on the quality requirements of higher vocational education, based on the classification analysis algorithm in data mining and machine learning, and taking the enrollment, student status management and employment data of Yunnan Institute of Mechanical and Electrical Technology as samples, analyzes the employment factors of students through learning decision tree classifier, and obtains the scores of student enrollment, comprehensive quality evaluation The prediction model of the region and nature of the employment unit on the smooth employment and the type of the employment unit is designed to provide a scientific basis for the employment guidance and talent training program of higher vocational colleges, and has certain practical value.
••
27 Aug 2001TL;DR: This paper investigates the help bit problem in the decision tree model proposed by Nisan, Rudich and Saks (FOCS '94), and shows new functions satisfying the above conditions whose complexity are only 2√k.
Abstract: In this paper, we consider the help bit problem in the decision tree model proposed by Nisan, Rudich and Saks (FOCS '94). When computing k instances of a Boolean function f, Beigel and Hirst (STOC '98) showed that ⌊log2 k⌋ + 1 help bits are necessary to reduce the complexity of f, for any function f, and exhibit the functions for which ⌊log2 k⌋+1 help bits reduce the complexity. Their functions must satisfy the condition that their complexity is greater than or equal to k - 1. In this paper, we show new functions satisfying the above conditions whose complexity are only 2√k. We also investigate the help bit problem when we are only allowed to use decision trees of depth 1. Moreover, we exhibit the close relationship between the help bit problem and the complexity for circuits with a majority gate at the top.
••
01 Jul 2019
TL;DR: Intelligent automatic end-to-end link fault diagnosis based on an artificial intelligence expert system is realized in communication network management.
Abstract: Automatic link fault diagnosis has always been a difficult problem in communication network management due to link complexity and fault factors. This paper analyzes the traditional link state monitoring technology and its deficiency, and studies the application of the CLIPS expert system in automatic link fault diagnosis in communication network. The fault tree and decision tree model of link faults are established and an expert system knowledge base is constructed. An automatic CLIPS-based link fault diagnosis system is designed. Simulation experiments verify the efficiency and accuracy of the automatic fault diagnosis mechanism of the system. Intelligent automatic end-to-end link fault diagnosis based on an artificial intelligence expert system is realized.
•
08 May 2020
TL;DR: In this paper, the authors proposed a travel mode planning method consisting of the following steps: receiving a travel-planning request sent by a user terminal, wherein the travel-mode planning request carries a current geographic position and a target position; querying a weather state corresponding to the current geographical position; acquiring classification nodes in a pre-trained decision tree model when the weather state meets the requirement.
Abstract: The invention relates to a user travel planning method, a user travel planning method device, computer equipment and a storage medium. The travel mode planning method comprises the following steps of:receiving a travel mode planning request sent by a user terminal, wherein the travel mode planning request carries a current geographic position and a target position; querying a weather state corresponding to the current geographic position; acquiring classification nodes in a pre-trained decision tree model when the weather state meets the requirement, wherein the pre-trained decision tree model is obtained by training according to preset statistics and multiple corresponding travel modes; determining a target parameter according to the classification nodes, and querying and/or calculatinga current geographic position and classification parameters corresponding to the target position according to the target parameter; inputting the classification parameters into the pre-trained decision tree model, and judging the classification parameters by means of the classification nodes in the pre-trained decision tree model to obtain travel modes corresponding to the classification parameters; and sending the travel modes to a user terminal. By adopting the travel mode planning method, the intelligent level can be improved.