检索结果-内蒙古大学图书馆

Prediction of unplanned islanding using an energy based strategy

IET GENERATION TRANSMISSION & DISTRIBUTION 2016年第1期10卷 183-191页

作者： Kamali, Sadegh Amraee, Turaj Bathaee, Seyed Mohammad Taghi KN Toosi Univ Technol Dept Elect Engn Tehran Iran

In this study a new index is proposed for power system islanding prediction. The total energy absorbed by coherent synchronous generators during unplanned islanding conditions is formulated as an islanding predictor. decision tree (DT) algorithm is utilised to extract the information gain of the proposed predictor over the input training samples. A comprehensive list of input scenarios, including island and non-island conditions is constructed. The rotor angles of synchronous generators are estimated by phasor measurements at generators' terminals and used for calculating the predictor over the input samples. The results of DT algorithm are rearranged as a set of if-then rules for practical applications. The proposed method is implemented in the 10-machine 39-bus New-England test system.

关键词： synchronous generators decision trees phasor measurement rotors power distribution faults power distribution protection unplanned islanding prediction energy based strategy power system islanding prediction coherent synchronous generators islanding predictor decision tree algorithm information gain extraction input training samples island condition non island condition DT algorithm rotor angle estimation phasor measurements 10-machine 39-bus New-England test system

来源：评论

学校读者我要写书评

暂无评论

Simulation of E-learning in English learner writing teaching based on natural language processing and machine learning algorithms

引用

ENTERTAINMENT COMPUTING 2024年 50卷

作者： Li, Yuntao Li, Xiang Li, Xueqin Mianyang Teachers Coll Sch Foreign Languages Mianyang 621006 Sichuan Peoples R China Mianyang Teachers Coll Sch Literature & Hist Mianyang 621006 Sichuan Peoples R China Mianyang Nanshan Middle Sch Mianyang 621006 Sichuan Peoples R China

This article collected a large number of writing samples from computer English learners, which included various types of writing errors. Subsequently, natural language processing techniques were used to extract and preprocess the features of these writing samples. Select the decision tree algorithm as the construction method for the error classification model, and classify the samples by constructing a tree like structure. In the process of building the model, writing samples are used as training sets, feature values are used to determine the type of writing errors, and they are classified. Based on the classification results of the model for samples, corresponding correction suggestions and improvement strategies are provided. A fault classification model based on natural language processing and decision tree algorithm is constructed, and corresponding correction suggestions and improvement strategies are provided. This model has shown good results in experiments and evaluations, and can accurately identify and correct various common writing errors. The research results indicate that the method is effective in helping computer English learners improve their writing ability and accuracy. Future research will further explore other machine learning algorithms and technologies to further improve the effectiveness of error classification and correction.

关键词： Natural language processing decision tree algorithm Writing errors System design

来源：评论

学校读者我要写书评

暂无评论

A robust approach to pore pressure prediction applying petrophysical log data aided by machine learning techniques

引用

ENERGY REPORTS 2022年 8卷 2233-2247页

作者： Zhang, Guodao Davoodi, Shadfar Band, Shahab S. Ghorbani, Hamzeh Mosavi, Amir Moslehpour, Massoud Zhejiang Univ Technol Coll Comp Sci & Technol Hangzhou 310023 Peoples R China Tomsk Polytech Univ Sch Earth Sci & Engn Lenin Ave Tomsk Russia Natl Yunlin Univ Sci & Technol Future Technol Res Ctr 123 Univ RdSect 3 Touliu 64002 Yunlin Taiwan Islamic Azad Univ Ahvaz Branch Young Researchers & Elite Club Ahvaz Iran Univ Tradit Med Armenia UTMA Fac Gen Med Yerevan Armenia Univ Publ Serv Inst Informat Soc H-1083 Budapest Hungary Obuda Univ John von Neumann Fac Informat Budapest Hungary Slovak Univ Technol Bratislava Inst Informat Engn Automat & Math Bratislava Slovakia Asia Univ Dept Business Adm 500 Lioufeng Rd Taichung 41354 Taiwan Calif State Univ San Bernardino Dept Management 5500 Univ Pkwy San Bernardino CA 92407 USA

Determination of pore pressure (PP), a key reservoir parameter that is beneficial for evaluating geomechanical parameters of the reservoir, is so important in oil and gas fields development. Accurate estimation of PP is also essential for safe drilling of oil and gas wells since PP data are used as the input for safe mud window determination. In the present study, empirical equations along with machine learning methods, namely random forest algorithm, support vector regression (SVR) algorithm, artificial neural network (ANN) algorithm, and decision tree (DT) algorithm, are employed for PP prediction applying well log data. To this end, 2827 data records collected from three wells (Well A, Well B, and Well C) drilled in one of the Middle East oil fields are used. The dataset of Wells A and B is used for models' training, validating, and testing, while Well C dataset is applied for evaluating the models' generalizability in PP prediction in the field under study. To construct the predictive algorithms, 12 input variables are initially considered in the study. A feature selection analysis is conducted to find the most influential input variables set for developing PP predictive models. The results obtained suggest that the 9-input-variable set is the most efficient combination of inputs used in the ML models construction. Among all the four ML algorithms proposed, the DT algorithm presents the most accurate predictions for PP, delivering R-2 and RMSE values of 0.9985 and 14.460 psi, respectively. Furthermore, the model generalization analysis results reveal that the 9-input-variable DT model developed can be used for PP prediction throughout the field of study since it presented an excellent accuracy performance in predicting PP when applied to Well C dataset. (C)& nbsp;2022 Published by Elsevier Ltd.

关键词： Pore pressure Machine learning algorithms Petrophysical data decision tree algorithm

来源：评论

学校读者我要写书评

暂无评论

Knowledge-based adaptable scheduler for SaaS providers in cloud computing

引用

HUMAN-CENTRIC COMPUTING AND INFORMATION SCIENCES 2015年第1期5卷 1页

作者： Motavaselalhagh, Farzaneh Esfahani, Faramarz Safi Arabnia, Hamid Reza Islamic Azad Univ Fac Comp Engn Najafabad Branch Najafabad Isfahan Iran Univ Georgia Dept Comp Sci Athens GA 30602 USA

Software as a Service (SaaS) in Cloud Computing offers reliable access to software applications for end users over the Internet without direct investment in infrastructure and software. SaaS providers utilize resources of internal datacenters or rent resources from a public Infrastructure as a Service (IaaS) provider in order to serve their customers. Internal hosting can increase cost of administration and maintenance, whereas hiring from an IaaS provider can impact quality of service due to its variable performance. To surmount these challenges, we propose a knowledge-based admission control along with scheduling algorithms for SaaS providers to effectively utilize public Cloud resources in order to maximize profit by minimizing cost and improving customers' satisfaction level. In the proposed model, the admission control is based on Service Level Agreement (SLA) and uses different strategies to decide upon accepting user requests for that minimal performance impact, avoiding SLA penalties that are giving higher profit. However, because the admission control can make decisions optimally, there is a need of machine learning methods to predict the strategies. In order to model prediction of sequence of strategies, a customized decision tree algorithm has been used. In addition, we conducted several experiments to analyze which solution in which scenario fit better to maximize SaaS provider's profit. Results obtained through our simulation shows that our proposed algorithm provides significant improvement (up to 38.4 % cost saving) compared to the previous research works.

关键词： Cloud computing Service Level Agreement (SLA) Admission control Software as a service Scalability of application services Knowledge-based Data mining decision tree algorithm

来源：评论

学校读者我要写书评

暂无评论

The Application of decision tree in Security Audit

The Application of Decision Tree in Security Audit

引用

2012 International Conference Mechatronic Systems and Materials Application(ICMSMA 2012)

作者： Dan Shao Gang Ma Department of Computer Changchun University Network Information Center Beijing University of Posts and Telecommunications

Network security audit is an important part in network security system, which, to some extent, makes up for the deficiencies in firewalls and intrusion detectionsAccording to the characteristics of the network data, the traditional decision tree model is modified, and the application pattern in which the decision tree model is used to network data security audit is also proposedSimulations show that the decision tree classification model not only is adaptive to the characteristics of network data, but also can prevent malicious attacks effectivelyThe effects of the attributes such as IP, port, and protocol type on classification are also uncovered.

关键词： Network data Security audit decision tree algorithm Classification of data

来源：评论

学校读者我要写书评

暂无评论

Real-time implementation of an IoT-based intelligent source allocation system using machine learning technique in a commercial building

引用

ELECTRICAL ENGINEERING 2024年第6期106卷 6815-6835页

作者： Kumar, V. Suresh Parameswari, S. Raja, S. Charles Karthick, T. Thiagarajar Coll Engn Dept Elect & Elect Engn Madurai Tamil Nadu India Quantan Techserv Pvt Ltd Madurai Tamil Nadu India

Building Energy Management is one of the prominent means of devising building-specific energy strategy and most of the research studies address the approach from the demand end. While, this study presents supply side management toward the challenge of implementing supply side management, due to the uncertainty of renewable power sources which are effectively tackled in the real-time scenario. In this paper, a novel Internet of Things-based Intelligent Source Allocation System (IoT-ISAS) has been designed specifically for the implementation within commercial buildings. The primary goal of this system is to ensure consistent and reliable power supply to critical loads within the building's direct current (DC) infrastructure. By leveraging a machine learning decision tree algorithm, the IoT-ISAS continuously allocates power sources to critical loads, thereby optimizing efficiency and minimizing downtime. The IoT-ISAS has been successfully deployed in a real-time commercial establishment at M/s Quantanics Techserv Private Limited. The IoT-ISAS incentivizes the commercial consumers to increase their utilization of renewable power sources and thereby, alleviates the burden on the grid. Based on the obtained results, it is observed that the sources are effectively shared and the tariff is found to be reduced by 9.76% for the best source allocating scenario using IoT-ISAS.

关键词： Internet of Things Source allocation system Energy management Machine learning decision tree algorithm

来源：评论

学校读者我要写书评

暂无评论

Genome-wide sequence-based prediction of peripheral proteins using a novel semi-supervised learning technique

引用

BMC BIOINFORMATICS 2010年第1期11卷 1-8页

作者： Bhardwaj, Nitin Gerstein, Mark Lu, Hui Univ Illinois Bioinformat Program Dept Bioengn Chicago IL 60607 USA Yale Univ Program Computat Biol & Bioinformat New Haven CT 06520 USA Yale Univ Dept Mol Biophys & Biochem New Haven CT 06520 USA Yale Univ Dept Comp Sci New Haven CT 06520 USA

Background: In supervised learning, traditional approaches to building a classifier use two sets of examples with pre-defined classes along with a learning algorithm. The main limitation of this approach is that examples from both classes are required which might be infeasible in certain cases, especially those dealing with biological data. Such is the case for membrane-binding peripheral domains that play important roles in many biological processes, including cell signaling and membrane trafficking by reversibly binding to membranes. For these domains, a well-defined positive set is available with domains known to bind membrane along with a large unlabeled set of domains whose membrane binding affinities have not been measured. The aforementioned limitation can be addressed by a special class of semi-supervised machine learning called positive-unlabeled (PU) learning that uses a positive set with a large unlabeled set. Methods: In this study, we implement the first application of PU-learning to a protein function prediction problem: identification of peripheral domains. PU-learning starts by identifying reliable negative (RN) examples iteratively from the unlabeled set until convergence and builds a classifier using the positive and the final RN set. A data set of 232 positive cases and similar to 3750 unlabeled ones were used to construct and validate the protocol. Results: Holdout evaluation of the protocol on a left-out positive set showed that the accuracy of prediction reached up to 95% during two independent implementations. Conclusion: These results suggest that our protocol can be used for predicting membrane-binding properties of a wide variety of modular domains. Protocols like the one presented here become particularly useful in the case of availability of information from one class only.

关键词： decision tree algorithm Peripheral Protein Modular Domain Bioinformatics Problem Peripheral Domain

来源：评论

学校读者我要写书评

暂无评论

Significance of machine learning algorithms in professional blogger's classification

引用

COMPUTERS & ELECTRICAL ENGINEERING 2018年 65卷 461-473页

作者： Asim, Yousra Shahid, Ahmad Raza Malik, Ahmad Kamran Raza, Basit COMSATS Inst Informat Technol Dept Comp Sci Islamabad Pakistan

Outreach of internet has opened new horizons for the people who want quick and widespread dissemination of their ideas, and the tool to do so is blogging. Sloggers can broadly be classified into two groups: professional and non-professional bloggers. As for professional bloggers, there are many factors that influence individuals to opt this profession. This study, with the help of an online dataset, attempts to identify such factors. Data analysis was made by using decision tree algorithms, lazy learning algorithms and ensembling methods. Nearest-neighbour classifier (IB1) and RandomForest have results with 85% accuracy and 84.8% precision for classification. The proof of concept is provided for result validation. The causes behind the varying performance of algorithms are elaborated. The factors that influence a blogger to behave professionally are identified based on the classifier with the best results. (C) 2017 Elsevier Ltd. All rights reserved.

关键词： Machine learning Blogging decision tree algorithm Lazy learning algorithm Ensembling techniques Classification

来源：评论

学校读者我要写书评

暂无评论

Development and validation of a risk prediction model and prediction tools for post-thrombotic syndrome in patients with lower limb deep vein thrombosis

引用

INTERNATIONAL JOURNAL OF MEDICAL INFORMATICS 2024年 187卷 105468-105468页

作者： Sun, Xiao-Xuan Ling, Hua Zhang, Lei Chen, Rui-Bin Zhong, An-qi Feng, Li-qun Yu, Ran Chen, Ying Liu, Jia-Qiu Nanchang Univ Affiliated Hosp 1 Jiangxi Med Coll Nursing Dept Nanchang 330000 Peoples R China Nanchang Univ Jiangxi Med Coll Sch Nursing Nanchang 330000 Peoples R China Nanchang Univ Jiangxi Med Coll Sch Clin Med 1 Nanchang 330000 Peoples R China Nanchang Univ Affiliated Hosp 1 Jiangxi Med Coll Informat Off Nanchang 330000 Peoples R China Jiangsu Univ Jingjiang Coll Sch Life Sci & Technol Jiangsu 212013 Zhenjiang Peoples R China Nanchang Univ Affiliated Hosp 1 Jiangxi Med Coll Dept Vasc Surg Nanchang 330000 Peoples R China Nanchang Univ Affiliated Hosp 1 Jiangxi Med Coll Cardiovasc Med Dept Nanchang 330000 Peoples R China

Purpose: Our research aims to compare the predictive performance of decision tree algorithms (DT) and logistic regression analysis (LR) in constructing models, and develop a Post-Thrombotic Syndrome (PTS) risk stratification tool. Methods: We retrospectively collected and analyzed relevant case information of 618 patients diagnosed with DVT from January 2012 to December 2021 in three different tertiary hospitals in Jiangxi Province as the modeling group. Additionally, we used the case information of 212 patients diagnosed with DVT from January 2022 to January 2023 in two tertiary hospitals in Hubei Province and Guangdong Province as the validation group. We extracted electronic medical record information including general patient data, medical history, laboratory test indicators, and treatment data for analysis. We established DT and LR models and compared their predictive performance using receiver operating characteristic (ROC) curves and confusion matrices. Internal and external validations were conducted. Additionally, we utilized LR to generate nomogram charts, calibration curves, and decision curves analysis (DCA) to assess its predictive accuracy. Results: Both DT and LR models indicate that Year, Residence, Cancer, Varicose Vein Operation History, DM, and Chronic VTE are risk factors for PTS occurrence. In internal validation, DT outperforms LR (0.962 vs 0.925, z = 3.379, P < 0.001). However, in external validation, there is no significant difference in the area under the ROC curve between the two models (0.963 vs 0.949, z = 0.412, P = 0.680). The validation results of calibration curves and DCA demonstrate that LR exhibits good predictive accuracy and clinical effectiveness. A web-based calculator software of nomogram (https://***/dynnomapp/) was utilized to visualize the logistic regression model. Conclusions: The combination of decision tree and logistic regression models, along with the web-based calculator software of nomogram, can

关键词： Post-thrombotic syndrome (PTS) decision tree algorithm Logistic Regression model Predictive modeling Risk stratification

来源：评论

学校读者我要写书评

暂无评论

Missing value imputation using decision trees and decision forests by splitting and merging records: Two novel techniques

引用

KNOWLEDGE-BASED SYSTEMS 2013年第Nov.期53卷 51-65页

作者： Rahman, Md Geaur Islam, Md Zahidul Charles Sturt Univ Ctr Res Complex Syst Sch Comp & Math Bathurst NSW 2795 Australia

We present two novel techniques for the imputation of both categorical and numerical missing values. The techniques use decision trees and forests to identify horizontal segments of a data set where the records belonging to a segment have higher similarity and attribute correlations. Using the similarity and correlations, missing values are then imputed. To achieve a higher quality of imputation some segments are merged together using a novel approach. We use nine publicly available data sets to experimentally compare our techniques with a few existing ones in terms of four commonly used evaluation criteria. The experimental results indicate a clear superiority of our techniques based on statistical analyses such as confidence interval. (C) 2013 Elsevier B.V. All rights reserved.

关键词： Data pre-processing Data cleansing Missing value imputation decision tree algorithm decision forest algorithm EM algorithm

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：