检索结果-内蒙古大学图书馆

IEEE International Conference on Electrical Engineering, Big Data and algorithms (EEBDA)

作者： Long Jing Pan Xiuzhi Zhao Qianrong Li Junjiang Nanning Univ Coll Accounting & Auditing Nanning Guangxi Peoples R China Guangxi Univ Foreign Languages Sch Accounting Nanning Guangxi Peoples R China

ISBN: (纸本)9781665416061

2020 is the end of the poverty alleviation exit effectiveness inspection. To consolidate the achievements of poverty alleviation, promote the Rural Revitalization Strategy, and prevent poverty return will be its key means and important guarantee. At present, although many experts and scholars have studied the related fields of dynamic monitoring of poverty return, most of them focus on macro policy content, and the research on poverty return identification for the poor is still relatively lacking. At the same time, the in-depth mining and application of the accumulated large-scale targeted poverty alleviation data is insufficient. This paper finds relevant literature and combines China's achievements in precise poverty alleviation work and the construction of precise poverty alleviation systems, using Yulin's poor household record-keeping data as the research object. The three integrated learning algorithms, xgboost, LightGBM and CatBoost, were used to identify poor households in three categories, out of poverty, poor and returning to poverty. The results show that the xgboost algorithm model achieves optimal results, with an overall accuracy of 95.55% for three classification recognition, and can better identify the poor categories of the poor population. At the same time, the model's feature importance ranking can reveal the importance of povertycausing characteristics of poor households in Fuping County. By analyzing the current work flow of helpers, it is clear that good dynamic monitoring of poverty return should achieve the needs of dynamic updating of data, dynamic feedback of results and dynamic adjustment of countermeasures.

关键词： Integrated learning Rural revitalization Poverty return identification xgboost algorithm Guangxi

来源：评论

学校读者我要写书评

暂无评论

Comparisons of different methods used for second-hand car price prediction 2

Comparisons of different methods used for second-hand car pr...

引用

2nd International Conference on Applied Mathematics, Modelling, and Intelligent Computing (CAMMIC)

作者： Chen, Jian Li, Fangfang Xu, Jing Wang, Qing Han, Qingzhen Yan, Ming Yangzhou Univ Sch Mech Engn Huayang Weststr 196 Yangzhou 225000 Jiangsu Peoples R China Shandong Shuncheng Grp Podium Jinan 250000 Peoples R China

ISBN: (纸本)9781510655201;9781510655195

By establishing correlation coefficient matrix, huge sample data of second-hand car trading was processed so that, the irrelevant variables were deleted, as well as the missing and outlier values were handled. Then, the main variables have been extracted by using xgboost algorithm. 13 of 36 major characteristic variables affecting the second-hand car price were filtered out according to their importance ranking, which include the mileage, tradeTime, brand, model et al. With the selected variables as independent variables and the price of second-hand car as dependent variable, the BP neural network model, linear regression model and random forest model were established to predict the price of second-hand cars. Finally, the predicting results were compared, which show that the fit goodness of random forest model is 0.992, and the model evaluation is 0.527, which gives the best performance.

关键词： correlation coefficient matrix xgboost algorithm BP neural network linear regression random forest

来源：评论

学校读者我要写书评

暂无评论

TBM rock mass classification using xgboost and Interpretable Machine learning

引用

ADVANCED ENGINEERING INFORMATICS 2025年 66卷

作者： Nie, Yaoqi Zhang, Qian Hou, Lili Du, Lijie Zhao, Xiaolong Xue, Yujie Lin, Zhicheng Cao, Xiuxiu Wang, Zixin Shijiazhuang Tiedao Univ Sch Safety Engn & Emergency Management Shijiazhuang 050043 Peoples R China Shijiazhuang Tiedao Univ Key Lab Struct Hlth Monitoring & Control Shijiazhuang 050043 Peoples R China Shijiazhuang Tiedao Univ Sch Civil Engn Shijiazhuang 050043 Hebei Peoples R China Shijiazhuang Tiedao Univ Sch Informat Sci & Technol Shijiazhuang 050043 Peoples R China Beijing Jiaotong Univ Sch Civil Engn 3 Shangyuancun Beijing 100044 Peoples R China Nagasaki Univ Sch Engn Nagasaki 8528521 Japan

Accurate classification of surrounding rock grades during Tunnel Boring Machine (TBM) operations is essential for optimizing excavation parameters and ensuring construction safety. However, traditional classification methods face challenges, particularly in adapting to complex geological conditions and achieving high efficiency in model optimization. To address these issues, this study proposes an identification methodology based on the COA-xgboost framework. Initially, raw data is preprocessed to eliminate anomalous instances, such as those arising from equipment malfunctions or maintenance activities, using a state discrimination function. To better capture the interaction dynamics between the TBM and the surrounding rock, a novel feature parameter, specific energy, is introduced. The Relief algorithm is employed to evaluate feature importance and assign weights to TBM operational parameters, amplifying the role of critical features while minimizing interference from redundant ones. Subsequently, the Coati Optimization algorithm (COA) is integrated with the xgboost classifier, enabling global parameter optimization and enhancing the model's performance. The proposed method was validated using data from the water conveyance tunnel section of the Yinchuojiliao Project. Results demonstrate that the Relief algorithm effectively enhances the model's ability to identify critical parameters through feature weighting. The COA-optimized xgboost model achieves a significant improvement in recognition accuracy compared to traditional approaches, with accuracy gains of approximately 8%, particularly excelling under complex geological conditions such as Class IV and Class V surrounding rocks. The final model achieves an accuracy of 91.5%, with recall and F1 scores reaching 91.5% and 91.4%, respectively. Additionally, five-fold cross-validation highlights the model's robustness and generalization capabilities. Furthermore, a SHAP-based interpretability analysis clarifies the re

关键词： TBM Rock Grade Identification xgboost algorithm Coati optimization algorithm SHAP

来源：评论

学校读者我要写书评

暂无评论

xgboost based solutions for detecting fraudulent credit card transactions

XGBoost based solutions for detecting fraudulent credit card...

引用

International Conference on Advanced Creative Networks and Intelligent Systems (ICACNIS) - Blockchain Technology, Intelligent Systems, and the Applications for Human Life

作者： El Kafhali, Said Tayebi, Mohammed Hassan First Univ Settat Fac Sci & Tech IR2M Lab Settat Morocco

ISBN: (纸本)9798350334449

Due to the emigration of businesses to the internet, credit cards have become a widely used tool for customers to pay for purchases both online and offline. However, fraudsters try to attack these payment tools using various techniques, and credit card fraud transactions have become dangerous. Credit card payment security is becoming an important research topic, and different ways are proposed to overcome this problem. In this article, we will propose a solution that combines the strengths of three methods to secure credit card fraud transactions. The Differential Evolution (DE) algorithm is used to select the best hyperparameters of the xgboost algorithm (eXtreme Gradient Boosting). Synthetic Minority Oversampling (SMOTE) combined with Edited Nearest Neighbour (ENN) to handle the imbalanced data issues. Finally, we will classify fraud transactions using the optimized xgboost algorithm. The proposed solution is evaluated using the European data set in terms of Accuracy, Recall, F1-score, and AUC. As a result, the proposed solution generally achieved the best score in terms of all the measurements used in this study. In terms of accuracy, we achieved 99.94%, similarly, we reached the best score in terms of the Precision score, which is 80.68%, in addition, we got 86.02% of recall score, 83.27 of F-measure, and 99.21 of AUC score. Thus, we emphasize the superiority of our proposed method over the competitive machine learning model utilized in this work.

关键词： Fraud Transactions Detection Hyperparameters Optimization Differential Evolution algorithm xgboost algorithm Synthetic Minority Oversampling Edited Nearest Neighbor

来源：评论

学校读者我要写书评

暂无评论

Using Multi-Feature Fusion and xgboost to Recognize the Pedestrian with Multiple Angles in Different Videos 13

Using Multi-Feature Fusion and XGBoost to Recognize the Pede...

引用

13th International Conference on Graphics and Image Processing (ICGIP)

作者： Zhang, Zhanwei Jiang, Murong Huang, Yaqun Liu, Xinfu Zhou, Yingying Yunnan Univ Sch Informat Sci & Engn Kunming 650091 Yunnan Peoples R China

ISBN: (数字)9781510650435

ISBN: (纸本)9781510650435;9781510650428

Pedestrian target recognition in multiple videos is a hot issue in video image processing. Many existing recognition algorithms have problems in extracting pedestrian image features, such as multiple dimensions, slow recognition speed and so on. In this paper, a pedestrian recognition method with multiple angles in different videos based on the fusion of HOG, LBP, HSV features and xgboost classify is proposed. First, use the coefficient variation to reduce the HOG feature dimension;then use LBP to extract the strong expressive features as the local features of the image;then fuse the HOG, LBP and HSV to enhance the ability of pedestrian target features;finally, use the xgboost algorithm to classify the fusion features, use Cosine similarity to calculate the distance between target and candidates. Experiments show that the proposed method has greatly improved the recognition speed and recognition accuracy in public data sets and selfmade data sets.

关键词： Pedestrian recognition from multiple angles HOG LBP HSV Feature fusion xgboost algorithm

来源：评论

学校读者我要写书评

暂无评论

Identity Identification of Power Intelligent Terminals Based on Behavior Modeling 6

Identity Identification of Power Intelligent Terminals Based...

引用

6th International Symposium on Computer Science and Intelligent Control (ISCSIC)

作者： Huang, Xinghe Su, BeiBei Dai, ZaoJian Zhao, JinMeng Zhang, Jing Lin, BingJie State Grid Informat & Telecommun Branch Beijing 100761 Peoples R China 8 Nanrui Rd Nanjing 210000 Peoples R China State Grid Smart Grid Res Inst Co Ltd Grid Digitizing Technol Dept Nanjing 210003 Jiangsu Peoples R China State Grid Key Lab Informat & Network Secur 8 Nanrui Rd Nanjing 210000 Peoples R China

ISBN: (纸本)9781665454889

In order to ensure the security of power intelligent terminals, an identity identification method based on behavior feature modeling was proposed. Firstly, user behavior data was collected. Then the user behavior was modeled according to the collected data. Finally, xgboost regression model was used to identify and classify the user identity. The results showed that the identification accuracy, recall rate and Fl value of user identity identification through behavior modeling and xgboost regression reach more than 90%, which has a good identification effect;Compared with SVM algorithm and random forest algorithm, the xgboost regression has better identification effect, and its identification accuracy is 93.09%. Therefore, the proposed identity identification method based on behavior modeling and xgboost regression can more accurately identify the user identity, so as to improve the security of using terminal.

关键词： behavior features identity identification xgboost algorithm power intelligent terminal random forest algorithm

来源：评论

学校读者我要写书评

暂无评论

Sequence Alignment Using Machine Learning-Based Needleman-Wunsch algorithm

引用

IEEE ACCESS 2021年 9卷 109522-109535页

作者： El-Din Rashed, Amr Ezz Amer, Hanan M. El-Seddek, Mervat El-Din Moustafa, Hossam Mansoura Univ Dept Commun & Elect Fac Engn Mansoura 35516 Egypt Taif Univ Coll Comp & Informat Technol At Taif 26571 Saudi Arabia Higher Inst Engn & Technol Mansoura 35516 Egypt

Biological pairwise sequence alignment can be used as a method for arranging two biological sequence characters to identify regions of similarity. This operation has elicited considerable interest due to its significant influence on various critical aspects of life (e.g., identifying mutations in coronaviruses). Sequence alignment over large databases cannot yield results within a reasonable time, power, and cost. heuristic methods, such as FASTA, the BLAST family have been demonstrated to perform 40 times faster than DP-based (e.g., Needleman-Wunsch) techniques they cannot guarantee an optimum alignment result An optimized software platform of a widely used DNA sequence alignment algorithm called the Needleman-Wunsch (NW) algorithm based on a lookup table, is described in this study. This global alignment algorithm is the best approach for identifying similar regions between sequences. This study presents a new application of classical machine learning (ML) to global sequence alignment. Customized ML models are used to implement NW global alignment. An accuracy of 99.7% is achieved when using a multilayer perceptron with the ADAM optimizer, and up to 2912 Giga cell updates per second are realized on two real DNA sequences with a length of 4.1 M nucleotides. Our implementation is valid for RNA/DNA sequences. This study aims to parallelize the computation steps involved in the algorithm to accelerate its performance by using ML algorithms. All datasets used in this study are available from https://***/documents/dna-sequence-alignment-datasets-based-nw-algorithm.

关键词： DNA Machine learning algorithms Heuristic algorithms Classification algorithms RNA Graphics processing units Approximation algorithms Bioinformatics DNA RNA pairwise sequence alignment (PWSA) Needlema-Wunsch (NW) algorithm machine learning (ML) algorithms multilayer perceptron (MLP) xgboost algorithm

来源：评论

学校读者我要写书评

暂无评论

Dynamic Forecasting of Solar Energy Microgrid Systems Using Feature Engineering

Dynamic Forecasting of Solar Energy Microgrid Systems Using ...

引用

IEEE International Conference on Power Electronics, Drives and Energy Systems (PEDES)

作者： Mohamed, Muamar Mahmood, Farhad E. E. Abd, Mehmmood A. A. Chandra, Ambrish Singh, Bhim Univ Quebec Ecole Technol Super Dept Elect Engn Montreal PQ H3C 1K3 Canada Univ Mosul Dept Elect Engn Mosul 00964 Iraq IBM Corp Austin TX 78758 USA Indian Inst Technol Delhi New Delhi 110016 India

The intermittent and stochastic nature of solar energy generation systems, climate change, and the inefficiency of modern power systems due to zero inertia have created many challenges for on-grid operators. Solar forecasting systems based on machine learning algorithms are an emerging and effective solution that uses Big Data related to weather phenomena. However, the predictive ability of these algorithms is hampered by the sporadic nature of solar energy generation. In this article, a robust hybrid machine learning system that utilizes multiple linear regression (MLR) and a Pearson correlation coefficient (PCC) was tested on solar power plant sites of varying capacities in Germany (100-8500 kW). The volume of Big Data features can be reduced by focusing on the features that significantly improve the reliability of the mid-term forecasting system. In this way, drastic fluctuations in the prediction of photovoltaic (PV) power generation can be avoided. The results of our approach are evaluated regarding real-world data using the extreme gradient boosting (xgboost) with feature engineering, and principal component analysis (PCA), in order to forecast PV energy, rank, and track the importance of feature engineering for different PV capacities. Furthermore, we found that the need for selectivity and reduction of performance error was supported by ridge regression. In addition, the proposed novel xgboost forecast system decreased the root-mean-square error (RMSE) and mean absolute error (MAE) by 30% and 18%, respectively, compared to the Autoencoder and long short-term memory (LSTM) for same datasets. Furthermore, the CoD determination coefficient (R-2) increased by 85% compared to the statistical model's autoregressive integrated moving average (ARIMA).

关键词： Artificial intelligence data mining algorithms forecasting techniques machine learning power system statistical analysis solar microgrid xgboost algorithm

来源：评论

学校读者我要写书评

暂无评论

Statistical Analysis and Prediction of Employee Turnover Propensity Based on Data Mining

Statistical Analysis and Prediction of Employee Turnover Pro...

引用

International Conference on Big Data, Information and Computer Network (BDICN)

作者： Duan, Yongkang Sichuan Univ Sch Publ Adm Chengdu 630065 Peoples R China

ISBN: (纸本)9781665484763

Nowadays, talent competition is becoming more and more fierce, and retaining talents is the key to the survival of enterprises. In this paper, we use enterprise employee departure data to analyze the factors that lead to employee departure by using the Logistic model and xgboost algorithm, to predict and control the tendency of employees to leave, and to make suggestions to enterprises. The results show that the prediction accuracy and fit of the xgboost algorithm is better. In addition, this paper finds that employee turnover is not determined by a single variable, but by several factors together. The results suggest that companies should reduce employee turnover intentions in terms of satisfaction, performance evaluation, and working time arrangement.

关键词： Employee Turnover Analysis Logistic Model xgboost algorithm Data Mining

来源：评论

学校读者我要写书评

暂无评论

xgboost-based failure prediction method for metal additive manufacturing equipment 34

XGBoost-based failure prediction method for metal additive m...

引用

34th Chinese Control and Decision Conference (CCDC)

作者： Wang, Lingfeng Zhang, Wei Bao, Qiao Wang, Qiang Nanjing Univ Post & Telecommun Coll Automat Nanjing 210023 Peoples R China Nanjing Univ Post & Telecommun Coll Artificial Intelligence Nanjing 210023 Peoples R China Nanjing Zhongke Raycham Laser Technol Co Ltd Nanjing 210038 Peoples R China

ISBN: (纸本)9781665478960

In order to overcome the complexity of failure modeling and limited health monitoring means of metal additive manufacturing equipment, a data-driven failure prediction system framework for metal additive manufacturing equipment is proposed, and a metal additive manufacturing equipment operational state data management platform is established. The proposed failure modeling method is validated by using the actual data of the Directed Energy Deposition equipment as an example, and the results show that the modeling method based on xgboost algorithm can effectively the higher the depth value of the tree used, the faster the iterative convergence rate. Compared with other algorithms, the xgboost-based modeling method can achieve higher prediction accuracy, and the accuracy of predicting the occurrence of failure after 1 minute and 30 seconds in advance for a given sample can reach more than 90%, which verifies the applicability and performance advantages of the method under large-scale conditions. The method's applicability and performance advantages under large-scale conditions are verified.

关键词： Additive Manufacturing Health Management Failure Prediction xgboost 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：