检索结果-南通市图书馆

基于数据挖掘和randomforest算法的助学金分类研究

在线全文

学校读者我要写书评

暂无评论

中国市场 2019年第3期 50-52页

作者：王雨萌武小军罗雅晨同济大学上海201804

在普及高等教育的过程中,发放助学金作为帮助贫困学生完成学业的重要手段之一。目前国内高校的助学金发放准则存在一定的问题,因此如何在高校缺乏学生的真实家庭情况以及助学金的金额有限的背景下,将助学金发放到最需要帮助的学生手上... 详细信息

在普及高等教育的过程中,发放助学金作为帮助贫困学生完成学业的重要手段之一。目前国内高校的助学金发放准则存在一定的问题,因此如何在高校缺乏学生的真实家庭情况以及助学金的金额有限的背景下,将助学金发放到最需要帮助的学生手上成为亟待解决的问题。文章以某高校大学生一卡通脱敏数据为原始数据,采用大数据挖掘技术和机器学习算法等AI技术进行拟合训练,以期有效预测需要帮助的学生,发挥助学金的作用。

关键词：数据挖掘 randomforest 机器学习助学金

在线全文

学校读者我要写书评

暂无评论

基于智能合约分类的庞氏骗局检测方法

网络安全技术与应用 2025年第1期 48-53页

作者：李慧韩红旗张运良陈红倩中国科学技术信息研究所北京联合大学管理学院北京工商大学计算机学院

针对区块链中的庞氏骗局的检测，本文设计了基于Xgboost和randomforest两种算法的智能合约分类模型，实现针对庞氏骗局检测的方法。该方法首先分析了智能合约中账户地址的行为特性，通过对合约中交易与资产流向的分析，提取庞氏骗局的... 详细信息

针对区块链中的庞氏骗局的检测，本文设计了基于Xgboost和randomforest两种算法的智能合约分类模型，实现针对庞氏骗局检测的方法。该方法首先分析了智能合约中账户地址的行为特性，通过对合约中交易与资产流向的分析，提取庞氏骗局的账户交易行为特征，并基于数据挖掘补充了账户交易特征；然后利用Xgboost和randomforest算法对代码特征进行分类，实现了一种不需要源代码且在智能合约运行前检测的庞氏骗局检测模型；最后，对其行为特征进行分类研究，丰富以太坊智能合约的交易规律。实验结果表明，本文提出的方法可以较好的对智能合约进行庞氏骗局分类检测，在精度和召回率方面具有更好的表现。

关键词：区块链智能合约分类庞氏骗局检测 Xgboost randomforest

A Two-Step Algorithm to Estimate Variable Importance for Multi-State Data:An Application to COVID-19

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Computer Modeling in Engineering & Sciences 2023年第6期135卷 2047-2064页

作者： Behnaz Alafchi Leili Tapak Hassan Doosti Christophe Chesneau Ghodratollah Roshanaei Department of Biostatistics School of Public HealthModeling of Noncommunicable Diseases Research CenterHamadan University of Medical SciencesHamadanIran School of Mathematical and Physical Sciences Macquarie UniversitySydneyAustralia Department of Mathematics LMNOUniversity of Caen-NormandieCaenFrance

Survival data with amulti-state structure are frequently observed in follow-up *** analytic approach based on a multi-state model(MSM)should be used in longitudinal health studies in which a patient experiences a sequence of clinical progression *** main objective in the MSM framework is variable selection,where attempts are made to identify the risk factors associated with the transition hazard rates or probabilities of disease *** usual variable selection methods,including stepwise and penalized methods,do not provide information about the importance of *** this context,we present a two-step algorithm to evaluate the importance of variables formulti-state *** differentmachine learning approaches(randomforest,gradient boosting,and neural network)as themost widely usedmethods are considered to estimate the variable importance in order to identify the factors affecting disease progression and rank these factors according to their *** performance of our proposed methods is validated by simulation and applied to the COVID-19 data *** results revealed that the proposed two-stage method has promising performance for estimating variable importance.

关键词： Multi-state data deviance residual martingale residual gradient boosting randomforest neural network variable importance variable selection

Genotyping Characteristics of Human Fecal Escherichia coli and Their Association with Multidrug Resistance in Miyun District, Beijing

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Biomedical and Environmental Sciences 2023年第5期36卷 406-417页

作者： ZHANG Wei Wei ZHU Xiao Lin DENG Le Le HAN Ya Jun LI Zhuo Wei WANG Jin Long CHEN Yong Liang WANG Ao Lin TIAN Er Li CHENG Bin XU Lin Hua CHEN Yi Cong TIAN Li Li HE Guang Xue National Institute for Viral Disease Control and Prevention Chinese Center for Disease Control and PreventionBeijing 102206China Miyun District Center for Disease Control and Prevention Beijing 101520China Berger Bioengineering Co. LtdShanghai 201401China Xicheng District Commission of Health of Beijing Municipality Beijing 100044China Miyun District Hospital Beijing 101520China Hebei North University Zhangjiakou 075000HeibeiChina

Objective To explore the genotyping characteristics of human fecal Escherichia coli(E. coli) and the relationships between antibiotic resistance genes(ARGs) and multidrug resistance(MDR) of E. coli in Miyun District, Beijing, an area with high incidence of infectious diarrheal cases but no related *** Over a period of 3 years, 94 E. coli strains were isolated from fecal samples collected from Miyun District Hospital, a surveillance hospital of the National Pathogen Identification Network. The antibiotic susceptibility of the isolates was determined by the broth microdilution method. ARGs,multilocus sequence typing(MLST), and polymorphism trees were analyzed using whole-genome sequencing data(WGS).Results This study revealed that 68.09% of the isolates had MDR, prevalent and distributed in different clades, with a relatively high rate and low pathogenicity. There was no difference in MDR between the diarrheal(49/70) and healthy groups(15/24).Conclusion We developed a random forest(RF) prediction model of TEM.1 + baeR + mphA + mphB +QnrS1 + AAC.3-IId to identify MDR status, highlighting its potential for early resistance identification. The causes of MDR are likely mobile units transmitting the ARGs. In the future, we will continue to strengthen the monitoring of ARGs and MDR, and increase the number of strains to further verify the accuracy of the MDR markers.

关键词： E.coli Multidrug resistance Whole-genome sequencing Antibiotic resistance genes randomforest

Multi Class Brain Cancer Prediction System Empowered with BRISK Descriptor

在线全文

学校读者我要写书评

暂无评论

Intelligent Automation & Soft Computing 2023年第5期36卷 1507-1521页

作者： Madona B.Sahaai G.R.Jothilakshmi E.Praveen V.Hemath Kumar Department of Electronics and Communication Engineering VISTASChennaiTamil NaduIndia

Magnetic Resonance Imaging(MRI)is one of the important resources for identifying abnormalities in the human *** work proposes an effective Multi-Class Classiﬁcation(MCC)system using Binary Robust Invariant Scalable Keypoints(BRISK)as texture descriptors for effective classiﬁ***ﬁrst,the potential Region Of Interests(ROIs)are detected using features from the acceler-ated segment test ***,non-maxima suppression is employed in scale space based on the information in the *** discriminating power of BRISK is examined using three machine learning classiﬁers such as k-Nearest Neighbour(kNN),Support Vector Machine(SVM)and Random Forest(RF).An MCC sys-tem is developed which classiﬁes the MRI images into normal,glioma,meningio-ma and pituitary.A total of 3264 MRI brain images are employed in this study to evaluate the proposed MCC *** show that the average accuracy of the proposed MCC-RF based system is 99.62%with a sensitivity of 99.16%and spe-ciﬁcity of 99.75%.The average accuracy of the MCC-kNN system is 93.65%and 97.59%by the MCC-SVM based system.

关键词： Braincancer BRISKdescriptor randomforest multi-classclassiﬁcation brain image analysis

Impacts of predictor variables and species models on simulating Tamarix ramosissima distribution in Tarim Basin, northwestern China

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Plant Ecology 2012年第3期5卷 337-345页

作者： Qiang Zhang Xinshi Zhang State Key Laboratory of Vegetation and Environmental Change Institute of BotanyChinese Academy of Sciences20 NanxincunXiangshanBeijing 100093China Graduate University of Chinese Academy of Sciences 19A YuquanluBeijing 100049China

Aims Preserving and restoring Tamarix ramosissima is urgently required in the Tarim Basin,Northwest *** species distribution models to predict the biogeographical distribution of species is regularly used in conservation and other management ***,the uncertainty in the data and models inevitably reduces their prediction *** major purpose of this study is to assess the impacts of predictor variables and species distribution models on simulating *** distribution,to explore the relationships between predictor variables and species distribution models and to model the potential distribution of *** in this *** Three models—the generalized linear model(GLM),classification and regression tree(CART)and Random Forests—were selected and were processed on the BIOMOD *** presence/absence data of *** in the Tarim Basin,which were calculated from vegetation maps,were used as response ***,soil and digital elevation model(DEM)data variables were divided into four datasets and then used as *** four datasets were(i)climate variables,(ii)soil,climate and DEM variables,(iii)principal component analysis(PCA)-based climate variables and(iv)PCA-based soil,climate and DEM *** Findings The results indicate that predictive variables for species distribution models should be chosen carefully,because too many predictors can reduce the prediction *** effectiveness of using PCA to reduce the correlation among predictors and enhance the modelling power depends on the chosen predictor variables and *** results implied that it is better to reduce the correlating predictors before model *** Random Forests model was more precise than the GLM and CART *** best model for *** was the Random Forests model with climate predictors *** variables considered in this study could not significantly improve the model’s prediction accuracy for ***

关键词： species distribution model Tamarix ramosissima generalized linear models classification and regression trees randomforest

Employee Attrition Classification Model Based on Stacking Algorithm

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Psychology Research 2023年第6期13卷 279-285页

作者： CHEN Yanming LIN Xinyu ZHAN Kunye Shantou University South China Normal University Shenzhen University

This paper aims to build an employee attrition classification model based on the Stacking *** algorithm is applied to address the issue of data imbalance and the randomforest feature importance ranking method is used to resolve the overfitting problem after data cleaning and ***,different algorithms are used to establish classification models as control experiments,and R-squared indicators are used to ***,the Stacking algorithm is used to establish the final classification *** model has practical and significant implications for both human resource management and employee attrition analysis.

关键词： employee attrition classification model machine learning ensemble learning oversampling algorithm randomforest stacking algorithm

基于抽象API调用序列的Android恶意软件检测方法

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

计算机应用与软件 2019年第9期36卷 321-326页

作者：崔艳鹏颜波胡建伟西安电子科技大学网络与信息安全学院

随着Android版本的不断更替,以及恶意软件的代码混淆技术的发展,主流的静态检测方法开始面临检测效率逐年下降的问题。针对上述问题,提出一种基于抽象API调用序列的Android恶意软件检测方法。该方法采用API包名、混淆名和自定义名来抽象... 详细信息

随着Android版本的不断更替,以及恶意软件的代码混淆技术的发展,主流的静态检测方法开始面临检测效率逐年下降的问题。针对上述问题,提出一种基于抽象API调用序列的Android恶意软件检测方法。该方法采用API包名、混淆名和自定义名来抽象API调用序列,使得抽象出来的序列不依赖API版本,同时又包含混淆代码特征,具有更好的容错性。在此基础上,计算抽象API调用序列之间的转移概率矩阵作为分类特征,采用randomforest分类算法进行恶意软件检测。实验结果表明,该方法对API版本依赖性小,且判别准确率高于一般使用API调用序列作为特征的判别方法,从而能更有效地检测未知应用软件的恶意性。

关键词： Android 恶意软件检测抽象API调用序列代码混淆 randomforest

基于K-means和Random Forest的WiFi室内定位方法

在线全文

学校读者我要写书评

暂无评论

控制工程 2017年第4期24卷 787-792页

作者：李军何星蔡云泽徐琴上海交通大学自动化系系统控制与信息处理教育部重点实验室上海200240 国网上海市电力公司电力科学研究院上海200437

为了减小室内环境因素对室内WiFi定位的影响,降低定位成本,提高定位精度以及扩大定位区域,通过对室内定位系统和机器学习算法的讨论,提出了一种基于K-means和Random Forest融合的WiFi室内定位算法。针对室内WiFi信号强度分布的特点,该... 详细信息

为了减小室内环境因素对室内WiFi定位的影响,降低定位成本,提高定位精度以及扩大定位区域,通过对室内定位系统和机器学习算法的讨论,提出了一种基于K-means和Random Forest融合的WiFi室内定位算法。针对室内WiFi信号强度分布的特点,该算法通过K-means聚类改进算法对数据进行初始分类,然后使用Random Forest对初始分类结果进行二次分类。实验结果表明,该定位算法的定位精度在2米以内的概率为89.1%,达到预期的定位效果,同时对缺失值数据具有较好的适应能力。

关键词：室内定位 WiFi randomforest K-means 多模融合