期刊文献+
共找到8篇文章
< 1 >
每页显示 20 50 100
LightGBM+CatBoost+XGBoost集成学习加权融合的室内指纹定位算法
1
作者 郑新鹏 张烈平 +1 位作者 陈耀 张翠 《科学技术与工程》 北大核心 2025年第30期12982-12990,共9页
针对WiFi室内指纹定位中指纹库易受环境变化影响、定位精度低等问题,提出了一种LightGBM+CatBoost+XGBoost集成学习加权融合的室内指纹定位算法。在离线阶段,采用基于中位数绝对偏差的Boxplot滤波,有效过滤了指纹库中的异常值。然后对... 针对WiFi室内指纹定位中指纹库易受环境变化影响、定位精度低等问题,提出了一种LightGBM+CatBoost+XGBoost集成学习加权融合的室内指纹定位算法。在离线阶段,采用基于中位数绝对偏差的Boxplot滤波,有效过滤了指纹库中的异常值。然后对过滤后指纹库的缺失值,采用了K近邻(K-nearest neighbors,KNN)填补指纹库中缺失值,确保指纹库的稳定性。在在线阶段,结合LightGBM(light gradient boosting machine)、CatBoost(categorical boosting)和XGBoost(extreme gradient boosting)3种集成学习模型,通过混沌自适应JAYA算法动态调整模型权重,构建加权融合的坐标预测模型。实验结果表明,提出算法的平均定位误差为1.38 m,相较于粒子群优化(particle swarm optimization,PSO)-极限学习机(extreme learning machine,ELM)、KNN、LightGBM、CatBoost、XGBoost和KNN+XGBoost算法降低了6.52%~37.7%,为室内定位提供了一种精确且鲁棒的解决方案。 展开更多
关键词 室内指纹定位 Boxplot滤波 K近邻填补 集成学习 混沌自适应JAYA算法
在线阅读 下载PDF
BOXPLOT——描述统计的一个简便工具 被引量:28
2
作者 庄作钦 《统计教育》 2003年第1期34-35,共2页
箱线图是描述统计的一个简便工具,其功能主要是识别数据批中的异常值;判断数据分布的偏态和尾重;比较不同数据批分布形状特征等。本文阐述了它的绘制、功能和应用。
关键词 BOXPLOT 描述统计 箱线图 异常值 分布形状
在线阅读 下载PDF
供水管网流量监测数据异常值检测方法对比分析 被引量:5
3
作者 胡诗苑 高金良 +2 位作者 钟丹 武睿 刘路明 《中国给水排水》 CAS CSCD 北大核心 2024年第3期53-59,共7页
随着信息化技术的发展,水务企业迎来了智慧化转型升级。数据采集与预处理作为水务企业实现智慧管理的重要前序步骤,为后续数据挖掘、运营管理、调度决策提供了基础。由于环境的影响、管网中的随机扰动、管网事故等原因,监测数据的质量... 随着信息化技术的发展,水务企业迎来了智慧化转型升级。数据采集与预处理作为水务企业实现智慧管理的重要前序步骤,为后续数据挖掘、运营管理、调度决策提供了基础。由于环境的影响、管网中的随机扰动、管网事故等原因,监测数据的质量问题广泛存在,因此寻求有效的供水管网流量监测数据的异常值检测方法至关重要。基于此,首先根据供水管网流量监测数据的基本特征和时间维度的相关性,将常见异常归纳为3个类型;其次,以东南沿海某市的真实小区流量监测数据为例,分别探究基于统计、密度和预测的Boxplot、LOF与Prophet异常值检测模型在不同类型异常数据检测中的性能。结果表明,Boxplot与LOF模型能够较准确地识别出异常数据,但Boxplot对异常的判断标准较宽泛,容易将部分非异常数据识别为异常点,Prophet对于不稳定性较高的流量数据识别效果有限。 展开更多
关键词 流量监测数据 异常值检测 Boxplot LOF PROPHET
原文传递
AN OPERATIONAL STATISTICAL SCHEME FOR TROPICAL CYCLONE INDUCED RAINFALL FORECAST 被引量:4
4
作者 李晴岚 兰红平 +3 位作者 陈仲良 曹春燕 李程 王兴宝 《Journal of Tropical Meteorology》 SCIE 2015年第2期101-110,共10页
A non-parametric method is used in this study to analyze and predict short-term rainfall due to tropical cyclones(TCs) in a coastal meteorological station. All 427 TCs during 1953-2011 which made landfall along the So... A non-parametric method is used in this study to analyze and predict short-term rainfall due to tropical cyclones(TCs) in a coastal meteorological station. All 427 TCs during 1953-2011 which made landfall along the Southeast China coast with a distance less than 700 km to a certain meteorological station- Shenzhen are analyzed and grouped according to their landfalling direction, distance and intensity. The corresponding daily rainfall records at Shenzhen Meteorological Station(SMS) during TCs landfalling period(a couple of days before and after TC landfall) are collected. The maximum daily rainfall(R-24) and maximum 3-day accumulative rainfall(R-72) records at SMS for each TC category are analyzed by a non-parametric statistical method, percentile estimation. The results are plotted by statistical boxplots, expressing in probability of precipitation. The performance of the statistical boxplots is evaluated to forecast the short-term rainfall at SMS during the TC seasons in 2012 and 2013. Results show that the boxplot scheme can be used as a valuable reference to predict the short-term rainfall at SMS due to TCs landfalling along the Southeast China coast. 展开更多
关键词 tropical cyclone rainfall forecast non-parametric method boxplot
在线阅读 下载PDF
Delineation of Geochemical Anomalies Based on Cu by the Boxplot as an Exploratory Data Analysis (EDA) Method and Concentration-Volume (C-V) Fractal Modeling in Mesgaran Mining Area, Eastern Iran 被引量:2
5
作者 Mohammadreza Agharezaei Ardeshir Hezarkhani 《Open Journal of Geology》 2016年第10期1269-1278,共11页
The target in this investigation is separation and delineation of geochemical anomalies for the single element Cu in Mesgaran mining area, eastern Iran. Mesgaran mining area is located in south part of Sarbishe county... The target in this investigation is separation and delineation of geochemical anomalies for the single element Cu in Mesgaran mining area, eastern Iran. Mesgaran mining area is located in south part of Sarbishe county with about 29 Km distance to the county center. This region is part of an Ophiolite sequence and the copper anomalies seem to be related to a volcanic massive sulfide (VMS) deposit whose main part (massive sulfide Lens) has been eroded. In order to delineate Cu anomalies, the boxplot as an Exploratory Data Analysis (EDA) method and concentration-volume (C-V) Fractal modeling are employed. Both of the methods reveal low-deep anomalies which are highly correlated with geological and geophysical studies. As the main result of this study we show that Fractal modeling in spite of the Boxplot, is not recommended for complex geological settings. The proved shallow anomalies recorded by geophysical studies and defined by the used methods are in accordance to the stringer zone of a volcanic massive sulfide (VMS) deposit in Mesgaran mining area which means this region is the bottom of a VMS deposit and geochemical anomalies are related to the remained parts of the deposit. 展开更多
关键词 Mesgaran Geochemistry Fractal Modeling The Boxplot VMS Deposit
在线阅读 下载PDF
OPERATIONAL FORECAST OF RAINFALL INDUCED BY LANDFALLING TROPICAL CYCLONES ALONG GUANGDONG COAST
6
作者 LI Qing-lan LIU Bing-rong +6 位作者 WAN Qi-lin WANG Yu-qing LI Guang-xin LI Tie-jian LAN Hong-ping FENG Sheng-zhong LIU Chun-xia 《Journal of Tropical Meteorology》 SCIE 2020年第1期1-13,共13页
Following previous studies of the rainfall forecast in Shenzhen owing to landfalling tropical cyclones(TCs),a nonparametric statistical scheme based on the classification of the landfalling TCs is applied to analyze a... Following previous studies of the rainfall forecast in Shenzhen owing to landfalling tropical cyclones(TCs),a nonparametric statistical scheme based on the classification of the landfalling TCs is applied to analyze and forecast the rainfall induced by landfalling TCs in the coastal area of Guangdong province,China.All the TCs landfalling with the distance less than 700 kilometers to the 8 coastal stations in Guangdong province during 1950—2013 are categorized according to their landfalling position and intensity.The daily rainfall records of all the 8 meteorological stations are obtained and analyzed.The maximum daily rainfall and the maximum 3 days’accumulated rainfall at the 8 coastal stations induced by each category of TCs during the TC landfall period(a couple of days before and after TC landfalling time)from 1950 to 2013 are computed by the percentile estimation and illustrated by boxplots.These boxplots can be used to estimate the rainfall induced by landfalling TC of the same category in the future.The statistical boxplot scheme is further coupled with the model outputs from the European Centre for Medium-Range Weather Forecasts(ECMWF)to predict the rainfall induced by landfalling TCs along the coastal area.The TCs landfalling in south China from 2014 to 2017 and the corresponding rainfall at the 8 stations area are used to evaluate the performance of these boxplots and coupled boxplots schemes.Results show that the statistical boxplots scheme and coupled boxplots scheme can perform better than ECMWF model in the operational rainfall forecast along the coastal area in south China. 展开更多
关键词 tropical cyclone coastal area rainfall forecast statistical boxplot scheme coupled boxplot scheme
在线阅读 下载PDF
基于机器学习的射灯天线监控方法研究和应用
7
作者 谌晓明 许清 《电信工程技术与标准化》 2023年第1期56-61,共6页
目前,4G和5G网络室分系统对天线等无源器件缺乏实时有效的监控手段,本文通过采集UE MR数据并进行聚类训练获得室分小区的多个类簇,利用Boxplot函数计算类簇的波动阈值区间,结合工参建立每个射灯天线与类簇的初始映射覆盖关系模型,最后... 目前,4G和5G网络室分系统对天线等无源器件缺乏实时有效的监控手段,本文通过采集UE MR数据并进行聚类训练获得室分小区的多个类簇,利用Boxplot函数计算类簇的波动阈值区间,结合工参建立每个射灯天线与类簇的初始映射覆盖关系模型,最后判断波动是否在阈值区间,实现监控射灯天线等无源器件是否存在异常的目的。 展开更多
关键词 室分系统 无源器件 大数据 DBSCAN算法 Boxplot函数
在线阅读 下载PDF
Scanning for Genomic Regions Subject to Selective Sweeps Using SNP-MaP Strategy
8
作者 Libin Deng Xiaoli Tang +4 位作者 Wei Chen Jiari Lin Zhiqing Lai Zuoqi Liu Dake Zhang 《Genomics, Proteomics & Bioinformatics》 SCIE CAS CSCD 2010年第4期256-261,共6页
Population genomic approaches, which take advantages of high-throughput genotyping, are powerful yet costly methods to scan for selective sweeps. DNA-pooling strategies have been widely used for association studies be... Population genomic approaches, which take advantages of high-throughput genotyping, are powerful yet costly methods to scan for selective sweeps. DNA-pooling strategies have been widely used for association studies because it is a cost-effective alternative to large-scale individual genotyping. Here, we performed an SNP-MaP (single nucleotide polymorphism microarrays and pooling) analysis using samples from Eurasia to evaluate the efficiency of pooling strategy in genome-wide scans for selection. By conducting simulations of allelotype data, we first demonstrated that the boxplot with average heterozygosity (HET) is a promising method to detect strong selective sweeps with a moderate level of pooling error. Based on this, we used a sliding window analysis of HET to detect the large contiguous regions (LCRs) putatively under selective sweeps from Eurasia datasets. This survey identified 63 LCRs in a European population. These signals were further supported by the integrated haplotype score (iHS) test using HapMap II data. We also confirmed the European-specific signatures of positive selection from several previously identified genes (KEL, TRPV5, TRPV6, EPHB6). In summary, our results not only revealed the high credibility of SNP-MaP strategy in scanning for selective sweeps, but also provided an insight into the population differentiation. 展开更多
关键词 selective sweep SNP-MaP boxplot
原文传递
上一页 1 下一页 到第
使用帮助 返回顶部