检索结果-内蒙古大学图书馆

Driver identification in intelligent vehicle systems using machine learning algorithms

IET INTELLIGENT TRANSPORT SYSTEMS 2019年第1期13卷 40-47页

作者： Li, Zhengping Zhang, Kai Chen, Bokui Dong, Yuhan Zhang, Lin Tsinghua Univ Div Logist & Transportat Grad Sch Shenzhen Shenzhen Peoples R China Natl Univ Singapore Sch Comp Dept Comp Sci Singapore Singapore Tsinghua Univ Div Informat Sci & Technol Grad Sch Shenzhen Shenzhen Peoples R China Tsinghua Berkeley Shenzhen Inst Data Sci & Informat Technol Res Ctr Shenzhen Peoples R China

This study proposes an applicable driver identification method using machine learning algorithms with driving information. The driving data are collected by a 3-axis accelerometer, which records the lateral, longitudinal and vertical accelerations. In this research, a data transformation way is developed to extract interpretable statistics features from raw 3-axis sensor data and utilise machine learning algorithms to identify drivers. To eliminate the bias caused by the sensor installation and ensure the applicability of their approach, they present a data calibration method which proves to be necessary for a comparative test. Four basic supervised classification algorithms are used to perform on the data set for comparison. To improve classification performance, they propose a multiple classifier system, which combines the outputs of several classifiers. Experimental results based on real-world data show that the proposed algorithm is effective on solving driver identification problem. Among the four basic algorithms, random forests (RFs) algorithm has the greatest performance on accuracy, recall and precision. With the proposed multiple classifier system, a greater performance can be achieved in small number of drivers' groups. RFs algorithm takes the lead in running speed. In their experiment, ten drivers are involved and over 5,500,000 driving records per driver are collected.

关键词： learning (artificial intelligence) intelligent transportation systems feature extraction traffic engineering computing image classification calibration statistical analysis RFs algorithm random forests algorithm multiple classifier system supervised classification algorithms data calibration method sensor installation raw 3-axis sensor data interpretable statistics feature extraction data transformation lateral accelerations longitudinal accelerations vertical accelerations 3-axis accelerometer driving data collection machine learning algorithms intelligent vehicle systems driver identification method

来源：评论

学校读者我要写书评

暂无评论

Maize and sorghum field segregation using multi-temporal Sentinel-2 data in central Mexico

引用

JOURNAL OF APPLIED REMOTE SENSING 2021年第2期15卷

作者： Soler-Perez-Salazar, Maria J. Ortega-Garcia, Nicolas Vaca-Mier, Mabel Cram-Hyedric, Silke Univ Autonoma Metropolitana Energy Dept Azcapotzalco Mexico Inst Tecnol Super Salvatierra Guanajuato Mexico Univ Nacl Autonoma Mexico Inst Geog Coyoacan Mexico

Crop segregation in optical remote sensing cannot always be easily achieved among similar species since their spectral response can be similar. We aimed to distinguish fields of two C4 gramineae with similar plant structure and crop calendar, maize (Zea mays) and sorghum (Sorghum bicolor), in an agricultural area of the state of Guanajuato, in central Mexico. One hundred and forty-three fields of these two crops were identified and their average spectral signatures were derived at different phenological stages, using digital information from 11 Sentinel 2A/B images, corresponding to the 2019 spring-summer cycle. We also calculated the temporal profile of six spectral indices for each crop, to evaluate seasonal variations and conducted a cropland classification, using the random forests algorithm and different combinations of dates and indices. Results show that segregation of maize and sorghum fields can be achieved due to small differences in the near-infrared region of their spectral signatures and disparities in the rate of decay during the senescence stage. Classification results also confirmed the separability of these two crops, obtaining a very high overall accuracy and kappa values (98.43% and 97.07%, correspondingly) based on the reflectance of nine images and only three spectral indices: the normalized difference vegetation index, the normalized difference water index, and the structure insensitive pigment index. This investigation demonstrates that the combined use of time series of high-resolution images and spectral indices can contribute to distinguish fields of similar crop species. (C) 2021 Society of Photo-Optical Instrumentation Engineers (SPIE)

关键词： crop classification maize sorghum Sentinel-2 random forests algorithm spectral indices

来源：评论

学校读者我要写书评

暂无评论

Spatio-temporal interpolation of soil water, temperature, and electrical conductivity in 3D+T: The Cook Agronomy Farm data set

引用

SPATIAL STATISTICS 2015年第PartA期14卷 70-90页

作者： Gasch, Caley K. Hengl, Tomislav Graeler, Benedikt Meyer, Hanna Magney, Troy S. Brown, David J. Washington State Univ Dept Crop & Soil Sci Pullman WA 99164 USA Wageningen Univ & Res ISRIC World Soil Informat Wageningen Netherlands Univ Munster Inst Geoinformat Munster Germany Univ Marburg Dept Geog Environm Informat D-35032 Marburg Germany Univ Idaho Coll Nat Resources Moscow ID 83843 USA

The paper describes a framework for modeling dynamic soil properties in 3-dimensions and time (3D + T) using soil data collected with automated sensor networks as a case study. Two approaches to geostatistical modeling and spatio-temporal predictions are described: (1) 3D + T predictive modeling using random forests algorithms, and (2) 3D + T kriging model after detrending the observations for depth-dependent seasonal effects. All the analyses used data from the Cook Agronomy Farm (37 ha), which includes hourly measurements of soil volumetric water content, temperature, and bulk electrical conductivity at 42 stations and five depths (0.3, 0.6, 0.9, 1.2, and 1.5 m), collected over five years. This data set also includes 2-and 3-dimensional, temporal, and spatio-temporal covariates covering the same area. The results of (strict) leave-onestation- out cross-validation indicate that both models accurately predicted soil temperature, while predictive power was lower for water content, and lowest for electrical conductivity. The kriging model explained 37%, 96%, and 18% of the variability in water content, temperature, and electrical conductivity respectively versus 34%, 93%, and 5% explained by the random forests model. A less rigorous simple cross-validation of the random forests model indicated improved predictive power when at least some data were available for each station, explaining 86%, 97%, and 88% of the variability in water content, temperature, and electrical conductivity respectively. The high difference between the strict and simple cross-validation indicates high temporal auto-correlation of values at measurement stations. Temporal model components (i.e. day of the year and seasonal trends) explained most of the variability in observations in both models for all three variables. The seamless predictions of 3D + T data produced from this analysis can assist in understanding soil processes and how they change through a season, under different land management

关键词： Digital soil mapping random forests algorithm Regression-kriging Soil sensor network

来源：评论

学校读者我要写书评

暂无评论

Multiple intra-urban land use simulations and driving factors analysis: a case study in Huicheng, China

引用

GISCIENCE & REMOTE SENSING 2019年第2期56卷 282-308页

作者： Zhang, Dachuan Liu, Xiaoping Wu, Xiaoyu Yao, Yao Wu, Xinxin Chen, Yimin Sun Yat Sen Univ Sch Geog & Planning Guangdong Key Lab Urbanizat & Geosimulat Guangzhou Guangdong Peoples R China Peking Univ Inst Remote Sensing & Geog Informat Syst Beijing Peoples R China China Univ Geosci Sch Informat Engn Wuhan Hubei Peoples R China Alibaba Grp Dept Data Technol & Prod Hangzhou Zhejiang Peoples R China

Simulations of intra-urban land use changes have gradually attracted more attention as these approaches are extremely helpful in regard to decision making and policy formulation. While prior studies mostly focused on methods of developing intra-urban level simulations, very little research has been conducted explain the factors driving intra-urban land use change. Urban planners are highly concerned with how inner-city structures are formed and how they function. Here, to simulate multiple intra-urban land use changes and to identify the contribution of different driving factors, we developed a random forests (RF) algorithm-based cellular automata (CA) simulation model. In this study, the model applied diverse categories of spatial variables, including traffic location factors, environmental factors, public services, and population density, as the driving factors to enhance our understanding of the dynamics of internal urban land use. The CA model was tested using data from the Huicheng district of Huizhou city in the Guangdong province of China. The Model was validated using actual historical land use data from 2000 to 2010. By applying the validated model, multiple intra-urban land use maps were simulated for 2015. Simultaneously, spatial variable importance measures (VIMs) were calculated by using the out-of-bag (OOB) error estimation approach of the RF algorithm. Based on the calculation results, we assessed and analysed the significance of each intra-urban land use driver for this region. This study provides urban planners and relevant scholars with detailed and targeted information that can aid in the formulation of specific planning strategies for different intra-urban land uses and support the future evolution of this area.

关键词： cellular automata urban planning multiple intra-urban land use simulations driving factors analysis random forests algorithm

来源：评论

学校读者我要写书评

暂无评论

A validated approach for supervised dive classification in diving vertebrates

引用

JOURNAL OF EXPERIMENTAL MARINE BIOLOGY AND ECOLOGY 2008年第1-2期363卷 75-83页

作者： Thums, Michele Bradshaw, Corey J. A. Hindell, Mark A. Univ Tasmania Sch Zool Antarctic Wildlife Res Unit Hobart Tas 7001 Australia Univ Adelaide Sch Earth & Environm Sci Res Inst Climate Change & Sustainabil Adelaide SA 5005 Australia S Australian Res & Dev Inst Henley Beach SA 5022 Australia

Supervised dive classification is a commonly used technique for categorising time-depth Profiles of diving vertebrates. Such analyses permit the description and quantification of dive behaviour and foraging tactics, and highlight feeding locations. Ideally, classification functions should be validated, and this is commonly done visually. Visual classification is subjective, but it is currently one of the few measures available for validation. We develop several approaches to validate a supervised dive classification: (1) two people visually assigning dives and developing a dataset where both agree, and (2) use of dives from southern elephant seals identified as "drift dives" with characteristic velocity signatures. We classified the dives of three seals from their post-moult foraging trips and estimated the error associated with visual classification. We found classification error (disagreement) between classifiers up to 57%. We created a training dataset based on dives with agreement and applied this to a relatively new, automated classification method - the random forests (RF) algorithm. A supervised function developed using this algorithm estimated a classification error of 5% on elephant seal dives;classification error on underrepresented dive classes ranged from 2 - 12%. Testing this classification function on independent data produced a low error (1.6%). RF function errors were lower than for visual classification, and errors were similar to or better than those estimated using discriminant functions. Swim velocity parameters were the most important predictors, but their absence did not reduce the random forests function's effectiveness by much. Our results suggest that there is a temporal shift in diving behaviour as seals become more buoyant. We compared the temporal patterns in drift rate from the drift dives classified using the RF function with the drift dives validated via characteristic velocity signatures. This indicated that the classifications produc

关键词： dive classification diving elephant seal random forests algorithm supervised classification time-depth profiles time-depth recorders

来源：评论

学校读者我要写书评

暂无评论

Regional-scale controls on the spatial activity of rockfalls (Turtmann Valley, Swiss Alps) - A multivariate modeling approach

引用

GEOMORPHOLOGY 2017年 287卷 29-45页

作者： Messenzehl, Karoline Meyer, Hanna Otto, Jan-Christoph Hoffmann, Thomas Dikau, Richard Univ Bonn Dept Geog Bonn Germany Philipps Univ Marburg Fac Geog Marburg Germany Univ Salzburg Dept Geog & Geol Salzburg Austria Fed Inst Hydrol BfG Koblenz Germany

In mountain geosystems, rockfalls are among the most effective sediment transfer processes, reflected in the regional-scale distribution of talus slopes. However, the understanding of the key controlling factors seems to decrease with increasing spatial scale, due to emergent and complex system behavior and not least to recent methodological shortcomings in rockfall modeling research. In this study, we aim (i) to develop a new approach to identify major regional-scale rockfall controls and (ii) to quantify the relative importance of these controls. Using a talus slope inventory in the Turtmann Valley (Swiss Alps), we applied for the first time the decision-tree based random forest algorithm (RF) in combination with a principal component logistic regression (PCLR) to evaluate the spatial distribution of rockfall activity. This study presents new insights into the discussion on whether periglacial rockfall events are controlled more by topo-climatic, cryospheric, paraglacial or/and rock mechanical properties. (i) Both models explain the spatial rockfall pattern very well, given the high areas under the Receiver Operating Characteristic (ROC) curves of >0.83. Highest accuracy was obtained by the RF, correctly predicting 88% of the rockfall source areas. The RF appears to have a great potential in geomorphic research involving multicollinear data. (ii) The regional permafrost distribution, coupled to the bedrock curvature and valley topography, was detected to be the primary rockfall control. Rockfall source areas cluster within a low-radiation elevation belt (2900-3300 m a.s.l,) consistent with a permafrost probability of >90%. The second most important factor is the time since deglaciation, reflected by the high abundance of rockfalls along recently deglaciated (<100 years), north-faring slopes. However, our findings also indicate a strong rock mechanical control on the paraglacial rockfall activity, declining either exponentially or linearly since deglaciation. The s

关键词： Rockfall Logistic regression model random forests algorithm Rock mechanical properties Paraglacial Permafrost

来源：评论

学校读者我要写书评

暂无评论

PROJECTIONS OF SUITABLE HABITAT FOR RARE SPECIES UNDER GLOBAL WARMING SCENARIOS

引用

AMERICAN JOURNAL OF BOTANY 2010年第6期97卷 970-987页

作者： Ledig, F. Thomas Rehfeldt, Gerald E. Saenz-Romero, Cuauhtemoc Flores-Lopez, Celestino US Forest Serv Inst Forest Genet Pacific SW Res Stn USDA Placerville CA 95667 USA Univ Calif Davis Dept Plant Sci Davis CA 95616 USA US Forest Serv Forestry Sci Lab Rocky Mt Res Stn USDA Moscow ID 83843 USA UMSNH IIAF Tarimbaro 58880 Michoacan Mexico Univ Autonoma Agraria Antonio Narro Dept Forestal Saltillo 25000 Coahuila Mexico

Premise of the study: Modeling the contemporary and future climate niche for rare plants is a major hurdle in conservation, yet such projections are necessary to prevent extinctions that may result from climate change. Methods: We used recently developed spline climatic models and modified random forests statistical procedures to predict suitable habitats of three rare, endangered spruces of Mexico and a spruce of the southwestern USA. We used three general circulation models and two sets of carbon emission scenarios ( optimistic and pessimistic) for future climates. Key results: Our procedures predicted present occurrence perfectly. For the decades 2030, 2060, and 2090, the ranges of all taxa progressively decreased, to the point of transient disappearance for one species in the decade 2060 but reappearance in 2090. Contrary to intuition, habitat did not develop to the north for any of the Mexican taxa;rather, climate niches for two taxa re-materialized several hundred kilometers southward in the Trans-Mexican Volcanic Belt. The climate niche for a third Mexican taxon shrank drastically, and its two mitotypes responded differently, one of the first demonstrations of the importance of intraspecific genetic variation in climate niches. The climate niche of the U. S. species shrank northward and upward in elevation. Conclusion: The results are important for conservation of these species and are of general significance for conservation by assisted colonization. We conclude that our procedures for producing models and projecting the climate niches of Mexican spruces provide a way for handling other rare plants, which constitute the great bulk of the world's endangered and most vulnerable flora.

关键词： assisted colonization climatic models conservation Picea engelmannii Picea martinezii Picea mexicana random forests algorithm Trans-Mexican Volcanic Belt

来源：评论

学校读者我要写书评

暂无评论

Refining Traceability Links Between Vulnerability and Software Component in a Vulnerability Knowledge Graph 18th

Refining Traceability Links Between Vulnerability and Softwa...

引用

18th International Conference on Web Engineering (ICWE)

作者： Du, Dongdong Ren, Xingzhang Wu, Yupeng Chen, Jien Ye, Wei Sun, Jinan Xi, Xiangyu Gao, Qing Zhang, Shikun Peking Univ Sch Elect Engn & Comp Sci Beijing Peoples R China Peking Univ Sch Software & Microelect Beijing Peoples R China Peking Univ Natl Engn Res Ctr Software Engn Beijing Peoples R China

ISBN: (纸本)9783319916620;9783319916613

Software vulnerabilities and their corresponding software components information are usually stored in different locations with different representations. Building accurate traceability links between them to form a unified knowledge graph can be very helpful for vulnerability spreading analysis, component dependency management, and relationship inference. In this paper, we first propose a software vulnerability knowledge graph model which integrates CVE (Common Vulnerabilities and Exposures) information, Java Component metadata in Maven repository and project collaboration data on Github. To construct the knowledge graph, we then propose two ontology matching approaches. The first one links Maven project and Github project in a URL textmatching way. The second one introduces random forests algorithm to link CVE project version and Maven project version based on 16 well-defined features. Experimental results show that matching between CVE project version and Maven project version are highly promising with an accuracy rate as high as 99.8%. The traceability links between vulnerabilities and software components can be more accurate based on our approach.

关键词： Vulnerability knowledge graph Software security vulnerabilities Software dependencies Vulnerability traceability random forests algorithm

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of E-Mail Spam Classification using different Machine Learning Techniques

Performance Analysis of E-Mail Spam Classification using dif...

引用

International Conference on Advances in Computing and Communication Engineering (ICACCE)

作者： Vinitha, V. Sri Renuka, D. Karthika Bannari Amman Inst Technol Dept Informat Technol Sathyamangalam Erode India PSG Coll Technol Dept Informat Technol Coimbatore Tamil Nadu India

ISBN: (纸本)9781728132501

Most of the business and general communication is done through email because of its cost effectiveness. This efficiency leads email exposed to various attacks including spamming. Nowadays spam email is the foremost concern for email users. These spams are used for sending fake proposals, advertisements, and harmful contents in the form of executable file to attack user systems or the link to the malicious websites resulting in the unessential consumption of network bandwidth. This paper elucidates the different Machine Learning Techniques such as J48 classifier, Adaboost, K-Nearest Neighbor, Naive Bayes, Artificial Neural Network, Support Vector Machine, and random forests algorithm for filtering spam emails using different email dataset. However, here the comparison of different spam email classification technique is presented and summarizes the overall scenario regarding accuracy rate of different existing approaches.

关键词： Email Spam J48 classifier Adaboost K-Nearest Neighbor Naive Bayes Artificial Neural Network Support Vector Machine random forests algorithm

来源：评论

学校读者我要写书评

暂无评论

Network Traffic Classification - A Comparative Study of Two Common Decision Tree Methods: C4.5 and random Forest 2

Network Traffic Classification - A Comparative Study of Two ...

引用

2nd International Conference Electronic Design ICED

作者： Munther, Alhamza Othman, Rozmie R. Alalousi, Alabass Anbar, Mohammed Nizam, Shahrul Univ Malaysia Perlis Sch Comp & Commun Engn Perlis Malaysia Univ Thamar Sch Comp & Informat Syst Dept Comp Thamar Yemen Univ Sains Malaysia Natl Adv Ctr Excellence IPv6 George Town Malaysia

ISBN: (纸本)9781479961030

Network traffic classification gains continuous interesting while many applications emerge on the different kinds of networks with obfuscation techniques. Decision tree is a supervised machine learning method used widely to identify and classify network traffic. In this paper, we introduce a comparative study focusing on two common decision tree methods namely: C4.5 and random forest. The study offers comparative results in two different factors are accuracy of classification and processing time. C4.5 achieved high percentage of classification accuracy reach to 99.67 for 24000 instances while random Forest was faster than C4.5 in term of processing time.

关键词： Traffic Classification Machine learning Supervised Learning random forests 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：