检索结果-内蒙古大学图书馆

A "Density-Based" algorithm for Cluster Analysis Using Species Sampling Gaussian Mixture Models

JOURNAL OF COMPUTATIONAL AND GRAPHICAL STATISTICS 2014年第4期23卷 1126-1142页

作者： Argiento, Raffaele Cremaschi, Andrea Guglielmi, Alessandra CNR IMATI I-20133 Milan Italy Univ Kent Sch Math Stat & Actuarial Sci Canterbury Kent England Politecn Milan Dipartimento Matemat I-20133 Milan Italy

We propose a new model for cluster analysis in a Bayesian nonparametric framework. Our model combines two ingredients, species sampling mixture models of Gaussian distributions on one hand, and a deterministic clustering procedure (dbscan) on the other. Here, two observations from the underlying species sampling mixture model share the same cluster if the distance between the densities corresponding to their latent parameters is smaller than a threshold;this yields a random partition which is coarser than the one induced by the species sampling mixture. Since this procedure depends on the value of the threshold, we suggest a strategy to fix it. In addition, we discuss implementation and applications of the model;comparison with more standard clustering algorithms will be given as well. Supplementary materials for the article are available online.

关键词： dbscan algorithm Bayesian nonparametrics Dirichlet process

来源：评论

学校读者我要写书评

暂无评论

Design of intelligent acquisition system for moving object trajectory data under cloud computing

引用

JOURNAL OF INTELLIGENT SYSTEMS 2021年第1期30卷 763-773页

作者： Zhang, Yang Asthana, Abhinav Asthana, Sudeep Khanna, Shaweta Mihai, Ioan-Cosmin JSS Acad Tech Educ Noida India Liaoning Equipment Mfg Vocat & Tech Coll Shenyang 110161 Peoples R China Liaoning Radio & TV Univ Shenyang 110034 Peoples R China HSBC Technol India Dept OSS Core Banking Pune Maharashtra India Natl Inst Technol Elect & Instrumentat Engn Dept Silchar Assam India Lovely Profess Univ Sch Chem Engn & Phys Sci Phagwara India Al I Cuza Police Acad Bucharest Romania

In order to study the intelligent collection system of moving object trajectory data under cloud computing, information useful to passengers and taxi drivers is collected from massive trajectory data. This paper uses cloud computing technology, through clustering algorithm and density-based dbscan algorithm combined with Map Reduce programming model and design trajectory clustering algorithm. The results show that based on the 8-day data of 15,000 taxis in Shenzhen, the characteristic time period is determined. The passenger hot spot area is obtained by clustering the passenger load points in each time period, which verifies the feasibility of the passenger load point recommendation application based on trajectory clustering. Therefore, in the absence of holidays, the number of passenger hotspots tends to be stable. It is reliable to perform cluster analysis. The recommended application has been demonstrated through experiments, and the implementation results show the rationality of the recommended application design and the feasibility of practice.

关键词： cloud computing clustering algorithm taxi data collection dbscan algorithm

来源：评论

学校读者我要写书评

暂无评论

A general method to filter out defective spatial observations from yield mapping datasets

引用

PRECISION AGRICULTURE 2018年第5期19卷 789-808页

作者： Leroux, Corentin Jones, Hazael Clenet, Anthony Dreux, Benoit Becu, Maxime Tisseyre, Bruno SMAG Montpellier France Montpellier SupAgro Irstea UMR ITAP Montpellier France DEFISOL Evreux France

Yield maps are recognized as a valuable tool with regard to managing upcoming crop production but can contain a large amount of defective data that might result in misleading decisions. These anomalies must be removed before further processing to ensure the quality of future decisions. This paper proposes a new holistic methodology to filter out defective observations likely to be present in yield datasets. The notion of spatial neighbourhood has been refined to embrace the specific characteristics of such on-the-go vehicle based datasets. Observations are compared with their newly-defined spatial neighbourhood and the most abnormal ones are classified as defective observations based on a density-based clustering algorithm. The approach was conceived to be as non-parametric and automated as far as possible to pre-process a growing number of datasets without supervision. The proposed approach showed promising results on real yield datasets with the detection of well-known sources of errors such as filling and emptying times, speed changes and non-fully used cutting bar.

关键词： dbscan algorithm Filtering Local outliers On-board sensors Spatial neighbourhood Yield

来源：评论

学校读者我要写书评

暂无评论

Twitter emergency response system during flood-related disaster

引用

INTERNATIONAL JOURNAL OF EMERGENCY MANAGEMENT 2021年第2期17卷 177-193页

作者： Singh, Jagrati Singh, Anil Kumar Motilal Nehru Natl Inst Technol Allahabad Dept Comp Sci Engn Allahabad 211004 Uttar Pradesh India

The ubiquity of mobile, laptop and social media platforms such as Twitter is accelerating the information flow around the world. This can be useful to handle emergencies during a natural disaster, as victims can share on-the-spot situations and officials can put the solutions on the same platform. We proposed a new emergency response system, aimed at providing help to victims during flood-related disasters based on their tweets. The system consists of three modules: The first module identifies high priority tweets that are asking for help. In the second module, each high priority tweet is given an emergency score based on the victim's location information to help them at an early stage. We proposed a new natural language technique named LDFT (location detection from a tweet) to infer the mentioned locations in the text of the tweet. The third module applies the dbscan clustering algorithm on high scoring tweets and displays the obtained clusters on Google Maps to visualise the hot-spot areas easily. The proposed disaster response system works well, with its maximum accuracy of 78%, and location prediction accuracy of 75%.

关键词： Twitter stream dbscan algorithm location prediction emergency-score classification clustering

来源：评论

学校读者我要写书评

暂无评论

Spatiotemporal properties of the 2020-2021 Petrinja (Croatia) earthquake sequence

引用

JOURNAL OF SEISMOLOGY 2024年第4期28卷 899-920页

作者： Sardeli, Eirini Michas, Georgios Pavlou, Kyriaki Zaccagnino, Davide Vallianatos, Filippos Natl & Kapodistrian Univ Athens Dept Geol & Geoenvironm Sect Geophys Geotherm Athens Greece Sapienza Univ Earth Sci Dept Piazzale Aldo Moro 5 I-00185 Rome Italy Hellen Mediterranean Univ Res Inst Phys Earths Interior & Geohazards UNESCO Chair Solid Earth Phys & Geohazards Risk Re Innovat Ctr Khania Greece

The Petrinja earthquake sequence started on December 28, 2020, with a destructive ML 6.2 mainshock occurring in the area, preceded by a ML 5.08 foreshock, following a long period of relative seismic quiescence. Over the first six months of the Petrinja earthquake sequence, almost 14,000 events were recorded. In the present work, we separated seismic events based on their spatial concentration using a density-based clustering algorithm, dbscan. We identified four main clusters and analyzed their spatiotemporal properties using the notions of Non-Extensive Statistical Physics (NESP). This framework, which relies on Tsallis entropy (Sq), describes the scaling behavior of complex systems. In this frame, we investigated the inter-event time (T) and distance (D) distributions, providing the qT and qD entropic parameters, respectively. Additionally, we studied the frequency-magnitude distributions in terms of the fragment-asperity model, leading to the determination of the non-extensive parameter qM. The results of the analysis suggest that the statistical properties of the Petrinja earthquake sequence can be effectively reproduced utilizing NESP. Furthermore, the coseismic static Coulomb stress changes were estimated, indicating that the clusters' seismic events may have resulted from a complex fault system's (re)activation. In addition, the effective static stress drop was estimated for each spatial cluster. Lastly, the temporal patterns of the earthquake evolution are discussed using the superstatistics approach, indicating that the temporal progression of the Petrinja earthquake clusters is governed by a very low number of degrees of freedom, highlighting the spatiotemporal organization of each cluster.

关键词： Petrinja earthquake sequence Tsallis entropy Non-extensive statistical physics dbscan algorithm Complexity

来源：评论

学校读者我要写书评

暂无评论

Applications of QGIS and machine learning for road crash spot identification

引用

EARTH SCIENCE INFORMATICS 2024年第3期17卷 2331-2346页

作者： Pusuluri, Vijaya Lakshmikanthi Dangeti, Mukund Rao Gayatri Vidya Parishad Coll Degree & PG Courses A Civil Engn Dept Engn & Technol Program Visakhapatnam 530045 India GITAM Civil Engn Dept Visakhapatnam 530045 India

Road intersections or linear segments of roads with frequent road crashes are termed as 'blackspots.' There are many blackspot identification methodologies developed and implemented in global cities with varying results. Cross-country adaptability of such methods is limited due to differences in road design parameters, vehicle modal composition, mixed land uses, and varying driver profiles. The United Nations recognizes road crash fatalities as the eighth most significant cause of death, and detecting their occurrence assumes critical prominence. There is an immediate need to find easy-to-adopt, cost-effective strategies that can assist rapidly urbanizing towns in identifying and predicting crash zones. This study considers Visakhapatnam as a study area for black spot identification using Andhra Pradesh Traffic police crash data between 2014 and 2021 and the Weighted Severity Index (WSI). It studies VMRDA Master Plans between 1988 and 2041 for land use changes and visualizes crash spots in QGIS. Machine Learning algorithm dbscan is used to define crash clusters and validate the latitude and longitude of the crash spots. The results have found that fatalities are high in Gajuwaka and P M Palem Police Station Jurisdictions (PSJs). The study identified seven black spots on National Highway 16 in these two areas by their latitude and longitude. It found that the dbscan algorithm is precise and adaptable to analyze the crash spot data. This methodology combining open source QGIS and dbscan algorithm is proven applicable for 'black spot' identification in the entire city and for cities with similar traffic problems. Geographic and road profile variations do not limit the scope of this study. Land use variations and their influence on black spot formation are the future scope of this study.

关键词： Road crashes Land use QGIS Weighted Severity Index dbscan algorithm

来源：评论

学校读者我要写书评

暂无评论

A Data-Mining Interpretation Method of Pavement Dynamic Response Signal by Combining dbscan and Findpeaks Function

引用

SENSORS 2024年第3期24卷 939页

作者： Liu, Hailong Yao, Ruqing Cui, Chunyi Zhao, Jiuye Dalian Maritime Univ Coll Transportat Engn Dalian 116026 Peoples R China Dalian Maritime Univ Ctr Port & Maritime Safety Dalian 116026 Peoples R China Dalian Maritime Univ Coll Int Collaborat Dalian 116026 Peoples R China

During a heavy traffic flow featuring a substantial number of vehicles, the data reflecting the strain response of asphalt pavement under the vehicle load exhibit notable fluctuations with abnormal values, which can be attributed to the complex operating environment. Thus, there is a need to create a real-time anomalous-data diagnosis system which could effectively extract dynamic strain features, such as peak values and peak separation from the large amount of data. This paper presents a dynamic response signal data analysis method that utilizes the dbscan clustering algorithm and the findpeaks function. This method is designed to analyze data collected by sensors installed within the pavement. The first step involves denoising the data using low-pass filters and other techniques. Subsequently, the dbscan algorithm, which has been improved using the K-Dist method, is used to diagnose abnormal data after denoising. The refined findpeaks function is further implemented to carry out the adaptive feature extraction of the denoised data which is free from anomalies. The enhanced dbscan algorithm is tested via simulation and illustrates its effectiveness while detecting abnormal data in the road dynamic response signal. The findpeaks function enables the relatively accurate identification of peak values, thus leading to the identification of strain signal peaks of complex multi-axle lorries. This study is valuable for efficient data processing and effective information utilization in pavement monitoring.

关键词： dynamic response of pavement abnormal data diagnosis adaptive feature extraction dbscan algorithm findpeaks function

来源：评论

学校读者我要写书评

暂无评论

Application of Particle Swarm Optimization Based on Clustering Analysis in Logistics Distribution

Application of Particle Swarm Optimization Based on Clusteri...

引用

3rd International Conference on Management of e-Commerce and e-Government

作者： Shi, Haobin Li, Zhonghua Li, Wenbin Yu, Zhujun Northwestern Polytech Univ Sch Comp Sci Xian 710072 Peoples R China Jiangxi Univ Finance & Econom Sch Informat Technol Nanchang Jiangxi Peoples R China

ISBN: (纸本)9780769537788

In order to solve the modern logistics problem of vehicle distribution, a particle swarm optimization (PSO) algorithm based on clustering analysis is proposed in this paper. This algorithm clusters the target points in need of distribution primarily by dbscan algorithm, and then weighted k-means algorithm is used to cluster the target points finally based on the primary clustering. Corresponding vehicles are allocated to every target cluster according to result of clustering analysis, furthermore, path of vehicles are optimized by use of PSO algorithm until all the distribution tasks are finished. Simulation experiments result shows that PSO algorithm based on clustering analysis is feasible and effective in modern logistics distribution process.

关键词： logistics distribution particle swarm optimization (PSO) algorithm dbscan algorithm weighted k-means algorithm

来源：评论

学校读者我要写书评

暂无评论

Anomaly Detection from Call Data Records

Anomaly Detection from Call Data Records

引用

3rd International Conference on Pattern Recognition and Machine Intelligence

作者： Nithi Dey, Lipika TCS Innnovat Labs Delhi India

In this paper, we propose an efficient algorithm for anomaly detection from call data records. Anomalous users are detected based on fuzzy attribute values derived from their communication patterns. A clustering based... 详细信息

ISBN: (纸本)9783642111631

关键词： Anomaly detection Fuzzy logic dbscan algorithm Principal Component Analysis

来源：评论

学校读者我要写书评

暂无评论

Spatial cluster analysis of bursting pipes in water supply networks

Spatial cluster analysis of bursting pipes in water supply n...

引用

12th International Conference on Computing-and-Control-for-the-Water-Industry (CCWI)

作者： Sun, J. Wang, R. Wang, X. Yang, H. Ping, J. Thinghuct Univ Grad Sch Shenzhen Shenzhen 518055 Peoples R China

Urban water supply network is a hidden underground asset;therefore, it is difficult to make a direct diagnosis towards the faults of pipe network by means of the detecting technology. Based on the historical data of the rupture of water supply pipe network, a spatial cluster analysis will be carried out towards the historical data of spatial fault in water supply pipeline, using density-based cluster analysis and the dbscan algorithm. K-neighborhood graph is well-used in optimizing the input parameter radius of neighborhood (Eps) and density (MinPts) and classifying the historical data of the rupture of pipeline. According to the pipe network failure point coordinates (X, Y), adopting density-based cluster analysis, a danger level classification will be researched without knowing the reasons of the rupture of pipe network, which lays the foundation for finding out pipeline rupture in local areas in the future. Meanwhile, a noise analysis will be processed in terms of the historical data of pipeline rupture in water supply network, avoiding the ineffective data caused by recording errors and regular analysis. This research focuses on the reasons that result in the rupture of water supply network, which plays a significant role in the identification of high-density and high-danger zones in water supply networks. (C) 2013 The Authors. Published by Elsevier Ltd. Selection and peer-review under responsibility of the CCWI2013 Committee

关键词： dbscan algorithm Spatial cluster analysis Pipe burst Water supply network Data mining

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：