检索结果-内蒙古大学图书馆

Railway accidents analysis based on the improved algorithm of the maximal information coefficient

INTELLIGENT DATA ANALYSIS 2016年第3期20卷 597-613页

作者： Shao, Fubo Li, keping Xu, Xiaoming Beijing Jiaotong Univ State Key Lab Rail Traff Control & Safety Beijing Peoples R China Beijing Jiaotong Univ Beijing Lab Urban Rail Transit Beijing Peoples R China

The maximal information coefficient (MIC), a measure of dependence for two-variable relationships, can be used to discover the relationships between two variables in big data. This paper proposes a new mathematical program model for calculating the value of MIC. A corresponding efficient algorithm is designed to solve the model in big data environment. In order to illustrate the validity of the proposed algorithm, the proposed algorithm is applied into the analysis of railway accidents data. Experimental results show that the proposed algorithm could find important relationships between two variables from big data. And some factors influencing accidents are identified from many factors. In addition, compared with the algorithm proposed by Reshef et al. in 2011, the proposed algorithm has lower time complexity and needs less computation time. Hence the proposed algorithm is more suitable for big data environment.

关键词： Maximal information coefficient k-means clustering algorithm big data railway accidents analysis

来源：评论

学校读者我要写书评

暂无评论

Automatic identification of the critical slip surface of slopes

引用

ENGINEERING GEOLOGY 2020年 273卷 105672-105672页

作者： Wang, Yankun Huang, Jinsong Tang, Huiming China Univ Geosci Fac Engn Wuhan 430074 Hubei Peoples R China Univ Newcastle Prior Res Ctr Geotech Sci & Engn Discipline Civil Surveying & Environm Engn Callaghan NSW 2308 Australia China Univ Geosci Three Gorges Res Ctr Geohazards Minist Educ Wuhan 430074 Hubei Peoples R China

Although numerical methods based on strength reduction are becoming popular in slope stability analysis, they fail to provide a distinct critical slip surface and only provide a shear band. The widely used visualization techniques for defining the critical slip surface are susceptible to subjective judgment and are inefficient for batch analysis and three-dimensional analysis. When a slope fails, the displacements on the two sides of the critical slip surface will be substantially different. Based on this observation, an automatic identification method for locating the critical slip surface is proposed. The k-means clustering algorithm is first applied to automatically separate the nodal displacements into two categories representing the sliding mass and the stable block. Then, the scatters near the separation surface are obtained by constructing the alpha shape of the sliding mass. Finally, the critical slip surface is obtained by fitting the extracted scatters. A homogeneous slope, a slope with a thin weak layer and a real landslide are used to test the effectiveness of the proposed method. The results show that the proposed method can automatically and accurately identify two-dimensional and three-dimensional critical slip surfaces.

关键词： Critical slip surface k-means clustering algorithm Automatic identification Slope stability Strength reduction method

来源：评论

学校读者我要写书评

暂无评论

Improved landslide susceptibility assessment: A new negative sample collection strategy and a comparative analysis of zoning methods

引用

ECOLOGICAL INDICATORS 2024年 169卷

作者： Wang, Jiani Wang, Yunqi Li, Manyi Qi, Zihan Li, Cheng Qi, Haimei Zhang, Xiaoming Beijing Forestry Univ Sch Soil & Water Conservat Beijing 100083 Peoples R China Three Gorges Reservoir Area Chongqing Forest Ecosy Chongqing 400700 Peoples R China Chongqing Inst Geol & Mineral Resources Observat & Res Stn Ecol Restorat Chongqing Typ Min Minist Nat Resources Chongqing 401120 Peoples R China China Inst Water Resources & Hydropower Res Beijing 100048 Peoples R China

Landslide susceptibility assessment (LSA) aims to determine the spatial probability of landslides, reducing the loss caused by future landslides. In order to assess the impact of various negative sample collection strategies on the prediction accuracy of the landslide susceptibility assessment (LSA) model, and to investigate the effectiveness of landslide susceptibility zoning methods. Taking Fengjie County, Chongqing City, China as the study area, this study proposes three negative sample collection strategies based on slope unit, buffer zone, and information value, and combines them with C5.0 decision tree (DT) model respectively to construct an LSA model. Concurrently, the landslide susceptibility indexes (LSIs) were divided using the k-means clustering algorithm and contrasted with the natural breakpoint classification (NBC), quantile classification (QC), equal interval classification (EIC), and geometric interval classification (GIC) methods. The results show that: (1) Rainfall, elevation, and water system are the primary conditioning factors of landslide development in the study area. (2) The accuracy of the negative sample collection strategy based on the slope units on the model training subset and the test subset reached 97.78 % and 92.99 %, respectively, and the AUC values were 0.978 and 0.930, indicating high model accuracy. (3) The zoning effect based on the k-means clustering algorithm was the best, and the predicted very-high and high susceptibility areas were 805.73 km2 and 567.66 km2, respectively, accounting for 19.59 % and 13.80 % of Fengjie County. The very-high and high susceptibility areas had maximum FR values of 3.963 and 1.432, respectively, when compared to other zoning methods. This study can provide a more objective and scientific method for LSA, and the findings can offer more precise decision assistance for risk management and geological disaster prevention.

关键词： Landslide susceptibility assessment Negative sample collection strategy C5.0 decision tree k-means clustering algorithm Landslide susceptibility zoning

来源：评论

学校读者我要写书评

暂无评论

A Molecular Communication Perspective on Synchronization of Coupled Microfluidic-Spectroscopy

IEEE TRANSACTIONS ON NANOBIOSCIENCE

引用

IEEE TRANSACTIONS ON NANOBIOSCIENCE 2024年第3期23卷 458-471页

作者： Qian, Xuewen Angerbauer, Stefan Egan, Malcolm Di Renzo, Marco Haselmayr, Werner Univ Paris Saclay Lab Signauxet Syst CNRS Cent Supelec F-91192 Gif Sur Yvette France Johannes Kepler Univ Linz Inst Commun Engn & RF Syst A-4040 Linz Austria INSA Lyon UR3720 CITI Inria F-69621 Villeurbanne France

A challenge for real-time monitoring of biochemical processes, such as cells, is detection of biologically relevant molecules. This is due to the fact that spectroscopy methods for detection may perturb the cellular environment. One approach to overcome this problem is coupled microfluidic-spectroscopy, where a microfluidic output channel is introduced in order to observe biologically relevant molecules. This approach allows for non-passive spectroscopy methods, such as mass spectrometry, to identify the structure of molecules released by the cell. Due to the non-negligible length of the microfluidic channel, when a sequence of stimuli are applied to a cell it is not straightforward to determine which spectroscopy samples correspond to a given stimulus. In this paper, we propose a solution to this problem by taking a molecular communication (MC) perspective on the coupled microfluidic-spectroscopy system. In particular, assignment of samples to a stimulus is viewed as a synchronization problem. We develop two new algorithms for synchronization in this context and carry out a detailed theoretical and numerical study of their performance. Our results show improvements over maximum-likelihood synchronization algorithms in terms of detection performance when there are uncertainties in the composition of the microfluidic channel.

关键词： Molecular communication synchronization Skellam distribution k-means clustering algorithm

来源：评论

学校读者我要写书评

暂无评论

Fuzzy time series forecasting based on fuzzy logical relationships and similarity measures

引用

INFORMATION SCIENCES 2016年 327卷 272-287页

作者： Cheng, Shou-Hsiung Chen, Shyi-Ming Jian, Wen-Shan Chien Kuo Technol Univ Dept Informat Management Changhua Taiwan Chien Kuo Technol Univ Dept Kinesiol Hlth Leisure Studies Changhua Taiwan Natl Taiwan Univ Sci & Technol Dept Comp Sci & Informat Engn Taipei Taiwan

In this paper, we propose a new fuzzy time series forecasting method for forecasting the Taiwan Stock Exchange Capitalization Weighted Stock Index (TAIEX) based on fuzzy time series, fuzzy logical relationships, particle swarm optimization techniques, the k-means clustering algorithm, and similarity measures between the subscript of the fuzzy set of the fuzzified historical testing datum on the previous trading day and the subscripts of the fuzzy sets appearing in the current states of the fuzzy logical relationships in the chosen fuzzy logical relationship group. The particle swarm optimization techniques are used to get the optimal partition of the intervals in the universe of discourse. The k-means clustering algorithm is used to cluster the subscripts of the fuzzy sets of the current states of the fuzzy logical relationships to get the cluster center of each cluster and to divide the constructed fuzzy logical relationships into fuzzy logical relationship groups. The experimental results show that the proposed fuzzy forecasting method gets higher forecasting accuracy rates than the existing methods. The advantages of the proposed fuzzy forecasting method is that it uses the particle swarm optimization techniques to get the optimal partition of the intervals in the universe of discourse and uses the k-means clustering algorithm to cluster the subscripts of the fuzzy sets of the current states of the fuzzy logical relationships to get the cluster center of each cluster and to divide the constructed fuzzy logical relationships into fuzzy logical relationship groups for increasing the forecasting accuracy rates. (C) 2015 Elsevier Inc. All rights reserved.

关键词： Fuzzy logical relationships Fuzzy time series k-means clustering algorithm Particle swarm optimization Similarity measures

来源：评论

学校读者我要写书评

暂无评论

Battery Swapping Dispatch for Self-Sustained Highway Energy System Based on Spatiotemporal Deep-Learning Traffic Flow Prediction

引用

IEEE TRANSACTIONS ON INDUSTRY APPLICATIONS 2024年第1期60卷 1058-1070页

作者： Sun, Yuxin Li, Yiqun Borozan, Stefan Wang, Guibin Qiu, Jing Strbac, Goran Univ Liverpool Dept Elect & Elect Engn Liverpool L69 7ZX England Shenzhen Urban Transport Planning Ctr Shenzhen 518060 Peoples R China Imperial Coll London Dept Elect & Elect Engn London SW7 2AZ England Shenzhen Univ Coll Mechatron & Control Engn Shenzhen 518060 Peoples R China Univ Sydney Sch Elect & Informat Engn Sydney NSW 2006 Australia

Due to the complexity of traffic flow and the stochastic swapping behavior of electric vehicles (EVs), efficient battery dispatch is challenging. Therefore, the battery swapping dispatch framework based on traffic flow prediction is proposed to overcome this inconvenience. The framework is solved by minimizing the total transportation cost and satisfying the EV battery swapping requirement. Naturally, precise traffic flow prediction plays a vital role in efficient battery dispatch. Therefore, this article designs a deep learning prediction framework by leveraging the graph convolutional network (GCN) and the temporal convolutional network (TCN), named Spatiotemporal traffic flow network (STFNet). GCN is applied to learn the topology characteristic of the daily spatiotemporal traffic, which enables STFNet to capture the spatial feature. TCN is developed to acquire the daily traffic flow temporal dependence. Additionally, a pre-partition method based on k-means clustering is applied to improve the effectiveness of the battery dispatch framework. The experimental results indicate that the proposed battery dispatch framework is skillful. Due to the precise prediction of STFNet, the battery swapping dispatch based on STFNet prediction is the most economical, achieving a minimum of 25.82% reduction in the total transportation cost compared to benchmark models. Furthermore, the impact of the pre-partition method has been proven in the case of studies with a huge routing distance declining, dramatically reducing the total transportation cost and making the dispatch more reasonable.

关键词： Batteries Costs Road transportation Transportation Spatiotemporal phenomena Predictive models Biological system modeling Battery swapping daily traffic flow prediction deep learning k-means clustering algorithm vehicle routing problem

来源：评论

学校读者我要写书评

暂无评论

Image classification based on improved VLAD

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2016年第10期75卷 5533-5555页

作者： Long, Xianzhong Lu, Hongtao Peng, Yong Wang, Xianzhong Feng, Shaokun Nanjing Univ Posts & Telecommun Sch Software Sch Comp Sci & Technol Nanjing 210023 Jiangsu Peoples R China Shanghai Jiao Tong Univ Dept Comp Sci & Engn Key Lab Shanghai Educ Commiss Intelligent Interac Shanghai 200240 Peoples R China

Recently, a coding scheme called vector of locally aggregated descriptors (VLAD) has got tremendous successes in large scale image retrieval due to its efficiency of compact representation. VLAD employs only the nearest neighbor visual word in dictionary to aggregate each descriptor feature. It has fast retrieval speed and high retrieval accuracy under small dictionary size. In this paper, we give three improved VLAD variations for image classification: first, similar to the bag of words (BoW) model, we count the number of descriptors belonging to each cluster center and add it to VLAD;second, in order to expand the impact of residuals, squared residuals are taken into account;thirdly, in contrast with one nearest neighbor visual word, we try to look for two nearest neighbor visual words for aggregating each descriptor. Experimental results on UIUC Sports Event, Corel 10 and 15 Scenes datasets show that the proposed methods outperform some state-of-the-art coding schemes in terms of the classification accuracy and computation speed.

关键词： Image classification Scale-invariant feature transform Vector of locally ggregated descriptors k-means clustering algorithm

来源：评论

学校读者我要写书评

暂无评论

An initialization method for the k-means algorithm using neighborhood model

引用

COMPUTERS & MATHEMATICS WITH APPLICATIONS 2009年第3期58卷 474-483页

作者： Cao, Fuyuan Liang, Jiye Jiang, Guang Shanxi Univ Sch Comp & Informat Technol Taiyuan 030006 Shanxi Peoples R China Minist Educ Key Lab Computat Intelligence & Chinese Informat Taiyuan 030006 Peoples R China Chinese Acad Sci Key Lab Intelligent Informat Proc Inst Comp Technol Beijing 100190 Peoples R China

As a simple clustering method, the traditional k-means algorithm has been widely discussed and applied in pattern recognition and machine learning. However, the k-means algorithm could not guarantee unique clustering result because initial cluster centers are chosen randomly. In this paper, the cohesion degree of the neighborhood of an object and the coupling degree between neighborhoods of objects are defined based on the neighborhood-based rough set model. Furthermore, a new initialization method is proposed, and the corresponding time complexity is analyzed as well. We study the influence of the three norms on clustering, and compare the clustering results of the k-means with the three different initialization methods. The experimental results illustrate the effectiveness of the proposed method. (C) 2009 Elsevier Ltd. All rights reserved.

关键词： Neighborhood model Initial cluster centers Cohesion degree Coupling degree k-means clustering algorithm

来源：评论

学校读者我要写书评

暂无评论

Typical current modelling and feature extraction of high voltage circuit breaker towards condition analysis and fault diagnosis

引用

IET GENERATION TRANSMISSION & DISTRIBUTION 2020年第8期14卷 1521-1527页

作者： Ji, Tianyao Ye, Xiuzhen Shi, Mengjie Li, Mengshi Wu, Qinghua SCUT Sch Elect Power Engn Guangzhou 510641 Peoples R China

This study proposes a coil current model and an energy storage motor current (ESMC) model of circuit breakers (CBs) with spring operated mechanism. To make sure the signals generated by the models are identical to the actual ones, this study proposes a stochastic optimisation algorithm to optimise the model parameters. Based on the data produced by the optimised models, two fault diagnosis methods are proposed to assess operational condition and detect faults. The first method is based on fast template matching, which adopts k-means clustering algorithm to cluster the data and form a template library. The second one combines deep belief network and Softmax classifier, which can not only extract high level information of the characteristic signals, but also avoid the negative impact of the large dimension on classification results. In the simulation studies, the two methods are tested on various scenarios and their merits are demonstrated, respectively, where the latter one shows superior performance.

关键词： optimisation coils circuit breakers pattern clustering fault diagnosis feature extraction belief networks stochastic processes signal classification power engineering computing electric motors feature extraction high voltage circuit breaker condition analysis coil current model energy storage motor current model spring operated mechanism stochastic optimisation algorithm fault diagnosis methods fast template matching k-means clustering algorithm template library characteristic signals ESMC CBs deep belief network Softmax classifier

来源：评论

学校读者我要写书评

暂无评论

Research on weeds identification based on k-means feature learning

引用

SOFT COMPUTING 2018年第22期22卷 7649-7658页

作者： Tang, JingLei Zhang, ZhiGuang Wang, Dong Xin, Jing He, LiJun Northwest A&F Univ Coll Informat Engn Yangling 712100 Shaanxi Peoples R China Xian Univ Technol Shaanxi Key Lab Complex Syst Control & Intelligen Xian 710048 Shaanxi Peoples R China Hebei Normal Univ Sci & Technol Sch Math & Informat Sci & Technol Qinhuangdao 066004 Peoples R China

This paper aims to overcome the unstable identification results and weak generalization ability in feature extraction based on manual design to realize the automatic weeds identification. On the basis of unsupervised feature learning identification model, k-means clustering algorithm after data preprocessing is used to realize feature learning and construct feature dictionary. Then this feature dictionary is used to extract features from labeled data and train the classification model to realize the automatic weeds identification. In this process, this paper focuses on the effect of parameters such as the clustering number to identification accuracy under single-layer network structure, and the identification accuracy between the single-layer and the two-layer network structure was compared and analyzed. Experimental results show that identification rate can be improved by increasing the network levels, as well as fine-tuning the parameters under the premise of selecting reasonable parameters.

关键词： Feature learning k-means clustering algorithm Feature dictionary Weeds identification

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：