检索结果-内蒙古大学图书馆

Partial discharge direction-of-arrival estimation in air-insulated substation by UHF wireless array and RSSI maximum likelihood estimator

引用

IET GENERATION TRANSMISSION & DISTRIBUTION 2020年第23期14卷 5491-5497页

作者： Han, Bei Luo, Lingen Sheng, Gehao Jiang, Xiuchen Shanghai Jiao Tong Univ Dept Elect Engn 800 Dongchuan Rd Shanghai Peoples R China

The quick detection and localisation of partial discharge (PD) in an air-insulated substation (AIS) based on ultrahigh-frequency (UHF) sensor arrays are efficient for power equipment monitoring. The adopted UHF PD time difference-of-arrival (DOA) methods mainly use the time difference of electromagnetic wave signals. Thus, the system requires both a high-sampling rate and time synchronisation accuracy, leading to a high cost and large size. In this study, the feasibility and accuracy of PD DOA in an AIS were investigated using an UHF wireless sensor array and the received signal strength indicator. First, the power pattern of the designed UHF wireless sensor array was obtained via an offline experiment. Then, a statistical approach to the PD DOA method based on the maximum likelihood estimator was employed to obtain the preliminary DOA result. Finally, interpolation and clustering algorithms were used to improve the accuracy of the DOA. A laboratory test was conducted. The average error of the PD DOA was <6 degrees, and the cost-effectiveness and portability were clearly improved.

关键词： wireless sensor networks direction-of-arrival estimation maximum likelihood estimation sensor arrays synchronisation gas insulated substations partial discharge measurement interpolation air-insulated substation UHF wireless array RSSI maximum likelihood estimator partial discharge detection AIS ultrahigh-frequency sensor arrays power equipment monitoring electromagnetic wave signals high-sampling rate time synchronisation accuracy received signal strength indicator power pattern UHF wireless sensor array PD DOA method preliminary DOA result partial discharge direction-of-arrival estimation partial discharge localisation PD time difference-of-arrival methods interpolation algorithm clustering algorithm

来源：评论

学校读者我要写书评

暂无评论

Improved Artificial Bee Colony algorithm and Its Application to Fundus Retinal Blood Vessel Image Binarization

引用

IEEE ACCESS 2020年 8卷 123726-123734页

作者： Pan, Xiuqin Zhang, Qinrui Pan, Haichuan Minzu Univ China Sch Informat Engn Beijing 100081 Peoples R China

The content of this work is based on the characteristics of standard artificial bee colony(ABC) algorithm with weak local search ability and slow convergence speed. Then, an improved algorithm named KD-ABC is proposed. For improving the diversity and quality of the solution, it changes the generation method of honey source. In the initialization phase, it uses the cluster center generated by the K-MEANS method as the initial honey source instead of the initialization in the standard method. For improving the local optimization ability and the convergence speed without reducing the global search, we proposed a dynamic neighborhood search mechanism based on the number of iterations in terms of ABC search strategy and neighborhood selection stage. In order to find a suitable threshold to divide the grayscale image into blood vessels and background parts, we applied the characteristics of the KD-ABC algorithm to the binary processing stage of the fundus retinal blood vessel image, which lays the foundation for future image recognition.

关键词： Artificial bee colony algorithm clustering algorithms Particle swarm optimization Blood vessels Biomedical imaging Heuristic algorithms Retina Initialization clustering algorithm dynamic neighborhood search binarization

来源：评论

学校读者我要写书评

暂无评论

Examining plant uptake and translocation of emerging contaminants using machine learning: Implications to food security

引用

SCIENCE OF THE TOTAL ENVIRONMENT 2020年 698卷 133999-000页

作者： Bagheri, Majid Al-jabery, Khalid Wunsch, Donald Burken, Joel G. Missouri Univ Sci & Technol Civil Architectural & Environm Engn Dept 1401 N Pine St Rolla MO 65409 USA Missouri Univ Sci & Technol Appl Computat Intelligence Lab Elect & Comp Engn Dept Rolla MO 65409 USA

When water and solutes enter the plant root through the epidermis, organic contaminants in solution either cross the root membranes and transport through the vascular pathways to the aerial tissues or accumulate in the plant roots. The accumulation of contaminants in plant roots and edible tissues is measured by root concentration factor (RCF) and fruit concentration factor (FCF). In this paper, 1) a neural network (NN) was applied to model RCF based on physicochemical properties of organic compounds, 2) correlation and significance of physicochemical properties were assessed using statistical analysis, 3) fuzzy logic was used to examine the simultaneous impacts of significant compound properties on RCF and FCF, 4) a clustering algorithm (k-means) was used to identify unique groups and discover hidden relationships within contaminants in various parts of the plants. The physicochemical cutoffs achieved by fuzzy logic for the RCF and the FCF were compared versus the cutoffs for compounds that crossed the plant root membranes and found their way into transpiration stream (measured by transpiration stream concentration factor, TSCF). The NN predicted the RCF with improved accuracy compared to mechanistic models. The analysis indicated that log K-ow, molecular weight, and rotatable bonds are the most important properties for predicting the RCF. These significant compound properties are positively correlated with RCF while they are negatively correlated with TSCF. Comparing the relationships between compound properties in various plant tissues showed that compounds detected in the edible parts have physicochemical cutoffs that are more like the compounds crossing the plant root membranes (into xylem tissues) than the compounds accumulating in the plant roots, with clear relationships to food security. The cluster analysis placed the contaminants into three meaningful groups that were in agreement with the results of fuzzy logic. (C) 2019 Elsevier B.V. All rights reserved

关键词： Plant uptake Food security Neural network Fuzzy logic clustering algorithm

来源：评论

学校读者我要写书评

暂无评论

Driving Conditions of New Energy Logistics Vehicles Using Big Data Technology

引用

IEEE ACCESS 2020年 8卷 123891-123903页

作者： Mao, Jia Hong, Dou Ren, Runwang Li, Xiangyu Wang, Ju Nasr, Emad S. Abouel Jilin Univ Sch Transportat Changchun 130025 Peoples R China Jilin Univ Coll Automot Engn Changchun 130025 Peoples R China Jilin Univ Coll New Energy & Environm Changchun 130012 Peoples R China King Saud Univ Ind Engn Dept Coll Engn Riyadh 12372 Saudi Arabia Helwan Univ Mech Engn Dept Fac Engn Cairo Egypt

With the development of e-commerce and trade, China's logistics transportation demand has increased significantly. To improve the operation efficiency of new energy trucks, logistics transportation companies need scientific management methods. They need to analyze a large number of real driving conditions for new energy trucks. Additionally, to reduce new energy trucks' energy consumption and pollutant emissions, automobile manufacturers have increased the research and development of new energy trucks, and the analysis of new energy truck driving conditions is the basis for the technical development and evaluation of new models. The research in this article is based on an actual project of an automobile manufacturing company, consulting a large amount of relevant domestic and foreign literature, summarizing the current status of driving conditions at home and abroad, explaining the principle of data collection for the driving conditions of new energy trucks, and developing in-vehicle data for driving conditions based on the principle transmission method and remote transmission method. Using the membership function and K-means clustering algorithm to determine the attribute characteristics of the new energy truck driving condition analysis, a truck driving condition analysis model is built, the software function of the model is designed, and a small amount of sample data is used to import the model instance to verify the model effectiveness. Finally, based on the constructed new energy truck driving condition analysis model, big data technology was used to perform a big data analysis experiment on the actual operation data of 200 trucks of an automobile manufacturing enterprise. The Spark big data calculation framework was used to perform stream calculation and offline analysis calculations on a large amount of data from the new energy trucks. The results show that the operating efficiency of the new energy truck driving condition analysis method using big data techn

关键词： New energy trucks driving conditions big data analysis clustering algorithm membership function

来源：评论

学校读者我要写书评

暂无评论

Change Point Estimation in a Dynamic Stochastic Block Model

引用

JOURNAL OF MACHINE LEARNING RESEARCH 2020年第1期21卷 1-59页

作者： Bhattacharjee, Monika Banerjee, Moulinath Michailidis, George Univ Florida Informat Inst Gainesville FL 32611 USA Univ Michigan Dept Stat Ann Arbor MI 48109 USA Univ Florida Dept Stat Informat Inst Gainesville FL 32611 USA

We consider the problem of estimating the location of a single change point in a network generated by a dynamic stochastic block model mechanism. This model produces community structure in the network that exhibits change at a single time epoch. We propose two methods of estimating the change point, together with the model parameters, before and after its occurrence. The first employs a least-squares criterion function and takes into consideration the full structure of the stochastic block model and is evaluated at each point in time. Hence, as an intermediate step, it requires estimating the community structure based on a clustering algorithm at every time point. The second method comprises the following two steps: in the first one, a least-squares function is used and evaluated at each time point, but ignoring the community structure and only considering a random graph generating mechanism exhibiting a change point. Once the change point is identified, in the second step, all network data before and after it are used together with a clustering algorithm to obtain the corresponding community structures and subsequently estimate the generating stochastic block model parameters. The first method, since it requires knowledge of the community structure and hence clustering at every point in time, is significantly more computationally expensive than the second one. On the other hand, it requires a significantly less stringent identifiability condition for consistent estimation of the change point and the model parameters than the second method;however, it also requires a condition on the misclassification rate of misallocating network nodes to their respective communities that may fail to hold in many realistic settings. Despite the apparent stringency of the identifiability condition for the second method, we show that networks generated by a stochastic block mechanism exhibiting a change in their structure can easily satisfy this condition under a multitude of scenari

关键词： stochastic block model Erdos-Renyi random graph change point edge probability matrix community detection estimation clustering algorithm convergence rate

来源：评论

学校读者我要写书评

暂无评论

A two-level authentication scheme for clone node detection in smart cities using Internet of things

引用

COMPUTATIONAL INTELLIGENCE 2020年第3期36卷 1200-1220页

作者： Shanmugam, Anitha Paramasivam, Jayanthi Kongu Engn Coll Dept Informat Technol Perundurai Tamil Nadu India Kongu Engn Coll Dept Comp Sci & Engn Perundurai India

Clone node attack in IoT sensor devices remains a grave security concern as it paves the way for sinkhole, wormhole, and selective forwarding attacks. In this paper, a two-level authentication scheme named Fingerprint-based Zero-Knowledge Authentication (FZKA) algorithm is proposed to improve the detection rate of clone node among the sensor devices. In the fingerprint generation phase, the base station calculates a distinct fingerprint value for each and every node in the network by gathering neighborhood information, represented in the form of superimposed s-disjunct code matrix. The calculated fingerprint is considered as a secret value and distributed to each cluster nodes for the process of authentication. The FZKA algorithm improves the cloned node detection accuracy with minimal detection time. The simulation results highlight the cloned node detection rate of the proposed scheme by a margin of 92.5% against the existing Exponential Smoothing algorithm (ETS), Position Verification Method, and Message Verification and Passing algorithms.

关键词： authentication clone node clustering algorithm Internet of things security

来源：评论

学校读者我要写书评

暂无评论

Development of an Equivalent Wind Farm Model for Frequency Regulation

引用

IEEE TRANSACTIONS ON INDUSTRY APPLICATIONS 2020年第3期56卷 2360-2374页

作者： Wu, Yuan-Kang Zeng, Jyun-Jie Lu, Guan-Liang Chau, Shiu-Wu Chiang, Yen-Cheng Natl Chung Cheng Univ Chiayi 62102 Taiwan Natl Taiwan Univ Taipei 10617 Taiwan

The operational security of power systems for wind farm (WF) integration becomes more important as the penetration of wind generation increases. A WF may contain hundreds of wind turbines (WT) and thus the power system simulations based on the complex model of a WT consume much time. This article proposes an equivalent WF model with the frequency-regulation function. The main research works include the establishment of the generic model of a WT, the development of single- and multimachine equivalent models for a large WF, the clustering of WTs based on the developed nonlinear wake model and the fuzzy C-means (FCM) clustering algorithm, the integration of the frequency-regulation function into the equivalent WF model, and the validation of the developed equivalent WF model by various operating scenarios. The results demonstrate that the proposed multimachine equivalent method based on the FCM clustering provides a more accurate model than a single-WT equivalent model. Consequently, the research results provide a solution for simulating a large-scale wind power integration, providing efficient, accurate, and fast steady-state and dynamic analyses.

关键词： Wind farms Wind turbines Wind speed Computational modeling Frequency control clustering algorithms Rotors clustering algorithm equivalent wind farm (WF) model frequency regulation wake model WF integration

来源：评论

学校读者我要写书评

暂无评论

Commuting versus consumption: The role of core city in a metropolitan area

引用

CITIES 2023年 141卷

作者： Zhou, Yang Yang, Chao Chen, Mingyang Liu, Yunhao Yuan, Quan Tongji Univ Coll Transportat Engn Shanghai Peoples R China Nanjing Univ Sci & Technol Sch Automat Nanjing Peoples R China Tongji Univ Urban Mobil Inst Shanghai Peoples R China 4800 Caoan Rd Shanghai Peoples R China

The concept of "consumer city" has reshaped the growth and prosperity of major cities in the world. Although the literature has extensively documented the role of central cities in generating jobs, there has been limited empirical evidence on how those cities have developed into agglomerations of consumption opportunities by offering metropolitan residents high-quality consumer goods and services. We use large-scale cellular signaling data to distinguish commuting and consumption connections between the Shanghai City and a suburban town Huaqiao. Through the clustering algorithm, we categorize residents of Huaqiao into groups according to their frequency of visiting Shanghai and length of the visits. Results show that while travel time does not differ across the three groups of trips, non-commuters' consumption trips are more spatially expansive and intensive than the others. The average per capita visit frequencies also indicate the outstanding role of consumption-oriented travel. Spatial lag models suggest that although non-commuters are more sensitive to travel time than commuters, they are still willing to make long consumption trips to access the consumer goods and services the central city can provide. The findings would encourage city managers and planners to reconsider the roles of major cities, and redefine them as space that best match the changing demand of people.

关键词： Commuting Consumption Cellular signaling data clustering algorithm Shanghai metropolitan area

来源：评论

学校读者我要写书评

暂无评论

Using Machine Learning to Efficiently Vaccinate Homebound Patients Against COVID-19: A Real-time Immunization Campaign

引用

JOURNAL OF MEDICAL INTERNET RESEARCH 2022年第7期24卷 e37744页

作者： Kumar, Anish Ren, Jennifer Ornstein, Katherine A. Gliatto, Peter M. Icahn Sch Med Mt Sinai New York NY USA Icahn Sch Med Mt Sinai Dept Geriatr & Palliat Med New York NY USA Icahn Sch Med Mt Sinai Inst Care Innovat Home New York NY USA Icahn Sch Med Mt Sinai Dept Med New York NY USA

Methods Ethics Approval The Icahn School of Medicine at Mount Sinai’s Program for the Protection of Human Subjects approved and granted a waiver of consent for this secondary data analysis study (STUDY- 21-00157) which was conducted in accordance with the Helsinki Declaration. Using the Google Maps Geocoding application programming interface (API), we obtained latitude/longitude coordinates of patient residences, which served as the input data to our algorithm. Value Patient demographics Patients who are homebound 428 Average age (years) 83.9 Average Elixhauser comorbidity score [6]a 3.8 Sex, n (%) Female 323 (75.5) Male 105 (24.5) Racial/ethnic identity, n (%) White 148 (34.6) Black or African American 63 (14.7) Asian 15 (3.5) Hispanic 108 (25.2) Other 86 (20.1) Unknown 8 (1.9) Patient’s family members and caregivers, n 92 Vaccination campaign statistics Providers vaccinating per day (n), range 3-6 Average number of patients vaccinated per day 22.1 Average duration of provider time spent vaccinating (hours) 4.6 Average duration of individual vaccination (including transit time, vaccine administration, and 15-minute postvaccination observation time; minutes) 52 aElixhauser scores were available for 372 of the patients who are homebound.

关键词： home care covid vaccination COVID-19 machine learning vaccine geographic cluster patient data clustering algorithm geospatial digital surveillance public health logistic operation electronic health record integration

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Deep Embedding clustering for High--Dimensional Visual Features of Fashion Images

Unsupervised Deep Embedding Clustering for High--Dimensional...

引用

作者： Malhi,Umar Subhan 东华大学

学位级别：硕士

Can a computer algorithm detect images of pants,shirts,sneakers,clothes,and dresses automatically?It turns out that it is amazingly simple to do correctly classifying pictures of fashion products,considering the quality training data,to begin *** in real-world fashion datasets areconsist of products of various kinds.(***,top,hat,footwear).We have to describe fashion product characteristics manually based on their pattern,color,look,material,*** such cases,data become noisy because of human error and it also a quite expensive *** problem leads to unsupervised learning,where we train our model without an object *** this thesis,we will use the real-world amazon dataset to build a machine-learning model to recognize cluster of fashion objects.　　The currently widely used feature extraction methods based on deep learning such as a convolutional neural network(CNN)can generate feature vector up to4096dimensions,which provides a guarantee for accurate image ***,high dimensions can lead to the curse of dimensionality,which makes subsequent clustering *** fashion images oriented deep clustering(FIDC)method is proposed in *** method uses CNNto generate a4096-dimensional feature vector for each fashion image through migration learning,and then performs dimensionality reduction through a deep-stacked auto-encoder model,and finally does clustering on these low-dimensional *** dimensional vectors are capable of representing image features and dimensionality reduction avoids the curse of dimensionality during clustering tasks.　　While for feature encoding,we employ a suitable encoding method to perform efficient clustering *** jointly perform dimension reduction with optimal parameter and clustering assignments.　　A special point in the method is the joint learning and optimization of the dimensionality reduction process and the clustering *** optimize the cluster centroid byusing back-propagation a

关键词： clustering algorithm dimensionality reduction fashionimages deep embedding stacked autoencoder

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：