检索结果-内蒙古大学图书馆

33rd Irish Signals and Systems Conference (ISSC)

作者： Wang, Luhan Davis, Mark Technol Univ Dublin Sch Elect & Elect Engn Dublin Ireland

ISBN: (纸本)9781665452274

Wi-Fi as a Wireless Local Area Network (WLAN) technology is now widely deployed. The basic access mechanism of CSMA/CA of Wi-Fi is the Distributed Coordination Function (DCF). It is a distributed access mechanism that allows for different channel conditions within a network, especially in modern deployments where it is possible to have multiple networks operating at the same location. Being able to monitor local channel conditions in Wi-Fi application scenarios can help to analyse the cause of local channel condition anomalies and improve Wi-Fi network quality and end-user quality of experience. On account of the rate adaptation mechanism, Wi-Fi devices will adjust their link rate to respond to channel conditions Therefore, in this paper, we propose a new method for monitoring local channel conditions in Wi-Fi networks by leveraging the Physical layer (PHY) line rate adaptation mechanism as a proxy agent. We built a monitor device from a TP-link AC1750 router that is used to collect Wi-Fi link rate data in an apartment block in central Dublin for 24 hours and use this data to illustrate the operation of the proposed method. We found that in the active link rate lists collected from this area, most of the devices experienced a normal local channel condition, only a few of the devices experienced a good local channel condition and a small number of the devices experienced a poor channel condition.

关键词： Wi-Fi Network IEEE 802.11 Rate Adaptation Mechanism clustering algorithm

来源：评论

学校读者我要写书评

暂无评论

An efficient approach for clustering and classification for fraud detection using bankruptcy data in IoT environment

引用

International Journal of Information Technology (Singapore) 2021年第6期13卷 2497-2503页

作者： Srikanth, Panigrahi Department of CSE GMR Institute of Technology GMR Nagar Rajam 532127 Andhra Pradesh India

The fraud identification area is distinguished by a classify the data (also known as fraud/legitimate) which are not representative general of the population due to sampling bias. To deal with unsupervised fraud detection (FD) methods, which are uncommon in policies fraud detection studies, we use with these problems with the domain. Our approach consists of applying FD approaches to companies in the same sector and facilitates an effective auditing technique that can be implemented by policy authorities. Therefore, new technology must be researched and evaluated in order to leverage the insight gained from the study for the prediction of fraud and for the creation of systems to avoid fraud with additional checks for minimizing suspicious occurrences. Increased reliance on emerging technology such as Internet of Things (IoT) with FD has compounded the issue in recent years. In this context, the key challenges are to determine the proposed novel similarity measure to satisfy properties, to generate clusters with the proposed measure of similarity and to minimize dimensionality, and to recognize fraud to increase machine efficiency. Our administration involves the regulation issuers to effectively identify illegal activities to protect consumer rights and reduce fraud risks and compliance costs. Our proposed methods are highly efficient and successful have demonstrated real time polish companies data to improve high accuracy and system performance. © 2021, Bharati Vidyapeeth's Institute of Computer Applications and Management.

关键词： Bankruptcy data Classification algorithm clustering algorithm Dimensionality reduction Fraud detection with IoT Similarity measure

来源：评论

学校读者我要写书评

暂无评论

OPTIMIZATION APPROACH FOR WIND FARM CABLE LAYOUT BASED ON ITERATIVE SELF-ORGANIZING DATA ANALYSIS TECHNIQUE algorithm AND SWAP SEQUENCE BASED PARTICLE SWARM algorithmS

OPTIMIZATION APPROACH FOR WIND FARM CABLE LAYOUT BASED ON IT...

引用

67th ASME Turbomachinery Technical Conference and Exposition (Turbo Expo) on Road Mapping the Future of Propulsion and Power

作者： Yu Deqi Li Ming Shanghai Elect Grp Co Ltd PG EPC Shanghai Peoples R China Dalian Univ Technol Dalian Peoples R China

ISBN: (纸本)9780791886137

In the fast evolving and increasingly competitive wind energy market, to minimize initial capex and maximize production profits are essential when designing a wind farm. The electrical cable accounts for around 10% of the total capex, reasonable layout of cable connections might induce significant reduction of electrical and construction cost. In this paper, the Fuzzy C-means (FCM) clustering algorithm is adopted to determine the location of the substation(s) and the ISODATA (Iterative Self-Organizing Data Analysis Technique algorithm) is employed to divide the wind farm into finite sub-domains, effectively reducing the complexity of the NP-hard (Non-deterministic polynomial-time hard) problem of cable layout optimization. The optimal cable layout in each sub-domain is obtained through the swap sequence based particle swarm optimization (SSPSO) and practical electrical constraints, while the objective function is to minimize the total cable costs, including material cost and cable laying cost. Current study highlights both applicability of clustering algorithm and particle swarm optimization to the cable layout problem in wind farm.

关键词： wind farm clustering algorithm particle swarm optimization electrical cable layout optimization

来源：评论

学校读者我要写书评

暂无评论

Detection of Rotated Objects Using the Improved YOLOv5 algorithm 3

Detection of Rotated Objects Using the Improved YOLOv5 Algor...

引用

3rd International Conference on Electronics and Communication;Network and Computer Technology (ECNCT)

作者： Tang Wudi Xuan, Huang Hu, Wei Dong, Li Anhui Univ Inst Phys Sci & Informat Technol Hefei 230601 Anhui Peoples R China Chinese Acad Sci CAS Hefei Inst Technol Innovat Engn Hefei Inst Phys Sci Hefei 230031 Anhui Peoples R China

ISBN: (数字)9781510652118

ISBN: (纸本)9781510652118;9781510652101

Common object detection algorithms have too many backgrounds, duplicated boxes, and a high miss ratio in detecting rotated objects, which limit their applications on the industrial site. To address these problems, this paper proposed an improved YOLOv5 to detect rotated objects. First, this paper used the K-means clustering algorithm to develop clustering analysis for trained datasets to confirm more proper anchor boxes to reduce the training time. Then this paper transferred the angle issue to a classification problem. This paper also learned angles in the original loss function combined with the circular smooth label (CSL) algorithm, thus avoiding the periodicity of angle regression. Last, this paper selected one from different detection results of an object to increase the accuracy of the detection results. The experiment showed that the proposed algorithm had a higher detection precision than other methods in the public dataset DOTA. When the proposed algorithm detected rotated objects in the dataset collected on the industrial site, its mAP reached 94.35%. This value was 8.20% higher than that of YOLOv5, satisfying the detection requirement on the industrial site.

关键词： YOLO YOLOv5 clustering algorithm object detection

来源：评论

学校读者我要写书评

暂无评论

A cluster-based intelligence ensemble learning method for classification problems

引用

INFORMATION SCIENCES 2021年 560卷 386-409页

作者： Cui, Shaoze Wang, Yanzhang Yin, Yunqiang Cheng, T. C. E. Wang, Dujuan Zhai, Mingyu Dalian Univ Technol Sch Econ & Management Dalian 116023 Peoples R China Univ Elect Sci & Technol China Sch Econ & Management Chengdu 610064 Peoples R China Hong Kong Polytech Univ Dept Logist & Maritime Studies Hung Hom Kowloon Hong Kong Peoples R China Sichuan Univ Business Sch Chengdu 610064 Peoples R China

Classification is a vital task in machine learning. By learning patterns of samples of known categories, the model can develop the ability to distinguish the categories of samples of unknown categories. Noticing the advantages of the clustering method in cluster structure analysis, we combine the clustering and classification methods to develop the novel cluster-based intelligence ensemble learning (CIEL) method. We use the clustering method to analyze the inherent distribution of the data and divide all the samples into clusters according to the characteristics of the dataset. Then, for each specific cluster, we use differ-ent classification algorithms to establish the corresponding classification model. Finally, we integrate the prediction results of each base classifier to form the final prediction result. In view of the problem of parameter sensitivity, we use a swarm intelligence algorithm to optimize the key parameters involved in the clustering, classification, and ensemble stages in order to boost the classification performance. To assess the effectiveness of CIEL, we per -form tenfold cross-validation experiments on the 24 benchmark datasets provided by UCI and KEEL. Designed to improve the performance of the classifiers, CIEL outperforms other popular machine learning methods such as naive Bayes, k-nearest neighbors, random for -est, and support vector machine. (c) 2021 Elsevier Inc. All rights reserved.

关键词： Ensemble learning Classification algorithm Combination strategy clustering algorithm Swarm intelligence algorithm

来源：评论

学校读者我要写书评

暂无评论

A Machine Learning Approach to Estimating Queuing Delay on a Router over a Single-Hop Path

A Machine Learning Approach to Estimating Queuing Delay on a...

引用

IEEE International Conference on Communications (ICC)

作者： Ricker, Travis Salehin, Khondaker Wang, Yi Chen, Alex Oki, Eiji Rojas-Cessa, Roberto Calif State Univ Dominguez Hills Carson CA 90747 USA Kyoto Univ Kyoto Japan NJIT Newark NJ USA

ISBN: (数字)9781538683477

ISBN: (纸本)9781538683477

Queuing delay is a dynamic network parameter that plays an important role in defining the performance of Internet applications over an end-to-end path. However, measurement of queuing delay is challenging because it requires a large infrastructural support from the path under test. In this paper, we propose an active scheme to measure queuing delay on a router using a probe-gap model. The scheme uses a popular data-clustering algorithm to process its data samples;therefore, its measurement efficacy is not dependent on the issues related to infrastructural access, certain variations (e.g., compression) in the probe gaps, and the number of clusters in the data processing. Here, we present a detailed evaluation of the scheme against the current state-of-the-art on a single-hop path through ns-3 simulation. Our results show that the proposed scheme is robust, consistent, quick, and highly accurate under different traffic conditions.

关键词： Network measurement queuing delay clustering algorithm wired networks ns-3 simulator

来源：评论

学校读者我要写书评

暂无评论

Research on Phase identification in Distribution Area Based on Smart meter 9

Research on Phase identification in Distribution Area Based ...

引用

9th International Forum on Electrical Engineering and Automation (IFEEA)

作者： Liu, Bin Tan, Zhukui Zhang, Qiuyan Xu, Yutao Dai, Jiyulei Guizhou Power Grid Co Ltd Elect Power Res Inst Guiyang Guizhou Peoples R China

ISBN: (纸本)9781665464215

Low-voltage distribution network is the last link connecting consumer in power system, and it takes a large impact on user experience, so it needs to be paid due attention. In view of the acceleration of the transformation and construction of the distribution network line, the topological file management in the low-voltage platform area is confused and the phase information is not accurate. However, Advanced Metering Infrastructure (AMI) can provide a new way to identify user phases. This paper provides a user phase recognition method based on the sampling data of smart electricity meter. Firstly, the data related to users' electricity meters in the distribution area are collected by the low voltage distribution acquisition system, and then some missing data are supplemented based on Lagrange interpolation method. Finally, the actual phase of users in the distribution area is topological verified based on nonlinear descending and clustering method. The European low-voltage feeder is used as an example to verify that the proposed method has obvious and accurate recognition effect on user phase in low-voltage distribution area

关键词： Low voltage topology Smart electric meter clustering algorithm Phase identification

来源：评论

学校读者我要写书评

暂无评论

REBench: Microbenchmarking Framework for Relation Extraction Systems 21st

REBench: Microbenchmarking Framework for Relation Extraction...

引用

21st International Semantic Web Conference (ISWC)

作者： Ali, Manzoor Saleem, Muhammad Ngomo, Axel-Cyrille Ngonga Univ Paderborn Dept Comp Sci DICE Grp Paderborn Germany Univ Leipzig AKSW Res Grp Leipzig Germany

ISBN: (纸本)9783031194320;9783031194337

In recent years, several relation extractions (RE) models have been developed to extract knowledge from natural language texts. Accordingly, several benchmark datasets have been proposed to evaluate these models. These RE datasets consisted of natural language sentences with a fixed number of relations from a particular domain. Albeit useful for general-purpose RE benchmarking, they do not allow the generation of customized microbenchmarks according to user-specified criteria for a specific use case. Microbenchmarks are key to testing the individual functionalities of a system and hence pinpoint component-based insights. This article proposes REBench, a framework for microbenchmarking RE systems, which can select customized relation samples from existing RE datasets from diverse domains. The framework is flexible enough to choose relation samples of different sizes and according to the user-defined criteria on essential features to be considered for RE benchmarking. We used various clustering algorithms to generate microbenchmarks. We evaluated the state-of-the-art RE systems using different RE benchmarking samples. The evaluation results show that specialized microbenchmarking is crucial for identifying the limitations of various RE models and their components.

关键词： Microbenchmark Relation extraction clustering algorithm

来源：评论

学校读者我要写书评

暂无评论

Residential Load Pattern clustering Based on Smart Meter Data Using Weighted Self-Organizing Map 33

Residential Load Pattern Clustering Based on Smart Meter Dat...

引用

33rd Chinese Control and Decision Conference (CCDC)

作者： Peng, Qing Chi, Ming Zhu, Mingxi Yu, Yunfan Wan, Diandian Liu, Zhi-Wei Huazhong Univ Sci & Technol Sch Articial Intelligence & Automat Wuhan 430074 Peoples R China State Grid Int Dev Co Ltd 15 West Changan St Beijing 100031 Peoples R China

ISBN: (纸本)9781665440899

With arrival of big data of smart meters, a large number of residential power consumption data are collected according to different sampling frequency, namely Residential Load Profiles (RLPs). In this paper, RLPs of smart meter customers are analyzed by clustering, which is of great significance to load management of smart grid. A two-stage Weighted Self-Organizing Map (WSOM) clustering algorithm and a clustering performance evaluation method, SSE-DBI, combining Sum of Squares Error (SSE) and Davies-Bouldin (DBI) are proposed. In first stage, Principal Component Analysis (PCA) is used to reduce the dimension of the RLPs. When dimension reduced data is fed into SOM network for clustering, update of weights of SOM is weighted according to PCA, and these clustering centers, namely Typical Residential Load Profiles (TRLPs) of each customer are obtained after some iterations of training. In second stage, above processing is repeated for TRLPs of each customer, TRLPs of all customer are obtained. According to SSE-DBI, final optimal cluster number and clustering performance score of the model are determined. Compared with several benchmark methods, the proposed method obtains optimal performance.

关键词： smart meters RLPs WSOM clustering algorithm SSE-DBI PCA TRLPs

来源：评论

学校读者我要写书评

暂无评论

A fuzzy clustering technique for enhancing the convergence performance by using improved Fuzzy c-means and Particle Swarm Optimization algorithms

引用

DATA & KNOWLEDGE ENGINEERING 2022年 140卷

作者： Kumar, Niteesh Kumar, Harendra Gurukula Kangri Dept Math & Stat Haridwar Uttarakhand India

Fuzzy clustering is a well-established technique among the well-known clustering techniques in several real-world applications due to easy implementation and produces satisfactory clustering result. However, it has some deficiency such as sensitive to outliers, result dependency on choosing initial centroid, etc. To eradicate the shortcoming of FCM algorithm, this article introduces a robust clustering technique, particle swarm optimization improved fuzzy c-means is developed by the hybridization of particle swarm optimization and improved fuzzy c-means techniques, to deal with noisy data and initialization problem. In this article, a fuzzy clustering technique is developed to increase the convergence performance of clustering techniques. Fuzzy c-means is improved by developing a new metric to tolerate the noisy environment. Particle swarm optimization has an inbuilt guidance strategy which leads the solution in particle swarm optimization to obtain useful information from the better solution and thereby helping them improve their own solution. To handle the initialization problem of fuzzy c-means, particle swarm optimization technique is used. PSO effectively enhance the performance of improved FCM to increase the effectiveness of clustering. The effectiveness of the proposed clustering technique over existing techniques in literature has been illustrated by adopting eight real worlds and three artificial data sets. The results show that the proposed algorithm generates encouraging results as compared to the established clustering technique in literature.

关键词： clustering algorithm Clusters Fuzzy c-means Objective function values Particle swarm optimization

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：