检索结果-内蒙古大学图书馆

34th Chinese Control and Decision Conference (CCDC)

作者： Cai Guoliang Wang Guicheng Guan Changliang Yin Fengfeng Zhu Jiale Zijin ZhiKong Ziamen Technol Co Ltd Xiamen 361026 Peoples R China State Key Lab Proc Automat Min Met Beijing 102600 Peoples R China Beijing Key Lab Proc Automat Min & Met Beijing 102600 Peoples R China Shanghai Inst Technol Shanghai 201418 Peoples R China

ISBN: (纸本)9781665478960

Through data analysis method to obtain the internal connection of the data set, and extract different characteristics from it, and provide a strategy for the self-learning and acquisition of the expert system rule base. The article analyzes the composition and operating principle of the expert system, and selects the clustering algorithm to design the process of self-learning rules, and then obtains the rule base of the expert system, trying to solve the problem of difficulty in obtaining the empirical reasoning rule base. A circuit fault diagnosis example is selected to verify the feasibility of the method. After simulation tests, it is proved that the algorithm can realize self-learning rules, and an expert system rule base is initially formed, and fault information can be reasoned and diagnosed to simulate or replace empirical rules to a certain extent.

关键词： Self-learning K-means clustering algorithm Expert System Rule Base

来源：评论

学校读者我要写书评

暂无评论

Weighted Fuzzy clustering algorithm Based on Max-Min Distance Criterion and Jeffrey Divergence 10

Weighted Fuzzy Clustering Algorithm Based on Max-Min Distanc...

引用

10th International Conference on Advanced Cloud and Big Data (CBD)

作者： Wang, Hailan Xie, Xiaolan Chen, Jili Liu, Yarong Guilin Univ Technol Guangxi Key Lab Embedded Technol & Intelligent Sy Guilin Peoples R China Guilin Univ Technol Coll Informat Sci & Engn Guilin Peoples R China

ISBN: (纸本)9798350309713

Randomly selecting the initial clustering centers and setting the number of clusters has some influence on the results of the Fuzzy C-means (FCM) clustering algorithm. To address this problem, a weighted Fuzzy C-means clustering algorithm based on max-min distance, called the MJ-WFCM algorithm, is proposed. First, the algorithm assigns corresponding weights to the eigenvalues of the data, selects the clustering centers heuristically by the max-min distance criterion to avoid the clustering results from falling into the local optimum, and finally uses the ratio of intra-cluster distance and inter-cluster distance to determine the number of clusters without setting the number of clusters based on experience. Considering that the similarity measure of Euclidean distance only considers the local consistency between data points, a similarity measure based on Jeffery divergence is proposed to improve the clustering accuracy of non-convex complex datasets. Experimental results on artificial datasets and UCI datasets show that the MJ-WFCM algorithm not only exhibits better clustering performance on non-convex datasets, but also improves the efficiency of high-dimensional data clustering.

关键词： weighted Fuzzy C-means Jeffrey Divergence max-min distance clustering algorithm

来源：评论

学校读者我要写书评

暂无评论

Multi-agent reinforcement learning clustering algorithm based on silhouette coefficient

引用

NEUROCOMPUTING 2024年 596卷

作者： Du, Peng Li, Fenglian Shao, Jianli Taiyuan Univ Technol Coll Elect Informat & Opt Engn Taiyuan 030024 Peoples R China Beijing Inst Technol State Key Lab Explos Sci & Safety Protect Beijing 100081 Peoples R China

As an important branch of emerging artificial intelligence algorithms, multi-agent reinforcement learning (MARL) has shown strong performance in collaborative environments. It can utilize multiple agents to find the optimal set of strategies for solving sequential decision problem through trial-and-error. One of the main challenges facing multi-agent system is the non-stationarity problem, which brings poor convergence and seriously affects its performance. clustering is a commonly used unsupervised analytical method in machine learning, which aims to group samples with similar internal properties into the same cluster. In this paper, we propose a MARL clustering algorithm based on silhouette coefficient (SC-MARLC), and use the trial-and-error strategy to find the best cluster groups. In SC-MARLC, we establish a mapping relationship between multi-agent and samples, construct a novel clustering model based on MARL, and design a good clustering subset structure based on the sample silhouette coefficient. The designed structure is helpful for multi-agent system to solve the nonstationary problem. Finally, we compare the performance of SC-MARLC with 11 existing clustering algorithms on fifteen public datasets. The results show that the new clustering algorithm performs best on ten datasets.

关键词： clustering algorithm Multi -agent reinforcement learning Non-stationarity problem Silhouette coefficient Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

A clustering algorithm Based on Node Cost and Service Priority for Urban Rail In-Vehicle Ad-Hoc Network 96

A Clustering Algorithm Based on Node Cost and Service Priori...

引用

IEEE 96th Vehicular Technology Conference (VTC-Fall)

作者： Su, Zhaoyang Liu, Liu Cai, Shiyuan Suo, Lei Bao, Feng Beijing Jiaotong Univ Sch Elect & Informat Engn Beijing 100044 Peoples R China Traff Control Technol Co Ltd Beijing 100160 Peoples R China

ISBN: (纸本)9781665454681

Urban rail transit has become an important way for people to travel. The traditional urban rail transit system has fixed infrastructure, relies on base stations for communication, and has poor network robustness. The ad-hoc network has developed rapidly in recent years due to its high stability. And it can be used in urban rail to improve the performance of communication networks. In this paper, a clustering algorithm based on urban rail in-vehicle ad-hoc networks is proposed. The algorithm includes cluster head selected strategy and low-delay queuing strategy. We introduce the network architecture and algorithm theory in detail, and verify the algorithm performance in terms of end-to-end delay and packet loss rate through simulation. As the result, the algorithm can effectively improve communication efficiency and reliability.

关键词： urban rail ad-hoc network clustering algorithm delay packet lose rate

来源：评论

学校读者我要写书评

暂无评论

Radial Basis Function Neural Network Model for Dissolved Oxygen Concentration Prediction Based on an Enhanced clustering algorithm and Adam

引用

IEEE ACCESS 2021年 9卷 44521-44533页

作者： Li, Dashe Wang, Xueying Sun, Jiajun Feng, Yanli Shandong Technol & Business Univ Sch Comp Sci & Technol Yantai 264005 Peoples R China Coinnovat Ctr Shandong Coll & Univ Future Intelli Yantai 264005 Peoples R China

In fishery aquaculture, water quality directly determines the economic benefits of aquatic products, and dissolved oxygen is an important factor affecting water quality. To accurately grasp the trends of variation in dissolved oxygen, a dissolved oxygen concentration forecasting model based on an enhanced clustering algorithm and Adam with a radial basis function neural network (ECA-Adam-RBFNN) is proposed. An enhanced clustering algorithm (ECA) combining K-means with ant colony optimization is introduced in place of random selection to determine the center positions of the neural network hidden layer units. If the number of center points is too high, the neural network will be overfit, whereas if it is too low, sudden changes will appear in the results. Once the hidden layer centers have been determined, the radial basis function (RBF) width is calculated from the maximum center distance and the number of center points to avoid the two extreme cases of RBF that are too peaked or flat. The recursive least squares (RLS) algorithm is introduced to obtain the connection weights from the hidden layer to the output layer. The Adam algorithm is introduced to iteratively differentiate the objective function to adjust the center values, weights and width while adaptively varying the learning rates for these three types of parameters. Finally, the improved forecasting algorithm is applied for the prediction of the dissolved oxygen concentration in fishery aquaculture. The experimental results show that under identical conditions, compared with a long short-term memory (LSTM) network, a backpropagation neural network (BPNN), a traditional RBF neural network, a support vector regression (SVR) model, an autoregressive integrated moving average (ARIMA), K-MLPNN (K-means muhilayer perceptron neural networks), and SC-K-means-RBF model, the improved algorithm achieves significant reductions in the mean absolute error (MAE), mean absolute percentage error (MAPE) and root mean square

关键词： Prediction algorithms clustering algorithms Predictive models Forecasting Water quality Training Data models Radial basis function networks ant colony optimization clustering algorithm

来源：评论

学校读者我要写书评

暂无评论

New distances for dual hesitant fuzzy sets and their application in clustering algorithm

引用

JOURNAL OF INTELLIGENT & FUZZY SYSTEMS 2021年第6期41卷 6221-6232页

作者： Wei, Yanxia Wang, Qinghai Qinghai Normal Univ Sch Comp Xining 810016 Qinghai Peoples R China

Compared to hesitant fuzzy sets and intuitionistic fuzzy sets, dual hesitant fuzzy sets can model problems in the real world more comprehensively. Dual hesitant fuzzy sets explicitly show a set of membership degrees and a set of non-membership degrees, which also imply a set of important data: hesitant degrees. The traditional definition of distance between dual hesitant fuzzy sets only considers membership degree and non-membership degree, but hesitant degree should also be taken into account. To this end, using these three important data sets (membership degree, non-membership degree and hesitant degree), we first propose a variety of new distance measurements (the generalized normalized distance, generalized normalized Hausdorff distance and generalized normalized hybrid distance) for dual hesitant fuzzy sets in this paper, based on which the corresponding similarity measurements can be obtained. In these distance definitions, membership degree, non-membership-degree and hesitant degree are of equal importance. Second, we propose a clustering algorithm by using these distances in dual hesitant fuzzy information system. Finally, a numerical example is used to illustrate the performance and effectiveness of the clustering algorithm. Accordingly, the results of clustering in dual hesitant fuzzy information system are compared using the distance measurements mentioned in the paper, which verifies the utility and advantage of our proposed distances. Our work provides a new way to improve the performance of clustering algorithms in dual hesitant fuzzy information systems.

关键词： Dual hesitant fuzzy set distance measures similarity measures clustering algorithm

来源：评论

学校读者我要写书评

暂无评论

Dairy brand loyalty measurement model based on machine learning clustering algorithm

引用

JOURNAL OF INTELLIGENT & FUZZY SYSTEMS 2021年第4期40卷 7601-7612页

作者： Liu, Xiujuan Zhao, Huifeng Hebei Agr Univ Baoding Peoples R China

At present, the dairy brand loyalty evaluation model is not perfect, and the dairy brand loyalty measurement model for the consumer-oriented industry needs to be further studied. Through machine learning methods, online consumer brand product purchase behaviors are clustered to achieve clustering of users with similar loyalty and to measure online dairy brand loyalty. This study has the advantages of applying machine learning to processing online consumer big data, that is, it has advantages when processing high-dimensional data, when processing data in multiple ways, and when analyzing data with high complexity algorithms. The independent variables, dependent variables, and adjusted variables in the model are measured in the form of a Likert five-level scale. Moreover, this study combines with actual cases to make adjustments to the measurement of dairy brand loyalty and verifies the model performance through simulation experiments. The research results show that the validity of the scale structure is good, and the research model has certain practical effects.

关键词： Machine learning clustering algorithm dairy brand loyalty simulation model

来源：评论

学校读者我要写书评

暂无评论

Consensus model based on probability K-means clustering algorithm for large scale group decision making

引用

INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS 2021年第6期12卷 1609-1626页

作者： Liu, Qian Wu, Hangyao Xu, Zeshui Sichuan Univ Business Sch Chengdu 610064 Sichuan Peoples R China

Nowadays, the increasing complexity of the social environment brings much difficulty in group decision making. The more uncertainty exists in a decision-making problem, the more collective wisdom is needed. Therefore, large scale group decision making has attracted a lot of researchers to investigate. Since the probabilistic linguistic terms have impressive performance in expressing DMs' opinions, this paper proposes a novel method for large scale group decision making with probabilistic linguistic preference relations. More specifically, (1) a probability k-means clustering algorithm is introduced to segment DMs with similar features into different sub-groups;(2) an integration method is proposed to construct the collective probabilistic preference relation that retains initial information to the most extent;(3) taking the personality of each DM into account, a consensus model is constructed to improve the rationality and efficiency of consensus reaching process. Several simulation experiments are designed to analyze the influence factor in the feedback mechanism and make some comparative analysis with the existing method. Finally, an illustrative example of contractor selection is conducted to verify the validity of the proposed method.

关键词： Large scale group decision making clustering algorithm Consensus reaching process Feedback mechanism Probabilistic linguistic preference relation

来源：评论

学校读者我要写书评

暂无评论

Distributed Dynamic clustering algorithm for Formation of Heterogeneous Virtual Power Plants Based on Power Requirements

引用

IEEE TRANSACTIONS ON SMART GRID 2021年第1期12卷 192-204页

作者： Zhang, Runfan Hredzak, Branislav Univ New South Wales Sch Elect Engn & Telecommun Sydney NSW 2052 Australia

Real-time distributed clustering algorithm for aggregation of distributed energy storage systems into heterogeneous virtual power plants is proposed. Two types of virtual power plants are formed: one for provisioning the bulk (low-frequency) power demand and one for provisioning the high-frequency power demand. The proposed distributed clustering algorithm determines the virtual power plants' memberships, for each distributed energy storage system, based on each energy storage system's capacity and owner's willingness to participate in one of the virtual power plants. The proposed distributed secondary level control system regulates each energy storage system according to each virtual power plant's operational objectives. Specifically, a balanced state of charge of all energy storage systems inside each virtual power plant is maintained. One of the virtual power plants is responsible for the frequency and voltage regulation by providing the required high-frequency power, while the other one provides the required bulk (low-frequency) power demand. In addition, the proposed clustering algorithm enables to meet a required energy capacity of the bulk virtual power plant by automatically tuning the clustering algorithm parameters. RTDS real-time technique verifies the proposed clustering algorithm and control systems on the IEEE 13 nodes power system with distributed energy storage systems and photovoltaic sources. The presented results demonstrate dynamic aggregation of energy storage systems into heterogeneous virtual power plants based on power demand while all regulation requirements are met.

关键词： clustering algorithms Power generation Energy storage Power demand Heuristic algorithms Communication networks Control systems Heterogeneous virtual power plants energy storage photovoltaic real-time distributed communication network clustering algorithm frequency regulation voltage restoration bulk power supply state of charge balancing

来源：评论

学校读者我要写书评

暂无评论

An intelligent algorithm based on evolutionary strategy and clustering algorithm for Lamb wave defect location

引用

STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL 2021年第4期20卷 2088-2109页

作者： Chen, Honglei Liu, Zenghua Wu, Bin He, Cunfu Beijing Univ Technol Fac Mat & Mfg Pingleyuan 100 Beijing 100124 Peoples R China Beijing Univ Technol Beijing Engn Res Ctr Precis Measurement Technol & Beijing Peoples R China

Imaging algorithms for visualization of defects play a significant role in Lamb wave-based research of nondestructive testing and structural health monitoring. In classical algorithms, the position or distribution of defects is located by mapping the amplitude or phase information of signals from the time domain to every discrete spatial grid of the structure. It is time-consuming. In this study, the diversity, statistical, and fuzzy characteristics of the elliptic imaging algorithm are analyzed first;then, an intelligent defect location algorithm is proposed based on the evolutionary strategy and the K-means algorithm. The position of defects can be identified by observing the distribution of individuals. There are six parts in the proposed algorithm, including the data structure design, adaptive population screening, adaptive population reproduction, diversity maintenance mechanism, and cutoff criterion. Considering the statistical and fuzzy characteristics in the detection, several specific input parameters are defined in our algorithm, such as the distance-dependent screening threshold, path-dependent residual vector, and path-independent residual. To maintain the diversity of individuals in the analysis, we have made two adjustments to the evolutionary strategy: one is to optimize the population screening and reproduction steps with the K-means algorithm, and the other is to add a diversity maintenance method into the evolutionary strategy. The effectiveness of the proposed intelligent defect location algorithm is verified by numerical simulations and experiments. Numerical studies indicate that the proposed algorithm has a reliable performance in the detection of defects with different shapes and sizes. In the experimental research, we demonstrate that the efficiency of the proposed algorithm is about 200 times faster than the elliptic imaging algorithm. And the optimum parameter setting of the algorithm is investigated by analyzing the influence of parameter

关键词： Lamb waves evolutionary strategy clustering algorithm defect location intelligent detection

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：