检索结果-内蒙古大学图书馆

International Conference on Fuzzy Systems and Knowledge Discovery

作者： Yu Zhan Haiwei Pan Qilong Han Xiaoqin Xie Zhiqiang Zhang Xiao Zhai Coll. of Comput. Sci. & Technol. Harbin Eng. Univ. Harbin China

ISBN: (纸本)9781467376839

Recently, a variety of medical imaging technologies have been used widely in clinical diagnosis. As a large number of medical images are produced everyday, it becomes a hot issue of data mining on medical image in current that how to make full use of these medical images and cluster efficiently to help doctors to diagnose. In this paper, we propose a medical image clustering method. Firstly, medical image dataset is represented as a weighted, undirected and completed graph. Secondly, the graph is sparsified and pruned. This model can describe the similarity between medical images very well. Last, weighted and undirected graph clustering method based on graph entropy is proposed to cluster these medical images. The experimental results show that this method can cluster medical images efficiently and run well in time complexity and clustering results.

关键词： component medical image entropy-based sparsification clustering algorithm

来源：评论

学校读者我要写书评

暂无评论

Distributed Task Allocation algorithm for Heterogeneous UAV Cluster Based on Game Theory

引用

Guidance, Navigation and Control 2024年第4期4卷 58-85页

作者： Shuxin Xue Yajie Ma Bin Jiang Xuan Lyu College of Automation Engineering Nanjing University of Aeronautics and Astronautics Nanjing 210016 P.R.China

This paper proposes a distributed task allocation algorithm based on game theory to solve the complex task allocation optimization problem when UAV clusters carry heterogeneous resources and tasks have heterogeneous demands. Considering the heterogeneity of resources,two pre-processing methods are proposed: one is the grouping algorithm that combines greedy algorithm with simulated annealing algorithm, and the other is the improved K-medoids clustering algorithm based on heterogeneous resources. These pre-process methods, through grouping and clustering, can reduce the complexity of task allocation. The entropy weight method is utilized to prioritize tasks based on multiple metrics. Considering task demands,airborne resources and path cost, a coalition formation game model is established, which is proved to be a potential game. Then a distributed task allocation algorithm based on coalition formation game is designed to address the task allocation problem. Finally, the simulation involving 30 tasks with heterogeneous requirements assigned to 100 UAVs validates the effectiveness of the proposed algorithm, showing that it can achieve good task allocation results with great real-time performance.

关键词： Task allocation heterogeneous UAV cluster clustering algorithm coalition formation game potential game

来源：评论

学校读者我要写书评

暂无评论

Automatic Detection Method of Website Vulnerabilities Based on an Associated Data Drive

引用

JOURNAL OF WEB ENGINEERING 2025年第2期24卷 217-242页

作者： Li, Xiaoli Zhao, Ling Shen, Haobin Du, Hanlin Guo, Zhida Guangdong Power Grid Co Ltd Huizhou Power Supply Bur Huizhou 516000 Peoples R China

In order to reduce the probability of website users being attacked and maintain the safety of website operation, this study proposes an automatic vulnerability detection method of websites based on associated data. We use plug-ins to scan the website in all directions, establish a scanning database, and classify and store the scanned web data. By applying optimized an a priori association rule algorithm, key features are extracted from web scan data, which are then transformed into input samples for a K-means clustering algorithm. The aim is to efficiently extract feature attributes of website vulnerability data and ultimately construct a text vectorized representation of vulnerability data. Convolutional neural networks can automatically detect website vulnerabilities by using the constructed text vector as input. Experimental verification shows that this method demonstrates comprehensive data coverage, efficient processing speed, and high-precision recognition perforensures the accuracy and timeliness of vulnerability detection.

关键词： A priori algorithm website website vulnerability automated detection clustering algorithm convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

Optimal Load Shedding Under Extreme Weather Events

Optimal Load Shedding Under Extreme Weather Events

引用

IEEE-Power-and-Energy-Society General Meeting (PESGM)

作者： Bernabeu, Emanuel Chen, Y. Militello, N. Furtaw, N. Martin, A. Wharton, M. PJM Interconnect Phoenixville PA 19460 USA

ISBN: (纸本)9798350381849;9798350381832

On June 13-14, 2022 a derecho storm caused numerous forced outages in the Columbus Ohio area;including fifteen 138 kV lines and one 345 kV line. PJM, in coordination with American Electric Power (AEP), implemented corrective actions (generation re-dispatch, topology control, and demand response) in an attempt to restore the grid to an N-1 secure state. Ultimately, 500 MWs of firm load were shed to mitigate the risk of cascading outages. PJM's post-event analysis revealed that, due to the numerous potential cascading failures, operators had a difficult time developing a load shed plan. The purpose of this paper is to provide a methodology that minimizes the amount of load shed needed and jointly mitigates all potential cascading outages. The proposed methodology consists of two steps: (1) linear optimization using post-contingency power flow distribution factors, and (2) a machine-learning based clustering algorithm (DBSCAN). The methodology was evaluated using Real Time saved State Estimator (SE) Energy Management System (EMS) cases from the event. Results show that the proposed method enhances situational awareness, simplifies the risk-based decision making process, and potentially reduces the amount of load shed needed by 20%.

关键词： cascading outages clustering algorithm extreme weather load shedding machine learning optimization

来源：评论

学校读者我要写书评

暂无评论

Accelerating DNN-Based Detection by MADDNESS Approximation 99

Accelerating DNN-Based Detection by MADDNESS Approximation

引用

IEEE 99th Vehicular Technology Conference (VTC-Spring)

作者： Gong, Shuaicong Qian, Shuangyi Zhao, Chunming Jiang, Ming Zhang, Yifan Southeast Univ Natl Mobile Commun Res Lab Nanjing 210096 Peoples R China Purple Mt Labs Nanjing Peoples R China

ISBN: (纸本)9798350387414

Non-rectangular QAM can achieve better bit error rate performance in the face of different channel characteristics, and finding the constellation distribution that best matches the channel characteristics has always been a topic of discussion. The NVIDIA/Sionna open-source library provides a scheme of end-to-end transmission comprised of trainable constellation and deep neural network detection to achieve accurate information transfer. However, this application has a high computational complexity in the detection part, which contains dense layers that involve intensive and massive matrix multiplication operations. This study considers using an approximate matrix multiplication (AMM) algorithm based on table lookup, Multiply-ADDitioN-lESS (MADDNESS), to replace the accurate multiplication calculations in the DNN-Based detection and achieves a significant reduction in overall computational complexity at the cost of certain storage.

关键词： DNN detection Deep Learning clustering algorithm Approximate Multiplication Vector Quantization

来源：评论

学校读者我要写书评

暂无评论

Research on K-medoids algorithm with Probabilistic-based Expressions and Its Applications

引用

APPLIED INTELLIGENCE 2022年第10期52卷 12016-12033页

作者： He, Yue Xu, Zeshui Liu, Nana Sichuan Univ West China Second Univ Hosp Chengdu 610041 Sichuan Peoples R China Sichuan Univ Sch Business Chengdu 610064 Peoples R China

Nowadays, the decision environment is becoming more and more complicated due to the development of society and science, and people receiving different types of information every day and gradually form their unique cognitions and knowledge backgrounds. In this situation, people tend to provide their preferences or evaluations through multiple information expression formats, such as the probabilistic hesitant fuzzy sets, the probabilistic linguistic term sets and the probabilistic interval preference ordering sets. In this paper, we deeply investigate the relationships among these three probabilistic-based expressions and introduce two transformation functions for them in order to make the information formats unified. Besides, for the probabilistic hesitant fuzzy sets, three novel distance measures are proposed, i.e., the minimal distance, the central distance, and the improved distance, which are useful tools to measure the difference between the probabilistic hesitant fuzzy elements. In order to fuse the different formats of information and get valuable results from it, the K-medoids algorithm for the probabilistic-based expressions is developed. The algorithm is applied to classify the merchants on the website of , so that the results can be provided to customers to help them make decisions.

关键词： K-medoids clustering algorithm Probabilistic-based expression Distance measure

来源：评论

学校读者我要写书评

暂无评论

Stakeholder-Centric clustering Methods for Conflict Resolution in the Requirements Engineering Process 16th

Stakeholder-Centric Clustering Methods for Conflict Resoluti...

引用

16th International Conference on Evaluation of Novel Approaches to Software Engineering (ENASE)

作者： Gambo, Ishaya Taveter, Kuldar Univ Tartu Inst Comp Sci Tartu Estonia Obafemi Awolowo Univ Dept Comp Sci & Engn Ife Nigeria

ISBN: (纸本)9783030966485;9783030966478

This paper describes the development and evaluation of a framework that combines expert-based and clustering methods for resolving conflicts in requirements elicited from stakeholders. The purpose of the framework was to identify and resolve conflicts among expectations by multiple stakeholders that often arise during the requirements elicitation phase. By means of qualitative and quantitative research approaches, face-to-face oral interviews, quantitative surveys, brainstorming sessions, and focus groups, scenarios were generated with stakeholders of a given problem domain. Our approach was implemented within an interactive system that empirically supports the adequacy of our framework with the involvements of experts and other stakeholders of the chosen problem domain. In addition, we presented a dataset of requirements with their weight scales that formed the basis for resolving conflicting views by stakeholders by applying scientific criteria. The framework was validated in a real-life case study. The results demonstrated 85.71% of correctly clustered instances of requirements, based on which the experts agreed that the interactive system was good enough for resolving conflicting subjective views in requirements analysis. The research performed has the two-fold threat to validity, which suggests (i) the need to adequately capture and harmoniously represent the views by different stakeholders in a multicultural and multidisciplinary domain and (ii) the need to validate the framework in other real life case studies in different domains. The research performed has a high potential for reducing software development costs and saving time at the early stage of the development of software products.

关键词： Requirements engineering Stakeholders Conflict resolution clustering algorithm Delphi method Software engineering

来源：评论

学校读者我要写书评

暂无评论

Adaptive Load Balancing Routing algorithm For Low Earth Orbit Satellite Cluster Networks 9

Adaptive Load Balancing Routing Algorithm For Low Earth Orbi...

引用

9th International Conference on Computer and Communication Systems (ICCCS)

作者： Wang, Liming Xu, Zhan Zhi, Ruxin Wang, Jiahui Beijing Informat Sci & Technol Univ Sch Elect & Commun Engn Beijing Peoples R China Beijing Informat Sci & Technol Univ Key Lab Informat & Commun Syst Minist Informat Ind Beijing Peoples R China Beijing Informat Sci & Technol Univ Key Lab Modern Measurement & Control Technol Minist Educ Beijing Peoples R China

ISBN: (纸本)9798350350227;9798350350210

Large-scale satellite networks are a crucial component of future communication systems. However, they pose several challenges to satellite routing design and link recovery. This paper proposes an Adaptive Load Balancing routing algorithm for Low Earth Orbit (LEO) Satellite Cluster Networks (ALBSCN) to meet the needs of large-scale Low Earth Orbit LEO satellite networks. The constellation is divided into clusters, with each cluster maintaining the intra-cluster link state by electing a cluster head. The cluster head computes intra-cluster and inter-cluster routes. Messages are forwarded using inter-cluster multipath routing and intra-cluster routing techniques. We validated the algorithm's performance and compared it with other algorithms in terms of packet delivery delay using simulation. Simulation results indicate that the proposed clustering routing scheme effectively reduced packet loss and end-to-end delay, while also increasing network throughput.

关键词： clustering algorithm load balancing LEO routing

来源：评论

学校读者我要写书评

暂无评论

Analysis of Customer Energy Consumption Patterns using an Online Fuzzy clustering Technique

Analysis of Customer Energy Consumption Patterns using an On...

引用

IEEE International Conference on Fuzzy Systems (FUZZ-IEEE) / IEEE World Congress on Computational Intelligence (IEEE WCCI) / International Joint Conference on Neural Networks (IJCNN) / IEEE Congress on Evolutionary Computation (IEEE CEC)

作者： Aguilar, Jose Quintero Gull, Carlos R-Moreno, Maria D. Viera, Juan Univ Alcalci Escuela Politecn Super ISG Alcala De Henares 28805 Spain Univ Los Andes CEMISID Merida 5101 Venezuela Univ EAFIT GIDITIC Medellin 50022 Colombia Univ Los Andes Fac Ingn Ciencias Aplicadas Dpto Ciencias Aplicadas Humanist Merida 5101 Venezuela Intelligent Autonomous Syst Grp IAS TNO The Hague Netherlands

ISBN: (数字)9781665467100

ISBN: (纸本)9781665467100

Currently, there is a high rate of generation of new information about the Energy Consumption of customers. It is important the traceability of its consumption pattern evolution to determine in real-time the services of a smart energy management system. This paper analyses the evolution of the Energy Consumption Pattern of customers using the Learning algorithm for Multivariable Data Analysis (LAMDA). LAMDA is a fuzzy approach for supervised and unsupervised learning, based on the calculation of the Global Adequacy Degree (GAD) of one individual to a class/cluster, through the contributions of all its descriptors. LAMDA can create new classes/clusters after the training stage (online learning). If an individual does not have enough similarity to the preexisting classes/clusters, it is evaluated with respect to a threshold called the Non-Informative Class (MC) to define if it is a new class/cluster. Particularly, the algorithm of the LAMDA family used in this paper is LAMDA-RD (Robust Distance). In the paper is analyzed the patterns of the initial grouping of the data, as well as, the patterns through their evolution (traceability). For the analysis of the patterns different metrics are considers: Calinski- Harabasz Index and Silhouette Score.

关键词： clustering algorithm fuzzy systems LAMDA Online Learning pattern evolution

来源：评论

学校读者我要写书评

暂无评论

Analysis of Operational Data and Self-learning Control Rules for Mining Mill Equipment 14

Analysis of Operational Data and Self-learning Control Rules...

引用

14th Asian Control Conference (ASCC)

作者： Wang, Guicheng Yuan, Liang Bai, Zhicheng Cai, Guoliang Hua, Ning Li, Xiaobin Shanghai Inst Technol Sch Elect & Elect Engn Shanghai Peoples R China State Key Lab Intelligent Optimized Mfg Min & Met Beijing Peoples R China Beijing Key Lab Proc Automat Min & Met Beijing Peoples R China Zijin Intelligent Control Xiamen Technol Co Ltd Xiamen Peoples R China

ISBN: (纸本)9798331540845;9789887581598

The engineering application under industrial big-data analysis is of great significance for improving the optimization effect of enterprise production process control processes. By analyzing the operating principle of the semi-automatic mill and studying its control optimization strategy, based on the operational data of the SAG mill, industrial big-data analysis is adopted to self-learning its control optimization rules. Firstly, SPSS is used to preprocess the high-dimensional process data generated during the operation of the semi-automatic mill. Four parameters, namely power, axial pressure, grinding sound, and grinding concentration, are preliminarily selected. Then, PCA is used to screen and reduce the dimensionality of multidimensional data, and K-Means clustering algorithm is used to classify and identify the reduced dataset. After simulation research, the results show that PCA can reduce the redundancy of SAG mill operation data, and the control optimization rules formed by self-learning can serve as operational guidance for improving the efficiency and energy-saving of SAG mill operation. The effectiveness can be further verified in practical engineering applications in the later stage.

关键词： SAG mill industrial big-data PCA clustering algorithm control 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：