检索结果-内蒙古大学图书馆

International Conference on Mechatronics and Control (ICMC)

作者： Cui, Xiaohua Cao, Jiangtao Zhang, Yi Liaoning Shihua Univ Sch Informat & Control Engn Fushun Peoples R China

ISBN: (纸本)9781479925384

In clustered heterogeneous networks, some nodes are set as cluster heads, responsible to integrate the information from the intra-cluster members and send it to the sink node. Therefore cluster heads dissipate much more energy than other sensor nodes. And the stability of networks can be affected when the first node dies. We assume that nodes are assumed be equipped with different energy randomly, a clustering algorithm based on residual energy and multi-management for cluster heads is proposed. By adding a parameter into the probability of cluster head election, the proposed algorithm makes nodes with more initial energy and residual energy become cluster heads with large probability. It balances the energy consumption of network and prolongs the survival time of network. At the same time, in order to ensure the quality of network transmission, the strategy of multi-hop management is introduced in this algorithm. We show by simulation that the algorithm has a longer lifetime and more stable capacity of data transmission than LEACH, DEEC and SEP in the multi-level energy heterogeneous network.

关键词： heterogeneous sensor network clustering algorithm energy balance

来源：评论

学校读者我要写书评

暂无评论

Evil vs evil: using adversarial examples to against backdoor attack in federated learning

引用

MULTIMEDIA SYSTEMS 2023年第2期29卷 553-568页

作者： Liu, Tao Li, Mingjun Zheng, Haibin Ming, Zhaoyan Chen, Jinyin Zhejiang Univ Technol Coll Informat Engn Hangzhou 310023 Peoples R China Zhejiang Univ Technol Inst Cyberspace Secur Hangzhou 310023 Peoples R China Zhejiang Univ City Coll Coll Comp & Comp Sci Hangzhou 310015 Peoples R China

As a distributed learning paradigm, federated learning (FL) has shown great success in aggregating information from different clients to train a shared global model. Unfortunately, by uploading carefully crafted updated models, a malicious client can embed a backdoor into the global model during FL's training. Numerous secure aggregation strategies and robust training protocols have been proposed to defend FL against backdoor attacks. However, they are still challenged, either being bypassed by adaptive attacks or sacrificing the main task performance of FL. By conducting empirical studies of backdoor attacks in FL, we gain an interesting insight that adversarial perturbations can activate backdoors in backdoor models. Consequently, behavior differences of models fed by adversarial examples are compared for backdoor update detection. We propose a novel FL backdoor defense method using adversarial examples, denoted as Evil vs Evil (EVE). Specifically, a small data set of clean examples for FL's main task training is collected in the sever for adversarial examples generation. By observing the behavior of updated models under the adversarial examples, EVE uses a clustering algorithm to select benign models and to exclude the other models, without any loss of the main task performance of FL itself. Extensive evaluations across four data sets and the corresponding DNNs demonstrate the state-of-the-art (SOTA) defense performance of EVE compared with five baselines. In particular, EVE under 40% of malicious clients can reduce the attack success rate from 99% to 1%. In addition, we verify that EVE is still robust under the adaptive attacks. EVE is open sourced to facilitate future research.

关键词： Federated learning Backdoor attacks Defense Adversarial attacks clustering algorithm

来源：评论

学校读者我要写书评

暂无评论

Application of computer information management system in universities in the information age

引用

JOURNAL OF COMPUTATIONAL METHODS IN SCIENCES AND ENGINEERING 2024年第3期24卷 1557-1569页

作者： Yin, Li Chen, Yijun Nantong Univ Informatizat Ctr Nantong 226019 Jiangsu Peoples R China

The application of computer information management system (IMS for short here) in university management faces problems such as incomplete system software and complex system design. Applying clustering algorithms (CA for short here) to computer student IMS can help optimize the system's overall effectiveness. This article constructed a computer student IMS based on computer technology and applied it to the management of college students. This article also combined CA to conduct relevant effectiveness tests on the system, in order to optimize the overall effectiveness of the system. Under the algorithm in this article, the average connection speed for each user accessing the system was 9.17 Mbps. The average reaction time was 0.34 seconds, the average security level was 92.47%, and the highest memory usage rate of the system was 34.27%;Under the decision tree algorithm, the average connection speed of each user accessing the system was 8.82 Mbps, and the average reaction time reached 0.64 s. The average security level was 88.41%, and the highest memory usage rate was 42.58%. Under the artificial neural network algorithm, the average connection speed of the system was 8.47 Mbps, the average response time was 0.86 s, and the highest memory usage rate was 45.97%. Analyzing the data reveals that the algorithm introduced in this paper significantly enhances system connection speed and reduces reaction time. This improvement not only enhances security measures but also minimizes memory usage, effectively optimizing the overall efficiency of the system.

关键词： Computer information management system university management work student information management system safety clustering algorithm

来源：评论

学校读者我要写书评

暂无评论

Reliability analysis of railway assets considering the impact of geographical and climatic properties

引用

INTERNATIONAL JOURNAL OF SYSTEM ASSURANCE ENGINEERING AND MANAGEMENT 2024年 1-14页

作者： Kasraei, Ahmad Garmabaki, A. H. S. Lulea Univ Technol Dept Civil Environm & Nat Resources Engn Div Operat & Maintenance S-97187 Lulea Sweden

Various factors, including climate change and geographical features, contribute to the deterioration of railway infrastructures over time. The impacts of climate change have caused significant damage to critical components, particularly switch and crossing (S&C) elements in the railway network. These components are sensitive to abnormal temperatures, snow and ice, and flooding, making them susceptible to failures. The consequences of S&C failures can have a detrimental effect on the reliability and safety of the entire railway *** is crucial to have a reliable clustering of railway infrastructure assets based on various climate zones to make informed decisions for railway network operation and maintenance in the face of current and future climate scenarios. This study employs machine learning models to categorize S & Cs;therefore, historical maintenance data, asset registry information, inspection data, and weather data are leveraged to identify patterns and cluster failures. The analysis reveals four distinct clusters based on climatic patterns. The effectiveness of the proposed model is validated using S&C data from the Swedish railway *** utilizing this clustering approach, the whole of Sweden railway network divided into 4 various groups. Utilizing this groups the development of model can associated with enhancing certainty of decision-making in railway operation and maintenance management. It provides a means to reduce uncertainty in model building, supporting robust and reliable decision-making. Additionally, this categorization supports infrastructure managers in implementing climate adaptation actions and maintenance activities management, ultimately contributing to developing a more resilient transport infrastructure.

关键词： Climate zones clustering algorithm Railway asset Reliability analysis

来源：评论

学校读者我要写书评

暂无评论

Occlusion target recognition algorithm based on improved YOLOv4

引用

JOURNAL OF COMPUTATIONAL METHODS IN SCIENCES AND ENGINEERING 2024年第6期24卷 3799-3811页

作者： Jia, Fengguang Shandong Jiaotong Univ Coll Naval Architecture & Port Engn Weihai 264200 Peoples R China

With the development of deep learning, recognition algorithms are increasingly widely used in various fields, and face recognition is a technological embodiment of recognition algorithms in real life. Due to the limited recognition range, the face may be occluded, so it is necessary to design an occluded target recognition algorithm model. This article aims to optimize the "You Only Look Once Version 4" algorithm and propose an improved occlusion target recognition algorithm model by introducing separable convolutional optimization and embedding attention mechanism. This paper designed relevant experiments to verify the model performance and compared the facial recognition model designed by MM Goyani. The experiment shows that the median accuracy of this algorithm and the comparison algorithm are 0.97 and 0.92, respectively, with a distinction of 0.05, and the average values are 0.962 and 0.902, with a discrepancy of 0.060. About the accuracy, the improved algorithm is higher than that unimproved algorithm, with a difference of 16% and an average accuracy difference of 7.5%. Therefore, the constructed algorithm has effectiveness and feasibility, and to a certain extent has good development potential and reference value.

关键词： object detection clustering algorithm occlusion recognition attention mechanism separable convolution feature information

来源：评论

学校读者我要写书评

暂无评论

Optimization on Multimodal Network Considering Time Window Under Uncertain Demand

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2025年

作者： Bei, Honghan Lin, Han Yang, Fangjiao Li, Xiaolong Murcio, Roberto Yang, Tianren Dalian Maritime Univ Sch Maritime Econ & Management Dalian 116026 Peoples R China Dalian Maritime Univ Collaborat Innovat Ctr Transport Studies Dalian 116026 Peoples R China COSCO SHIPPING Logist & Supply Chain Management Co Dalian 116001 Peoples R China Birkbeck Univ London Sch Social Sci London WC1E 7HX England UCL Ctr Adv Spatial Anal London W1T 4TJ England Univ Hong Kong Dept Urban Planning & Design Hong Kong Peoples R China

Improving transport efficiency is challenging for multimodal transport participants to improve cost-effectiveness. This paper proposes to select city nodes and establish a multi-objective fuzzy optimization model with mixed time window constraints to consider customer demand and transportation time uncertainty. T-rex Optimization algorithm (TROA) is used to solve the problem, which efficiently lowers transportation costs and carbon emissions and has higher precision and dependability than Particle Swarm Optimization (PSO) and Genetic algorithm (GA). The efficacy of this method is proven using the example of the multimodal transportation network in China's central-eastern economic zone. These findings provide potential solutions for multimodal transportation aimed at enhancing transportation efficiency.

关键词： Transportation Optimization Uncertainty Planning Costs Routing Carbon dioxide Optimization models Logistics Biological system modeling clustering algorithm mixed time windows multimodal transport network optimization uncertain demand

来源：评论

学校读者我要写书评

暂无评论

Improvement of clustering algorithm for WSNs

Improvement of Clustering Algorithm for WSNs

引用

International Conference on Application of Materials Science and Environmental Materials (AMSEM)

作者： Chen, QiGong Wang, YongZhi Wei, LiSheng Gao, WenGen Anhui Polytech Univ Anhui Prov Detect Lab Wuhu 241000 Anhui Peoples R China

ISBN: (纸本)9783038352709

Energy consumption is a hot issue in WSNs (Wireless Sensor Networks). In this paper, we present an improved clustering algorithm. By changing the order of traditional WSNs clustering algorithm, this algorithm uses k-means clustering firstly base on optimal number of cluster head is determined;Then selects cluster head by an improved LEACH (Low Energy Adaptive clustering Hierarchy) algorithm;Finally, Our experimental results demonstrate that this approach can reduces energy consumption and increases the lifetime of the WSNs.

关键词： energy consumption WSNs k-means LEACH clustering algorithm

来源：评论

学校读者我要写书评

暂无评论

A Greedy Dynamic clustering algorithm of Joint Transmission In Dense Small Cell Deployment

A Greedy Dynamic Clustering Algorithm of Joint Transmission ...

引用

IEEE 11th Consumer Communications and Networking Conference (CCNC)

作者： Qin, Cheng Tian, Hui Beijing Univ Posts & Telecommun State Key Lab Neworking & Switching Technol Beijing 100876 Peoples R China

ISBN: (纸本)9781479923557

In a dense small cell deployment scenario, users are always prone to suffer severe interferences from neighbor base stations (BS) because the BSs are usually located closely. Coordinated Multi-Point (CoMP) can be introduced to alleviate these interferences and improve the system performance. It is necessary to determine coordination areas (CA) before implementation. In this paper, a novel dynamic clustering algorithm in CoMP joint transmission system is proposed based on graph theory. Firstly a feedback procedure is designed for interference reports mainly based on large scale fading. By building a graph according to the interferences, the clustering problem is equivalent to dividing the graph into several subgraphs. Each subgraph represents a CoMP cluster. It can be solved through a greedy strategy that each BS searches its best coordinated BSs. Compared with some other dynamic algorithms, the complexity of the proposed scheme is lower because it can be implemented in a decentralized way. Therefore this method is suitable in dense cell deployment with a large number of BSs. The simulation results show that the novel clustering algorithm performs better in user capacity than other traditional dynamic schemes. The influences of some parameters in this method are also considered and evaluated in the simulation.

关键词： Small cell deployment clustering algorithm Joint Transmission

来源：评论

学校读者我要写书评

暂无评论

Adaptive state augmented clustering-based fuzzy learning control of a passive torque simulator

引用

INTERNATIONAL JOURNAL OF DYNAMICS AND CONTROL 2022年第3期10卷 917-929页

作者： Saadat, Seyyed Amirhossein Fateh, Mohammad Mehdi Keighobadi, Javad Shahrood Univ Technol Control & Robot Fac Shahrood Iran

This paper presents a newclustering-based fuzzy learning controller for a passive torque simulator (PTS) system in the presence of nonlinear friction and disturbance. An adaptive network-based fuzzy inference system is integrated with clustering algorithm to deal with unknown terms. Besides, a state-augmented technique is also employed in the framework of the backstepping method to improve the performance of system. The simplicity of design, fast learning speed and robust behavior are the main properties of the proposed controller for PTS system. In addition, the online computational burden is also alleviated due to employing the clustering algorithm. The stability of the closed-loop system is confirmed by the Lyapunov theorem. Furthermore, different simulation results are provided to validate the potential of the proposed control system in comparison with previous related research.

关键词： Passive torque simulator clustering algorithm Adaptive backstepping method Network-based fuzzy inference system Learning-based controller

来源：评论

学校读者我要写书评

暂无评论

A Vertex-clustering algorithm Based on the Cluster-Clique

A Vertex-Clustering Algorithm Based on the Cluster-Clique

引用

14th International Conference on algorithms and Architectures for Parallel Processing (ICA3PP)

作者： Wang, Deqiang Zhang, Bin Wang, Kelun Dalian Maritime Univ Inst Naut Sci & Technol Dalian Peoples R China Dalian Maritime Univ Dept Math Dalian Peoples R China

ISBN: (纸本)9783319111940;9783319111933

The vertex-clustering algorithm based on intra connection ratio (MV-ICR algorithm) is a graph-clustering algorithm proposed by Moussiades and Vakali[clustering dense graph: A web site graph paradigm. Information Processing and Management, 2010, 46: 247-267]. In this paper, we propose a new conception called cluster-clique for vertex-clustering of graphs. And based on the cluster-clique and the intra connection ratio, a new vertex-clustering algorithm is proposed. This algorithm is more reasonable and effective than MV-ICR algorithm for some clusters which have the same maximum intra connection ratio.

关键词： graph clustering algorithm cluster-clique intra connection ratio

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：