检索结果-内蒙古大学图书馆

An Improved SFLA-Kmeans Algorithm Based on Approximate Backbone and Its Application in Retinal Fundus Image

IEEE ACCESS 2021年 9卷 72259-72268页

作者： Ding, Weiping Zhang, Yi Sun, Ying Qin, Tingzhen Nantong Univ Sch Informat Sci & Technol Nantong 226019 Peoples R China

In order to improve the global search ability of K-means algorithm and the clustering effect, a K-means method based on the approximate backbone and the shuffled frog leaping algorithm was proposed. Firstly, the classic iterative formula of the K-means algorithm is replaced by the classic shuffled frog leaping algorithm to obtain better clustering results. Secondly, the K-means algorithm based on the approximate backbone and the shuffled frog leaping algorithm is used for the obtained clustering results. Instead of searching for cluster centers, the cluster division is directly modified. Finally, the experimental results on the UCI dataset show that, the running time of the improved clustering algorithm is shorter than that based on the shuffled frog leaping algorithm only, and clustering results obtained by using the improved clustering algorithm are better than those of other algorithms. In addition, the paper uses the improved clustering algorithm to preprocess medical fundus images to optimize the effect of vascular cutting.

关键词： clustering algorithms Approximation algorithms Heuristic algorithms Particle swarm optimization Optimization Licenses Convergence K-means algorithm shuffled frog leaping algorithm approximate backbone

来源：评论

学校读者我要写书评

暂无评论

Algorithmic Splitting: A Method for Dataset Preparation

引用

IEEE ACCESS 2021年 9卷 125229-125237页

作者： Kahloot, Khalid M. Ekler, Peter Budapest Univ Technol & Econ Dept Automat & Appl Informat H-1117 Budapest Hungary

The datasets that appear in publications are curated and have been split into training, testing and validation sub-datasets by domain experts. Consequently, machine learning models typically perform well on such split-by-hand prepared datasets. Whereas preparing real-world datasets into curated split training, testing and validation sub-dataset requires extensive effort. Usually, repetitive random splits are carried out and trained and evaluated on until reaching out a good score on the evaluation metrics. In this paper, an algorithmic method is proposed for preparing the sub-datasets splits for machine learning models. The objective of the proposed method is to achieve an evenly representative splits out of the dataset with standard and algorithmic way that reduce the perplexity of random splitting.

关键词： Training Testing Data models Machine learning Machine learning algorithms Standards clustering algorithms Data preprocessing clustering algorithms machine learning

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning Power Control Algorithm Based on Graph Signal Processing for Ultra-Dense Mobile Networks

引用

IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING 2021年第3期8卷 2694-2705页

作者： Li, Yujie Tang, Zhoujin Lin, Zhijian Gong, Yanfei Du, Xiaojiang Guizani, Mohsen Beijing Informat Sci & Technol Univ Key Lab Modern Measurement & Control Technol Minist Educ Beijing 100101 Peoples R China Fuzhou Univ Fac Comp Sci Fuzhou 350108 Fujian Peoples R China China Acad Informat & Communt Technol Beijing 100191 Peoples R China Temple Univ Dept Comp & Informat Sci Philadelphia PA 19122 USA Qatar Univ Dept Comp Sci & Engn Doha 2713 Qatar

Ultra-dense mobile networks (UDMNs) represent a promising technology for improving the network performance and providing the ubiquitous network accessibility in the beyond 5 G (B5G) mobile networks. Heterogenous densely deployed networks can dynamically offer high spectrum efficiency and enhance frequency reuse, which ultimately improves quality of service (QoS) and the user experience. However, mass inter- or intra-cell interference generated from overlap between small cells greatly limits network performance, especially when there is mobility between UEs and access points (APs). Even so, when network density increases, the complexity of conventional allocation methods can increase also. In this paper, we investigate a power control of downlink (DL) connection in the UNMNs with different types of APs. We propose a reinforcement learning (RL) power allocation algorithm based on graph signal processing (GSP) for ultra-dense mobile networks. Firstly, we construct a realistic system model under ultra-dense mobile networking, which includes the system channel mode and instantaneous rate. Then we employ a GSP tool to analyze network interference, the interference analysis results for the entire network are obtained to determine optimal RL power allocation. Finally, simulation results indicate that the proposed RL power control algorithm outperforms baseline algorithms when applied to a ultra-dense mobile networks.

关键词： Interference Resource management Power control Signal processing algorithms Complexity theory clustering algorithms Heuristic algorithms B5G graph signal processing power control reinforcement learning ultra-dense mobile networks

来源：评论

学校读者我要写书评

暂无评论

Improving Domain-Adaptive Person Re-Identification by Dual-Alignment Learning With Camera-Aware Image Generation

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2021年第11期31卷 4334-4346页

作者： Zhang, Chenyang Tang, Yongqiang Zhang, Zhizhong Li, Ding Yang, Xuebing Zhang, Wensheng Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing 101408 Peoples R China Chinese Acad Sci Res Ctr Precis Sensing & Control Inst Automat Beijing 100190 Peoples R China

Domain adaptation in person re-identification (re-ID) has always been challenging, especially for the lack of supervision information on the target domain. Existing methods generally introduced extra supervision by adversarial learning techniques, then added all the augmented data in the training process to optimize the re-ID model. However, the direct utilization of all the generated data not only increases additional computational cost but also ignores the potential correlation between the origin and generated data. In this article, we propose a novel dual-alignment learning framework (DAL) with camera-aware image generation to efficiently and effectively tackle this issue. Specifically, we propose a camera transfer matching module to generate additional training images with different camera styles, and construct the matching pairs with each containing a origin image and one corresponding camera transferred image. To strengthen the correlation of images for each matching pair, we align the pseudo-labels via clustering algorithm to reduce the pseudo-labels distribution discrepancy between the origin and generated images. Besides, to avoid model degeneration affected by some inaccurate pseudo-labels on unlabelled data, we maximize the mutual information to align the image feature representations of matching pair. The DAL allows us to decrease the camera variance and enhance the discrimination ability of re-ID model. Extensive experiments on three large-scale benchmarks demonstrate the superiority of DAL over state-of-the-art methods.

关键词： Cameras Training Data models Correlation clustering algorithms Adaptation models Prediction algorithms Person re-identification convolutional neural networks generative adversarial networks mutual information

来源：评论

学校读者我要写书评

暂无评论

An Imbalanced-Data Processing Algorithm for the Prediction of Heart Attack in Stroke Patients

引用

IEEE ACCESS 2021年 9卷 25394-25404页

作者： Wang, Meng Yao, Xinghua Chen, Yixiang East China Normal Univ Sch Comp Sci & Software Engn Shanghai 200241 Peoples R China East China Normal Univ Sch Software Engn Shanghai 200241 Peoples R China Shanghai Univ Tradit Chinese Med Sch Basic Med Shanghai 201203 Peoples R China

Early predicting heart attack out of stroke patients in a view of data analysis is an approach to reduce a high mortality rate. Stroke-patient data in Intensive Care Unit are imbalanced due to that stroke patients with heart attack are in the minority of stroke patients. How to predict heart attack in the stroke-patient data becomes a challenge. For processing the imbalanced data, this paper designs an algorithm by leveraging random undersampling, clustering and oversampling techniques, which is called undersampling-clustering-oversampling algorithm (shortly, UCO algorithm). The UCO algorithm generates nearly balanced data which are utilized to train machine-learning models for predicting heart attack. Over the database of Medical Information Mart for Intensive Care III, extensive experiments are conducted to evaluate the UCO algorithm. A setting of undersampling number of 120 in the algorithm UCO, denoted UCO(120), shows good performance in helping machine-learning classifiers extract features. Five classifiers are separately deployed to predict heart attack based on outputs of the UCO(120). Our results show that random forest classifier achieves the best predicting performance with an accuracy of 70.29%, and precision of 70.05%. It could be well-predicted using UCO(120) and random forest that whether a stroke patient will have heart attack or not.

关键词： Cardiac arrest Stroke (medical condition) Prediction algorithms Heart clustering algorithms Predictive models Machine learning Undersampling clustering oversampling imbalanced data stroke heart attack

来源：评论

学校读者我要写书评

暂无评论

An Energy-Efficient Routing Protocol for 3D Wireless Sensor Networks

引用

IEEE SENSORS JOURNAL 2021年第17期21卷 19550-19559页

作者： Xu, Yun Jiao, Wanguo Tian, Mengqiu Nanjing Forestry Univ Coll Informat Sci & Technol Nanjing 210037 Jiangsu Peoples R China

Energy optimization is a key problem of the energy-limited wireless sensor network (WSN), which is usually deployed in the three-dimensional space. In order to alleviate this problem, this paper studies the energy-efficient routing protocol for 3D WSN. The less sensor nodes work simultaneously, the more energy is saved. To minimize energy consumption on the premise of satisfying the full coverage of discrete points of interest (DPOI), finding the least and optimal node set for routing is an important problem. Through studying this problem, we propose an algorithm employing the improved genetic algorithm to find the minimum set of sensor nodes which can ensure the full coverage of DPOI. On the basis of the optimal node set, we propose a new adaptive clustering routing optimizing energy consumption, which includes three parts. The first one is selecting the cluster head according to the residual energy of the sensor node and the distance from the base station. The second one is setting the intra-cluster communication mode by considering the angle of node space. The last one is deciding inter-cluster communication mode by combining single-hop and multi-hop. To fully utilize the energy of the network, we design a node wake-up scheme to wake up the sleep node to replace the sensor nodes which runs out of energy. This policy also can make our proposed protocol suitable for the rechargeable WSN. In addition, we also consider the additional energy consumption of retransmission caused by the unreliable wireless channel. Simulation results show that our proposed scheme is obviously superior to other existing schemes in prolonging the WSN lifetime.

关键词： Sensors Wireless sensor networks Routing Three-dimensional displays Energy consumption Routing protocols clustering algorithms Energy optimization 3D WSN routing protocol unreliable wireless channel

来源：评论

学校读者我要写书评

暂无评论

A Many-Objective Artificial Bee Colony Algorithm Based on Adaptive Grid

引用

IEEE ACCESS 2021年 9卷 97138-97151页

作者： Zhang, Weicun Li, Yanan Hebei Univ Technol Sch Econ & Management Tianjin 300401 Peoples R China

Many-objective optimization problems are widely applied and complex to solve. For most many-objective evolutionary algorithms, maintaining the balance of solution convergence and diversity is a challenging problem. Considering the convergence and diversity at the same time, a many-objective artificial bee colony algorithm based on adaptive grid(MOABCAG) is proposed. By searching for the ideal target point in the grid, the solution selection pressure is enhanced, the solution is positioned under the designed grid, and the grid is adaptively divided to improve the convergence and diversity of the solution. The algorithm improves the position sharing mechanism of the leader and follower bees in the artificial bee colony algorithm, and it sets the variable neighborhood search method of the follower bee to improve the precision of the solution vectors. MOABCAG is compared with five well-known evolutionary algorithms on thirteen benchmark test functions. The results show that the proposed MOABCAG algorithm obtains better performance than other related state-of-the-art algorithms in solving such many-objective optimization problems.

关键词： Optimization Convergence Search problems Artificial bee colony algorithm clustering algorithms Statistics Sociology Many-objective optimization adaptive grid artificial bee colony algorithm

来源：评论

学校读者我要写书评

暂无评论

Lithofacies Identification from Well Log and Data clustering 1

Lithofacies Identification from Well Log and Data Clustering

引用

1st EAGE Workshop on East Canada Offshore Exploration

作者： Hasan, M.M.U. Hasan, T. Shahidi, R. James, L. Gosine, R. Peters, D. Department of Electrical and Computer Science Memorial University Of Newfoundland Canada Department of Process Engineering Memorial University Of Newfoundland Canada Department of Electrical and Computer Science Memorial University Of Newfoundland Canada

ISBN: (纸本)9789462824010

The conventional method of lithofacies identification uses well logs and core samples. Manual effort is required for this identification. We hypothesize that we can achieve similar results using the unsupervised data clustering technique newly introduced in this work. Using this data clustering method, we aim to identify the number of possible lithofacies and map the well log signatures to those lithofacies without using core samples. A newly developed unsupervised data clustering algorithm is used in this study. Unlike other clustering algorithms, the Piecemeal Algorithm does not require the number of clusters to be provided as a parameter of the algorithm. Instead, it identifies the number of clusters from the data itself. We tested the algorithm on publicly-released data from nine wells drilled in the Hugoton and Panoma fields of southwest Kansas and northwest Oklahoma to validate the hypothesis. The algorithm is able to identify 9 clusters, which is the same as the number of clusters found in the published work using the same data. We also found mapping accuracies of 81.90% and 45.20% with and without considering the adjacency facies, respectively. © 1st EAGE Workshop on East Canada Offshore Exploration 2021.

关键词： clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

A New MSGSA-Optimized Dynamic Window of Spatiotemporal Scan Statistics for Disease Outbreak Detection

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2021年 14卷 10821-10834页

作者： Wang, Haiqi Kong, Haoran Yan, Bin Li, Liuke Xu, Jianbo Wang, Zhihai Wang, Qiong China Univ Petr East China Coll Oceanog & Space Informat Qingdao 266580 Peoples R China Chinese Acad Sci State Key Lab Resources & Environm Informat Syst Beijing 100101 Peoples R China Chinese Acad Sci Inst Geog Sci & Nat Resources Res Beijing 100101 Peoples R China

The spatiotemporal scan statistics proposed by Kulldorff have been applied to detect numerous disease clusters, and scan statistics based on heuristic algorithm optimization have also been utilized for disease cluster detection. The gravitational search algorithm (GSA) and the recent human mental search (HMS) possess superior performance in comparison with several heuristic algorithms, and neither algorithm has yet been applied in spatiotemporal scan statistics. However, the size of the spatiotemporal scanning window utilized in disease applications is constant in the time dimension, and it is difficult to detect changes in the size of an anomalous cluster over time. In this study, we proposed a dynamic cylinder with a variable radius as a spatiotemporal scanning window. In addition, we proposed an improved GSA based on mental search (MSGSA), and the MSGSA was utilized to optimize the dynamic scanning window to detect spatiotemporally anomalous clusters. The performance of the MSGSA was verified on 23 benchmark functions in comparison with the GSA and HMS. Simulated experiments based on the MSGSA and SaTScan showed that the MSGSA-optimized dynamic window yielded better performance based on the obtained accuracies and error rates. Finally, we utilized the MSGSA-optimized dynamic window and other methods to detect spatiotemporally anomalous clusters of hand-foot-and-mouth disease (HFMD) in China (2016) and Guangdong (2009), and the MSGSA-optimized dynamic window yielded better performance on both HFMD datasets. Moreover, the conclusions obtained with the MSGSA-optimized dynamic window were consistent with those of relevant researchers, indicating that the MSGSA possesses certain disease outbreak detection ability.

关键词： Spatiotemporal phenomena Diseases clustering algorithms Heuristic algorithms Shape Sociology Optimization Gravitational search algorithm (GSA) mental search scan statistics spatiotemporal anomaly detection spatiotemporal dynamic scanning window

来源：评论

学校读者我要写书评

暂无评论

An Algorithm for Detection of Traffic Attribute Exceptions Based on Cluster Algorithm in Industrial Internet of Things

引用

IEEE ACCESS 2021年 9卷 53370-53378页

作者： Fu, Lidong Zhang, Wenbo Tan, Xiaobo Zhu, Hongbo Shenyang Ligong Univ Sch Informat Sci & Engn Shenyang 110159 Peoples R China Northeastern Univ Sch Comp Sci & Engn Shenyang 110169 Peoples R China

With the focus on network security and the goal of meeting the requirements of fast speed and high accuracy of abnormal traffic detection of industrial Internet of Things, this paper proposes a hierarchical abnormal traffic detection method for the industrial Internet of Things. This method includes two abnormal detection methods: the first (crude) one detects traffic frequency based on statistical analysis;the second (sophisticated) one detects traffic attributes based on a clustering algorithm. The hierarchical detection method first detects the abnormal frequency of the network traffic. Property exceptions are then detected for suspected traffic. The paper first calculates the difference in the value of traffic frequency and smoothes it. Then, the exponential weighted moving average model is used to make the data conform to the statistical law, and the deviation correction of the model is proposed to reduce the error caused by the initial value. Focusing on the fact that a fixed threshold is not suitable for a dynamic network environment, a two-layer threshold interval method is proposed to reduce the rate of false alarms. For traffic attribute detection, this paper designs a clustering optimization anomaly detection algorithm for complex attribute feature data. The algorithm classifies the weighted distance and safety coefficient of the data according to the priority of the traffic attribute features, selects the data with the high safety coefficient as the clustering center, clusters the multi-feature data around the center, and applies it to the attribute anomaly detection. The simulation results show that the traffic frequency detection algorithm based on statistical analysis proposed in this paper can quickly detect the traffic frequency anomalies in the network. Moreover, the clustering optimization anomaly detection algorithm based on complex attribute features proposed in this paper can effectively detect the malicious attributes contained in network traf

关键词： clustering algorithms Industrial Internet of Things Security Data models Feature extraction Production Machine learning algorithms clustering algorithms industrial Internet of Things traffic attribute detection traffic frequency 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：