检索结果-内蒙古大学图书馆

19th International Conference on Machine Learning and Cybernetics, ICMLC 2020

作者： Song, Jingjing Jiang, Zehua Dou, Huili Tsang, Eric C. C. Jiangsu University of Science and Technology School of Computer Jiangsu Province Zhenjiang212003 China Key Laboratory of Data Science and Intelligence Application Fujian Province University Zhangzhou363000 China Macau University of Science and Technology Faculty of Information Technology China

ISBN: (纸本)9780738124261

In neighborhood based attribute reduction, neighborhood relation is a typical tool for distinguishing samples. Notably, the neighborhood relation may be powerless in providing satisfactory distinguishing ability. In view of this, the supervised neighborhood based attribute reduction has been explored. However, the supervised neighborhood based reduct may be lack of universality. To file such gap, an ensemble strategy for computing supervised neighborhood based reduct is proposed in our paper. Such ensemble strategy is realized through considering the requirement of each decision class. The experimental results on 8 UCI data sets show that the supervised neighborhood based ensemble strategy can generate reduct not only with higher generalization performance but also with higher stability. © 2020 IEEE.

关键词： Machine learning Tools Cybernetics

来源：评论

学校读者我要写书评

暂无评论

BCTCP:A Feedback-Based Congestion Control Method

引用

China Communications 2020年第6期17卷 13-25页

作者： Yuyu Zhao Guang Cheng Weici Zhang Xin Chen Jin Li School of Cyber Science&Engineering Southeast UniversityNanjing 211189China Key Laboratory of Computer Network and Information Integration of Ministry of Education Southeast UniversityNanjing 211189China Key Laboratory of Computer Network Technology of Jiangsu Province China Huawei Technologies Co. Ltd.No 101Software AvenueNanjing 211189China

Delay and throughput are the two network indicators that users most care *** congestion control methods try to occupy buffer aggressively until packet loss being detected,causing high delay and *** AQM and ECN can highly reduce packet drop rate and delay,however they may also lead to low *** queue size of routers properly means a lot to congestion control *** traffic size varying around bottleneck bandwidth creates some degree of persistent queue in the router,which brings in additional delay into network unwillingly,but a corporation between sender and router can keep it under *** persistent queue not only keeps routers being fully utilized all the time,but also lower the variation of throughput and delay,achieving the balance between delay and *** this paper,we present BCTCP(Buffer Controllable TCP),a congestion control protocol based on explicit feedback from *** requires sender,receiver and routers cooperating with each other,in which senders adjust their sending rate according to the multiple bit load factor information from *** keeps queue length of bottleneck under control,leading to very good delay and utilization result,making it more applicable to complex network environments.

关键词： explicit congestion control active queue management delay variation low latency high throughput

来源：评论

学校读者我要写书评

暂无评论

Semisupervised Encrypted Traffic Identification Based on Auxiliary Classification Generative Adversarial Network

引用

computer Systems Science & Engineering 2021年第12期39卷 373-390页

作者： Jiaming Mao Mingming Zhang Mu Chen Lu Chen Fei Xia Lei Fan ZiXuan Wang Wenbing Zhao State Grid Jiangsu Electric Power Co. Ltd.Information and Telecommunication BranchNanJing210003China Institute of Information and Communication Global Energy Interconnection Research InstituteState Grid Key Laboratory of Information and Network SecurityNanjing210003China Engineering Research Center of Post Big Data Technology and Application of Jiangsu Province Research and Development Center of Post Industry Technology of the State Posts Bureau(Internet of Things Technology)Broadband Wireless Communication Technology Engineering Research Center of the Ministry of EducationNanjing University of Posts and TelecommunicationsNanjing210003China Department of Electrical Engineering and Computer Science Cleveland State UniversityCleveland44115USA

The rapidly increasing popularity of mobile devices has changed the methods with which people access various network services and increased net-work traffic *** the past few decades,network traffic identification has been a research hotspot in the field of network management and security ***,as more network services use encryption technology,network traffic identification faces many *** classic machine learning methods can solve many problems that cannot be solved by port-and payload-based methods,manually extract features that are frequently updated is time-consuming and *** learning has good automatic feature learning capabilities and is an ideal method for network traffic identification,particularly encrypted traffic identification;Existing recognition methods based on deep learning primarily use supervised learning methods and rely on many labeled ***,in real scenarios,labeled samples are often difficult to *** paper adjusts the structure of the auxiliary classification generation adversarial network(ACGAN)so that it can use unlabeled samples for training,and use the wasserstein distance instead of the original cross entropy as the loss function to achieve semisupervised *** results show that the identification accuracy of ISCX and USTC data sets using the proposed method yields markedly better performance when the number of labeled samples is small compared to that of convolutional neural network(CNN)based classifier.

关键词： Encrypted traffic recognition deep learning generative adversarial network traffic classification semisupervised learning

来源：评论

学校读者我要写书评

暂无评论

Chrysanthemum Classification Method Via Multi-Stream Deep Color Space Feature Fusion

SSRN

引用

SSRN 2024年

作者： Jiang, Jian Yang, Xichen Yan, Hui Liu, Jia Chen, Yifan Mao, Zhongyuan Wang, Tianshu Key Laboratory for High Technology Research of TCM Formulae China School of Computer and Electronic Information School of Artificial Intelligence Nanjing Normal University Jiangsu Nanjing210046 China National and Local Collaborative Engineering Center of Chinese Medicinal Resources Industrialization and Formulae Innovative Medicine China Jiangsu Collaborative Innovation Center of Chinese Medicinal Resources Industrialization Nanjing University of Chinese Medicine Jiangsu Nanjing210023 China College of Artificial Intelligence and Information Technology Nanjing University of Chinese Medicine Jiangsu Nanjing210023 China Jiangsu Province Engineering Research Center of TCM Intelligence Health Service Nanjing University of Chinese Medicine Jiangsu Nanjing China

Chrysanthemum is a traditional Chinese medicinal herb which widely employed in various medical applications. And the medicinal value of different chrysanthemums is highly correlated with their classification. The existing traditional chrysanthemum classification methods have shortcomings such as time-consuming and high costs. Therefore, a novel chrysanthemum classification method based on multi-stream deep color space feature fusion is proposed. Firstly, chrysanthemum images are transformed from the RGB color space to the HSV and LAB color spaces. And the classification-aware features are extracted from the H, S, and L channels, respectively. Secondly, a multi-stream deep network is designed, which employing both 1D and 2D networks. The 1D network focus on further analyzing the features from the H, S, and L channels. And, the 2D network extracts deep classification-aware features from the original image. Thirdly, an effective feature fusion method is designed to descript the characteristics of different chrysanthemums more efficiently, which take both inter-layer interaction and inter-path interaction into consideration. Finally, all the features extracted from different streams of the network are fused to gain the deep color space feature. The performance comparisons are conducted on the dataset which contain 4276 real chrysanthemum images of 18 categories. The experimental results demonstrates the proposed method is more accuracy and stability than existing methods. © 2024, The Authors. All rights reserved.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Fuzzy Association Rules Mining based on Type-2 Fuzzy Sets over Data Stream

引用

Procedia computer Science 2022年 199卷 456-462页

作者： Jing Chen Peng Li Weiqing Fang Ning Zhou Yue Yin He Xu Hui Zheng School of Internet of Things Nanjing University of Posts and Telecommunications Nanjing 210023 China Baotou Teachers’ College of Inner Mongolia University of Science and Technology Inner Mongolia Baotou 014030 China School of Computer Science Nanjing University of Posts and Telecommunications Nanjing 210023 China Jiangsu High Technology Research Key Laboratory for Wireless Sensor Networks Jiangsu Province Nanjing 210023 China

Fuzzy set theory aims to solve the problem of mining more valuable human reasoning knowledge from quantitative databases, and to narrow the gap between computer and human understanding. Fuzzy Frequent Itemset (FFI) mining, which is very important in fuzzy association rule mining, converts quantitative values into language, and finds fuzzy frequency itemset according to the defined membership function. In the traditional fuzzy frequent pattern mining method, only the language item with the largest scalar base is considered, and the uncertainty of the membership function is not considered. At the same time, it is mainly considered for the fixed data set. This paper proposes a Fuzzy Frequent Pattern mining algorithm based on the Type-2 Fuzzy Set (T2FS) theory of the data stream. Under the T2FS theory, the data stream is dynamically divided based on the sliding window method, and the ambiguity is quickly found from the numerical data stream. In order to reduce the search space and improve over-mining, this paper designs a dynamic compressed lists structure and trees method. Under different minimum support degrees and sliding window sizes, many experiments have been carried out, and the experiments have verified the efficiency and effectiveness of the designed method in terms of running time and memory usage. The results can also contribute to exchange the information and preferences among the people who cooperate in decision-making.

关键词： Fuzzy Frequent Itemset (FFI) Fuzzy Association Rules Interval Type-2 Fuzzy Set Data Stream Sliding Window

来源：评论

学校读者我要写书评

暂无评论

Detection of Virtual Machines Based on Thread Scheduling 7th

Detection of Virtual Machines Based on Thread Scheduling

引用

7th International Conference on Artificial Intelligence and Security, ICAIS 2021

作者： Lin, Zhi Song, Yubo Wang, Junbo School of Information Science and Engineering Southeast University Nanjing211111 China Key Laboratory of Computer Network Technology of Jiangsu Province School of Cyber Science and Engineering Southeast University Nanjing211111 China Purple Mountain Laboratories Nanjing211111 China National Mobile Communications Research Laboratory Southeast University Nanjing211111 China

ISBN: (纸本)9783030786113

With the rapid development of cloud computing, virtual machines are now attracting more and more attention. Virtual machines used at malicious motivation cause enormous threats to the security of computer systems. Virtual machine detection is crucial for honeypot systems and software that provide free trials. Various strategies based on local register values affected by virtualization have been proposed. However, these strategies have a limited scope of application since they can only run natively. What’s more, the values they depend on can be modified with ease. In this paper, we propose a new remote virtual machine detection strategy applying to different types of virtual machines and different operating systems based on time difference in thread scheduling. Our main contribution is to set up a probability-based thread scheduling analysis model to describe the time difference between physical machines and virtual machines. This paper shows that the probability distribution of execution time of a piece of CPU-bound code in virtual machines has higher variance along with lower kurtosis and skewness, which make up our index system for detection. Results of Numeric simulation and real test show good agreement and provide a clear criterion for detection. In the real test all the virtual machines and 97.2% of the physical machines were identified correctly. © 2021, Springer Nature Switzerland AG.

关键词： Virtual machine

来源：评论

学校读者我要写书评

暂无评论

Optimizing multi-objective functions in fuzzy association rule mining

Optimizing multi-objective functions in fuzzy association ru...

引用

2020 IEEE/WIC/ACM International Joint Conference on Web Intelligence and Intelligent Agent technology, WI-IAT 2020

作者： Zheng, Hui Li, Peng Nanjing University of Posts and Telecommunications School of Computer Science Nanjing210023 China Jiangsu High Technology Research Key Laboratory for Wireless Sensor Networks Jiangsu Province Nanjing210023 China

ISBN: (纸本)9781665419246

Fuzzy association rule mining is a popular method to discover hidden patterns and associations in quantitative data. With fuzzy logic, fuzzy association rule mining is easier for explainable human linguistics in real-world applications. Finding a better performance of fuzzy association rules and building a more reliable model are two main challenges. Therefore, this paper aims to propose multi-objective functions based fuzzy association rule mining method. It can optimize all of the performance metrics of association rules simultaneously in each optimization step in mining fuzzy association rules. © 2020 IEEE.

关键词： Association rules

来源：评论

学校读者我要写书评

暂无评论

Multi-core Processor Performance Evaluation Model Based on DPDK Affinity Setting 6th

Multi-core Processor Performance Evaluation Model Based on D...

引用

6th International Conference on Data Science, ICDS 2019

作者： Wang, Canshuai Zhu, Wenjun Zhou, Haocheng Xu, Zhuang Li, Peng School of Computer Science Nanjing University of Posts and Telecommunications Nanjing210003 China Jiangsu High Technology Research Key Laboratory for Wireless Sensor Networks NanjingJiangsu Province210003 China

ISBN: (纸本)9789811528095

The general multi-core processor hardware platform combined with DPDK affinity binding technology can effectively reduce the performance overhead caused by CPU interrupts and inter-thread scheduling, and can achieve the performance equal to dedicated network processors. How to construct a model to analyze such processing systems is our focus. This paper combines the DPDK affinity feature on the general multi-core processor platform, establishes a fixed binding relationship between the processing thread and the processor logic core, and then analyzes the distribution features of the multi-core processor nodes after the binding relationship is determined, and builds a queuing model. Finally, the model is analyzed and performance indicators are provided. The model in this paper provides an analytical model for a general-purpose multi-core processor platform with affinity settings, and expressions for key indicators are provided for further research. © Springer Nature Singapore Pte Ltd 2020.

关键词： Queueing theory

来源：评论

学校读者我要写书评

暂无评论

Global assessment of terrestrial productivity in response to water stress

引用

Science Bulletin 2024年第15期69卷 2352-2356页

作者： Qi Liu Huadong Guo Jiahua Zhang Shijie Li Ji Li Fengmei Yao Miguel D.Mahecha Jian Peng School of Computer Engineering Jiangsu University of TechnologyChangzhou 213001China College of Earth and Planetary Sciences University of Chinese Academy of SciencesBeijing 101408China Department of Remote Sensing Helmholtz Centre for Environmental ResearchUFZLeipzig 04318Germany Remote Sensing Centre for Earth System Research Leipzig UniversityLeipzig 04103Germany Aerospace Information Research Institute Chinese Academy of SciencesBeijing 100094China Remote Sensing and Digital Earth Center School of Computer Science and TechnologyQingdao UniversityQingdao 266071China Key Laboratory of Earth Observation of Hainan Province Hainan Aerospace Information Research InstituteChinese Academy of SciencesSanya 572000China School of Geographical Sciences Nanjing University of Information Science and TechnologyNanjing 210044China Key Laboratory of Water Cycle and Related Land Surface Processes Institute of Geographic Sciences and Natural Resources ResearchChinese Academy of SciencesBeijing 100101China German Centre for Integrative Biodiversity Research(iDiv) Halle-Jena-Leipzig 04103Germany

In recent decades, climate warming has led to an increase in atmospheric water demand, a potential reduction in soil moisture and a rise in the frequency and intensity of droughts. This has intensified the effects of water stress on plants, leading to more vegetated areas experiencing water stress [1,2]. Soil moisture (SM)and vapor pressure deficit (VPD) are considered the two main factors that exert water stress on vegetation activity and terrestrial productivity, thereby affecting the global carbon cycle [3].

关键词： soil moisture terrestrial

来源：评论

学校读者我要写书评

暂无评论

Direct synthesis of large-area Al-doped graphene by chemical vapor deposition:Advancing the substitutionally doped graphene family

引用

Nano Research 2022年第2期15卷 1310-1318页

作者： Sami Ullah Yu Liu Maria Hasan Wenwen Zeng Qitao Shi Xiaoqin Yang Lei Fu Huy Q.Ta Xueyu Lian Jingyu Sun Ruizhi Yang Lijun Liu Mark H.Rummeli College of Energy Soochow Institute for Energy and Materials Innovations Soochow UniversitySuzhou 215006China Key Laboratory of Advanced Carbon Materials and Wearable Energy Technologies of Jiangsu Province Soochow UniversitySuzhou 215006China NUTECH School of Applied Sciences&Humanities and Computer Engineering Department National University of TechnologyIslamabad 42000Pakistan Centre of Polymer and Carbon Materials Polish Academy of SciencesM.Curie-Sklodowskiej 34Zabrze 41-819Poland School of Energy and Power Engineering Xian Jiaotong UniversityXian 710049China College of Chemistry and Molecular Science Wuhan UniversityWuhan 430072China Institute for Complex Materials IFW Dresden 20 Helmholtz Strasse Dresden 01069Germany Institute of Environmental Technology VSB-Technical University of Ostrava17.listopadu 15Ostrava 70833Czech Republic

Graphene doping continues to gather momentum because it enables graphene properties to be tuned,thereby affording new properties to,improve the performance of,and expand the application potential of *** can be chemically doped using various methods such as surface functionalization,hybrid composites(e.g.,nanoparticle decoration),and substitution doping,wherein C atoms are replaced by foreign ones in the graphene *** works have predicted that graphene could be substitutionally doped by aluminum(Al)atoms,which could hold promise for exciting applications,including hydrogen storage and evolution,and *** theoretical predictions suggest that Al substitutionally doped graphene(AIG)could serve as a material for gas sensors and the catalytic decomposition of undesirable ***,fabricating Al substitutionally doped graphene has proven challenging until ***,we demonstrate how controlled-flow chemical vapor deposition(CVD)implementing a simple solid precursor can yield high-quality and large-area monolayer AIG,and this synthesis is unequivocally confirmed using various characterization methods including local electron energy-loss spectroscopy(EELS).Detailed high-resolution transmission electron microscopy(HRTEM)shows numerous bonding configurations between the Al atoms and the graphene lattice,some of which are not theoretically ***,the produced AIG shows a CO_(2) capturability superior to those of other substitutionally doped graphenes.

关键词： aluminum-doped graphene single-solid precursor chemical vapor deposition carbon dioxide capture energy storage catalytic applications

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：