检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2024年第12期5卷 6500-6508页

作者： Chen, Luefeng Cao, Wei Zheng, Biao Wu, Min Pedrycz, Witold Hirota, Kaoru China University of Geosciences School of Automation Wuhan430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China Ministry of Education Engineering Research Center of Intelligent Technology for Geo-Exploration Wuhan430074 China University of Alberta Department of Electrical and Computer Engineering EdmontonABT6G 2R3 Canada Macau University of Science and Technology Institute of Systems Engineering Taipa999078 China Istinye University Research Center of Performance and Productivity Analysis Istanbul34010 Turkey Tokyo Institute of Technology Yokohama226-8502 Japan

In the human pose estimation task, on the one hand, 3-D pose always has difficulty in dividing different 2-D poses if the view is limited;on the other hand, it is hard to reduce the lifting ambiguity because of the lack of depth information, it is an important and challenging problem. Therefore, two-stage representation refinement based on the convex combination for 3-D human pose estimation is proposed, in which the two-stage method includes a dense-spatial-temporal convolutional network and a local-to-refine network. The former is applied to determine the features between each video frame;the latter is used to get the different scales of pose details. It aims to address the difficulty of estimating 3-D human pose from 2-D image sequences. In such a way, it can better use the relations between every frame in the sequence of the pose video to produce more accurate results. Finally, we combine the above network with a block called convex combination to help refine the 3-D pose location. We test the proposed approach on both Human3.6m and MPII datasets. The result confirms that our method can achieve better performance than improved CNN supervision, a simple yet effective baseline, and coarse-to-fine volumetric prediction. Besides, a robustness test experiment is carried out for the proposed method while the input is interrupted. The result verifies that our method shows better robustness. © 2024 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Probabilistic Back-ends for Online Speaker Recognition and Clustering

arXiv

引用

arXiv 2023年

作者： Sholokhov, Alexey Kuzmin, Nikita Lee, Kong Aik Chng, Eng Siong Federal Research Center "Computer Science and Control" The Russian Academy of Sciences Moscow Russia Nanyang Technological University Singapore Institute for Infocomm Research ASTAR Singapore

This paper focuses on multi-enrollment speaker recognition which naturally occurs in the task of online speaker clustering, and studies the properties of different scoring back-ends in this scenario. First, we show that popular cosine scoring suffers from poor score calibration with a varying number of enrollment utterances. Second, we propose a simple replacement for cosine scoring based on an extremely constrained version of probabilistic linear discriminant analysis (PLDA). The proposed model improves over the cosine scoring for multi-enrollment recognition while keeping the same performance in the case of one-to-one comparisons. Finally, we consider an online speaker clustering task where each step naturally involves multi-enrollment recognition. We propose an online clustering algorithm allowing us to take benefits from the PLDA model such as the ability to handle uncertainty and better score calibration. Our experiments demonstrate the effectiveness of the proposed algorithm. Copyright © 2023, The Authors. All rights reserved.

关键词： Calibration

来源：评论

学校读者我要写书评

暂无评论

Masquerading Email Detection 8

Masquerading Email Detection

引用

8th International Conference on Information Technology and Nanotechnology, ITNT 2022

作者： Saurabh, Raman Bhasme, Sarang Balasaheb Saeed, Muhammad Salman Kumar, Chanchal Nazarov, Alexey Moscow Institute of Physics and Technology Department of Radio Engineering and Cybernetics Moscow Russia Jamia Millia Islamia Department of Computer Science New Delhi India Ciena India Pvt. Ltd Haryana India Federal Research Centre Computer Science and Control of Russian Academy of Sciences Moscow Russia

ISBN: (数字)9781665485715

ISBN: (纸本)9781665485715

The email which contains suspicious links or malicious files is one of the considerable threats in the digital world nowadays and because of these types of emails, enormous social and financial losses occur. The different approaches of detection of masquerading emails, which are already proposed, are unceasingly being renovated, the outcomes of that are not more impressive. Moreover, the masquerading email crisis is intensifying at a higher rate in the past few years. Because of the rapid increase in masquerading email threats, there is a need to develop new techniques to eliminate these types of masquerading email which is the present need of the hour. In our proposed work, the structure of the email was thoroughly analysed and then fed on recurrent convolutional neural networks. After that the Recurrent convolutional neural network model processes the email header and body of the email for detecting the suspicious or malicious files, elements and codes at character and word level of particular email;if the suspicious elements, file extension is detected then it will automatically transfer to the spam folder. For increasing the veracity of the design, the training of the model is performed with a balanced and unbalanced data set due to which improves the efficiency to distinguish between the legitimate and non-legitimate emails. Thus, the result of the experiment implies that the filtering or recognition probability of non-legitimate email is much closer to the value one, which also symbolizes that certainty of the proposed model enhances. As a result, classification of the spam and non-spam email is done by using the neural network classifier. The masquerading emails contain the suspicious links when the user clicks on the link the redirection takes place and the user reaches the suspicious website where the confidential information is asked from the user. The details shared by users results in financial and social losses. © 2022 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

A Win/Win Algorithm for the (k+1)-LST/k-Pathwidth Problem

引用

Journal of Applied and Industrial Mathematics 2021年第4期15卷 627-630页

作者： Klyuchikov, A.G. Vyalyi, M.N. Moscow Institute of Physics and Technology Moscow oblast Dolgoprudnyi141701 Russia Federal Research Center "Computer Science and Control Moscow119333 Russia National Research University "Higher School of Economics" Moscow109028 Russia

Abstract: We describe a Win/Win algorithm that produces in time polynomial in the size ofa graph G and a given parameter k either a spanning tree with at least k + 1 leaves or a path decomposition of width at mostk. T... 详细信息

关键词： Trees (mathematics)

来源：评论

学校读者我要写书评

暂无评论

Physical Layer Authentication Using Ensemble Learning Technique in Wireless Communications

引用

computers, Materials & Continua 2022年第12期73卷 4489-4499页

作者： Muhammad Waqas Shehr Bano Fatima Hassan Shanshan Tu Ghulam Abbas Ziaul Haq Abbas Engineering Research Center of Intelligent Perception and Autonomous Control Faculty of Information TechnologyBeijing University of TechnologyBeijing100124China Faculty of Computer Science and Engineering GIK Institute of Engineering Sciences and TechnologyTopi23460Pakistan School of Engineering Edith Cowan UniversityJoondalup Perth6027WA Australia Faculty of Electrical Engineering GIK Institute of Engineering Sciences and TechnologyTopi23460Pakistan

Cyber-physical wireless systems have surfaced as an important data communication and networking research *** is an emerging discipline that allows effective monitoring and efficient real-time communication between the cyber and physical worlds by embedding computer software and integrating communication and networking *** to their high reliability,sensitivity and connectivity,their security requirements are more comparable to the Internet as they are prone to various security threats such as eavesdropping,spoofing,botnets,man-in-the-middle attack,denial of service(DoS)and distributed denial of service(DDoS)and *** methods use physical layer authentication(PLA),themost promising solution to detect ***,the cyber-physical systems(CPS)have relatively large computational requirements and require more communication resources,thus making it impossible to achieve a low latency *** methods perform well but only in stationary *** have extracted the relevant features from the channel matrices using discrete wavelet transformation to improve the computational time required for data processing by considering mobile *** features are fed to ensemble learning algorithms,such as AdaBoost,LogitBoost and Gentle Boost,to classify *** authentication of the received signal is considered a binary classification *** transmitted data is labeled as legitimate information,and spoofing data is illegitimate ***,this paper proposes a threshold-free PLA approach that uses machine learning algorithms to protect critical data from spoofing *** detects the malicious data packets in stationary scenarios and detects them with high accuracy when receivers are *** proposed model achieves better performance than the existing approaches in terms of accuracy and computational time by decreasing the processing time.

关键词： Physical layer authentication machine learning cyber-physical systems security

来源：评论

学校读者我要写书评

暂无评论

Bandwidth Exploration for Spatial-Temporal Kernel Density Visualizations

SSRN

引用

SSRN 2024年

作者： Yin, Hongbo Zhang, Kaiqi Yang, Donghua Gao, Hong Li, Jianzhong School of Computer Science and Technology Harbin Institute of Technology Heilongjiang Harbin150001 China Shenyang Aircraft Design and Research Institute Liaoning Shenyang110035 China School of Computer Science and Technology Zhejiang Normal University Zhejiang Jinhua321004 China Faculty of Computer Science and Control Engineering Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Guangdong Shenzhen518055 China

As an important and extensively used data visualization tool for understanding a dataset, STKDV has been extensively used in a wide range of applications, such as crime hotspot detection, traffic accident hotspot detection, and disease outbreak analysis. In order to obtain a high-quality STKDV, choosing suitable bandwidths is the most important and challenging issue. However, the best bandwidth values are usually quite subjective and depend on different applications and datasets. Domain experts usually need to iteratively generate multiple STKDVs by tuning different bandwidth values. And finaly choose the best STKDV with the most suitable bandwidths. However, the expensive computation heavily limits the bandwidth exploration for STKDVs. The computation of just one single STKDV, let alone multiple STKDVs, is quite time-consuming using existing methods. To significantly improve the efficiency of the bandwidth exploration, we propose a parallel voxel-based method named PVSI Algorithm and a data-pointbased method named SPN Algorithm. Extensive comparison experiments on four real datasets have been done, and the results demonstrate superior performance of PVSI Algorithm. PVSI Algorithm can be applied to bring near real-time computing to the bandwidth exploration for STKDVs in the shortest time. © 2024, The Authors. All rights reserved.

关键词： Visualization

来源：评论

学校读者我要写书评

暂无评论

Event-triggered leader-following formation control for multi-agent systems under communication faults: application to a fleet of unmanned aerial vehicles

引用

Journal of Systems Engineering and Electronics 2021年第5期32卷 1014-1022页

作者： VAZQUEZ TREJO Juan Antonio GUENARD Adrien ADAM-MEDINA Manuel PONSART Jean-Christophe CIARLETTA Laurent ROTONDO Damiano THEILLIOL Didier Research Center for Automatic Control of Nancy University of LorraineNancy F-54000France Electronic Engineering Department National Institute of Technology of MexicoCuernavaca Morelos 62490Mexico Lorraine Research Laboratory in Computer Science and Its Applications University of LorraineNancy F-54000France University of Stavanger Department of Electrical and Computer EngineeringStavanger 4021Norway

The main contribution of this paper is the design of an event-triggered formation control for leader-following consensus in second-order multi-agent systems(MASs)under communication *** the agents must follow the trajectories of a virtual leader despite communication faults considered as smooth time-varying delays dependent on the distance between the *** matrix inequalities(LMIs)-based conditions are obtained to synthesize a controller gain that guarantees stability of the synchronization *** on the closed-loop system,an event-triggered mechanism is designed to reduce the control law update and information exchange in order to reduce energy *** proposed approach is implemented in a real platform of a fleet of unmanned aerial vehicles(UAVs)under communication faults.A comparison between a state-of-the-art technique and the proposed technique has been provided,demonstrating the performance improvement brought by the proposed approach.

关键词： event-triggered leader-following consensus communication fault formation control unmanned aerial vehicle(UAV) experimental result

来源：评论

学校读者我要写书评

暂无评论

Probabilistic Back-ends for Online Speaker Recognition and Clustering

Probabilistic Back-ends for Online Speaker Recognition and C...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Alexey Sholokhov Nikita Kuzmin Kong Aik Lee Eng Siong Chng Federal Research Center "Computer Science and Control" of the Russian Academy of Sciences Moscow Russia Nanyang Technological University Singapore Institute for Infocomm Research A⋆STAR Singapore

关键词： Uncertainty Signal processing algorithms Clustering algorithms Signal processing Probabilistic logic Speaker recognition Calibration

来源：评论

学校读者我要写书评

暂无评论

Growing Trees and Amoebas' Replications

arXiv

引用

arXiv 2024年

作者： Gurvich, Vladimir Krnc, Matjaž Vyalyi, Mikhail National Research University Higher School of Economics Russia FAMNIT IAM University of Primorska Slovenia National Research University Higher School of Economics Moscow Institute of Physics and Technology Federal Research Center "Computer Science and Control" of the Russian Academy of Science Russia

An amoeba is a tree with a number assigned to each vertex. We describe a natural process of growing trees from a given amoeba and discuss conditions for such a process to be *** Codes 05C75, 05C05 © 2024, CC BY.

关键词： Protozoa

来源：评论

学校读者我要写书评

暂无评论

GRU-Net: Gaussian Attention Aided Dense Skip Connection Based MultiResUNet for Breast Histopathology Image Segmentation 28th

GRU-Net: Gaussian Attention Aided Dense Skip Connection Base...

引用

28th Annual Conference on Medical Image Understanding and Analysis, MIUA 2024

作者： Roy, Ayush Pramanik, Payel Ghosal, Sohom Valenkova, Daria Kaplun, Dmitrii Sarkar, Ram Department of Electrical Engineering Jadavpur University Kolkata700032 India Department of Computer Science and Engineering Jadavpur University Kolkata700032 India Department of Electronics and Communication Engineering International Institute of Information Technology Chhattisgarh India Department of Automation and Control Processes Saint Petersburg Electrotechnical University LETI Saint Petersburg Russia Artificial Intelligence Research Institute China University of Mining and Technology Xuzhou China

ISBN: (纸本)9783031669545

Breast cancer is a major global health concern. Pathologists face challenges in analyzing complex features from pathological images, which is a time-consuming and labor-intensive task. Therefore, efficient computer-based diagnostic tools are needed for early detection and treatment planning. This paper presents a modified version of MultiResU-Net for histopathology image segmentation, which is selected as the backbone for its ability to analyze and segment complex features at multiple scales and ensure effective feature flow via skip connections. The modified version also utilizes the Gaussian distribution-based Attention Module (GdAM) to incorporate histopathology-relevant text information in a Gaussian distribution. The sampled features from the Gaussian text feature-guided distribution highlight specific spatial regions based on prior knowledge. Finally, using the controlled Dense Residual Block (CDRB) on skip connections of MultiResU-Net, the information is transferred from the encoder layers to the decoder layers in a controlled manner using a scaling parameter derived from the extracted spatial features. We validate our approach on two diverse breast cancer histopathology image datasets: TNBC and MonuSeg, demonstrating superior segmentation performance compared to state-of-the-art methods. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Gaussian distribution

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：