检索结果-内蒙古大学图书馆

Source-Free Unsupervised Domain Adaptation with Sample Transport Learning

Journal of computer science & Technology 2021年第3期36卷 606-616页

作者： Qing Tian Chuang Ma Feng-Yuan Zhang Shun Peng Hui Xue School of Computer and Software Nanjing University of Information Science and TechnologyNanjing 210044China Engineering Research Center of Digital Forensics Ministry of EducationNanjing University of Information Science and TechnologyNanjing 210044China School of Computer Science and Engineering Southeast UniversityNanjing 211189China

Unsupervised domain adaptation(UDA)has achieved great success in handling cross-domain machine learning *** typically benefits the model training of unlabeled target domain by leveraging knowledge from labeled source *** this purpose,the minimization of the marginal distribution divergence and conditional distribution divergence between the source and the target domain is widely adopted in existing ***,for the sake of privacy preservation,the source domain is usually not provided with training data but trained predictor(e.g.,classifier).This incurs the above studies infeasible because the marginal and conditional distributions of the source domain are *** this end,this article proposes a source-free UDA which jointly models domain adaptation and sample transport learning,namely Sample Transport Domain Adaptation(STDA).Specifically,STDA constructs the pseudo source domain according to the aggregated decision boundaries of multiple source classifiers made on the target ***,it refines the pseudo source domain by augmenting it through transporting those target samples with high confidence,and consequently generates labels for the target *** train the STDA model by performing domain adaptation with sample transport between the above steps in alternating manner,and eventually achieve knowledge adaptation to the target domain and attain confident labels for ***,evaluation results have validated effectiveness and superiority of the proposed method.

关键词： unsupervised domain adaptation domain shift sample transport pseudo source domain

来源：评论

学校读者我要写书评

暂无评论

Joint Multiple Access Based on RSMA for Integrated Satellite-Terrestrial Network

Joint Multiple Access Based on RSMA for Integrated Satellite...

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Han, Shuai Li, Zhiqiang Li, Cheng Benslimane, Abderrahim Harbin Institute of Technology School of Electronics and Information Engineering Harbin150001 China Simon Fraser University School of Engineering Science BurnabyBCV5A 1S6 Canada University of Avignon Department of Computer Science and Engineering Avignon84029 France

ISBN: (纸本)9798350351255

The integrated satellite-terrestrial network (ISTN) has attracted much interest due to its global information serviceability. Recently, rate-splitting multiple access (RSMA) has been widely investigated to achieve highly efficient access. Motivated by this, we design the joint RSMA scheme based on spectrum sharing for the downlink ISTN, where part data of terminals are shared by satellite and base station. Furthermore, the max-min rate (MMR) maximization problem is formulated, and an alternating optimization algorithm based on weighted minimum mean square error is introduced to solve the non-convex problem. Simulations show that the joint RSMA scheme has a higher MMR than baseline schemes. © 2024 IEEE.

关键词： Satellite communication systems

来源：评论

学校读者我要写书评

暂无评论

Joint Design of Probabilistic Constellation Shaping and Precoding for Multi-user VLC systems

Joint Design of Probabilistic Constellation Shaping and Prec...

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Nguyen, Thang K. Pham, Thanh V. Le, Hoang D. Nguyen, Chuyen T. Pham, Anh T. The University of Aizu Computer Communications Lab. Japan Shizuoka University Department of Mathematical and Systems Engineering Japan Hanoi University of Science & Technology School of Electrical and Electronic Engineering Viet Nam

ISBN: (纸本)9798350351255

This paper proposes a joint design of probabilistic constellation shaping (PCS) and precoding to enhance the sum-rate performance of multi-user visible light communications (VLC) broadcast channels subject to signal amplitude constraint. In the proposed design, the transmission probabilities of bipolar M-pulse amplitude modulation (M-PAM) symbols for each user and the transmit precoding matrix are jointly optimized to improve the sum-rate performance. The joint design problem is shown to be a complex non-convex problem due to the non-convexity of the objective function. To tackle the problem, the firefly algorithm (FA), a nature-inspired heuristic optimization approach, is employed to solve a local optima to the original non-convex optimization problem. The FA-based approach, however, suffers from high computational complexity. Therefore, we propose a low-complexity design based on zero-forcing (ZF) precoding, which is solved using an alternating optimization (AO) approach. Simulation results reveal that the proposed joint design with PCS significantly improves the sum-rate performance compared to the conventional design with uniform signaling. Some insights into the optimal symbol distributions of the two joint design approaches are also provided. © 2024 IEEE.

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

IHDNA: Identical Hybrid Deep Neural Networks for Alzheimer's Detection using MRI Dataset 3

IHDNA: Identical Hybrid Deep Neural Networks for Alzheimer's...

引用

3rd International Conference on Intelligent Communication and Computational Techniques, ICCT 2023

作者： Singh, Adwitiya Pratap Upadhyay, Nisarg Shankar, Venkatesh Gauri Devi, Bali School of Information Technology Manipal University Jaipur Jaipur Rajasthan India School of Computer Science and Engineering Manipal University Jaipur Jaipur Rajasthan India

ISBN: (纸本)9781665453578

It has been ascertained in recent studies that AD (Alzheimer's disease, a neurodegenerative disorder) and its earlier stages can be detected by neuroimaging biomarkers. To the prevention, previous studies have focused on volumetric asymmetry and brain atrophy. The identification of AD in its early stages has proven to be imperative, as Alzheimer's disease cannot be cured and can only slow its progression. Developing on that idea, this study aims to use the discriminative powers of a Siamese-inspired identical hybrid neural network for the task of classification between multiple stages. The proposed method uses a homemade pipeline for preprocessing and removing other unwanted components from the MRIs that might disturb the model. Registering all the MRI images to MNI space and resampling the slices helped in normalizing the whole dataset. This study uses feature-based methods to work with low-dimensional characteristics rather than high-dimensional voxel data can lessen computing cost and time spent. We used VGG-16 style net with image-net weights for the purpose of automatic feature extraction. T1-weighted MRIs were used for the research, which were accessed from the ADNI datasets ADNI2 and ADNI3. When compared to a normal DNN, our proposed identical hybrid neural network achieved better precision and F1-score. © 2023 IEEE.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Icon-to-Icon Translation using Pixel-Level Weight Adversarial Networks

Journal of Network Intelligence

引用

Journal of Network Intelligence 2022年第1期7卷 147-160页

作者： Pan, Yao-Ming Lin, Kai-Biao Chen, Chin-Ling School of Computer and Information Engineering Xiamen University of Technology Xiamen361024 China Engineering Research Center of Big Data Application in Private Health Medicine Fujian Provincial University Putian351100 China School of Information Engineering Changchun Sci-Tech University Changchun130600 China Department of Computer Science and Information Engineering Chaoyang University of Technology Taichung41349 Taiwan

We investigate image-to-image translation as a solution to icon-to-icon translation problems. Icon-to-icon translation aims to translate the input icon to appear like the target domain’s icons and simultaneously preserve the original icon’s information (e.g., application logo, text and background color). We present a novel approach to trans-lating icons to the version with the target style intelligently. By observing many icons with various styles, we propose a pixel-level weight matrix to calculating the weighted losses. These losses guide the generator to focus on the critical regions of the icon. People can clearly get the original icon’s information from the proposed method’s results, while the existing state-of-the-art image-to-image translation methods may fail to do this. © 2022, Taiwan Ubiquitous information CO LTD. All rights reserved.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Insurance Plan for Service Assurance in Cloud Computing Market with Incomplete information

引用

Journal of Communications and information Networks 2022年第1期7卷 11-22页

作者： Yanru Zhang Chunxiao Jiang Nguyen H.Tran Shengrong Bu FeiRichard Yu Zhu Han College of Computer Science and Engineering the University of Electronic Science and Technology of ChinaChengdu 611731China Shenzhen Institute for Advanced Study UESTCLonghuaShenzhen 518110China Tsinghua Space Center Tsinghua UniversityBeijing 10084China School of Computer Science the University of SydneySydneyNew South WalesAustralia Department of Engineering Brock UniversityONCanada School of Information Technology Depart.of Systems and Computer EngineeringCarleton UniversityOttawa K1S 5B6ONCanada Department of Electrical and Computer Engineering the University of HoustonHouston 77004TXUSA

Nowadays,cloud computing has been identified as new opportunities for migrating to the expected agility,reuse,and adaptive capabilities that can support the ever changing IT trends and ***,the rapid evolution of those technologies also comes with open issues such as security,privacy,integrity,quality of services,and their possible detrimental *** this work,the concept of insurance is introduced to compensate the cloud computing customers when encountering those failures if service providers(SPs)have insurance ***,we consider the situation when the insurer is unable to see the system failure risk levels of the SPs,which is usually seen as an incomplete information market,in contrast with the optimal situation in a complete information ***,an insurance-based cloud computing architecture is proposed to build a monetary credit system in which the cloud computing SP pays a premium for a certain coverage to the ***,problem is formulated to solve the optimal insurance plan in complete and incomplete information markets,together with detail analysis of insurance policies in both cases are ***,simulation results show the properties of the two insurance plans and parameters that affect the design of the insurance plan.

关键词： service assurance cloud computing market incomplete information game theory insurance plan

来源：评论

学校读者我要写书评

暂无评论

Enhancement of High Angular Resolution Diffusion-Weighted Imaging Through Parallel Imaging and Motion Correction 5th

Enhancement of High Angular Resolution Diffusion-Weighted Im...

引用

5th International Conference on Data science, Machine Learning and Applications, ICDSMLA 2023

作者： Sandhya, Prajapati Sreejith, V. Alam, Intekhab Haripriya Department of Electrical Engineering School of Engineering and Computing Dev Bhoomi Uttarakhand University Manduwala Dehradun Navgaon India School of Computer Science and Engineering Presidency University Karnataka Bengaluru India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh Lucknow India Karnataka Bangalore India

ISBN: (纸本)9789819780426

Excessive Angular decision Diffusion-Weighted Imaging (HARDI) is an effective imaging modality that produces high decision pictures of fiber tracts within the brain. Reconstruction of those pictures calls for a huge quantity of computational power and reminiscence, because it acquires appreciably extra diffusion weighted photographs than the conventional diffusion-weighted imaging (DWI) strategies. It makes use of multiple receiver coils in parallel, with every coil measuring the same records set. MC improves the accuracy of HARDI reconstruction by using correcting for motion artifacts. The application of PI and MC along with HARDI allows high-decision reconstruction of fiber tracts inside the mind, with stepped forward sign-to-noise ratio and decreased test instances. When used together, PI and MC also can improve the accuracy of HARDI tractography, providing extra designated records on fiber tract micros. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： measuring movement reconstruction

来源：评论

学校读者我要写书评

暂无评论

A sketch recognition method based on bi-modal model using cooperative learning paradigm

引用

Neural Computing and Applications 2024年第23期36卷 14275-14290页

作者： Zhang, Shihui Wang, Lei Cui, Zhiguo Wang, Shi School of Information Science and Engineering Yanshan University Hebei Street West Section Hebei Province Qinhuangdao066000 China Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province Yanshan University Hebei Street West Section Hebei Province Qinhuangdao066000 China School of Information Technology Hebei University of Business and Economics Xuefu Road Hebei Province Shijiazhuang050061 China School of Mathematics and Information Science and Technology Hebei Normal University of Science and Technology Hebei Street West Section Hebei Province Qinhuangdao066000 China

Static image is an important form of displaying a sketch, representing the appearance information of the sketch. And a stroke sequence composed of several points can also express the shape and contour information of the sketch. Therefore, it is very reasonable to treat a sketch as point-modal data and image-modal data simultaneously. In this paper, a method based on bi-modal model using cooperative learning paradigm is proposed for the sketch recognition task. Specifically, in the point-modal branch, a structural point convolution block is developed by properly dividing local regions to preserve the structural information. In the image-modal branch, the hierarchical residual structure is used to fully extract image-modal features. To reduce the negative impact of noisy samples on the recognition performance, a cooperative learning paradigm is designed based on different perceptual abilities of two modal branches on noisy samples, that is, when training the two branches, the noisy samples can be filtered out through information exchanges and mutual learning. Extensive experiments on the sketch datasets TU-Berlin and QuickDraw show that the proposed method outperforms most baseline methods and has many advantages such as no dependence on additional data and stroke information. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Depth map cavity repair algorithm based on RGB image 8

Depth map cavity repair algorithm based on RGB image

引用

8th International Conference on Intelligent Computing and Signal Processing, ICSP 2023

作者： Sheng, Yiyang Fu, Haohai Jilin Institute of Chemical Technology School of Information and Control Engineering Jilin China School of Computer Science and Technology Changchun Institute of Technology Changchun China

ISBN: (纸本)9798350302455

The 3D reconstruction process often requires high-precision depth images. However, based on the limitations of the current depth sensor's own equipment and the influence of shootingobjects, environment and other factors, the obtained depth map often has cavities and noise. Aiming at the problem that the traditional depth map cavity repair algorithm can not take into account the cavity filling and object edge preservation, and can noteffectively use the RGB image information obtained synchronously, a cavity repair algorithm based on RGB image is proposed. The algorithm divides the cavities in the depth map into edge parts and non-edge parts by obtaining the edge information in the RGB image, and then uses different methods to repair the two parts of the cavities:For non-edge cavities, because the neighborhood depth value changes continuously, the neighborhood depth value is directly used for repair;for the cavity at the edge, due to the discontinuous change of the neighborhood depth value, the depthvalue corresponding to the pointwith the largest distance centerweight in the neighborhood is selected to repair the cavity by using the pixel points corresponding to the cavity in the RGB image and its neighborhood. The experimental results show that the algorithm makes full use of the RGB image information, which can accurately fill the depth map cavitys and effectively avoid the edge blur of the object. © 2023 IEEE.

关键词： Repair

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based Intrusion Detection Technique for IoT Security 4

Deep Learning-Based Intrusion Detection Technique for IoT Se...

引用

4th International Conference on Electrical, computer, Communications and Mechatronics engineering, ICECCME 2024

作者： Ahanger, Tariq Ahamed Aljumah, Abdullah Ullah, Imdad Prince Sattam Bin Abdulariz University Department of Management Information Systems CoBA Al-Kharj11942 Saudi Arabia College of Computer Engineering and Sciences Prince Sattam Bin Abdulaziz University Al-Kharj11942 Saudi Arabia School of Computer Science The University of Sydney Faculty of Engineering SydneyNSW2006 Australia

ISBN: (纸本)9798350391183

Numerous connected machines compose the Internet of Things (IoT) like sensors and actuators, via wired or wireless networks. The number of IoT apps, including Vehicular Ad-hoc Networks (VANETs), Healthcare, Smart communities, and Wearable have recently risen significantly. Data Protection and Security is becoming more critical as the number of IoT-linked devices grows. In this paper, we suggest a new deep learning-based intrusion detection system (DL-IDS) to identify security breaches in IoT environments to address the difficulties of protecting IoT applications. There are several IDSs developed by researchers, optimal learning and management of data set functions are neglected, which are essential problems that impact the accuracy of tracking threats. To achieve optimum detection recognition, the presented framework incorporates the SMO technique and the Deep stacked polynomial network. SMO chooses the optimal features in the data, and SDPN categorizes it as regular or vulnerable. The presented model is analyzed for performance assessment in comparison to the state-of-The-Art decision-making models. In terms of accuracy, recall, precision, and F-score, the detailed review suggests that presented technique acquires enhanced performance and is immensely efficient. © 2024 IEEE.

关键词： Network intrusion

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：