检索结果-内蒙古大学图书馆

Class-conditional domain adaptation for semantic segmentation

Computational Visual Media 2024年第5期10卷 1013-1030页

作者： Yue Wang Yuke Li James H.Elder Runmin Wu Huchuan Lu School of Information and Communication Engineering Dalian University of TechnologyDalian 116024China School of Computer Science Wuhan UniversityWuhan 430072China Department of Electrical Engineering and Computer Science York UniversityToronto M3J 1P3Canada Department of Computer Science the University of Hong KongHong Kong 999077China

Semantic segmentation is an important sub-task for many ***,pixel-level ground-truth labeling is costly,and there is a tendency to overfit to training data,thereby limiting the generalization *** domain adaptation can potentially address these problems by allowing systems trained on labelled datasets from the source domain(including less expensive synthetic domain)to be adapted to a novel target *** conventional approach involves automatic extraction and alignment of the representations of source and target domains *** limitation of this approach is that it tends to neglect the differences between classes:representations of certain classes can be more easily extracted and aligned between the source and target domains than others,limiting the adaptation over all ***,we address:this problem by introducing a Class-Conditional Domain Adaptation(CCDA)*** incorporates a class-conditional multi-scale discriminator and class-conditional losses for both segmentation and ***,they measure the segmentation,shift the domain in a classconditional manner,and equalize the loss over *** results demonstrate that the performance of our CCDA method matches,and in some cases,surpasses that of state-of-the-art methods.

关键词： domain adaptation generative adversarial networks semantic segmentation cityscapes

来源：评论

学校读者我要写书评

暂无评论

Fuzzy clustering for electric field characterization and its application to thunderstorm interpretability

引用

Digital Communications and Networks 2025年第2期11卷 299-307页

作者： Xu Yang Hongyan Xing Xinyuan Ji Wei Xu Witold Pedrycz School of Electronics and Information Engineering Nanjing University of Information Science and TechnologyNanjing 210044China Department of Electrical and Computer Engineering University of AlbertaEdmonton AB T6G 2R3Canada Systems Research Institute Polish Academy of Sciences00-901 WarsawPoland Department of Computer Engineering Faculty of Engineering and Natural SciencesIstinye University34010 IstanbulTurkey

Changes in the Atmospheric Electric Field Signal(AEFS)are highly correlated with weather changes,especially with thunderstorm ***,little attention has been paid to the ambiguous weather information implicit in AEFS *** this paper,a Fuzzy C-Means(FCM)clustering method is used for the first time to develop an innovative approach to characterize the weather attributes carried by ***,a time series dataset is created in the time domain using AEFS *** AEFS-based weather is evaluated according to the time-series Membership Degree(MD)changes obtained by inputting this dataset into the ***,thunderstorm intensities are reflected by the change in distance from a thunderstorm cloud point charge to an AEF ***,a matching relationship is established between the normalized distance and the thunderstorm dominant MD in the space ***,the rationality and reliability of the proposed method are verified by combining radar charts and expert *** results confirm that this method accurately characterizes the weather attributes and changes in the AEFS,and a negative distance-MD correlation is obtained for the first *** detection of thunderstorm activity by AEF from the perspective of fuzzy set technology provides a meaningful guidance for interpretable thunderstorms.

关键词： Atmospheric electric field(AEF) Thunderstorm Fuzzy C-means(FCM) Attribute

来源：评论

学校读者我要写书评

暂无评论

Next-Generation Consumer Electronics Data Auditing Scheme Toward Cloud-Edge Distributed and Resilient Machine Learning

引用

IEEE Transactions on Consumer Electronics 2024年第1期70卷 2244-2256页

作者： Li, Yi Shen, Jian Vijayakumar, Pandi Lai, Chin-Feng Sivaraman, Audithan Sharma, Pradip Kumar Nanjing University of Information Science and Technology School of Computer Science Nanjing210044 China Zhejiang Sci-Tech University School of Information Science and Engineering Hangzhou310018 China University College of Engineering Tindivanam Anna University Chennai Department of Computer Science and Engineering Tindivanam604001 India National Cheng Kung University Department of Engineering Science Tainan701 Taiwan Netaji Subhas University of Technology Department of Information Technology New Delhi110078 India University of Aberdeen Department of Computing Science AberdeenAB24 3UE United Kingdom

Distributed and resilient machine learning (DRML) endues next-generation consumer electronics with AI function. Intuitively, AI provides innovative, humanized, convenient applications based on the data extended by next-generation consumer electronics. Cloud-edge computing is an ideal undertaken architecture of DRML due to its distributed property. However, as one of the core elements driving AI applications, data could be lost or corrupted owing to damaged electronics, unstable communication, and even cloud providers' malicious behavior. It is essential to ensure the data integrity of next-generation electronics before AI applications. To this end, we proposed a privacy-protection distributed data auditing scheme for cloud-edge DRML. An efficient data integrity verification method that only uses algebraic operation is constructed. Then, Function Secret Share (FSS) extends the data integrity verification method to protect consumer privacy. Besides, a consensus for data auditing results is designed among the edge servers. Finally, we present an abundance of theoretical analyses and experimental findings to substantiate and validate the efficiency and effectiveness of our proposed scheme. © 1975-2011 IEEE.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

computer Vision and Deep Learning-enabled Weed Detection Model for Precision Agriculture

引用

computer Systems science & engineering 2023年第3期44卷 2759-2774页

作者： R.Punithavathi A.Delphin Carolina Rani K.R.Sughashinir Chinnarao Kurangit M.Nirmala Hasmath Farhana Thariq Ahmed S.P.Balamurugan Department of Information Technology M.Kumarasamy College of EngineeringKarur6391 I3India Department of Computer Science and Engineering K.Ramakrishnan College of TechnologyTiruchirapalli621112India Department of Electronics and Instrumentation Easwani Engineering CollegeTamil Nadu600089India Pondichery University Puducherry605014India Department of computer science and engineering The Oxford college of EngineeringBangalore560068India Department of Computer Science Engineering Saveetha School of EngineeringSaveetha Institute of Medical and Technical SciencesSaveetha UniversityChennai602105India Department of Computer and Information Science Faculty of ScienceAnnamalai University Chidambaram608002India

Presently,precision agriculture processes like plant disease,crop yield prediction,species recognition,weed detection,and irrigation can be accom-plished by the use of computer vision(CV)*** plays a vital role in influencing crop *** wastage and pollution of farmland's natural atmosphere instigated by full coverage chemical herbicide spraying are *** the proper identification of weeds from crops helps to reduce the usage of herbicide and improve productivity,this study presents a novel computer vision and deep learning based weed detection and classification(CVDL-WDC)model for precision *** proposed CVDL-WDC technique intends to prop-erly discriminate the plants as well as *** proposed CVDL-WDC technique involves two processes namely multiscale Faster RCNN based object detection and optimal extreme learning machine(ELM)based weed *** parameters of the ELM model are optimally adjusted by the use of farmland fertility optimization(FFO)algorithm.A comprehensive simulation analysis of the CVDL-WDC technique against benchmark dataset reported the enhanced out-comes over its recent approaches interms of several measures.

关键词： Precision agriculture smart farming weed detection computer vision deep learning

来源：评论

学校读者我要写书评

暂无评论

An integrated strategy of AEF attribute evaluation for reliable thunderstorm detection

引用

Digital Communications and Networks 2025年第1期11卷 234-245页

作者： Xu Yang Hongyan Xing Xinyuan Ji Xin Su Witold Pedrycz School of Electronics and Information Engineering Nanjing University of Information Science and TechnologyNanjing 210044China Department of Electrical and Computer Engineering University of AlbertaEdmonton AB T6G 2R3Canada College of Internet of Things Engineering Hohai UniversityChangzhou 213022China Systems Research Institute Polish Academy of Sciences00-901 WarsawPoland Department of Computer Engineering Faculty of Engineering and Natural SciencesIstinye UniversitySariyer/IstanbulTurkey

Thunderstorm detection based on the Atmospheric Electric Field(AEF)has evolved from time-domain models to space-domain *** is especially important to evaluate and determine the particularly Weather Attribute(WA),which is directly related to the detection reliability and *** this paper,a strategy is proposed to integrate three currently competitive WA's evaluation ***,a conventional evaluation method based on AEF statistical indicators is *** evaluation approaches include competing AEF-based predicted value intervals,and AEF classification based on fuzzy *** AEF attributes contribute to a more accurate AEF classification to different *** resulting dynamic weighting applied to these attributes improves the classification *** evaluation method is applied to evaluate the WA of a particular AEF,to obtain the corresponding evaluation *** integration in the proposed strategy takes the form of a score *** cumulative score levels correspond to different final WA *** imaging is performed to visualize thunderstorm activities using those AEFs already evaluated to exhibit thunderstorm *** results confirm that the proposed strategy effectively and reliably images thunderstorms,with a 100%accuracy of WA *** is the first study to design an integrated thunderstorm detection strategy from a new perspective of WA evaluation,which provides promising solutions for a more reliable and flexible thunderstorm detection.

关键词： Atmospheric electric field(AEF) Thunderstorm Attribute Fuzzy c-means Imaging

来源：评论

学校读者我要写书评

暂无评论

Multi-domain feature-enhanced attribute updater for generalized zero-shot learning

引用

Neural Computing and Applications 2025年第14期37卷 8397-8414页

作者： Shi, Yuyan Jiang, Chenyi Song, Feifan Ye, Qiaolin Long, Yang Zhang, Haofeng School of Computer Science and Engineering Nanjing University of Science and Technology Jiangsu Nanjing210094 China School of Information Science and Technology Nanjing Forestry University Jiangsu Nanjing210037 China Department of Computer Science Durham University DurhamDH1 3LE United Kingdom

The goal of generalized zero-shot learning (GZSL) is to transfer knowledge from seen classes to unseen classes. However, a significant challenge is the single-category attributes are often inadequate to capture the intra-class variability of diverse image samples. During training, the model tends to cluster samples of seen categories based solely on semantic descriptions, overlooking subtle yet important visual differences. To address these challenges, this paper introduces an instance-level attribute updating method, termed as multi-domain feature-enhanced attribute updater (MDAU), which establishes a one-to-one alignment between visual and semantic by obtaining multiple instance-level attributes that closely correspond to the natural intra-class distribution of the image, in contrast to the many-to-one alignment typically used in traditional GZSL approaches. Specifically, we initially compute feature weights for each individual image, and then, the visual information is incorporated as conditions to facilitate the personalized updating of class attributes. We evaluate our model on three benchmark datasets, the results show that our model can achieve the state-of-the-art performance and detailed analysis also illustrates the effectiveness of each proposed module. Code is available at https://***/S-Silvia/MDAU. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Resource Allocation in Quantum-Key-Distribution Optical Data Center Networks

引用

Journal of Lightwave Technology 2025年第11期43卷 5086-5099页

作者： Chen, Bowen Ma, Weike He, Bin Chen, Hong Min, Jiang Shao, Weidong Gao, Mingyi Peng, Limei Ho, Pin-Han Jue, Jason P. Soochow University School of Electronic and Information Engineering Suzhou215006 China Kyungpook National University Department of Computer Science Daegu Korea Republic of University of Waterloo Department of Electrical and Computer Engineering WaterlooONN2L 3G1 Canada The University of Texas at Dallas Erik Jonsson School of Engineering and Computer Science RichardsonTX75080 United States

The paper investigates quantum key resource allocation in quantum-key-distribution optical data center networks (QKD-ODCNs). A novel framework of priority queue with multiple security levels is first proposed to achieve a multi-class networking environment with adaptive security level classification. Accordingly, a novel integer linear programming (ILP) model is developed for the quantum key resource allocation (QKRA) process. To overcome the high computation complexity in solving the ILP, two heuristic approaches are developed, namely QKRA with adaptive strong security level (QKRA-ASSL) and QKRA with adaptive weak security level (QKRA-AWSL), respectively, aiming to achieve as close performance to that by the ILP model as possible in terms of success rate of connection request and network security level. The simulation results verify that the proposed QKRA-ASSL and QKRA-AWSL approaches not only maximize the network security score, but also improve the timeslot resource utilization without compromising the establishment success rate of connection request. © 1983-2012 IEEE.

关键词： Data centers

来源：评论

学校读者我要写书评

暂无评论

AFuNet: an attention-based fusion network to classify texts in a resource-constrained language

引用

Neural Computing and Applications 2025年第9期37卷 6725-6748页

作者： Hossain, Md. Rajib Hoque, Mohammed Moshiul Dewan, M. Ali Akber Hoque, Enamul Siddique, Nazmul Department of Computer Science & Engineering Chittagong University of Engineering & Technology Chittagong4349 Bangladesh School of Computing and Information Systems Faculty of Science and Technology Athabasca University AthabascaABT9S 3A3 Canada School of Information Technology York University TorontoONM3J 1P3 Canada School of Computing Engineering and Intelligent Systems Ulster University Coleraine United Kingdom

In the era of widespread Internet use and extensive social media interaction, the digital realm is accumulating vast amounts of unstructured text data. This unstructured data often contain undesirable information, necessitating time-consuming manual classification efforts. An intelligent text classification system capable of automatically categorizing digitized texts based on semantic meaning is crucial. However, this task is particularly challenging for low-resource languages like Bengali due to a shortage of annotated corpora, issues with out-of-vocabulary words, lack of domain-specific hyperparameter tuning, limited ability to extract generalized text features, and class imbalances within the corpus. AFuNet: an attention-based fusion network to classify texts in a resource-constrained language. AFuNet undergoes a comprehensive four-phase experimental process, including baseline model evaluation and hyperparameter tuning, late fusion and model selection, attention-based early fusion and model identification, and an ablation study with impact analysis. Fine-tuned based on five Bengali text classification corpora, AFuNet achieves impressive accuracies: 96.60 ± 0.2 (BTCC11), 85.37 ± 0.2 (OSBC), 97.35 ± 0.2 (BARD), 93.74 ± 0.2 (IndicNLP), and 96.51 ± 0.2 (ProthomAlo). In comparison with previous state-of-the-art models on these corpora, AFuNet demonstrates significant accuracy improvements ranging from 0.54% to 4.49%, showcasing its effectiveness in advancing text classification capabilities for the Bengali language. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

The Low-Attenuation Endfire Leaky-Wave State on an Optically Transparent Lossy Film

引用

engineering 2024年第12期43卷 72-80页

作者： Ziheng Zhou Yongjian Zhang Yilin Zheng Ke Chen Yueming Gao Yuehe Ge Yue Li Yijun Feng Zhizhang(David)Chen College of Physics and Information Engineering Fuzhou UniversityFuzhou 350108China Department of Electronic Engineering Tsinghua UniversityBeijing 100084China School of Electronic and Information Engineering Soochow UniversitySoochow 215006China School of Electronic Science and Engineering Nanjing UniversityNanjing 210023China Department of Electrical and Computer Engineering Dalhousie UniversityHalifaxNS B3H 4R2Canada

The development of high-performance optically transparent radio frequency(RF)radiators is limited by the intrinsic loss issue of transparent conductive films(TCFs).Instead of pursuing expensive endeavors to improve the TCFs'electrical properties,this study introduces an innovative approach that leverages leaky-wave mode manipulation to mitigate the TCFs'attenuating effect and maximize the RF *** finding reveals that the precise control of the mode confinement on glass-coated TCFs can create a low-attenuation window for leaky-wave propagation,where the total attenuation caused by TCF dissipation and wave leakage is effectively *** observed low-attenuation leaky-wave state on lossy TCFs originates from the delicate balance between wave leakage and TCF dissipation,attained at a particular glass cladding *** leveraging the substantially extended radiation aperture achieved under suppressed wave attenuation,this study develops an optically transparent antenna with an enhanced endfire realized gain exceeding 15 dBi and a radiation efficiency of 66%,which is validated to offer competitive transmission performance for advancing ubiquitous wireless communication and sensing applications.

关键词： Antennas Endfire radiation Low attenuation Material losses Transparent conductive films

来源：评论

学校读者我要写书评

暂无评论

Quantum-Assisted activation for supervised learning in healthcare-based intrusion detection systems

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第3期5卷 977-984页

作者： Laxminarayana, Nikhil Mishra, Nimish Tiwari, Prayag Garg, Sahil Behera, Bikash K. Farouk, Ahmed Department of Electronics and Communications Engineering Indian Institute of Information Technology West Bengal 741235 India Department of Computer Science and Engineering Indian Institute of Information Technology West Bengal 741235 India Department of Computer Science Aalto University Espoo02150 Finland Ecole de Technologie Superieure MontrealQCH3C 1K3 Canada Pvt. Ltd. WB Mohanpur741246 India Department of Computer Science Faculty of Computers and Artificial Intelligence South Valley University Hurghada83523 Egypt

Intrusion detection systems (IDSs) are amongst the most important automated defense mechanisms in modern industry. It is guarding against many attack vectors, especially in healthcare, where sensitive information (patients medical history, prescriptions, electronic health records, medical bills/debts, and many other sensitive data points) is open to compromise from adversaries. In the big data era, classical machine learning has been applied to train IDS. However, classical IDS tend to be complex: either using several hidden layers susceptible to overfitting on training data or using overly complex architectures such as convolutional neural networks, long-short term memory systems, and recurrent neural networks. This article explored the combination of principles of quantum mechanics and neural networks to train IDS. A hybrid classical-quantum neural architecture is proposed with a quantum-Assisted activation function that successfully captures patterns in the dataset while having less architectural memory footprint than classical solutions. The experimental results are demonstrated on the popular KDD99 dataset while comparing our solution to other classical models. Impact Statement Intrusion detection systems are dynamic defenses against network breach attacks. Lately, machine learning has been leveraged to perform automated intrusion detection. However, classical machine learning needs a large amount of data and overly complex architectures to "learn" patterns from data. In this work, we leverage machine learning concepts to derive a novel quantum activation function that greatly simplifies neural architectural complexity while achieving same level of accuracy and performance. Our architecture is much simpler than state-ofthe-Art based classical systems, simpler to train, and easy to handle. © 2024 Institute of Electrical and Electronics Engineers Inc.. All rights reserved.

关键词： Network architecture

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：