检索结果-内蒙古大学图书馆

Differentiable Deformation Graph-Based Neural Non-rigid Registration

Communications in Mathematics and Statistics 2023年第1期11卷 151-167页

作者： Wanquan Feng Hongrui Cai Junhui Hou Bailin Deng Juyong Zhang School of Mathematical Sciences University of Science and Technology of ChinaHefei 230026People’s Republic of China School of Data Science University of Science and Technology of ChinaHefei 230026People’s Republic of China Department of Computer Science City University of Hong KongHong KongPeople’s Republic of China School of Computer Science and Informatics Cardiff UniversityCardiffUK

The traditional pipeline for non-rigid registration is to iteratively update the correspondence and alignment such that the transformed source surface aligns well with the target *** the pipeline,the correspondence construction and iterative manner are key to the results,while existing strategies might result in local *** this paper,we adopt the widely used deformation graph-based representation,while replacing some key modules with neural learning-based ***,we design a neural network to predict the correspondence and its reliability confidence rather than the strategies like nearest neighbor search and pair ***,we adopt the GRU-based recurrent network for iterative refinement,which is more robust than the traditional *** model is trained in a self-supervised manner and thus can be used for arbitrary datasets without *** experiments demonstrate that our proposed method outperforms the state-of-the-art methods by a large margin.

关键词： Differentiable deformation graph Non-rigid registration

来源：评论

学校读者我要写书评

暂无评论

IBAttack: Being Cautious about data Labels

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2023年第6期4卷 1484-1493页

作者： Agarwal, Akshay Singh, Richa Vatsa, Mayank Ratha, Nalini IISER Bhopal Department of Data Science and Engineering Bhopal462066 India IIT Jodhpur Department of Computer Science and Engineering Rajasthan Jodhpur342037 India University at Buffalo Department of Computer Science and Electrical Engineering BuffaloNY14260 United States

Traditional backdoor attacks insert a trigger patch in the training images and associate the trigger with the targeted class label. Backdoor attacks are one of the rapidly evolving types of attack which can have a significant impact. On the other hand, adversarial perturbations have a significantly different attack mechanism from the traditional backdoor corruptions, where an imperceptible noise is learned to fool the deep learning models. In this research, we amalgamate these two concepts and propose a novel imperceptible backdoor attack, termed as the IBAttack, where the adversarial images are associated with the desired target classes. A significant advantage of the adversarial-based proposed backdoor attack is the imperceptibility as compared to the traditional trigger-based mechanism. The proposed adversarial dynamic attack, in contrast to existing attacks, is agnostic to classifiers and trigger patterns. The extensive evaluation using multiple databases and networks illustrates the effectiveness of the proposed attack. © 2020 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

A Lightweight Sparse Interaction Network for Time Series Forecasting 39

A Lightweight Sparse Interaction Network for Time Series For...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Zhang, Xu Wang, Qitong Wang, Peng Wang, Wei Shanghai Key Laboratory of Data Science School of Computer Science Fudan University Shanghai China Universite Paris Cite Paris France

ISBN: (纸本)157735897X

Recent work shows that linear models can outperform several transformer models in long-term time-series forecasting (TSF). However, instead of explicitly performing temporal interaction through self-attention, linear models implicitly perform it based on stacked MLP structures, which may be insufficient in capturing the complex temporal dependencies and their performance still has potential for improvement. To this end, we propose a Lightweight Sparse Interaction Network (LSINet) for TSF task. Inspired by the sparsity of self-attention, we propose a Multihead Sparse Interaction Mechanism (MSIM). Different from self-attention, MSIM learns the important connections between time steps through sparsity-induced Bernoulli distribution to capture temporal dependencies for TSF. The sparsity is ensured by the proposed self-adaptive regularization loss. Moreover, we observe the shareability of temporal interactions and propose to perform Shared Interaction Learning (SIL) for MSIM to further enhance efficiency and improve convergence. LSINet is a linear model comprising only MLP structures with low overhead and equipped with explicit temporal interaction mechanisms. Extensive experiments on public datasets show that LSINet achieves both higher accuracy and better efficiency than advanced linear models and transformer models in TSF tasks. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Pre-trained Models Based on Primary Sequence to Classify Antibody Binding to Protein and Non-protein Targets with 80% Accuracy 18th

Pre-trained Models Based on Primary Sequence to Classify A...

引用

18th International Conference on Computational Intelligence Methods for Bioinformatics and Biostatistics, CIBB 2023

作者： Joubbi, Sara Maccari, Giuseppe Cardamone, Dario Ciano, Giorgio Micheli, Alessio Milazzo, Paolo Medini, Duccio Department of Computer Science University of Pisa Pisa Italy Data Science for Health Lab Toscana Life Sciences Foundation Siena Italy

ISBN: (纸本)9783031907135

Monoclonal antibodies provide targeted treatment options for various diseases. In infectious diseases, techniques like reverse vaccinology 2.0 can extract potent monoclonal antibodies from human donors. However, there is no control over the specific target to which the antibody binds. Therefore, it is crucial to thoroughly understand the characteristics of the antibody sequence to extract target information and prioritize potential candidates for further in-vitro analysis. Addressing this challenge requires integrating both in-vitro and in-silico approaches. This study aims to explore machine learning algorithms and various augmentation techniques to determine whether monoclonal antibodies bind to proteins or non-protein targets solely based on their sequence. We used oversampling, SMOTE, ESM1-b, and hallucination techniques to enhance sequence information. To the best of our knowledge, this research is the first attempt to apply machine learning methodologies to this specific classification task, resulting in an accuracy rate of 80%, and an MCC of 61%. These findings pave the way for further exploration and introduce a new approach to streamline and enhance antibody development processes. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Monoclonal antibodies

来源：评论

学校读者我要写书评

暂无评论

Expression Recognition Method Based on Convolutional Neural Network and Capsule Neural Network

引用

computers, Materials & Continua 2024年第4期79卷 1659-1677页

作者： Zhanfeng Wang Lisha Yao School of Computer Science and Artificial Intelligence Chaohu UniversityHefei238000China School of Big Data and Artificial Intelligence Anhui Xinhua UniversityHefei230088China

Convolutional neural networks struggle to accurately handle changes in angles and twists in the direction of images,which affects their ability to recognize patterns based on internal feature levels. In contrast, CapsNet overcomesthese limitations by vectorizing information through increased directionality and magnitude, ensuring that spatialinformation is not overlooked. Therefore, this study proposes a novel expression recognition technique calledCAPSULE-VGG, which combines the strengths of CapsNet and convolutional neural networks. By refining andintegrating features extracted by a convolutional neural network before introducing theminto CapsNet, ourmodelenhances facial recognition capabilities. Compared to traditional neural network models, our approach offersfaster training pace, improved convergence speed, and higher accuracy rates approaching stability. Experimentalresults demonstrate that our method achieves recognition rates of 74.14% for the FER2013 expression dataset and99.85% for the CK+ expression dataset. By contrasting these findings with those obtained using conventionalexpression recognition techniques and incorporating CapsNet’s advantages, we effectively address issues associatedwith convolutional neural networks while increasing expression identification accuracy.

关键词： Expression recognition capsule neural network convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

引用

IEEE Internet of Things Journal 2025年第12期12卷 22443-22462页

作者： Li, Yangning Kang, Hui Li, Jiahui Sun, Geng Sun, Zemin Wang, Jiacheng Zhao, Changyuan Niyato, Dusit Jilin University College of Computer Science and Technology Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Changchun130012 China Nanyang Technological University College of Computing and Data Science Jurong West 639798 Singapore

An expansion of Internet of Things (IoT) has led to significant challenges in wireless data harvesting, dissemination, and energy management due to the massive volumes of data generated by IoT devices. These challenges are exacerbated by data redundancy arising from spatial and temporal correlations. To address these issues, this article proposes a novel data-driven collaborative beamforming (CB)-based communication framework for IoT networks. Specifically, the framework integrates CB with an overlap-based multihop routing protocol (OMRP) to enhance data transmission efficiency while mitigating energy consumption and addressing hot spot issues in remotely deployed IoT networks. Based on the data aggregation to a specific node by OMRP, we formulate a node selection problem for the CB stage, with the objective of optimizing uplink transmission energy consumption. Given the complexity of the problem, we introduce a softmax-based proximal policy optimization with long-shortterm memory (SoftPPO-LSTM) algorithm to intelligently select CB nodes for improving transmission efficiency. Simulation results show that the proposed OMRP improves network lifetime by 17% compared to benchmark routing protocols, while the SoftPPO-LSTM method for CB node selection achieves an 8.3% increase in throughput over benchmark algorithms. The results also reveal that the combined OMRP with the SoftPPOLSTM method effectively mitigates hot spot problems and offers superior performance compared to traditional strategies. © 2014 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Design Principle Transfer in Neural Architecture Search via Large Language Models 39

Design Principle Transfer in Neural Architecture Search via ...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Zhou, Xun Wu, Xingyu Feng, Liang Lu, Zhichao Tan, Kay Chen Department of Data Science and Artificial Intelligence The Hong Kong Polytechnic University Hong Kong College of Computer Science Chongqing University China Department of Computer Science City University of Hong Kong Hong Kong

ISBN: (纸本)157735897X

Transferable neural architecture search (TNAS) has been introduced to design efficient neural architectures for multiple tasks, to enhance the practical applicability of NAS in real-world scenarios. In TNAS, architectural knowledge accumulated in previous search processes is reused to warm up the architecture search for new tasks. However, existing TNAS methods still search in an extensive search space, necessitating the evaluation of numerous architectures. To overcome this challenge, this work proposes a novel transfer paradigm, i.e., design principle transfer. In this work, the linguistic description of various structural components’ effects on architectural performance is termed design principles. They are learned from established architectures and then can be reused to reduce the search space by discarding unpromising architectures. Searching in the refined search space can boost both the search performance and efficiency for new NAS tasks. To this end, a large language model (LLM)-assisted design principle transfer (LAPT) framework is devised. In LAPT, LLM is applied to automatically reason the design principles from a set of given architectures, and then a principle adaptation method is applied to refine these principles progressively based on the new search results. Experimental results show that LAPT can beat the state-of-the-art TNAS methods on most tasks and achieve comparable performance on others. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Design for testability

来源：评论

学校读者我要写书评

暂无评论

Prediction of three-dimensional ocean temperature in the South China Sea based on time series gridded data and a dynamic spatiotemporal graph neural network

引用

Acta Oceanologica Sinica 2024年第7期43卷 26-39页

作者： Feng Nan Zhuolin Li Jie Yu Suixiang Shi Xinrong Wu Lingyu Xu Department of Computer Engineering and Science Shanghai UniversityShanghai 200444China Key Laboratory of Digital Ocean National Marine Data and Information ServiceTianjin 300171China

Ocean temperature is an important physical variable in marine ecosystems,and ocean temperature prediction is an important research objective in ocean-related ***,one of the commonly used methods for ocean temperature prediction is based on data-driven,but research on this method is mostly limited to the sea surface,with few studies on the prediction of internal ocean *** graph neural network-based methods usually use predefined graphs or learned static graphs,which cannot capture the dynamic associations among *** this study,we propose a novel dynamic spatiotemporal graph neural network(DSTGN)to predict threedimensional ocean temperature(3D-OT),which combines static graph learning and dynamic graph learning to automatically mine two unknown dependencies between sequences based on the original 3D-OT data without prior *** and spatial dependencies in the time series were then captured using temporal and graph *** also integrated dynamic graph learning,static graph learning,graph convolution,and temporal convolution into an end-to-end framework for 3D-OT prediction using time-series grid *** this study,we conducted prediction experiments using high-resolution 3D-OT from the Copernicus global ocean physical reanalysis,with data covering the vertical variation of temperature from the sea surface to 1000 m below the sea *** compared five mainstream models that are commonly used for ocean temperature prediction,and the results showed that the method achieved the best prediction results at all prediction scales.

关键词： dynamic associations three-dimensional ocean temperature prediction graph neural network time series gridded data

来源：评论

学校读者我要写书评

暂无评论

CoMO-NAS: Core-Structures-Guided Multi-Objective Neural Architecture Search for Multi-Modal Classification 24

CoMO-NAS: Core-Structures-Guided Multi-Objective Neural Arch...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Fu, Pinhan Liang, Xinyan Qian, Yuhua Guo, Qian Wei, Zhifang Li, Wen Institute of Big Data Science and Industry Shanxi University Taiyuan China School of Computer Science and Technology Taiyuan University of Science and Technolog Taiyuan China

ISBN: (纸本)9798400706868

Most existing NAS-based multi-modal classification (MMC-NAS) methods are optimized using the classification *** can not simultaneously provide multiple models with diverse perferences such as model complex and classification performance for meeting different users' demands. Combining NAS-MMC with multi-objective optimization is a nature way for this issue. However, the challenge problem of this solution is the high computation cost. For multi-objective optimization, the computing bottleneck is pareto front search. Some higher-quality MMC models (namely core structures, CSs) consisting of high-quality features and fusion operators are easier to identify. We find that CSs have a close relation with the pareto front (PF), i.e., the individuals lying in PF contain the CSs. Based on the finding, we propose an efficient multi-objective neural architecture search for multi-modal classification by applying CSs to guide the PF search (CoMO-NAS). In conclusion, experimental results thoroughly demonstrate the effectiveness of our CoMO-NAS. Compared to state-of-the-art competitors on benchmark multi-modal tasks, we achieve comparable performance with lower model complexity in shorter search time. © 2024 ACM.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

A Neural Computing-Based Access Control Protocol for AI-Driven Intelligent Flying Vehicles in Industry 5.0-Assisted Consumer Electronics

引用

IEEE Transactions on Consumer Electronics 2024年第1期70卷 3573-3581页

作者： Mahmood, Khalid Tariq, Tayyaba Sangaiah, Arun Kumar Ghaffar, Zahid Saleem, Muhammad Asad Shamshad, Salman National Yunlin University of Science and Technology Graduate School of Intelligent Data Science Douliu64002 Taiwan National Yunlin University of Science and Technology Department of Computer Science and Information Engineering Douliu64002 Taiwan National Yunlin University of Science and Technology International Graduate School of AI Douliu64002 Taiwan Lebanese American University Department of Electrical and Computer Engineering Byblos1102 2801 Lebanon University of Electronic Science and Technology of China School of Computer Science and Engineering Sichuan Chengdu611731 China The University of Lahore Department of Software Engineering Lahore54590 Pakistan

The continuous revolution in Artificial Intelligence (AI) has played a significant role in the development of key consumer applications, including Industry 5.0, autonomous decision-making, fault diagnosis, etc. In practice, autonomous and intelligent robots and flying vehicles (i.e., drones) are also becoming the integral part of Industry 5.0. These vehicles are attaining significant importance nowadays because of their applications in consumer electronics. However, there may be numerous privacy issues in such an infrastructure. Nevertheless, neural computing-driven security solutions have played a significant role in overcoming the security and privacy issues of AI-driven intelligent flying vehicles. Motivated by these facts, this article presents a neural computing-based access control protocol for AI-driven flying vehicles to prevent all possible security threats. A detailed security evaluation of the devised protocol is done formally using the extensively recognized Real-Or-Random (ROR) oracle model. Similarly, the informal security analysis ensures the resistance of our scheme against various potential attacks under the assumptions of CK and DY adversarial models. Moreover, detailed performance scrutiny of the devised protocol with various existing schemes shows the robustness and supremacy of our scheme in terms of computation, communication overhead, and security attributes. © 1975-2011 IEEE.

关键词： Authentication

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：