检索结果-内蒙古大学图书馆

22nd IEEE International Conference on Industrial Informatics, INDIN 2024

作者： Cao, Weipeng Yao, Xuyang Xu, Zhiwu Pan, Yinghui Sun, Yixuan Li, Dachuan Qiu, Bohua Wei, Muheng Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China College of Computer Science and Software Engineering Shenzhen University Shenzhen China Stony Brook University New York United States Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology Shenzhen China Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China ZhenDui Industry Artificial Intelligence Co. Ltd Shenzhen China Department of Automation Shanghai Jiao Tong University Shanghai China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai China

ISBN: (纸本)9798331527471

Realizing Generalized Zero-Shot Learning (GZSL) based on large models is emerging as a prevailing trend. However, most existing methods merely regard large models as black boxes, solely leveraging the features output by the final layer while disregarding potential performance enhancements from other layers. Indeed, numerous researchers have visually depicted variations in the features learned across different layers of neural networks. Motivated by this observation, we propose a Vision Transformer (ViT)-based GZSL method named Depth-Aware Multi-Modal ViT (DAM2ViT), which exploits multi-level features of ViT. DAM2ViT incorporates a multi-modal interaction block to align semantic information of categories across multiple layers, thereby augmenting the model’s capacity to learn associations between visual and semantic spaces. Extensive experiments conducted on three benchmark datasets (i.e., CUB, SUN, AWA2) have showcased that DAM2ViT achieves competitive results compared to state-of-the-art methods. © 2024 IEEE.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

AI-Based Child Care Parental Control System

AI-Based Child Care Parental Control System

引用

Advancements in Computing (ICAC), International Conference on

作者： Udara Jayasekara Hansindu Maniyangama Kalhan Vithana Tharana Weerasinghe Janaka Wijekoon Rrubaa Panchendrarajan Department of Computer Science and Software Engineering Sri Lanka Institute of Information Technology Sri Lanka Department of Computer System Engineering Sri Lanka Institute of Information Technology Sri Lanka

ISBN: (纸本)9798350398106

Due to the prevalence of the COVID-19 epidemic around the globe, children were compelled to engage in remote learning through online platforms, hence mobile phone has become one of their predominant devices. Mobile device with Internet access offers a major outlet for education, entertainment, and social connection, but this combination can lead to several significant bad sequences such as online exploitation, harmful addictions, and other negative impacts of online social networking. To address harmful effects, parental controls are becoming more crucial, yet Sri Lankan parents are less aware of this. Consequently, this study proposes a parental control system to monitor their child’s activities. Android, Microsoft Azure, Java, Python, OpenCV, MySQL, and FastAPI are among the most prominent technologies utilized in the proposed application’s development. The suggested approach focuses primarily on the Sri Lankan context and aims to enhance parental digital literacy while safeguarding children from cyber threats. Yielded results showed the proposed mobile application for the identification of toxic words, drugs & alcohol content, game character images, and Instagram Sinhala comments severity as 94%, 95%, 97%, and 55% respectively in controlled experiments.

关键词： Pediatrics Social networking (online) Multimedia Web sites Process control Control systems Real-time systems Mobile applications

来源：评论

学校读者我要写书评

暂无评论

Geometric structure and transversal logic of quantum Reed–Muller codes

arXiv

引用

arXiv 2024年

作者： Barg, Alexander Coble, Nolan J. Hangleiter, Dominik Kang, Christopher Joint Center for Quantum Information and Computer Science University of Maryland & NIST United States Institute for Systems Research Department of Electrical & Computer Engineering University of Maryland United States Department of Computer Science University of Maryland College Park United States Simons Institute for the Theory of Computing University of California at Berkeley United States Department of Computer Science University of Chicago United States

Designing efficient and noise-tolerant quantum computation protocols generally begins with an understanding of quantum error-correcting codes and their native logical operations. The simplest class of native operations are transversal gates, which are naturally fault-tolerant. In this paper, we aim to characterize the transversal gates of quantum Reed–Muller (RM) codes by exploiting the well-studied properties of their classical counterparts. We start our work by establishing a new geometric characterization of quantum RM codes via the Boolean hypercube and its associated subcube complex. More specifically, a set of stabilizer generators for a quantum RM code can be described via transversal X and Z operators acting on subcubes of particular dimensions. This characterization leads us to define subcube operators composed of single-qubit π/2k Z-rotations that act on subcubes of given dimensions. We first characterize the action of subcube operators on the code space: depending on the dimension of the subcube, these operators either (1) act as a logical identity on the code space, (2) implement non-trivial logic, or (3) rotate a state away from the code space. Second, and more remarkably, we uncover that the logic implemented by these operators corresponds to circuits of multi-controlled-Z gates that have an explicit and simple combinatorial description. Overall, this suite of results yields a comprehensive understanding of a class of natural transversal operators for quantum RM codes. Copyright © 2024, The Authors. All rights reserved.

关键词： Quantum computers

来源：评论

学校读者我要写书评

暂无评论

FedKD-hybrid: Federated Hybrid Knowledge Distillation for Lithography Hotspot Detection

arXiv

引用

arXiv 2025年

作者： Li, Yuqi Lin, Xingyou Zhang, Kai Yang, Chuanguang Guo, Zhongliang Gou, Jianping Li, Yanli Institute of Computing Technology Chinese Academy of Sciences China College of Information Engineering Sichuan Agricultural University China Shenzhen University of Advanced Technology China School of Computer Science University of St Andrews United Kingdom College of Computer and Information Science College of Software Southwest University China School of Artificial Intelligence and Computer Science Nantong University China The School of Electrical and Computer Engineering The University of Sydney Australia

Federated Learning (FL) provides novel solutions for machine learning (ML)-based lithography hotspot detection (LHD) under distributed privacy-preserving settings. Currently, two research pipelines have been investigated to aggregate local models and achieve global consensus, including parameter/non-parameter based (also known as knowledge distillation, namely KD). While these two kinds of methods show effectiveness in specific scenarios, we note they have not fully utilized and transferred the information learned, leaving the potential of FL-based LDH remains unexplored. Thus, we propose FedKD-hybrid in this study to mitigate the research gap. Specifically, FedKD-hybrid clients agree on several identical layers across all participants and a public dataset for achieving global consensus. During training, the trained local model will be evaluated on the public dataset, and the generated logits will be uploaded along with the identical layer parameters. The aggregated information is consequently used to update local models via the public dataset as a medium. We compare our proposed FedKD-hybrid with several state-of-the-art (SOTA) FL methods under ICCAD-2012 and FAB (real-world collected) datasets with different settings;the experimental results demonstrate the superior performance of the FedKD-hybrid algorithm. Our code is available at https://***/itsnotacie/NN-FedKD-hybrid. © 2025, CC BY-NC-ND.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Lightweight Strip Steel Surface Defect Detection Algorithm Based on YOLOv8s 3

Lightweight Strip Steel Surface Defect Detection Algorithm B...

引用

3rd International Conference on Image Processing, computer Vision and Machine Learning, ICICML 2024

作者： Feng, Zhining Sun, Shibao Shi, Nianfeng Wang, Guoqiang Henan University of Science and Technology School of Information Engineering Luoyang China Henan University of Science and Technology School of Software Luoyang China Henan Key Laboratory of Green Building Materials Manufacturing and Intelligent Equipment School of Computer Information Engineering Luoyang Institute of Science and Technology Luoyang China

ISBN: (纸本)9798350355413

To address the issues of low accuracy, high number of parameters and computational cost in strip steel surface defect detection algorithms, a lightweight strip steel surface defect detection algorithm based on YOLOv8s is proposed. Initially, the Cross-stage Focused Linear Attention (C2F-FLA) module is introduced to enhance the feature extraction capability of the backbone network. Subsequently, to improve the capture of multi-scale defect contours and reduce the model's parameters and computational complexity, a Wavelet Convolution-Bidirectional Weighted Feature Pyramid Network (WT-BiFPN) is employed in the model's Neck section for adaptive fusion of features at different resolutions. Finally, Haar Wavelet Downsampling (HWD) is utilized to retain more defect-related information, further reducing the parameters and computational complexity. The proposed method was validated on the NEU-DET dataset, and the results demonstrate that compared to YOLOv8s, this approach achieves a 4.1% increase in mAP, a 44.4% reduction in parameters, and a 32.8% decrease in computational complexity. The method ensures lightweight implementation while improving detection accuracy, offering more possibilities for defect detection on edge terminal devices. © 2024 IEEE.

关键词： NP-hard

来源：评论

学校读者我要写书评

暂无评论

Lightweight Strip Steel Surface Defect Detection Algorithm Based on YOLOv8s

Lightweight Strip Steel Surface Defect Detection Algorithm B...

引用

Image Processing, computer Vision and Machine Learning (ICICML), International Conference on

作者： Zhining Feng Shibao Sun Nianfeng Shi Guoqiang Wang School of Information Engineering Henan University of Science and Technology Luoyang China School of Software Henan University of Science and Technology Luoyang China School of Computer and Information Engineering Luoyang Institute of Science and Technology Henan Key Laboratory of Green Building Materials Manufacturing and Intelligent Equipment Luoyang China

ISBN: (数字)9798350355413

ISBN: (纸本)9798350355420

To address the issues of low accuracy, high number of parameters and computational cost in strip steel surface defect detection algorithms, a lightweight strip steel surface defect detection algorithm based on YOLOv8s is proposed. Initially, the Cross-stage Focused Linear Attention (C2F-FLA) module is introduced to enhance the feature extraction capability of the backbone network. Subsequently, to improve the capture of multi-scale defect contours and reduce the model’s parameters and computational complexity, a Wavelet Convolution-Bidirectional Weighted Feature Pyramid Network (WT-BiFPN) is employed in the model’s Neck section for adaptive fusion of features at different resolutions. Finally, Haar Wavelet Downsampling (HWD) is utilized to retain more defect-related information, further reducing the parameters and computational complexity. The proposed method was validated on the NEU-DET dataset, and the results demonstrate that compared to YOLOv8s, this approach achieves a 4.1% increase in mAP, a 44.4% reduction in parameters, and a 32.8% decrease in computational complexity. The method ensures lightweight implementation while improving detection accuracy, offering more possibilities for defect detection on edge terminal devices.

关键词： Strips Adaptation models Accuracy Surface waves Computational modeling Feature extraction Scattering parameters Steel Computational complexity Defect detection

来源：评论

学校读者我要写书评

暂无评论

Speech Master: Natural Language Processing and Deep Learning Approach for Automated Speech Evaluation 12

Speech Master: Natural Language Processing and Deep Learning...

引用

12th IEEE Annual information Technology, Electronics and Mobile Communication Conference, IEMCON 2021

作者： Kooragama, K.G.C.M. Jayashanka, L.R.W.D. Munasinghe, J.A. Jayawardana, K.W. Tissera, Muditha Buddhika, Thilini Sri Lanka Institue of Information Technology Department of Information Technology Malabe Sri Lanka Sri Lanka Institute of Information Technology Department of Computer Systems Engineering Malabe Sri Lanka Sri Lanka Institute of Information Technology Department of Computer Science and Software Engineering Malabe Sri Lanka

ISBN: (纸本)9781665400664

Every English speaker wishes to expertise his/her public speaking skills sharply. However, it is extremely difficult and requires a significant amount of practice and experience on an individual basis. This paper introduces a novel online tool 'Speech Master' to practice and improve public English speech delivering skills in a professional manner. Using natural language processing, machine learning, and deep learning approaches, the proposed system analyzes the user's speech in terms of content, grammatical accuracy, grammatical richness, facial expressions, and flow. The accuracy was checked by comparing actual results taken from experts with the predicted results obtained from the tool. 'Speech Master' achieves an average accuracy of more than 80% and produces a better overall result. This novel tool benefits English speakers all over the world by meeting the demand for a simple and easy-to-use solution for improving or practicing English speech delivery skills;enhancing oratory skills, boosting confidence, and delivering well-articulated speeches. © 2021 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

MEA-Defender: A Robust Watermark against Model Extraction Attack

MEA-Defender: A Robust Watermark against Model Extraction At...

引用

IEEE Symposium on Security and Privacy

作者： Peizhuo Lv Hualong Ma Kai Chen Jiachen Zhou Shengzhi Zhang Ruigang Liang Shenchen Zhu Pan Li Yingjun Zhang Institute of Information Engineering Chinese Academy of Sciences China School of Cyber Security University of Chinese Academy of Sciences China Department of Computer Science Metropolitan College Boston University USA Institute of Software Chinese Academy of Sciences China

ISBN: (数字)9798350331301

ISBN: (纸本)9798350331318

Recently, numerous highly-valuable Deep Neural Networks (DNNs) have been trained using deep learning algorithms. To protect the Intellectual Property (IP) of the original owners over such DNN models, backdoor-based watermarks have been extensively studied. However, most of such watermarks fail upon model extraction attack, which utilizes input samples to query the target model and obtains the corresponding outputs, thus training a substitute model using such input-output pairs. In this paper, we propose a novel watermark to protect IP of DNN models against model extraction, named MEA-Defender. In particular, we obtain the watermark by combining two samples from two source classes in the input domain and design a watermark loss function that makes the output domain of the watermark within that of the main task samples. Since both the input domain and the output domain of our watermark are indispensable parts of those of the main task samples, the watermark will be extracted into the stolen model along with the main task during model extraction. We conduct extensive experiments on four model extraction attacks, using five datasets and six models trained based on supervised learning and self-supervised learning algorithms. The experimental results demonstrate that MEA-Defender is highly robust against different model extraction attacks, and various watermark removal/detection approaches.

关键词： Training Symbiosis Computational modeling Supervised learning Watermarking Artificial neural networks Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning-Based Computation Rate Maximization for RIS-Aided Edge Computing in Wireless Consumer Application Networks

Deep Reinforcement Learning-Based Computation Rate Maximizat...

引用

IEEE International Conference on Consumer Electronics (ICCE)

作者： Tong Liu Dongyang Xu Tiantian Zhang Shilong Zhang Jinhua Chen Keping Yu Victor C. M. Leung Graduate School of Science and Engineering Hosei University Japan School of Information and Communications Engineering Xi'an Jiaotong University China Artificial Intelligence Research Institute Shenzhen MSU-BIT University China College of Computer Science and Software Engineering Shenzhen University China Department of Electrical and Computer Engineering The University of British Columbia Vancouver Canada

ISBN: (数字)9798331521165

ISBN: (纸本)9798331521172

The accelerated development of the Industrial Internet of Things (IoT) has significantly enhanced the computational efficiency and processing capabilities of Wireless Consumer Application Networks (WCAN). Despite these advancements, the performance of WCAN remains constrained by the inherent limitations in computational capacity and energy resources of wireless devices. To address these issues, this paper proposes a wireless powered-mobile edge computing system with Reconfigurable Intelligent Surface (RIS) assistance for WCAN, where wireless consumer devices can not only harvest energy from access point, but also offload computing tasks to edge server with the help of RIS. Aiming to maximize the system computation rate, a non-convex problem is developed and a block optimization with deep reinforcement learning (BO-DRL) scheme is proposed. First, the RIS phase shifts in the Wireless Power Transfer (WPT) stage and offloading stage are optimized using closed-form solutions and the gradient ascent algorithm, respectively. Subsequently, the offloading strategies are optimized using deep reinforcement learning, and a convex optimization algorithm is employed to obtain the time allocation for the WPT and offloading stages. Numerical results illustrate that the BO-DRL algorithm greatly enhances computation rate by 20% compared to without RIS.

关键词： Wireless communication Training Performance evaluation Wireless power transfer Reconfigurable intelligent surfaces Deep reinforcement learning Convex functions Resource management Servers Uplink

来源：评论

学校读者我要写书评

暂无评论

Bilinear-Experts Network with Self-Adaptive Sampler for Long-Tailed Visual Recognition

SSRN

引用

SSRN 2024年

作者： Wang, Qin Wang, Xizhao Big Data Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China The Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China

Long-tail distributed data hinders the practical application of state-of-the-art deep models in computer vision. Consequently, exclusive methodologies for handling the long-tailed problem are proposed, focusing on different hierarchies. For embedding hierarchy, existing works manually augment the diversity of tail-class features for specific datasets. However, prior knowledge about datasets is not always available for practical use, which brings unsatisfactory generalization ability in human fine-turned augmentation under such circumstances. To figure out this problem, we introduce a novel model named Bilinear-Experts Network (BENet) with Self-Adaptive Sampler (SAS). This model leverages model-driven perturbations to tail-class embeddings while preserving generalization capability on head classes through a designed bilinear experts system. The designed perturbations adaptively augment tail-class space and shift the class boundary away from the tail-class centers. Moreover, we surprisingly find that SAS automatically assigns more significant perturbations to specific tail classes rather than fewer-sample classes, which is against the common assumption that fewer-sample classes deserve greater attention. Also, experiments conducted across various long-tailed benchmarks validate the comparable efficacy of proposed BENet. © 2024, The Authors. All rights reserved.

关键词： Embeddings

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：