检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Xie, Kan Zhang, Zhe Li, Bo Kang, Jiawen Niyato, Dusit Xie, Shengli Wu, Yi The School of Automation Guangdong University of Technology Guangzhou510006 China The Key Laboratory of Intelligent Information Processing and System Integration of IoT Ministry of Education Guangzhou510006 China The Guangdong-HongKong-Macao Joint Laboratory for Smart Discrete Manufacturing Guangzhou510006 China The 111 Center for Intelligent Batch Manufacturing Based on IoT Technology Guangzhou510006 China The Guangdong Key Laboratory of IoT Information Technology Guangzhou510006 China The School of Data Science and Technology Heilongjiang University Harbin150080 China The Institute for Cryptology & Network Security Heilongjiang University Harbin150080 China School of Computer Science and Engineering Nanyang Technological University Singapore

With the gradual popularization of self-driving, it is becoming increasingly important for vehicles to smartly make the right driving decisions and autonomously obey traffic rules by correctly recognizing traffic signs. However, for machine learning-based traffic sign recognition on the Internet of Vehicles (IoV), a large amount of traffic sign data from distributed vehicles is needed to be gathered in a centralized server for model training, which brings serious privacy leakage risk because of traffic sign data containing lots of location privacy information. To address this issue, we first exploit privacy-preserving federated learning to perform collaborative training for accurate recognition models without sharing raw traffic sign data. Nevertheless, due to the limited computing and energy resources of most devices, it is hard for vehicles to continuously undertake complex artificial intelligence tasks. Therefore, we introduce powerful Spike Neural Networks (SNNs) into traffic sign recognition for energy-efficient and fast model training, which is the next generation of neural networks and is practical and well-fitted to IoV scenarios. Furthermore, we design a novel encoding scheme for SNNs based on neuron receptive fields to extract information from the pixel and spatial dimensions of traffic signs to achieve high-accuracy training. Numerical results indicate that the proposed federated SNN outperforms traditional federated convolutional neural networks in terms of accuracy, noise immunity, and energy efficiency as well. Copyright © 2022, The Authors. All rights reserved.

关键词： Traffic signs

来源：评论

学校读者我要写书评

暂无评论

Rate-Splitting for Cell-Free Massive MIMO: Performance Analysis and Generative AI Approach

arXiv

引用

arXiv 2024年

作者： Zheng, Jiakang Zhang, Jiayi Du, Hongyang Zhang, Ruichen Niyato, Dusit Dobre, Octavia A. Ai, Bo The School of Electronic and Information Engineering Beijing Jiaotong University Beijing100044 China The Frontiers Science Center for Smart High-speed Railway System Beijing Jiaotong University Beijing100044 China The Department of Electrical and Electronic Engineering University of Hong Kong Pok Fu Lam Hong Kong The College of Computing and Data Science Nanyang Technological University Singapore Faculty of Engineering and Applied Science Memorial University Canada The State Key Laboratory of Rail Traffic Control and Safety Beijing Jiaotong University Beijing100044 China The Frontiers Science Center for Smart High-speed Railway System China Henan Joint International Research Laboratory of Intelligent Networking and Data Analysis Zhengzhou University Zhengzhou450001 China Research Center of Networks and Communications Peng Cheng Laboratory Shenzhen China

Cell-free (CF) massive multiple-input multiple-output (MIMO) provides a ubiquitous coverage to user equipments (UEs) but it is also susceptible to interference. Rate-splitting (RS) effectively extracts data by decoding interference, yet its effectiveness is limited by the weakest UE. In this paper, we investigate an RS-based CF massive MIMO system, which combines strengths and mitigates weaknesses of both approaches. Considering imperfect channel state information (CSI) resulting from both pilot contamination and noise, we derive a closed-form expression for the sum spectral efficiency (SE) of the RS-based CF massive MIMO system under a spatially correlated Rician channel. Moreover, we propose low-complexity heuristic algorithms based on statistical CSI for power-splitting of common messages and power-control of private messages, and genetic algorithm is adopted as a solution for upper bound performance. Furthermore, we formulate a joint optimization problem, aiming to maximize the sum SE of the RS-based CF massive MIMO system by optimizing the power-splitting factor and power-control coefficient. Importantly, we improve a generative AI (GAI) algorithm to address this complex and non-convexity problem by using a diffusion model to obtain solutions. Simulation results demonstrate its effectiveness and practicality in mitigating interference, especially in dynamic environments. Copyright © 2024, The Authors. All rights reserved.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

PointCA: Evaluating the Robustness of 3D Point Cloud Completion Models Against Adversarial Examples

arXiv

引用

arXiv 2022年

作者： Hu, Shengshan Zhang, Junwei Liu, Wei Hou, Junhui Li, Minghui Zhang, Leo Yu Jin, Hai Sun, Lichao School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Computer Science and Technology Huazhong University of Science and Technology China School of Software Engineering Huazhong University of Science and Technology China Cluster and Grid Computing Lab China National Engineering Research Center for Big Data Technology and System Hubei Engineering Research Center on Big Data Security China Hubei Key Laboratory of Distributed System Security China Services Computing Technology and System Lab China City University of Hong Kong Hong Kong Deakin University Australia Lehigh University United States

Point cloud completion, as the upstream procedure of 3D recognition and segmentation, has become an essential part of many tasks such as navigation and scene understanding. While various point cloud completion models have demonstrated their powerful capabilities, their robustness against adversarial attacks, which have been proven to be fatally malicious towards deep neural networks, remains unknown. In addition, existing attack approaches towards point cloud classifiers cannot be applied to the completion models due to different output forms and attack purposes. In order to evaluate the robustness of the completion models, we propose PointCA, the first adversarial attack against 3D point cloud completion models. PointCA can generate adversarial point clouds that maintain high similarity with the original ones, while being completed as another object with totally different semantic information. Specifically, we minimize the representation discrepancy between the adversarial example and the target point set to jointly explore the adversarial point clouds in the geometry space and the feature space. Furthermore, to launch a stealthier attack, we innovatively employ the neighbourhood density information to tailor the perturbation constraint, leading to geometry-aware and distribution-adaptive modification for each point. Extensive experiments against different premier point cloud completion networks show that PointCA can cause a performance degradation from 77.9% to 16.7%, with the structure chamfer distance kept below 0.01. We conclude that existing completion models are severely vulnerable to adversarial examples, and state-of-the-art defenses for point cloud classification will be partially invalid when applied to incomplete and uneven point cloud data. Copyright © 2022, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

High Performance Solar-Blind Photodetectors Based on Plasma-Enhanced Atomic Layer Deposition of Thin Ga2o3 Films Annealed Under Different Atmosphere

SSRN

引用

SSRN 2022年

作者： Chen, Yu-Chang Chen, Ding-Bo Zeng, Guang Li, Xiao-Xi Li, Yu-Chun Zhao, Xue-Feng Chen, Na Wang, Ting-Yun Zhang, David Wei Lu, Hong-Liang State Key Laboratory of ASIC and System Shanghai Institute of Intelligent Electronics & Systems School of Microelectronics Fudan University Shanghai200433 China Yiwu Research Institute of Fudan University Chengbei Road Zhejiang Yiwu City322000 China Key Laboratory of Specialty Fiber Optics and Optical Access Networks Shanghai Institute Communication and Data Science Shanghai University Shanghai200444 China

Solar-blind photodetectors (SBPDs) have attracted great interests for the potential applications as missile guidance, biological detection, and ultra-violet imaging. Despite the large number of Ga 2 O 3 -SBPDs reported, most of them with thick light absorption layers fail to achieve both high responsivity and fast response time simultaneously. In this work, high-performance SBPDs with 20 nm thick Ga 2 O 3 film were demonstrated with an extremely low dark current at 0.76 pA, a great photo-dark current ratio of 10 6 , a high responsivity of 6.18 A/W, and an ultra-fast decay time ~45 ms. Moreover, the films annealed in nitrogen exhibit a more pronounced amorphous-to-polycrystalline transition, while the samples after oxygen annealing show a lower recrystallization and less oxygen vacancy concentration. This finding opens up the pathways and provide an alternative strategy towards developing the high photoresponse performance required for future applications using solar-blind detection. © 2022, The Authors. All rights reserved.

关键词： Atomic layer deposition

来源：评论

学校读者我要写书评

暂无评论

Dual-Channel Recalibration and Feature Fusion Method for Liver Image Classification 17th

Dual-Channel Recalibration and Feature Fusion Method for Liv...

引用

17th International Conference on intelligent Computing, ICIC 2021

作者： Niu, Tingting Zhang, Xiaolong Deng, Chunhua Chen, Ruoqin School of Computer Science and Technology Wuhan University of Science and Technology Wuhan China Institute of Big Data Science and Engineering Wuhan University of Science and Technology Wuhan China Hubei Key Laboratory of Intelligent Information Processing and Real-Time Industrial System Wuhan University of Science and Technology Wuhan China Tianyou Hospital Wuhan University of Science and Technology Wuhan China

ISBN: (纸本)9783030845285

Aiming at the problem of poor medical image recognition accuracy caused by the large individual differences in liver pathological images and the large single feature size, a liver image classification method based on dual-channel recalibration and feature fusion is proposed. Firstly, we construct a dual-channel recalibration model based on attention mechanism, suppress useless features and calculate different feature channel weights, and embed them into the Inception_ResNet_V2 network structure. Secondly, we design fully connected layers on the basis of two-dimensional and three-dimensional convolutional neural networks, then add feature fusion layers to obtain deep semantic information in different dimensions. Finally, we use pre-training models to initialize the network structure and input the fused features into the XGBoost classifier for classification prediction. Experiments have been carried out with liver cancer race imaging datasets and a hospital patient dataset. Experimental results show that this method is superior to previous ones. © 2021, Springer Nature Switzerland AG.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

UJN-Land: A Large-Scale High-Resolution Parcel of Land of Multi-temporal dataset with CNN Based Semantic Segmentation Analysis 7th

UJN-Land: A Large-Scale High-Resolution Parcel of Land of Mu...

引用

7th International Conference on Life system Modeling and Simulation, LSMS 2021, and the 7th International Conference on intelligent Computing for Sustainable Energy and Environment, ICSEE 2021

作者： Shen, Yuan Wang, Yulin Yang, Shiyong Li, Yan Han, Shiyuan Liu, Zhen Xu, Tao School of Information Science and Engineering University of Jinan Jinan250022 China Highresolution Earth Observation System Shandong Center of Data and Application University of Jinan Jinan250022 China Shandong Provincial Key Laboratory of Network Based Intelligent Computing University of Jinan Jinan250022 China Shandong Institutes of Industrial Technonlogy Jinan250102 China Land Spatial Data and Remote Sensing Technology Institute of Shandong Province Jinan250002 China

ISBN: (纸本)9789811672125

Semantic segmentation of land in remote sensing images plays an important role in urban management and rural planning, and can provide intelligent analysis for urban development. Convolutional neural network (CNN) based methods have achieved good performance in object detection in computer vision, which benefits from the popularity of large-scale datasets. However, most of segmentation of land dataset were constructed based on various satellite images and samples that lack the number and diversity of existing datasets. These problems have brought challenges to the improvement and application of CNN based land parcel segmentation methods. This paper presented a large-scale high-resolution land dataset based on CNN analysis. More than 200,000 images of 256*256 pixels were obtained from Gaofen satellite images with a spatial resolution of 0.8 m, in which four category samples were manually annotated. In the experiment, three CNN based semantic segmentation methods were used as experimental baseline methods. The experimental results showed that the availability of the UJN-Land dataset is beneficial to the planning and management of cultivated land. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Robust Dynamic Broadcasting for Multi-Hop Wireless Networks Under Time-Varying Connectivity and Dynamic SINR

引用

IEEE Transactions on Mobile Computing 2025年

作者： Tian, Xiang Yu, Jiguo Luo, Chuanwen Yu, Dongxiao Wang, Guijuan Feng, Bin Jinan250353 China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Industrial Network and Information System Security Jinan250353 China University of Electronic Science and Technology of China School of Information and Software Engineering Chengdu610054 China Qilu University of Technology Big Data Institute Jinan250353 China Beijing Forestry University School of Information Science and Technology Beijing100083 China Shandong University School of Computer Science and Technology Shandong Qingdao266237 China Taishan University School of Information Science and Technology 271000 China

Throughput-optimal dynamic broadcasting is an essential cornerstone for the efficient operation of Multi-hop Wireless Networks (MWNs). Most existing algorithms for this problem were developed assuming static interference environments and network connectivity. However, wireless interference environments and network connectivity are inherently time-varying in real-world scenarios, primarily due to uncontrollable interference sources and unreliable links. Such time-varying characteristics make these existing algorithms less robust. In this paper, we study the robust throughput-optimal dynamic broadcasting for MWNs with multi-dimensional time-varying characteristics in terms of interference environments, network connectivity, and data arrival. We model the time-varying link existence states using a random process and characterize the time-varying interference environments through a dynamic variant of the classical Signal-to-Interference-plus-Noise-Ratio (SINR) model. In this variant, the SINR model parameters are dynamically adjusted over time by an adversary. Based on this, we first design a Robust Throughput-optimal Dynamic Broadcast (RTDB) algorithm which makes efficient slot-based max-weight link scheduling, power allocation, and data forwarding decisions in each time slot. We then prove its throughput-optimality in time-varying acyclic directed MWNs under the dynamic SINR model. The effectiveness of RTDB is validated via numerous simulations. © 2002-2012 IEEE.

关键词： Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Siamese Delta Network with Multimodality Fusion for systemic Treatment Response Prediction in Pancreatic Cancer*

Siamese Delta Network with Multimodality Fusion for Systemic...

引用

Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

作者： Peijun Hu Xiang Li Na Lu Xueli Bai Tingbo Liang Jingsong Li Research Center for Healthcare Data Science Zhejiang Laboratory Hangzhou China Department of Hepatobiliary and Pancreatic Surgery First Affiliated Hospital Zhejiang University School of Medicine Hangzhou China Zhejiang Provincial Key Laboratory of Pancreatic Disease Hangzhou China Zhejiang University Cancer Center Hangzhou China Engineering Research Center of EMR and Intelligent Expert System Ministry of Education College of Biomedical Engineering and Instrument Science Zhejiang University Hangzhou China

systemic treatment is a main way for pancreas cancer patients that are ineligible for surgery. A subgroup of patients showed good response to systemic treatment and the rest received limited benefits. CT images provide a non-invasive way to assess the treatment response. Alternative non-image methods include radiology analysis, tumor marker analysis and combination analysis. To combine the image and non-image data, we propose the Siamese Delta Network with Multimodality Fusion (SDN-MF) to predict systemic treatment response in an end-to-end way. First, a Siamese Delta Network (SDN) is designed to process pre-treatment and pre-surgery CT images and get the image feature changes to predict response. Then, patients’ characteristics from EMR and alternative analysis results forms non-image data, which is incorporated into SDN with a multimodality fusion (MF) module. The proposed SDN-MF is evaluated on a private dataset and achieves average AUC value of 0.883 with five cross-validation. Comparison among image-only, non-image-only, and fusion models verifies the superior of multimodality model in predicting systemic treatment response of pancreas cancer patients.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Hybrid RAG-empowered Multi-modal LLM for Secure data Management in Internet of Medical Things: A Diffusion-based Contract Approach

arXiv

引用

arXiv 2024年

作者： Su, Cheng Wen, Jinbo Kang, Jiawen Wang, Yonghua Su, Yuanjia Pan, Hudan Zhong, Zishao Hossain, M. Shamim School of Automation The GuangdongHongKong-Macao Joint Laboratory for Smart Discrete Manufacturing Guangdong University of Technology Guangzhou510006 China College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing210016 China School of Automation The Guangdong Basic Research Center of Excellence for Ecological Security and Green Development Key Laboratory for City Cluster Environmental Safety Green Development The Ministry of Education Guangdong University of Technology Guangzhou510006 China School of Automation The Key Laboratory of Intelligent Detection and IoT in Manufacturing Ministry of Education Guangdong University of Technology Guangzhou510006 China School of Automation Key Laboratory of Intelligent Information Processing and System Integration of IoT Ministry of Education Guangdong University of Technology Guangzhou510006 China Guangzhou University of Traditional Chinese Medicine State Key Laboratory of Traditional Chinese Medicine Syndrome The Second Affiliated Hospital of Guangzhou University of Chinese Medicine Chinese Medicine Guangdong Laboratory Hengqin 519000 China Second Affiliated Hospital of Guangzhou University of Chinese Medicine Chinese Medicine Guangdong Laboratory Hengqin 519000 China Department of Software Engineering College of Computer and Information Sciences King Saud University Riyadh12372 Saudi Arabia

Secure data management and effective data sharing have become paramount in the rapidly evolving healthcare landscape, especially with the growing integration of the Internet of Medical Things (IoMT). The rise of generative artificial intelligence has further elevated Multi-modal Large Language Models (MLLMs) as essential tools for managing and optimizing healthcare data in IoMT. MLLMs can support multi-modal inputs and generate diverse types of content by leveraging large-scale training on vast amounts of multi-modal data. However, critical challenges persist in developing medical MLLMs, including security and freshness issues of healthcare data, affecting the output quality of MLLMs. To this end, in this paper, we propose a hybrid Retrieval-Augmented Generation (RAG)-empowered medical MLLM framework for healthcare data management. This framework leverages a hierarchical cross-chain architecture to facilitate secure data training. Moreover, it enhances the output quality of MLLMs through hybrid RAG, which employs multi-modal metrics to filter various unimodal RAG results and incorporates these retrieval results as additional inputs to MLLMs. Additionally, we employ age of information to indirectly evaluate the data freshness impact of MLLMs and utilize contract theory to incentivize healthcare data holders to share their fresh data, mitigating information asymmetry during data sharing. Finally, we utilize a generative diffusion model-based deep reinforcement learning algorithm to identify the optimal contract for efficient data sharing. Numerical results demonstrate the effectiveness of the proposed schemes, which achieve secure and efficient healthcare data management. Copyright © 2024, The Authors. All rights reserved.

关键词： Information management

来源：评论

学校读者我要写书评

暂无评论

Low-Light Enhancement Effect on Classification and Detection: An Empirical Study

arXiv

引用

arXiv 2024年

作者： Wu, Xu Lai, Zhihui Jie, Zhou Gao, Can Hou, Xianxu Zhang, Ya-Nan Shen, Linlin The Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518060 China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China School of AI and Advanced Computing Xi’an Jiaotong-Liverpool University China The National Engineering Laboratory for Big Data System Computing Technology Shenzhen University SZU Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society Guangdong Shenzhen518060 China

Low-light images are commonly encountered in real-world scenarios, and numerous low-light image enhancement (LLIE) methods have been proposed to improve the visibility of these images. The primary goal of LLIE is to generate clearer images that are more visually pleasing to humans. However, the impact of LLIE methods in high-level vision tasks, such as image classification and object detection, which rely on high-quality image datasets, is not well explored. To explore the impact, we comprehensively evaluate LLIE methods on these high-level vision tasks by utilizing an empirical investigation comprising image classification and object detection experiments. The evaluation reveals a dichotomy: While Low-Light Image Enhancement (LLIE) methods enhance human visual interpretation, their effect on computer vision tasks is inconsistent and can sometimes be harmful. Our findings suggest a disconnect between image enhancement for human visual perception and for machine analysis, indicating a need for LLIE methods tailored to support high-level vision tasks effectively. This insight is crucial for the development of LLIE techniques that align with the needs of both human and machine vision. Copyright © 2024, The Authors. All rights reserved.

关键词： Machine vision

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：