检索结果-内蒙古大学图书馆

A Theory for Semantic Channel Coding With Many-to-one Source

IEEE Transactions on cognitive Communications and Networking 2025年

作者： Ma, Shuai Zhang, Chuanhui Qi, Huayan Li, Hang Bi, Yue Shi, Guangming Al-Dhahir, Naofal Peng Cheng Laboratory Shenzhen518066 China China University of Mining and Technology School of Information and Control Engineering Xuzhou221116 China Shen zhen Research Institute of Big Data Guangdong Shenzhen518172 China Shanghai Jiao Tong University School of Electronic Information and Electrical Engineering Shanghai200240 China IP Paris LTCI Telecom Paris Palaiseau91120 France Xidian University School of Artificial Intelligence Shaanxi Xi'an710071 China Pengcheng Laboratory Shenzhen518066 China University of Texas at Dallas Electrical and Computer Engineering Department RichardsonTX75080 United States

As one of the potential key technologies of 6G, semantic communication is still in its infancy and there are many open problems, such as semantic entropy definition and semantic channel coding theory. To address these challenges, we investigate semantic information measures and semantic channel coding theorem. Specifically, we propose a semantic entropy definition as the uncertainty in the semantic interpretation of random variable symbols in the context of knowledge bases, which can be transformed into existing semantic entropy definitions under given conditions. Moreover, different from traditional communications, semantic communications can achieve accurate transmission of semantic information under a non-zero bit error rate. Based on this property, we derive a semantic channel coding theorem for a typical semantic communication with many-toone source (i.e., multiple source sequences express the same meaning), and prove its achievability and converse based on a generalized Fano's inequality. Finally, numerical results verify the effectiveness of the proposed semantic entropy and semantic channel coding theorem. © 2015 IEEE.

关键词： semantic channel coding theorem Semantic communications semantic entropy

来源：评论

学校读者我要写书评

暂无评论

Artificial intelligence in gastric cancer:applications and challenges

引用

Gastroenterology Report 2022年第1期10卷 227-242页

作者： Runnan Cao Lei Tang Mengjie Fang Lianzhen Zhong Siwen Wang Lixin Gong Jiazheng Li Di Dong Jie Tian School of Artificial Intelligence University of Chinese Academy of SciencesBeijingP.R.China CAS Key Laboratory of Molecular Imaging Beijing Key Laboratory of Molecular Imagingthe State Key Laboratory of Management and Control for Complex SystemsInstitute of AutomationChinese Academy of SciencesBeijingP.R.China Key Laboratory of Carcinogenesis and Translational Research(Ministry of Education/Beijing) Radiology DepartmentPeking University Cancer Hospital&InstituteBeijingP.R.China College of Medicine and Biological Information Engineering School Northeastern UniversityShenyangLiaoningP.R.China Beijing Advanced Innovation Center for Big Data-Based Precision Medicine School of Engineering MedicineBeihang UniversityBeijingP.R.China Engineering Research Center of Molecular and Neuro Imaging of Ministry of Education School of Life Science and TechnologyXidian UniversityXi’anShaanxiP.R.China

Gastric cancer(GC)is one of the most common malignant tumors with high *** diagnosis and treatment decisions for GC rely heavily on human experts’careful judgments on medical ***,the improvement of the accuracy is hindered by imaging conditions,limited experience,objective criteria,and inter-observer ***,the developments of machine learning,especially deep-learning algorithms,have been facilitating computers to extract more information from data *** are exploring the far-reaching applications of artificial intelligence(AI)in various clinical practices,including ***,we aim to provide a broad framework to summarize current research on AI in *** the screening of GC,AI can identify precancerous diseases and assist in early cancer detection with endoscopic examination and pathological *** the diagnosis of GC,AI can support tumor-node-metastasis(TNM)staging and subtype *** treatment decisions,AI can help with surgical margin determination and prognosis ***,current approaches are challenged by data scarcity and poor *** tackle these problems,more regulated data,unified processing procedures,and advanced algorithms are urgently needed to build more accurate and robust AI models for GC.

关键词： gastric cancer artificial intelligence radiomics endoscopy computed tomography pathology

来源：评论

学校读者我要写书评

暂无评论

Hawkes processes on graphons

arXiv

引用

arXiv 2021年

作者： Xu, Hongteng Luo, Dixin Zha, Hongyuan Gaoling School of Artificial Intelligence Renmin University of China Beijing China Beijing Key Laboratory of Big Data Management and Analysis Methods Beijing China School of Computer Science and Technology Beijing Institute of Technology Beijing China School of Data Science Shenzhen Research Institute of Big Data Chinese University of Hong Kong Shenzhen China

We propose a novel framework for modeling multiple multivariate point processes, each with heterogeneous event types that share an underlying space and obey the same generative mechanism. Focusing on Hawkes processes and their variants that are associated with Granger causality graphs, our model leverages an uncountable event type space and samples the graphs with different sizes from a nonparametric model called graphon. Given those graphs, we can generate the corresponding Hawkes processes and simulate event sequences. Learning this graphon-based Hawkes process model helps to 1) infer the underlying relations shared by different Hawkes processes;and 2) simulate event sequences with different event types but similar dynamics. We learn the proposed model by minimizing the hierarchical optimal transport distance between the generated event sequences and the observed ones, leading to a novel reward-augmented maximum likelihood estimation method. We analyze the properties of our model in-depth and demonstrate its rationality and effectiveness in both theory and experiments. © 2021, CC BY.

关键词： Maximum likelihood estimation

来源：评论

学校读者我要写书评

暂无评论

Blockchain-Based Homomorphic Transaction Framework for Enhanced Consumer Security and Business Scalability

引用

IEEE Transactions on Consumer Electronics 2024年

作者： Guo, Tao Shang, Fengjun Dai, Xiangguang Liu, Qilie Chongqing University of Posts and Telecommunications School of Computer Science and Technology Chongqing400065 China Key Laboratory of Big Data Intelligent Computing Chongqing400065 China Chongqing Three Gorges University Key Lab. of Intelligent Info. Proc. and Contr. of Chongqing Munic. Institutions of Higher Education Chongqing Engineering Research Center of Internet of Things and Intelligent Control Technology School of Three Gorges Artificial Intelligence Chongqing400044 China Chongqing University of Posts and Telecommunications School of Communications and Information Engineering Chongqing400065 China

Energy trading in distributed microgrids represents an effective means of enhancing the utilization of renewable energy. However, the aggregation of large-scale consumption data may encounter business scalability issues and potential privacy exposure concerns, necessitating the development of novel secure and scalable frameworks for integrating consumption demands between prosumer and microgrid entities. we research focuses on providing a user-friendly transaction model for consumers and microgrid operators. Firstly, a privacy aggregation scheme for user resource requests is designed to ensure the security and decentralization of user data. In addition, the model employs a bidirectional heterogeneous resource allocation mechanism to support the optimal allocation of multiple resources, such as renewable energy, power assets, energy storage devices, and carbon credits, among different microgrids. Finally, a microgrid transaction prototype has been constructed on the Truffle development framework. In this context, smart contracts has been designed to ensure that the transactions are carried out automatically. Experimental results indicate that the scheme provides enhanced security for multi-resource trading in a cluster context relative to existing methodologies. The number of transactions increases linearly with the resource overhead, resulting in more efficient utilization of energy trading. Furthermore, the framework's scalability has been demonstrated through both temporal and spatial considerations. © 1975-2011 IEEE.

关键词： Decentralized finance

来源：评论

学校读者我要写书评

暂无评论

Neuromodulated Meta-Learning

arXiv

引用

arXiv 2024年

作者： Wang, Jingyao Guo, Huijie Qiang, Wenwen Li, Jiangmeng Zheng, Changwen Xiong, Hui Hua, Gang University of Chinese Academy of Sciences Beijing China National Key Laboratory of Space Integrated Information System Institute of Software Chinese Academy of Sciences Beijing China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing China Thrust of Artificial Intelligence Hong Kong University of Science and Technology Guangzhou China Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong Wormpex AI Research LLC BellevueWA98004 United States

Humans excel at adapting perceptions and actions to diverse environments, enabling efficient interaction with the external world. This adaptive capability relies on the biological nervous system (BNS), which activates different brain regions for distinct tasks. Meta-learning similarly trains machines to handle multiple tasks but relies on a fixed network structure, not as flexible as BNS. To investigate the role of flexible network structure (FNS) in meta-learning, we conduct extensive empirical and theoretical analyses, finding that model performance is tied to structure, with no universally optimal pattern across tasks. This reveals the crucial role of FNS in meta-learning, ensuring meta-learning to generate the optimal structure for each task, thereby maximizing the performance and learning efficiency of meta-learning. Motivated by this insight, we propose to define, measure, and model FNS in meta-learning. First, we define that an effective FNS should possess frugality, plasticity, and sensitivity. Then, to quantify FNS in practice, we present three measurements for these properties, collectively forming the structure constraint with theoretical supports. Building on this, we finally propose Neuromodulated Meta-Learning (NeuronML) to model FNS in meta-learning. It utilizes bi-level optimization to update both weights and structure with the structure constraint. Extensive theoretical and empirical evaluations demonstrate the effectiveness of NeuronML on various tasks. Code is publicly available at https://***/WangJingyao07/NeuronML. Copyright © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Fast localization and single-pixel imaging of the moving object using time-division multiplexing

arXiv

引用

arXiv 2022年

作者： Guo, Zijun Meng, Wenwen Shi, Dongfeng Zha, Linbin Yang, Wei Huang, Jian Chen, Yafeng Wang, Yingjian Guo, Semon Key Laboratory of Atmospheric Optics Anhui Institute of Optics and Fine Mechanics Hefei Institutes of Physical Science Chinese Academy of Sciences Hefei230031 China University of Science and Technology of China Hefei230026 China Advanced Laser Technology Laboratory of Anhui Province Hefei230037 China School of Artificial Intelligence and Big Data Hefei University Hefei230601 China

When imaging moving objects, single-pixel imaging produces motion blur. This paper proposes a new single-pixel imaging method, which can achieve anti-motion blur imaging of a fast-moving object. The geometric moment patterns and Hadamard patterns are used to alternately encode the position information and the image information of the object with time-division multiplexing. In the reconstruction process, the object position information is extracted independently and combining motion-compensation reconstruction algorithm to decouple the object motion from image information. As a result, the anti-motion blur image and the high frame rate object positions are obtained. Experimental results show that for a moving object with an angular velocity of up to 0.5rad/s relative to the imaging system, the proposed method achieves a localization frequency of 5.55kHz, and gradually reconstructs a clear image of the fast-moving object with a pseudo resolution of 512×512. The method has application prospects in single-pixel imaging of the fast-moving object. © 2022, CC BY.

关键词： Time division multiplexing

来源：评论

学校读者我要写书评

暂无评论

Fast Localization and Single-Pixel Imaging of the Moving Object Using Time-Division Multiplexing

SSRN

引用

SSRN 2022年

作者： Guo, Zijun Shi, Dongfeng Meng, Wenwen Zha, Linbin Wang, Yingjian Huang, Jian Chen, Yafeng Yang, Wei Key Laboratory of Atmospheric Optics Anhui Institute of Optics and Fine Mechanics Hefei Institutes of Physical Science Chinese Academy of Sciences Hefei230031 China University of Science and Technology of China Hefei230026 China Advanced Laser Technology Laboratory of Anhui Province Hefei230037 China School of Artificial Intelligence and Big Data Hefei University Hefei230601 China

When imaging moving objects, single-pixel imaging produces motion blur. This paper proposes a method based on single-pixel imaging, which can achieve anti-motion blur imaging of fast-moving objects. In this method, the geometric moment patterns and Hadamard patterns are used to alternately encode the position information and the image information of the object with time-division multiplexing. In the reconstruction process, the object position information is extracted independently and combining motion-compensation reconstruction algorithm to decouple the object motion from image information. As a result, the anti-motion blur image and the high frame rate object positions are obtained. Experimental results show that for a moving object with an angular velocity of up to 0.5rad/s relative to the imaging system, the proposed method achieves a localization frequency of 5.55kHz, and gradually reconstructs a clear image of the object with a pseudo resolution of 512×512. The method has application prospects in single-pixel imaging for fast-moving objects. © 2022, The Authors. All rights reserved.

关键词： Time division multiplexing

来源：评论

学校读者我要写书评

暂无评论

Federated Learning-Based Intelligent Indoor Smoke and Fire Detection System for Smart Buildings

Federated Learning-Based Intelligent Indoor Smoke and Fire D...

引用

Telecommunications and Intelligent Systems (ICTIS), International Conference on

作者： Mohamed Rafik Aymene Berkani Ammar Chouchane Yassine Himeur Anes Abdennebi Seref Sagiroglu Abbes Amira Research Laboratory in Advanced Electronics Systems (LSEA) University Yahia Fares of Medea Medea Algeria Laboratory of LI3C University Biskra University Center of Barika Barika Algeria College of Engineering and Information Technology University of Dubai Dubai United Arab Emirates Software and Information Technology Engineering École de Technologie Supérieure Montréal Canada Artificial Intelligence and Big Data Analytics Security R&D Center Gazi University Ankara Turkey Department of Computer Science University of Sharjah Sharjah United Arab Emirates

ISBN: (数字)9798331527396

ISBN: (纸本)9798331527402

Ensuring safety in smart buildings is crucial due to the increasing prevalence of smoke and fire hazards in modern environments. This paper introduces a novel privacy-preserving FL approach based on a CNN1D for smoke and fire detection in smart buildings. Our system integrates data from wearable environmental sensors to train a lightweight, edge-deployable DL-CNN1D model, ensuring data privacy while enabling collaborative learning across distributed clients using Federated Averaging (FedAvg) aggregation. Experiments conducted on a comprehensive air measurement dataset for smoke and fire detection demonstrate exceptional performance, with the global model achieving 99.97% accuracy, 99.96% precision, in smoke and fire recognition. Our model demonstrates a low communication cost of 0.4 MB, underscoring its efficiency for real-time applications. Our FL-based approach represents a significant step towards balancing the need for robust safety systems with growing privacy concerns in smart building environments.

关键词： Privacy Smart buildings Costs Federated learning Atmospheric modeling data models Convolutional neural networks Wearable sensors Monitoring Intelligent sensors

来源：评论

学校读者我要写书评

暂无评论

ExpoNAS: Using Exposure-based Candidate Exclusion to Reduce NAS Space for Heterogeneous Pipeline of CNNs

ExpoNAS: Using Exposure-based Candidate Exclusion to Reduce ...

引用

International Conference on Parallel and Distributed Systems (ICPADS)

作者： Huijuan Duan Danghui Wang Xingting Zhao Kuizhi Mei Jihe Wang School of Computer Science Northwestern Polytechnical University Xi'an China Engineering Research Center of Embedded System Integration Ministry of Education Northwestern Polytechnical University Xi'an China Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University Xi'an China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Northwestern Polytechnical University Xi'an China

Efficiently deploying neural network models on heterogeneous edge systems faces unique challenges. Two major issues are underutilized pipelines caused by hardware heterogeneity and explosive growth of architecture search space. To address these challenges, we propose ExpoNAS, a framework enabling fast deployment-oriented neural architecture search on heterogeneous platforms. ExpoNAS evaluates model partitioning and deployability before search to meet accuracy and latency constraints. However, repeated partitioning leads to exponential growth in architecture search space. We first observe a strong correlation between operational exposure and accuracy improvement, and then we propose an exposure-based reduction technique that excludes the operations of low exposure. By removing these non-critical operations, the exposure-based pruning successfully reduces architecture search time. Our experiments on popular datasets show that the ExpoNAS pipelined design improves execution efficiency by a factor of 2 compared to traditional batch processing. Without compromising accuracy, ExpoNAS is able to reduce the architecture search time by 47.5% for discovering high-accuracy networks, compared to the SOTA NAS strategies.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Reconstructing Missing Modalities in Multi-Modal Endoscopic Ultrasound Via Cross-Modal Feature Replacement Representation

SSRN

引用

SSRN 2024年

作者： Zheng, Cenyang Gong, Xun Fan, Lin Li, Jiao School of Computing and Artificial Intelligence Southwest Jiaotong University Sichuan Chengdu611756 China Engineering Research Center of Sustainable Urban Intelligent Transportation Ministry of Education Chengdu611756 China National Engineering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University Chengdu611756 China Manufacturing Industry Chains Collaboration and Information Support Technology Key Laboratory of Sichuan Province Southwest Jiaotong University Chengdu611756 China Department of Gastroenterology The Third People’s Hospital of Chendu Affiliated Hospital of Southwest Jiaotong University Chengdu610031 China

Endoscopic ultrasound (EUS) is the primary diagnostic imaging technique for gastrointestinal stromal tumors. However, accurately identifying these tumors through EUS imaging alone remains challenging, even for experienced clinicians. They often rely on additional data, such as white light endoscopy (WLE) and EUS text reports, to aid in the diagnosis. Unfortunately, in practice, these supplementary modalities are sometimes overlooked during patient evaluation. To address these issues, we propose the Cross-modal Feature Reconstruction Network (CFRN), which integrates multimodal data modeling for medical diagnostic processes and performs specific learning for different modalities with missing data. The network fuses the multi-modal features based on the clinical medical process, realizes the feature-level missing modality reconstruction, and learns the refined features of different modal true cases by decoding the mode-specific missing. We trained and tested the model on two publicly available datasets, Audiovision-MNIST, MM-IMDb, and data sets collected from real clinical scenarios at three hospitals. Our results show that CFRN outperforms state-of-the-art methods, achieving higher prediction accuracy than using EUS alone. By simultaneously incorporating multimodal or reconstructed modal data for disease diagnosis, our single-modal EUS model proves to be more suitable for clinical scenarios. © 2024, The Authors. All rights reserved.

关键词： Endoscopy

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：