检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Zhang, Wei Cai, Miaoxin Zhang, Tong Lei, Guoqiang Zhuang, Yin Mao, Xuerui The Advanced Research Institute of Multidisciplinary Sciences Beijing Institute of Technology Beijing100081 China The School of Mechatronical Engineering Beijing Institute of Technology Beijing100081 China Yangtze Delta Region Academy of Beijing Institute of Technology Jiaxing314003 China The National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing Beijing Institute of Technology Beijing100081 China

Ship detection needs to identify ship locations from remote sensing (RS) scenes. Due to different imaging payloads, various appearances of ships, and complicated background interference from the bird’s eye view, it is difficult to set up a unified paradigm for achieving multi-source ship detection. To address this challenge, in this article, leveraging the large language models (LLMs)’s powerful generalization ability, a unified visual-language model called Popeye1 is proposed for multi-source ship detection from RS imagery. Specifically, to bridge the interpretation gap between the multi-source images for ship detection, a novel unified labeling paradigm is designed to integrate different visual modalities and the various ship detection ways, i.e., horizontal bounding box (HBB) and oriented bounding box (OBB). Subsequently, the hybrid experts encoder is designed to refine multi-scale visual features, thereby enhancing visual perception. Then, a visual-language alignment method is developed for Popeye to enhance interactive comprehension ability between visual and language content. Furthermore, an instruction adaption mechanism is proposed for transferring the pre-trained visual-language knowledge from the nature scene into the RS domain for multi-source ship detection. In addition, the segment anything model (SAM) is also seamlessly integrated into the proposed Popeye to achieve pixel-level ship segmentation without additional training costs. Finally, extensive experiments are conducted on the newly constructed ship instruction dataset named MMShip, and the results indicate that the proposed Popeye outperforms current specialist, open-vocabulary, and other visual-language models for zero-shot multi-source ship detection. Copyright © 2024, The Authors. All rights reserved.

关键词： Ships

来源：评论

学校读者我要写书评

暂无评论

Grid Construction of 5G Beam-Space via Matrix Completion and Principal Component Analysis

Grid Construction of 5G Beam-Space via Matrix Completion and...

引用

IEEE Conference on Global Communications (GLOBECOM)

作者： Zhiqiang Yao Hao Xuan Jiawei Xu Yue Sun Lei Wei Ruituo Jiang Qingjiang Shi Zheng Peng Hunan Province Key Laboratory of Credible Intelligent Navigation and Positioning Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education National Center for Applied Mathematics in Hunan Xiangtan University Xiangtan China Huawei Technologies Shenzhen China Shenzhen Research Institute of Big Data Shenzhen China

Deriving the spatial features of user equipment (UE) and traffic distribution is crucial for optimizing real-world wireless network performance, such as load balancing and improving cell-edge user experience. In this paper, we creatively construct the beam-space grid with high-dimensional beam reference signal receiving power (RSRP), serving as spatial reference system for 5G mobile networks. However, this is a challenging task due to i) access to 3D UE geographic information is limited by privacy protection and device settings, ii) beam-RSRP with up to 75% loss in measurement reports (MRs), iii) large computation and storage requirements of grid information caused by the exploding grid number in high-dimensional beam-space. A novel approach is designed to tackle these challenges, that coherently integrate low-rank matrix completion and dimension reduction techniques. Using telco big data, specifically MRs from live networks, we recover the beam-RSRP with high-precision and construct the beam-space grid even without geographic information. This research ensures stable derivation of spatial distribution features in the beam-space grid while efficiently processing grid information.

关键词：

来源：评论

学校读者我要写书评

暂无评论

EarthGPT: A Universal Multi-modal Large Language Model for Multi-sensor Image Comprehension in Remote Sensing Domain

arXiv

引用

arXiv 2024年

作者： Zhang, Wei Cai, Miaoxin Zhang, Tong Zhuang, Yin Mao, Xuerui The Advanced Research Institute of Multidisciplinary Sciences Beijing Institute of Technology Beijing100081 China The School of Mechatronical Engineering Beijing Institute of Technology Beijing100081 China Yangtze Delta Region Academy of Beijing Institute of Technology Jiaxing314003 China The National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing Beijing Institute of Technology Beijing100081 China

Multi-modal large language models (MLLMs) have demonstrated remarkable success in vision and visual-language tasks within the natural image domain. Owing to the significant diversities between the natural and remote sensing (RS) images, the development of MLLMs in the RS domain is still in the infant stage. To fill the gap, a pioneer MLLM named EarthGPT integrating various multi-sensor RS interpretation tasks uniformly is proposed in this paper for universal RS image comprehension. Firstly, a visual-enhanced perception mechanism is constructed to refine and incorporate coarse-scale semantic perception information and fine-scale detailed perception information. Secondly, a cross-modal mutual comprehension approach is proposed, aiming at enhancing the interplay between visual perception and language comprehension and deepening the comprehension of both visual and language content. Finally, a unified instruction tuning method for multi-sensor multi-task in the RS domain is proposed to unify a wide range of tasks including scene classification, image captioning, region-level captioning, visual question answering (VQA), visual grounding, object detection, etc. More importantly, a dataset named MMRS-1M featuring large-scale multi-sensor multi-modal RS instruction-following is constructed, comprising over 1M image-text pairs based on 34 existing diverse RS datasets and including multi-sensor images such as optical, synthetic aperture radar (SAR), and infrared. The MMRS-1M dataset addresses the drawback of MLLMs on RS expert knowledge and stimulates the development of MLLMs in the RS domain. Extensive experiments are conducted, demonstrating the EarthGPT’s superior performance in various RS visual interpretation tasks compared with the other specialist models and MLLMs, proving the effectiveness of the proposed EarthGPT and offering a versatile paradigm for open-set reasoning tasks. Our code and dataset are available at https://***/wivizhang/EarthGPT. Copyright © 202

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

A Modeling Method Based on Koopman Operator Theory for Omnidirectional Mobile Manipulator System

A Modeling Method Based on Koopman Operator Theory for Omnid...

引用

IEEE International Conference on Mechatronics and Automation

作者： Dong Wang Binjie Wang Tong Zhang Chao Ren Tianjin Key Laboratory of Aerospace Intelligent Equipment Technology Tianjin Institute of Aerospace Mechanical and Electrical Equipment Tianjin China School of Electrical and Information Engineering Tianjin University Tianjin China Tianjin Jinhang Institute of Computing Technologies Tianjin China

ISBN: (数字)9798350388077

ISBN: (纸本)9798350388084

The omnidirectional mobile robotic arm system is a highly coupled, multivariate, and highly nonlinear system. The traditional modeling approach uses Lagrange method to establish dynamic model, which suffers from issues of complex modeling, unknown model parameters, and insufficient accuracy in modeling. In this paper, a modeling method based on Koopman operator theory is proposed for this system, which is essentially a data-driven modeling method. Specifically, this paper collects data on system dynamic characteristics and transforms complex nonlinear models into high-dimensional linear models. This paper preprocesses the voltage data in the dataset based on platform characteristics and obtains the Koopman high-dimensional linear model, avoiding the complex modeling problems using Lagrange methods. Simulation has been performed, which confirms the accuracy and effectiveness of using Koopman operator theory for modeling omnidirectional mobile manipulators.

关键词： Accuracy Trajectory tracking System dynamics Simulation Transforms Predictive models Trajectory

来源：评论

学校读者我要写书评

暂无评论

Knowledge Graph Embedding Based Graph Convolutional Network for Link Prediction

Knowledge Graph Embedding Based Graph Convolutional Network ...

引用

International Conference on Advanced Cloud and Big Data (CBD)

作者： Qiang Wu Qing He Henan Institute of Advanced Technology Zhengzhou University Zhengzhou P.R. China Key Lab of Intelligent Information Processing of Chinese Academy of Science (CAS) Institute of Computing Technology CAS Beijing China University of Chinese Academy of Science Beijing China

Knowledge Graph Embedding (KGE) aims to capture the inherent structural information within knowledge graphs (KGs) by means of representation learning. This is of paramount importance for various downstream tasks, including personalized recommendations, intelligent search, and relation extraction. Graph Convolutional Networks (GCNs), a type of neural network, have recently demonstrated significant success in modeling data structured as graphs. However, these models often overlook the intricate interrelation information between neighboring nodes, which can offer valuable insights for enhancing node embeddings. In this article, we present a knowledge graph embedding based graph convolutional network for link prediction. First, we utilize embeddings to represent entities and relations. Second, we perform circular correlation on subject embedding and relation embedding to generate two matrix and achieve full fusion of embedding at the element level. Third, we generate self-attention vectors using one of the matrices and perform the Hadamard product with the other matrix. Thereafter, new node features are generated through graph convolutional networks and residual unit. Finally, we use the scoring function to score the candidate triples. The experimental results demonstrate that our model achieves improved performance compared with a wide variety of baseline models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Leveraging Semisupervised Hierarchical Stacking Temporal Convolutional Network for Anomaly Detection in IoT Communication

Leveraging Semisupervised Hierarchical Stacking Temporal Con...

引用

作者： Cheng, Yongliang Xu, Yan Zhong, Hong Liu, Yi Anhui Engineering Laboratory of IoT Security Technologies Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Hefei China Shenzhen Key Laboratory of Intelligent Media and Speech Peking University Shenzhen Institute Shenzhen China

The rapid development of the Internet of Things (IoT) accumulates a large number of communication records, which are utilized for anomaly detection in IoT communication. However, only a small part of these records can be labeled, which increases the difficulty in anomaly detection. This article proposes a semisupervised hierarchical stacking temporal convolutional network (HS-TCN), which is the first semisupervised model for anomaly detection in IoT communication, and it can train unlabeled data based on a small number of labeled data. Furthermore, HS-TCN fully considers the features of streaming data in IoT communication and can weed out uncertain records. Finally, the experimental results demonstrate that HS-TCN promotes the performance of anomaly detection and attains better efficiency. © 2014 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Exploiting the Community Structure of Fraudulent Keywords for Fraud Detection in Web Search

引用

Journal of Computer Science & technology 2021年第5期36卷 1167-1183页

作者： Dong-Hui Yang Zhen-Yu Li Xiao-Hui Wang Kavé Salamatian Gao-Gang Xie Network Technology Research Center Institute of Computing TechnologyChinese Academy of Sciences Beijing 100190China University of Chinese Academy of Sciences Beijing 100049China Global Energy Interconnection Research Institute Co. Ltd.Beijing 102209China LISTIC Laboratory of Computer Science SystemsInformation and Knowledge ProcessingUniversitéSavoie Mont BlancChambéry 73011France Computer Network Information Center Chinese Academy of SciencesBeijing 100190China

Internet users heavily rely on web search engines for their intended *** major revenue of search engines is advertisements(or ads).However,the search advertising suffers from *** generate fake traffic which does not reach the intended audience,and increases the cost of the ***,it is critical to detect fraud in web *** studies solve this problem through fraudster detection(especially bots)by leveraging fraudsters'unique ***,they may fail to detect new means of fraud,such as crowdsourcing fraud,since crowd workers behave in part like normal *** this end,this paper proposes an approach to detecting fraud in web search from the perspective of fraudulent *** begin by using a unique dataset of 150 million web search logs to examine the discriminating features of fraudulent ***,we model the temporal correlation of fraudulent keywords as a graph,which reveals a very well-connected community ***,we design DFW(detection of fraudulent keywords)that mines the temporal correlations between candidate fraudulent keywords and a given list of *** particular,DFW leverages several refinements to filter out non-fraudulent keywords that co-occur with seeds *** evaluation using the search logs shows that DFW achieves high fraud detection precision(99%)and accuracy(93%).A further analysis reveals several typical temporal evolution patterns of fraudulent keywords and the co-existence of both bots and crowd workers as fraudsters for web search fraud.

关键词： community structure fraud analysis fraudulent keyword detection web search

来源：评论

学校读者我要写书评

暂无评论

C + L band seamless PM-256QAM DWDM transmission over 20.6 km low-loss hollow-core fiber enabled by low-complexity misaligned pilot-aided carrier recovery

引用

Optics Express 2025年第13期33卷 26899-26914页

作者： Chenchen Wang Zhipei Li Ran Gao Ze Dong Junyuan Song Qi Zhang Feng Tian Dong Guo Fu Wang Huan Chang Lei Zhu Xiaolong Pan Tianlei Mai Sitong Zhou Xiangjun Xin School of Information and Electronics Beijing Institute of Technology (BIT) Beijing 100081 China National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing Beijing 100081 China School of Electronic Engineering Beijing University of Posts and Telecommunications (BUPT) Beijing 100876 China Beijing Key Laboratory of Space-Ground Interconnection and Convergence BUPT Beijing 100876 China State Key Laboratory of Information Photonics and Optical Communications BUPT Beijing 100876 China School of Integrated Circuits Beijing University of Posts and Telecommunications Beijing 100876 China

Overcoming the capacity bottleneck of single-mode fiber (SMF), we exploit the exceptionally low-loss and low-nonlinearity characteristics of hollow-core fiber (HCF) to demonstrate a 198-channel × 40 Gbaud polarization multiplexed 256QAM (PM-256QAM) WDM system over a 20.6 km nested anti-resonant nodeless fiber (NANF) transmission link. A hardware-efficient, low-complexity carrier recovery algorithm is employed, relying entirely on polarized misaligned pilot symbols for robust frame synchronization and high-precision carrier recovery, eliminating the need for training sequences. Compared to conventional methods constrained by fourth-power operations and pilot symbol intervals, our approach offers a wider frequency offset estimation (FOE) range and enhanced carrier phase recovery (CPR). Experimental results demonstrate that the bit error rate (BER) of all 198 WDM channels remains below the 20% soft-decision forward error correction (SD-FEC) threshold, achieving spectral efficiencies of 12.8 bit/s/Hz in the C-band and 13.1 bit/s/Hz in the L-band. Benefiting from the unique properties of HCF, the system demonstrates superior performance compared to conventional single-mode fiber, particularly at high launch powers. This work paves the way for future ultra-high-capacity, low-latency optical networks, providing a viable technological path for next-generation communication systems.

关键词： Nonlinear impairments Optical networks Optical signals Optical transceivers Phase recovery Signal transmission

来源：评论

学校读者我要写书评

暂无评论

Zoom Out and Observe: News Environment Perception for Fake News Detection

arXiv

引用

arXiv 2022年

作者： Sheng, Qiang Cao, Juan Zhang, Xueyao Li, Rundong Wang, Danding Zhu, Yongchun Key Lab of Intelligent Information Processing of Chinese Academy of Sciences Institute of Computing Technology Chinese Academy of Sciences University of Chinese Academy of Sciences China

Fake news detection is crucial for preventing the dissemination of misinformation on social media. To differentiate fake news from real ones, existing methods observe the language patterns of the news post and "zoom in" to verify its content with knowledge sources or check its readers' replies. However, these methods neglect the information in the external news environment where a fake news post is created and disseminated. The news environment represents recent mainstream media opinion and public attention, which is an important inspiration of fake news fabrication because fake news is often designed to ride the wave of popular events and catch public attention with unexpected novel content for greater exposure and spread. To capture the environmental signals of news posts, we "zoom out" to observe the news environment and propose the News Environment Perception Framework (NEP). For each post, we construct its macro and micro news environment from recent mainstream news. Then we design a popularity-oriented and a novelty-oriented module to perceive useful signals and further assist final prediction. Experiments on our newly built datasets show that the NEP can efficiently improve the performance of basic fake news detectors. © 2022, CC BY-NC-SA.

关键词： Fake detection

来源：评论

学校读者我要写书评

暂无评论

Frequent Trajectory Mining with Local Differential Privacy

Frequent Trajectory Mining with Local Differential Privacy

引用

International Workshop on Advanced Computational Intelligence (IWACI)

作者： Yaqian Huang Huiwei Wang College of Electronic and Information Engineering Southwest University Chongqing China Key Laboratory of Intelligent Information Processing Chongqing Three Gorges University Chongqing China Chongqing Innovation Center Beijing Institute of Technology Chongqing China

With the rapid development of mobile Internet, trajectory data has become an indispensable data type in the era of big data due to its potential information. Since trajectory data of real number type cannot be directly applied to existing encoding mechanisms of local differential privacy and existing frequent item mining algorithms, we propose an approach called Private Frequent Trajectory Mining (PrivFTM). The implementation process of the algorithm is divided into three phases. Specifically, in the first phase, an adaptive spatial decomposition based on local differential privacy (PrivASD) is designed to discretize user trajectory data, while in the subsequent phase, the data collector completes the mining of candidate set and frequent items respectively according to the grouped user data. Extensive experiments performed on the two real-world datasets indicate that the performance of our PrivFTM is better than the existing algorithms.

关键词：

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：