检索结果-内蒙古大学图书馆

International Conference on Cyber-Enabled Distributed Computing and knowledge Discovery, CyberC

作者： Qinghua Deng Lanxiang Chen Yizhao Zhu Yi Mu Faculty of Data Science City University of Macau Macau Macau China School of Computer and Information Engineering Hanshan Normal University Chaozhou China College of Computer and Cyber Security Fujian Normal University Fujian Provincial Key Laboratory of Network Security and Cryptology Fuzhou China

ISBN: (数字)9798331506896

ISBN: (纸本)9798331506902

Symmetric searchable encryption (SSE) is crucial for promoting cloud storage. It enables users to encrypt private data and outsource it to untrusted servers while retaining query capabilities. To prevent the cloud from obtaining users’ private data, researchers have proposed numerous schemes to protect users' privacy. However, the issue of volume hiding has received less attention. Recent studies have demonstrated that volume leakage can be exploited to infer query *** mitigate the aforementioned leakage problem, we introduce an efficient volume-hiding SSE scheme supporting conjunctive queries, denoted as VHXT. The primary strategy for implementing volume hiding comprises two aspects: first, employing a bitmap-based inverted index to obscure the query response length of the least frequent keyword, and second, introducing laconic PSI for efficient membership testing. The laconic PSI enables our scheme to achieve approximately optimal overhead. Moreover, security analysis and performance evaluation demonstrate that VHXT effectively prevents volume leakage with minimal overhead.

关键词： Performance evaluation Cloud computing data privacy Protocols knowledge discovery Encryption Servers Indexes Distributed computing Testing

来源：评论

学校读者我要写书评

暂无评论

A Method for Updating Individual Tree Species Samples Based on Different Images

A Method for Updating Individual Tree Species Samples Based ...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Caiyan Chen Linhai Jing Fulong Chen Hui Li Baoxin Hu Key Laboratory of Digital Earth Science Aerospace Information Research Institute Chinese Academy of Sciences Beijing China International Research Center of Big Data for Sustainable Development Goals Beijing China School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing China Key Laboratory of Poyang Lake Wetland and Watershed Research Ministry of Education & School of Geography and Environment Jiangxi Normal University Nanchang China Department of Earth and Space Science and Engineering York University Toronto Ontario Canada

ISBN: (数字)9798350360325

ISBN: (纸本)9798350360332

The correct classification of individual tree species (ITS) is of great importance for forest resource management. However, current ITS samples collection is time-consuming and laborious in field surveys, and the samples cannot be updated in time. In this study, a sample update method is proposed, which updates samples by detecting the spectral angular similarity of samples at different times at the same location, enabling the reuse of historical samples and timely update of samples. Experimental results showed that the classification accuracy could reach more than 90% by using DenseNet model and the updated samples, which proved that the sample update method could achieve sample update and sample reuse effectively. In addition, there was significant improvement in the classification accuracy of the sample set using multispectral and texture information fusion, proving the effectiveness of information fusion in increasing classification information.

关键词： Surveys Accuracy Laser radar Soft sensors Geoscience and remote sensing Vegetation Forestry

来源：评论

学校读者我要写书评

暂无评论

The Privacy Computing for Digital Economy Development under New Technology Based on Spatial-Temporal Information Matrix, Especially among RCEP Nations 3

The Privacy Computing for Digital Economy Development under ...

引用

3rd International Conference on Pattern Recognition and Machine Learning, PRML 2022

作者： Liu, Haitao Zheng, Shenjun Hong, Yong Cao, Yujuan Lu, Yun Tian, Tian Guangxi Artificial Intelligence and Big Data Applying Institute Nanning530201 China Hangzhou ChinaOly Technology Co. Ltd. Hangzhou310015 China Wuhan University State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing Wuhan430079 China Guangxi Academy of Social Sciences Nanning530201 China

ISBN: (数字)9781665499507

ISBN: (纸本)9781665499507

With the coming of intelligent era, the wide using of new generation information technology, such as Internet on Things, AI, Big data and Cloud computing, digital economic development is more and more prosperous for every economic entity, specially, for some emerging economic entities, such as RCEP nations. However, the problem of objective evaluation of ability of digital economic development of different nations and dependence of digital economic development among each nation are very hard but necessary under not leaking digital economic data of all parts. For solving this problem, an improvement Meta Learning approach was proposed creatively which constructed temporal dimension factor and spatial dimension factor based on spatial-temporal information matrix method. It could make knowledge transfer from source network to target network according to the orthogonal rule between temporal dimension factor and spatial dimension factor. 3 different type and smart test ways were designed in order to validate the performance of the approach of this paper comprehensively. Digital economic development data of RECP nations were collected and employed for testing. The amount and accuracy of knowledge transfer from different source network to various target network were validated one by one. The results not only validate the effectiveness of improving Meta Learning approach of this article but also reveal that the diversity of digital economy development among RECP nations but impacting tightly each other. Moreover, there also have relative contribution on opening knowledge transfer from source network to target network under privacy data not be leaked. This content would be researched at more complex industrial data forward. © 2022 IEEE.

关键词： Economic and social effects

来源：评论

学校读者我要写书评

暂无评论

A Lightweight Api Recommendation Method for App Development Based on Multi-Objective Evolutionary Algorithm

SSRN

引用

SSRN 2022年

作者： Li, Xun Liu, Lei Liu, Yuzhou Liu, Huaxiao College of Computer Science and Technology Jilin University Jilin130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Changchun Jilin University Jilin130012 China

Context: API is important in daily programming activities during app development, but finding appropriate APIs is time-consuming for developers. To simplify this process, many researchers pay attention to overcoming the task-API knowledge gap using semantic information mined from the large-scale dataset for API recommendation. However, only semantic information is not enough since API descriptions and developer's query may not share similar words, meanwhile, large-scale data mining brings huge time cost and causes knowledge fixed problem (i.e. data cannot be timely updated). This limits the efficiency of existing API commendation methods. Objective: In this work, we aim at proposing a lightweight API recommendation method for app development based on the data in app store. Method: We model API recommendation as a multi-objective optimization problem by considering both structural and semantic information of API, and use the genetic algorithm to gain optimal solutions for overcoming limitations of the small-scale dataset. Specially, we collect APK files of related apps and API descriptions to establish a lightweight dataset, and extract the structural and semantic information of API from them with graph embedding and NLP techniques respectively. Then, we get the recommended APIs satisfying structural and semantic objectives according to the developers’ target functionality with a genetic algorithm. Finally, we give the interpretation of our recommendation information to help developers understand the results easily. Results and Conclusion: We conduct a series of experiments based on apps in Google Play and Q&As in Stack Overflow. The results show that Precision@N of our recommendation can be up to 0.89, MAP@N is up to 0.50, and MRR reaches 0.69, and our method achieves such good performance only utilizing less than 1/19 of the project number of our compared machine learning method. Besides, we conduct a survey and most of the participants confirm the understandabilit

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

A Review of dataset and labeling methods for causality extraction 28

A Review of dataset and labeling methods for causality extra...

引用

28th International Conference on Computational Linguistics, COLING 2020

作者： Xu, Jinghang Zuo, Wanli Liang, Shining Zuo, Xianglin College of Computer Science and Technology Jilin University China Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education China

ISBN: (纸本)9781952148279

Causality represents the most important kind of correlation between events. Extracting causality from text has become a promising hot topic in NLP. However, there is no mature research systems, evaluation rules and datasets for public evaluation. Moreover, there is a lack of unified causal sequence labeling methods, which constitute the key factors that hinder the progress of causality extraction research. We survey the limitations and shortcomings of existing causality research field comprehensively from the aspects of basic concepts, extraction methods, experimental data, and labeling methods, so as to provide reference for future research on causality extraction. We summarize the existing causality datasets, explore their practicability and extensibility from multiple perspectives. Aiming at the problem of causal sequence labeling, we analyze the existing methods of causal sequence labeling, with a summarizations of its regulation. Multiple candidate causal labeling sequences are put forward according to labeling controversy to explore the optimal labeling method through experiments, and suggestions are provided for selecting labeling method. © 2020 COLING 2020 - 28th International Conference on Computational Linguistics, Proceedings of the Conference. All rights reserved.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Number-Theoretic Net-Based Particle Filtering for Linear Phase Noise Tracking in CO-OFDM Systems 20

Number-Theoretic Net-Based Particle Filtering for Linear Pha...

引用

20th International Conference on Optical Communications and Networks, ICOCN 2022

作者： Xu, Yangfan Du, Xinwei Liu, Shuai Yu, Changyuan BNU-HKBU United International College Division of Science and Technology Zhuhai519087 China Guangdong Provincial Key Laboratory of Interdisciplinary Research and Application for Data Science BNU-HKBU United International College Zhuhai519087 China Hong Kong Polytechnic University Department of Electronic and Information Engineering Hung Hom Hong Kong

ISBN: (数字)9781665458986

ISBN: (纸本)9781665458986

In this paper, we propose a number-theoretic net-based particle filter (NT- PF) to dynamically estimate the linear phase noise (LPN) for CO-OFDM systems in the time domain. Inspired by the concept of uniform design (UD), we recursively draw the particles from the NT -net at each time index, which leads to a significant improvement on the algorithm efficiency compared with the conventional Gaussian particle filter (GPF). In addition, we propose a signal detection approach to estimate the LPN on the entire received signal first, then recover the transmitted signal from the received ones. The dynamic tracking performance, efficiency and robustness of the proposed NT-PF is verified in an 89 Gb/s 16-QAM CO-OFDM system. © 2022 IEEE.

关键词： Phase noise

来源：评论

学校读者我要写书评

暂无评论

Aerial Active STAR-RIS-assisted Satellite-Terrestrial Covert Communications

arXiv

引用

arXiv 2025年

作者： Zhang, Chuang Sun, Geng Li, Jiahui Wang, Jiacheng Zhang, Ruichen Niyato, Dusit Mao, Shiwen Quek, Tony Q.S. Computer Science and Technology Jilin University Changchun130012 China Singapore University of Technology and Design Singapore487372 Singapore College of Computer Science and Technology Jilin University Changchun130012 China College of Computing and Data Science Nanyang Technological University Singapore639798 Singapore Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun130012 China Department of Electrical and Computer Engineering Auburn University AuburnAL36849 United States Information System Technology and Design Pillar Singapore University of Technology and Design Singapore487372 Singapore

An integration of satellites and terrestrial networks is crucial for enhancing performance of next generation communication systems. However, the networks are hindered by the long-distance path loss and security risks in dense urban environments. In this work, we propose a satellite-terrestrial covert communication system assisted by the aerial active simultaneous transmitting and reflecting reconfigurable intelligent surface (AASTAR-RIS) to improve the channel capacity while ensuring the transmission covertness. Specifically, we first derive the minimal detection error probability (DEP) under the worst condition that the Warden has perfect channel state information (CSI). Then, we formulate an AASTAR-RIS-assisted satellite-terrestrial covert communication optimization problem (ASCCOP) to maximize the sum of the fair channel capacity for all ground users while meeting the strict covert constraint, by jointly optimizing the trajectory and active beamforming of the AASTAR-RIS. Due to the challenges posed by the complex and high-dimensional state-action spaces as well as the need for efficient exploration in dynamic environments, we propose a generative deterministic policy gradient (GDPG) algorithm, which is a generative deep reinforcement learning (DRL) method to solve the ASCCOP. Concretely, the generative diffusion model (GDM) is utilized as the policy representation of the algorithm to enhance the exploration process by generating diverse and high-quality samples through a series of denoising steps. Moreover, we incorporate an action gradient mechanism to accomplish the policy improvement of the algorithm, which refines the better state-action pairs through the gradient ascent. Simulation results demonstrate that the proposed approach significantly outperforms important benchmarks, and also validate the performance and practicality under different algorithm parameters and environment settings. Copyright © 2025, The Authors. All rights reserved.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Towards Unified Prompt Tuning for Few-shot Text Classification

Towards Unified Prompt Tuning for Few-shot Text Classificati...

引用

2022 Findings of the Association for Computational Linguistics: EMNLP 2022

作者： Wang, Jianing Wang, Chengyu Luo, Fuli Tan, Chuanqi Qiu, Minghui Yang, Fei Shi, Qiuhui Huang, Songfang Gao, Ming School of Data Science and Engineering East China Normal University Shanghai China Alibaba Group Hangzhou China Zhejiang Lab Hangzhou China Ant Group Hangzhou China Shanghai Key Laboratory of Mental Health and Psychological Crisis Intervention School of Psychology and Cognitive Science East China Normal University Shanghai China

Prompt-based fine-tuning has boosted the performance of Pre-trained Language Models (PLMs) on few-shot text classification by employing task-specific prompts. Yet, PLMs are unfamiliar with prompt-style expressions during pre-training, which limits the few-shot learning performance on downstream tasks. It would be desirable if the models can acquire some prompting knowledge before adapting to specific NLP tasks. We present the Unified Prompt Tuning (UPT) framework, leading to better few-shot text classification for BERT-style models by explicitly capturing prompting semantics from non-target NLP datasets. In UPT, a novel paradigm Prompt-Options-Verbalizer is proposed for joint prompt learning across different NLP tasks, forcing PLMs to capture task-invariant prompting knowledge. We further design a self-supervised task named knowledge-enhanced Selective Masked Language Modeling to improve the PLM's generalization abilities for accurate adaptation to previously unseen tasks. After multi-task learning across multiple tasks, the PLM can be better prompt-tuned towards any dissimilar target tasks in low-resourced settings. Experiments over a variety of NLP tasks show that UPT consistently outperforms state-of-the-arts for prompt-based fine-tuning. © 2022 Association for Computational Linguistics.

关键词： Modeling languages

来源：评论

学校读者我要写书评

暂无评论

Construction and Application of knowledge Graph for Risk Identification Methods of Counterfeit Cigarettes and Wine

Construction and Application of Knowledge Graph for Risk Ide...

引用

2023 International Conference on Intelligent Communication and Networking, ICN 2023

作者： Huang, Fulin Ning, Jie Liu, Lingjie Tian, Ye Wu, Jianghong Harbin Engineering University College of Computer Science and Technology Harbin150001 China Hangzhou Hikvision Digital Technology Co. Ltd. Hangzhou310051 China Hangzhou Public Security Bureau Environment and Food and Drug Crime Investigation Detachment Hangzhou310000 China Xidian University Hangzhou Institute of Technology Hangzhou311200 China Key Laboratory of Peace-Building Big Data of Zhejiang Province Hangzhou310000 China

ISBN: (纸本)9798350357677

In response to the sharp increase in cases of counterfeit cigarettes and counterfeit alcohol in recent years, based on the application of knowledge graphs in social entities and social relationships, a knowledge graph for risk identification of counterfeit cigarettes and counterfeit alcohol was constructed and applied. Based on the historical cases of counterfeit cigarettes and counterfeit wines and the relevant groups, we process the data through ontology construction, knowledge extraction, and knowledge fusion, and build a knowledge map of relevant personnel for testing counterfeit wines. We use the TransH model to complete the constructed knowledge graph to obtain a more complete knowledge graph for risk identification of counterfeit cigarettes and counterfeit alcohol, and then use PageRank and Louvain community discovery algorithms to screen out communities where people with major suspicions gather, and control the system. Gangs selling counterfeit cigarettes and alcohol provide risk warning. © 2023 IEEE.

关键词： Wine

来源：评论

学校读者我要写书评

暂无评论

Research on Hardware-in-the-Loop Test System for the Main Control Unit of Unmanned Vehicles

Research on Hardware-in-the-Loop Test System for the Main Co...

引用

Chinese Intelligent Systems Conference, CISC 2020

作者： Ni, Haoyuan Yu, Guizhen Zhou, Bin Liu, Guoqiang School of Transportation Science and Engineering Beijing Advanced Innovation Center for Big Data and Brain Computing Beijing Key Laboratory for Cooperative Vehicle Infrastructure Systems and Safety Control Beihang University Beijing100191 China School of Electronic Information Engineering Beihang University Beijing100191 China

ISBN: (纸本)9789811584572

At present, there are more researches on the automatic driving technology of unmanned vehicles. It needs a main control unit, which enables the vehicle to automatically drive. The main control unit supports the access of various sensors and controllers. It can process data of each device and control the movement state of vehicles. Therefore, the main control unit needs to be tested repeatedly to ensure its functionality and stability. Based on Prescan simulation software and Matlab/Simulink software, this paper studies a hardware-in-the-loop (HIL) test system for testing the main control unit of unmanned vehicles according to the communication protocol and communication method of the real sensor and controller hardware devices. At the same time, this paper studies a simulation method of the main control unit, which can effectively verify the function of the test system and conduct the feasibility test of the communication protocol and communication method used. © 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Simulink

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：