检索结果-内蒙古大学图书馆

9th IEEE International Conference on data Science in Cyberspace, DSC 2024

作者： Sun, Weixuan Tang, Jiuyang Fang, Yang Hong, Jinqiu Xu, Hao Wang, Mao National University of Defense Technology Laboratory for Big Data and Decision National University of Defense Technology Changsha China National University of Defense Technology Changsha China

ISBN: (纸本)9798350391367

Graph neural networks (GNNs) have emerged as a promising avenue for collaborative filtering (CF), offering a means to model inter-action graphs between users and items. However, existing GNN-based recommendation systems often struggle with limited, noisy, and skewed data, which can hinder their performance. In this paper, we present a Hypergraph Contrastive-Enhanced Transformer framework, to address these challenges and enhance user representation effectively. Our framework integrates hypergraph neural networks and transformer architectures to capture local interactive learning and global user multi-behavioral learning more robustly, and apply a noise-based contrastive enhancement method to regularize the embedding space into a more uniform representation distribution. Experiments have demonstrated that our model can significantly improve the performance over various state-of-the-art baselines. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Upconversion luminescence and optical thermometry behaviors of Yb^(3+)and Ho^(3+)co‑doped GYTO crystal

引用

Frontiers of Optoelectronics 2023年第3期16卷 179-189页

作者： Chuancheng Zhang Shoujun Ding Miaomiao Wang Hao Ren Xubing Tang Yong Zou Renqin Dou Wenpeng Liu School of Microelectronics and Data Science Anhui University of TechnologyMaanshan 243002China Anhui Institute of Optics and Fine Mechanics Chinese Academy of SciencesHefei 230031China Advanced Laser Technology Laboratory of Anhui Province Hefei 230037China Anhui Provincial Joint Key Laboratory of Disciplines for Industrial Big Data Analysis and Intelligent Decision Maanshan 243002China

Optical thermometry based on the upconversion(UC)luminescence intensity ratio(LIR)has attracted considerable attention because of its feasibility for achievement of accurate non-contact temperature *** with traditional UC phosphors,optical thermometry based on UC single crystals can achieve faster response and higher sensitivity due to the stability and high thermal conductivity of the single *** this study,a high-quality 5 at%Yb^(3+)and 1 at%Ho^(3+)co-doped Gd_(0.74)Y_(0.2)TaO_(4)single crystal was grown by the Czochralski(Cz)method,and the structure of the as-grown crystal was ***,the UC luminescent properties and optical thermometry behaviors of this crystal were *** 980 nm wavelength excitation,green and red UC luminescence lines at 550 and 650 nm and corresponding to the^(5)F_(4)/^(5)S_(2)→^(5)I_(8)and^(5)F_(5)→^(5)I_(8)transitions of Ho^(3+),respectively,were *** green and red UC emissions involved a two-photon mechanism,as evidenced by the analysis of power-dependent UC emission *** temperature-dependent UC emission spectra were measured in the temperature range of 330–660 K to assess the optical temperature sensing *** 660 K,the maximum relative sensing sensitivity(S_(r))was determined to be 0.0037 K^(−1).These results highlight the signifcant potential of Yb,Ho:GYTO single crystal for optical temperature sensors.

关键词： Yb,Ho:GYTO Optical temperature sensor Luminescence intensity ratio Upconversion luminescence

来源：评论

学校读者我要写书评

暂无评论

Efficient Trigger Word Insertion 9

Efficient Trigger Word Insertion

引用

9th International Conference on big data and Information Analytics, bigDIA 2023

作者： Zeng, Yueqi Li, Ziqiang Xia, Pengfei Liu, Lei Li, Bin University of Science and Technology of China Hefei230027 China Zhejiang Lab Hangzhou311121 China Laboratory for Big Data and Decision China

ISBN: (纸本)9798350330076

With the rapid advancements in the natural language processing (NLP) domain in recent years, the emergence of backdoor attacks presents substantial threats to deep neural network models. However, prior research has often overlooked the influence of the poisoning rate. This paper aims to address this gap by prioritizing the reduction of poisoned samples while still attaining a comparable Attack Success Rate (ASR) in the context of text backdoor attacks. Our primary focus revolves around introducing an efficient strategy for trigger word insertion, encompassing both trigger word optimization and poisoned sample selection. To achieve our objectives, extensive experiments were conducted across diverse datasets and models, showcasing the significant enhancements brought forth by our proposed methodology in the realm of text classification tasks. Remarkable outcomes include an ASR surpassing 90%, utilizing a mere 10 poisoned samples in the dirty-label setting, and delivering compelling performance with only 1.5% of the training data in the clean-label setting. © 2023 IEEE.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Multi-Agent Hierarchical decision Optimization Method Based on Curriculum Learning 9

Multi-Agent Hierarchical Decision Optimization Method Based ...

引用

9th International Conference on big data and Information Analytics, bigDIA 2023

作者： Liang, Wenqian Huang, Chengqi Zhang, Yong Zhang, Zhuxin Yang, Xiaolong Zhang, Pengcheng National University of Defense Technology Laboratory for Big Data and Decision Changsha China North Automatic Control Technology Institute Taiyuan China

ISBN: (纸本)9798350330076

The huge state space and varying action space will make the decision-making be a grand challenge for reinforcement learning. To address this problem, we propose a multi-agent hierarchical decision optimization algorithm, which utilizes macro-action abstraction based on expert experience knowledge and hierarchical abstraction based on hierarchical reinforcement learning theory to decompose the combat task into different hierarchical sub-task modules. The alternating update method is used to learn and train the network. Meanwhile, combined with the curriculum learning method, the training process of the neural network model can be improved. The algorithm is validated in the full-length game of StarCraft II. When playing against the built-in AI of level 7 difficulty, it achieved a win rate of over 93%. The experimental results show that it can effectively improve the collaborative ability of the decision-making model when the state space and the optional action space are huge and the decision-making process is complex. © 2023 IEEE.

关键词： decision making

来源：评论

学校读者我要写书评

暂无评论

Real is not True: Backdoor Attacks Against Deepfake Detection 9

Real is not True: Backdoor Attacks Against Deepfake Detectio...

引用

9th International Conference on big data and Information Analytics, bigDIA 2023

作者： Sun, Hong Li, Ziqiang Liu, Lei Li, Bin University of Science and Technology of China Hefei230027 China Laboratory for Big Data and Decision China Zhejiang Lab Hangzhou311121 China

ISBN: (纸本)9798350330076

The proliferation of malicious deepfake applications has ignited substantial public apprehension, casting a shadow of doubt upon the integrity of digital media. Despite the development of proficient deepfake detection mechanisms, they persistently demonstrate pronounced vulnerability to an array of attacks. It is noteworthy that the pre-existing repertoire of attacks predominantly comprises adversarial example attack, predominantly manifesting during the testing phase. In the present study, we introduce a pioneering paradigm denominated as "Bad-Deepfake,"which represents a novel foray into the realm of backdoor attacks levied against deepfake detectors. Our approach hinges upon the strategic manipulation of a delimited subset of the training data, enabling us to wield disproportionate influence over the operational characteristics of a trained model. This manipulation leverages inherent frailties inherent to deepfake detectors, affording us the capacity to engineer triggers and judiciously select the most efficacious samples for the construction of the poisoned set. Through the synergistic amalgamation of these sophisticated techniques, we achieve an remarkable performance - a 100% attack success rate (ASR) against extensively employed deepfake detectors. © 2023 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Multi Sensor Signal-based Multi-level Association strategy for Real-time Track Association and Fusion 9

Multi Sensor Signal-based Multi-level Association strategy f...

引用

9th International Conference on big data and Information Analytics, bigDIA 2023

作者： Guo, Jiaxin Fang, Zhi Yu, Zengwen Zhang, Hang Zheng, Yifan Zhang, Hong Beijing Institute of Computer Technology and Application Beijing China Laboratory for Big Data and Decision National University of Defense Technology Changsha China

ISBN: (纸本)9798350330076

The real-time track association and fusion task(the AF task) aims to integrate the tracks of maritime targets collected by sensors into a coherent track. In real-world scenarios, track data collected by a single sensor often lacks the required stability, falling short of meeting the demands of various applications. While adopting multi-sensor-based AF task methods is prevalent, existing approaches have overlooked critical aspects, including temporal consistency. This paper tackles crucial challenges in the multi-sensor AF tasks, focusing on problems such as asynchronous radar scanning and real-time matching across multiple sensors. Utilizing multi-level association and integrated learning algorithms, we enhance matching accuracy and efficiency while ensuring track continuity. Leveraging the dataset provided by the 2023 National big data and Computational Intelligence Challenge 1, our approach significantly outperforms traditional methods in three key aspects: the AF task of radar point trace , the AF task of ESM bearing line, and the AF task of rader and ESM. In comparison with conventional methods, three values are reduced by 1.1325, 0.0870, and 0.2637 on the difference metrics between the generated tracks and the actual tracks, respectively. These results further validate the significant improvements of our method in enhancing the effectiveness of the AF task. © 2023 IEEE.

关键词： multiple sensors Real-time track association and fusion

来源：评论

学校读者我要写书评

暂无评论

A Two-stage Framework for Online Unmanned Aerial Vehicles Search Planning 5

A Two-stage Framework for Online Unmanned Aerial Vehicles Se...

引用

5th International Conference on Algorithms, Computing and Artificial Intelligence, ACAI 2022

作者： Huang, Hongbin Duan, Haopeng Liu, Lihua Xiao, Kaiming Laboratory for Big Data and Decision National University of Defense Technology Changsha Hunan China

ISBN: (纸本)9781450398343

Unmanned Aerial Vehicles (UAV), also known as drones, have been widely used in regional data collection and information search, but there are also many practical challenges. In real-world operations of UAV search, the payoff and cost at each search point are unknown for the planner in advance which poses a great challenge to decision making. To this end, we first propose the problem of online decision making in UAV search planning where the drone has limited energy supply as a constraints and has to make an irrevocable decision to search this area or route to the next in an online manner. Then the online UAV search planning problem is decoupled into a traveling salesman problem (TSP) and an online resource planning problem such that it can be solved in a two-stage procedure. Specifically, the routing of search is obtained by solving TSP based on ant colony optimization, and the online decision is made through an online linear programming which is proven to be near-optimal. The effectiveness of the proposed two-stage approach is validated in wide-Applied dataset, and experimental results show the superior performance of online search decision making. © 2022 ACM.

关键词： Linear programming

来源：评论

学校读者我要写书评

暂无评论

On convergence of covariance matrix of empirical Bayes hyper-parameter estimator

引用

Control Theory and Technology 2024年第2期22卷 149-162页

作者： Yue Ju Biqiang Mu Tianshi Chen School of Data Science and Shenzhen Research Institute of Big Data The Chinese University of Hong KongShenzhenShenzhen518172GuangdongChina Division of Decision and Control Systems School of Electrical Engineering and Computer ScienceKTH Royal Institute of Technology10044StockholmSweden Key Laboratory of Systems and Control Institute of Systems ScienceAcademy of Mathematics and System ScienceChinese Academy of SciencesBeijing100190China

Regularized system identification has become the research frontier of system identification in the past *** related core subject is to study the convergence properties of various hyper-parameter estimators as the sample size goes to *** this paper,we consider one commonly used hyper-parameter estimator,the empirical Bayes(EB).Its convergence in distribution has been studied,and the explicit expression of the covariance matrix of its limiting distribution has been ***,what we are truly interested in are factors contained in the covariance matrix of the EB hyper-parameter estimator,and then,the convergence of its covariance matrix to that of its limiting distribution is *** general,the convergence in distribution of a sequence of random variables does not necessarily guarantee the convergence of its covariance ***,the derivation of such convergence is a necessary complement to our theoretical analysis about factors that influence the convergence properties of the EB hyper-parameter *** this paper,we consider the regularized finite impulse response(FIR)model estimation with deterministic inputs,and show that the covariance matrix of the EB hyper-parameter estimator converges to that of its limiting ***,we run numerical simulations to demonstrate the efficacy of ourtheoretical results.

关键词： Regularized system identification Hyper-parameter estimator Empirical Bayes Convergence of covariance matrix

来源：评论

学校读者我要写书评

暂无评论

Unraveling the Causal Graph: Investigating Disease Etiology through Causal Structure Learning 9

Unraveling the Causal Graph: Investigating Disease Etiology ...

引用

9th International Conference on big data and Information Analytics, bigDIA 2023

作者： Wu, Jibing Zhao, Yanqing Gao, Jianping Liu, Lihua Chen, Ting National University of Defense Technology Laboratory for Big Data and Decision Changsha China 31015 Army Beijing China 31151 Army Nanjing China

ISBN: (纸本)9798350330076

This paper aims to develop a robust methodology for unraveling the complex causal relationships inherent in disease dynamics, using observational data as a basis. Our primary objective is to elucidate the intricate network of causal factors influencing disease cases, with a specific focus on breast quadrant disease. To achieve this, we employ Directed Acyclic Graphs (DAGs) as our primary analytical tool. Our approach begins by constructing a fully connected graph to hypothesize potential causal links among various factors. This graph undergoes a meticulous refinement process through Conditional Independence (CI) tests, which systematically eliminates non-significant connections. The outcome is a streamlined DAG that clearly maps out both direct and indirect causal relationships relevant to disease progression. The validity and effectiveness of our model are rigorously tested using a score-based Hill-Climbing (HC) algorithm, which ensures that our causal inferences align accurately with real-world data. The culmination of this process is demonstrated through the application of our methodology to a dataset focusing on breast quadrant disease. Our findings reveal significant causal connections within this dataset, which have been corroborated by expert opinions in the field. These results not only validate our approach but also emphasize its practical utility in deciphering complex causal relationships in medical research. © 2023 IEEE.

关键词： Directed graphs

来源：评论

学校读者我要写书评

暂无评论

CMNEE: A Large-Scale Document-Level Event Extraction dataset based on Open-Source Chinese Military News 30

CMNEE: A Large-Scale Document-Level Event Extraction Dataset...

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Zhu, Mengna Xu, Zijie Zeng, Kaisheng Xiao, Kaiming Wang, Mao Ke, Wenjun Huang, Hongbin Laboratory for Big Data and Decision National University of Defense Technology China School of Computer Science and Engineering Southeast University China Computer Science and Technology Tsinghua University China

ISBN: (纸本)9782493814104

Extracting structured event knowledge, including event triggers and corresponding arguments, from military texts is fundamental to many applications, such as intelligence analysis and decision assistance. However, event extraction in the military field faces the data scarcity problem, which impedes the research of event extraction models in this domain. To alleviate this problem, we propose CMNEE, a large-scale, document-level open-source Chinese Military News Event Extraction dataset. It contains 17,000 documents and 29,223 events, which are all manually annotated based on a pre-defined schema for the military domain including 8 event types and 11 argument role types. We designed a two-stage, multi-turns annotation strategy to ensure the quality of CMNEE and reproduced several state-of-the-art event extraction models with a systematic evaluation. The experimental results on CMNEE fall shorter than those on other domain datasets obviously, which demonstrates that event extraction for military domain poses unique challenges and requires further research efforts. Our code and data can be obtained from https://***/Mzzzhu/CMNEE. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： data mining

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：