检索结果-内蒙古大学图书馆

12th International Conference on Identification, Information and Knowledge in the internet of Things, IIKI 2021

作者： Zhang, Xiangbo Rao, Yuan Sun, Ling Lab of Social Intelligence and Complexity Data Processing School of Software Engineering Xi'an Jiaotong University Shaanxi Xi'an710049 China Shannxi Joint Key Laboratory for Artifact Intelligence Sub-Lab of Xi'an Jiaotong University China Research Institute of Xi'an Jiaotong University Shenzhen China

Graph attention network (GAT) has achieved great success in graph representation learning in recent years. However, the lower Physical properties of GAT in training process severely affects the application of attention mechanism in graph domain. Particularly, the attention coefficients and the multi-head mechanism are calculated or introduced in the process of model training, which obviously increases the storage complexity. In this paper, we present a graph explicit attention network (GEAT), a novel graph attention architecture that leverage predefined strategy to calculate attention coefficients, which combine global structural and node feature information. In this way, GEAT can effectively reduce the storage complexity, improve the training efficiency and alleviate the over-smoothing problem of attention scores. Experiments on benchmark datasets — Core, Citeseer and Pubmed — demonstrate that our model outperforms the state-of-the-art methods with a clear margin in challenging classifcation tasks, while being computationally efficient. © 2022 The Authors. Published by Elsevier B.V.

关键词： Attention mechanism Deep Learning Graph neural network

来源：评论

学校读者我要写书评

暂无评论

Wideband polarization reconfigurable antenna based on double C-shaped radiators

Wideband polarization reconfigurable antenna based on double...

引用

2022 International Applied Computational Electromagnetics Society Symposium, ACES-China 2022

作者： Liang, Weilong Li, Long Wu, Zhao Huang, Yanhu Ma, Qingxiu Liang, Jiajun Nanjing Research Institute of Electronics Technology Nanjing210000 China Yulin Normal University School of Physics and Telecommunication Engineering Yulin537000 China Guangxi Colleges Universities Key Lab of Complex System Optimization and Big Data Processing Yulin Normal University Yulin537000 China

ISBN: (纸本)9781665452366

An enhancing bandwidth tri-polarization reconfigurable antenna based on double C-shaped radiators is proposed. The antenna consists of a modified ground plane, double C-shaped radiators, and a feedline with a simple parasitic stub. The modified ground plane and the parasitic stub can improve the impedance matching, meanwhile, adjust the axial ratio performance. Two PIN diodes are embedded between the C-shaped radiator and the feedline. Three polarization reconfigurable modes can be achieved caused by switching two PIN diodes state, linear polarization (LP), left-hand circular polarization (LHCP), and right-hand circular polarization (RHCP). As the simulated results show, the -10-dB impedance bandwidth reaches 126.6% (1.76-7.83 GHz) in LP mode and 78.4% (2.96-6.78 GHz) in CP modes. And the proposed antenna has a 3-dB axial ratio (AR) bandwidth of 84% (2.6-6.4 GHz) in two CP modes. Therefore, the proposed antenna can meet the requirement of the modern wireless and satellite communication system. © 2022 IEEE.

关键词： Radiators

来源：评论

学校读者我要写书评

暂无评论

Detection of Venous Thromboembolism Using Recurrent Neural Networks with Time-Series data 24

Detection of Venous Thromboembolism Using Recurrent Neural N...

引用

3rd Asia Conference on Algorithms, Computing and Machine Learning, CACML 2024

作者： Xu, Can Huang, Yaqin Xiang, Xinni Lei, Haike Yang, Jie Shanghai Jiao Tong University Shanghai China Chongqing University Cancer Hospital Chongqing China West China Hospital Sichuan University Chengdu China Shanghai Jiao Tong University Institute of Image Processing and Pattern Recognition China Chongqing Key Laboratory of Translational Research for Cancer Metastasis and Individualized Treatment China West China School of Medicine China Chongqing Cancer Multi-omics Big Data Application Engineering Research Center China

ISBN: (纸本)9798400716416

Machine Learning (ML) has been widely applied to medical science for decades. As common knowledge, the progress of many diseases is often chronic and dynamic. Longitudinal data, or time-series data, has better descriptions of certain diseases, as it naturally captures the dynamic over time. Venous thromboembolism (VTE), as a regular complication of cancer tumour treatments, has been emphasized in many studies. Recent research has shown that ML algorithms incredibly contribute to VTE risk estimation and prediction. However, existing methods rarely consider the dynamic changes during the development of VTE, and often make decisions based on time-point data, such as the latest blood test results of patients. In this paper, we propose a VTE detection model that takes advantage of capturing dynamic information using time-series data. The model consists of a Recurrent Neural Network (RNN) based framework with time embedding and Attention mechanism to encode longitudinal features of patients. We test our proposed model on a real-world dataset that contains multiple times of blood test results of patients together with other clinical features. The network is compared with several commonly used ML models in previous VTE studies. The results show that our model outperforms all baseline models, and achieved a state-of-art performance with 80.0% accuracy and 0.881 AUC. © 2024 ACM.

关键词： Risk assessment

来源：评论

学校读者我要写书评

暂无评论

Generated Compressed Domain Images to the Rescue: Cross Distillation from Compressed Domain to Pixel Domain

Generated Compressed Domain Images to the Rescue: Cross Dist...

引用

IEEE International Symposium on Circuits and Systems (ISCAS)

作者： Reyhan Kevser Keser Muhammet Sebul Beratoğlu Behçet Uğur Töreyin Signal Processing for Computational Intelligence Research Group (SP4CING) Informatics Institute İstanbul Technical University İstanbul Türkiye Dept. of Artificial Intelligence and Data Engineering Signal Processing for Computational Intelligence Research Group (SP4CING) İstanbul Technical University İstanbul Türkiye

ISBN: (数字)9798350330991

ISBN: (纸本)9798350331004

data are the essential component in the pipeline of training a model that determines the performance of the model. However, there may not be enough data that meet the requirements of some tasks. In this paper, we introduce a knowledge distillation-based approach that mitigates the disadvantages of data scarcity. Specifically, we propose a method that boosts the pixel domain performance of a model, by utilizing compressed domain knowledge via cross distillation between these two modalities. To evaluate our approach, we conduct experiments on two computer vision tasks which are object detection and recognition. Results indicate that compressed domain features can be utilized for a task in the pixel domain via our approach, where data are scarce or not completely available due to privacy or copyright issues.

关键词： Training data privacy Computer vision Image coding Computational modeling Pipelines Object detection

来源：评论

学校读者我要写书评

暂无评论

Technical Function-effect Based Patent Multi-to-One Negation Game Model 25

Technical Function-effect Based Patent Multi-to-One Negation...

引用

25th IEEE International Conference on Computer Supported Cooperative Work in Design, CSCWD 2022

作者： Du, Lu Liu, Weidong Xiao, Kaiyang Gao, Shixuan Han, Yong College of Computer Science Inner Mongolia University Hohhot China Institute of Scientific and Technical Information of China Beijing China Natl. and Loc. Jt. Eng. Res. Center of Intelligent Information Processing Technology for Mongolian Hohhot China Inner Mongolia Key Laboratory of Social Computing and Data Processing Hohhot China Inner Mongolia Engineering Laboratory for Big Data Analysis Technology Hohhot China Inner Mongolia Intellectual Property Service Center Hohhot China

ISBN: (纸本)9781665405270

As the number of patent applications increases yearly, the negation relation between patents has become intertwined, which makes it difficult for constructing negation relation in patent examination manually. Therefore, how to automatically construct negation relation between patents has become the hot research. Constructing negation relation is the process of comparing technical features between patents, which depends on the technical features in the patent claims and the technical function-effect. Although there are many researches on patent one-to-one negation, few researches on patent multi-to-one negation. The research on negation relation of multi-to-one patents, has the following challenges: (1) the definition of patent features is ambiguous in comparison of negation relation;(2) the role of patent function-effect is often ignored in judgement of negation relation. To solve the above issues, we propose a technical function-effect based patent multi-to-one negation game model. In the model, we decompose patent technical features into technical utility and technical function-effect. Patent technical utility is mainly realized by using the valence theory in linguistics. After obtaining technical utility, we choose to have the same technical effect, express the technical features of different technical functions, and obtain the patent technical function-effect. Finally, we combine the technical utility and function-effect to construct a technical utility/function-effect game tree to judge the patent negation relation. According to the two-tailed test in the A/B-test, our model outperforms the baseline model in the evaluation measurement. This model can subsequently be used to calculate the portfolio value and the strategic value of the patents. © 2022 IEEE.

关键词： Patents and inventions

来源：评论

学校读者我要写书评

暂无评论

Research On Tourist Destination Passenger Flow Prediction Based On Decomposition Clustering Technology For data Continuity Problem

Research On Tourist Destination Passenger Flow Prediction Ba...

引用

Culture-Oriented Science and Technology (CoST), International Conference on

作者： Lianze Feng Lin Mu Yi Yang Caihong Li School of information Science and Engineering Lanzhou University Lanzhou China Key Laboratory of Tourism Information Fusion Processing and Data Ownership Protection Ministry of Culture and Tourism Lanzhou China Tourism quality supervision and management institute of China Beijing China

ISBN: (数字)9798350380347

ISBN: (纸本)9798350380354

Tourist flow prediction faces challenges in achieving high accuracy due to the complex and dynamic nature of tourism data. This study addresses these challenges by proposing a multi-feature combined prediction model, Complete Ensemble Empirical Mode Decomposition with Adaptive Noise-Incremental Entropy-K-means clustering-Time Convolutional Network-Coati Optimization Algorithm (CEEMDAN-IEK-TT-COA). The model integrates signal decomposition, clustering reconstruction, component prediction, and optimization algorithms. Key features are selected through feature engineering, followed by data decomposition and reconstruction using CEEMDAN, Incremental Entropy, and K-means clustering. A model pool of Time Convolutional Network (TCN), Bidirectional Gated Recurrent Unit (Bi-GRU), Long Short-Term Memory network (LSTM), and Transformer filters optimal sub-models for combined prediction. The Coati Optimization Algorithm (COA) refines the final prediction. Experimental results on Jiuzhaigou and Siguniangshan datasets demonstrate significant RMSE improvements of $21.81 \%$ and $17.84 \%$, validating the model’s effectiveness.

关键词： Adaptation models Clustering algorithms Predictive models Prediction algorithms Feature extraction Transformers data models

来源：评论

学校读者我要写书评

暂无评论

Article reranking by memory-enhanced key sentence matching for detecting previously fact-checked claims 59

Article reranking by memory-enhanced key sentence matching f...

引用

Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language processing, ACL-IJCNLP 2021

作者： Sheng, Qiang Cao, Juan Zhang, Xueyao Li, Xirong Zhong, Lei Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China Key Lab of Data Engineering and Knowledge Engineering Renmin University of China China

ISBN: (纸本)9781954085527

False claims that have been previously fact-checked can still spread on social media. To mitigate their continual spread, detecting previously fact-checked claims is indispensable. Given a claim, existing works retrieve fact-checking articles (FC-articles) for detection and focus on reranking candidate articles in the typical two-stage retrieval framework. However, their performance may be limited as they ignore the following characteristics of FC-articles: (1) claims are often quoted to describe the checked events, providing lexical information besides semantics;and (2) sentence templates to introduce or debunk claims are common across articles, providing pattern information. In this paper, we propose a novel reranker, MTM (Memoryenhanced Transformers for Matching), to rank FC-articles using key sentences selected using event (lexical and semantic) and pattern information. For event information, we propose to finetune the Transformer with regression of ROUGE. For pattern information, we generate pattern vectors as a memory bank to match with the parts containing patterns. By fusing event and pattern information, we select key sentences to represent an article and then predict if the article fact-checks the given claim using the claim, key sentences, and patterns. Experiments on two real-world datasets show that MTM outperforms existing methods. Human evaluation proves that MTM can capture key sentences for explanations. The code and the dataset are at https://***/ICTMCG/MTM. © 2021 Association for Computational Linguistics

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Anchor-points Assisted Uplink Sensing in Perceptive Mobile Networks

arXiv

引用

arXiv 2024年

作者： Hu, Yanmo Andrew Zhang, J. Deng, Weibo Jay Guo, Y. Key Laboratory of Marine Envi-ronmental Monitoring and Information Processing Ministry of Industry and Information Technology China the School of Electronic and Information Engineering Harbin Institute of Technology China Global Big Data Technologies Centre the University of Technology Sydney Australia

Uplink sensing in integrated sensing and communications (ISAC) systems, such as Perceptive Mobile Networks, is challenging due to the clock asynchronism between transmitter and receiver. Existing solutions typically require the presence of a dominating line-of-sight path and the knowledge of transmitter location at the receiver. In this paper, relaxing these requirements, we propose a novel and effective uplink sensing scheme with the assistance of static anchor points. Two major algorithms are proposed in the scheme. The first algorithm estimates the relative timing and carrier frequency offsets due to clock asynchronism, with respect to those at a randomly selected reference snapshot. Theoretical performance analysis is provided for the algorithm. The estimates from the first algorithm are then used to compensate for the offsets and generate the angle-Doppler maps. Using the maps, the second algorithm identifies the anchor points, and then locates the UE and dynamic targets. Feasibility of UE localization is also analyzed. Simulation results are provided and demonstrate the effectiveness of the proposed algorithms. © 2024, CC BY.

关键词： Wireless networks

来源：评论

学校读者我要写书评

暂无评论

Neural Source Coding For Bandwidth-Efficient Brain-Computer Interfacing With Wireless Neuro-Sensor Networks

Neural Source Coding For Bandwidth-Efficient Brain-Computer ...

引用

International Conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Thomas Strypsteen Alexander Bertrand Department of Electrical Engineering (ESAT) STADIUS Center for Dynamical Systems Signal Processing and Data Analytics KU Leuven Leuven Belgium Leuven.AI KU Leuven Institute for AI Leuven Belgium

Neural Source Coding (NSC) is a technique that exploits the modelling power of (deep) neural network for the purpose of source coding. Its goal is to transform the data into a space of low entropy, where they can be coded by classic entropy coding schemes. In this paper, our goal is to investigate the use of NSC in so-called neuro-sensor networks, i.e., a type of body-sensor network consisting of a collection of wireless sensor nodes that record brain activity at different scalp locations, e.g., via electroencephalography (EEG) sensors. All nodes wirelessly transmit their data to a fusion center, where inference is then performed on the joint sensor signals by a given deep neural network. The NSC parameters and inference network are learned jointly, optimizing the trade-off between accuracy and bitrate for a given application. We validate this method on a motor execution task in an emulated EEG sensor network and compare the resulting trade-offs with those obtained by directly quantizing the transmitted data to low-bit precision. We demonstrate that NSC yields more favorable trade-offs than straightforward quantization for very low bit depths and allows for large bandwidth gains at little loss in accuracy on the investigated brain-computer interface (BCI) task.

关键词： Wireless communication Deep learning Wireless sensor networks Source coding Transforms Electroencephalography Brain-computer interfaces

来源：评论

学校读者我要写书评

暂无评论

Observation of spectral lines in the exceptional GRB 221009A

引用

Science China(Physics,Mechanics & Astronomy) 2024年第8期67卷 187-206页

作者： Yan-Qiu Zhang Shao-Lin Xiong Ji-Rong Mao Shuang-Nan Zhang Wang-Chen Xue Chao Zheng Jia-Cong Liu Zhen Zhang Xi-Lu Wang Ming-Yu Ge Shu-Xu Yi Li-Ming Song Zheng-Hua An Ce Cai Xin-Qiao Li Wen-Xi Peng Wen-Jun Tan Chen-Wei Wang Xiang-Yang Wen Yue Wang Shuo Xiao Fan Zhang Peng Zhang Shi-Jie Zheng Key Laboratory of Particle Astrophysics Institute of High Energy PhysicsChinese Academy of SciencesBeijing 100049China University of Chinese Academy of Sciences Beijing 100049China Yunnan Observatories Chinese Academy of SciencesKunming 650011China Center for Astronomical Mega-Science Chinese Academy of SciencesBeijing 100012China Key Laboratory for the Structure and Evolution of Celestial Objects Chinese Academy of SciencesKunming 650216China College of Physics and Hebei Key Laboratory of Photophysics Research and Application Hebei Normal UniversityShijiazhuang 050024China Guizhou Provincial Key Laboratory of Radio Astronomy and Data Processing Guizhou Normal UniversityGuiyang 550001China College of Electronic and Information Engineering Tongji UniversityShanghai 201804China

As the brightest gamma-ray burst ever observed,GRB 221009A provided a precious opportunity to explore spectral line *** this article,we performed a comprehensive spectroscopy analysis of GRB 221009A jointly with GECAM-C and Fermi/GBM data to search for emission and absorption *** the first time we investigated the line feature throughout this GRB including the most bright part where many instruments suffered problems,and identified prominent emission lines in multiple time *** central energy of the Gaussian emission line evolves from about 37 to 6 MeV,with a nearly constant ratio(about 10%)between the line width and central ***,we find that both the central energy and the energy flux of the emission line evolve with time as a power law decay with power law index of–1 and–2,*** suggest that the observed emission lines most likely origin from the blue-shifted electron positron pair annihilation 511 ke V *** find that a standard high latitude emission scenario cannot fully interpret the observation,thus we propose that the emission line comes from some dense clumps with electron positron pairs traveling together with the *** this scenario,we can use the emission line to directly,for the first time,measure the bulk Lorentz factor of the jet(Γ)and reveal its time evolution(i.e.,Γ~t^(-1))during the prompt ***,we find that the flux of the annihilation line in the co-moving frame keeps *** discoveries of the spectral line features shed new and important lights on the physics of GRB and relativistic jet.

关键词： GRB GRB 221009A emission line

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：