检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Li, Qian Guo, Shu Wu, Jia Li, Jianxin Sheng, Jiawei Wang, Lihong Dong, Xiaohan Peng, Hao Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing China School of Computer Science and Engineering Beihang University Beijing China National Computer Network Emergency Response Technical Team Coordination Center of China Beijing China Department of Computing Macquarie University Sydney Australia Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China

Event extraction (EE), which acquires structural event knowledge from texts, can be divided into two sub-tasks: event type classification and element extraction (namely identifying triggers and arguments under different role patterns). As different event types always own distinct extraction schemas (i.e., role patterns), previous work on EE usually follows an isolated learning paradigm, performing element extraction independently for different event types. It ignores meaningful associations among event types and argument roles, leading to relatively poor performance for less frequent types/roles. This paper proposes a novel neural association framework for the EE task. Given a document, it first performs type classification via constructing a document-level graph to associate sentence nodes of different types, and adopting a graph attention network to learn sentence embeddings. Then, element extraction is achieved by building a universal schema of argument roles, with a parameter inheritance mechanism to enhance role preference for extracted elements. As such, our model takes into account type and role associations during EE, enabling implicit information sharing among them. Experimental results show that our approach consistently outperforms most state-of-the-art EE methods in both sub-tasks. Particularly, for types/roles with less training data, the performance is superior to the existing methods. Copyright © 2021, The Authors. All rights reserved.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Graph structure learning with Variational Information Bottleneck

arXiv

引用

arXiv 2021年

作者： Sun, Qingyun Li, Jianxin Peng, Hao Wu, Jia Fu, Xingcheng Ji, Cheng Yu, Philip S. Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100191 China School of Computer Science and Engineering Beihang University Beijing100191 China Shenyuan Honors College Beihang University Beijing100191 China School of Computing Macquarie University Sydney Australia Department of Computer Science University of Illinois at Chicago Chicago United States

Graph Neural Networks (GNNs) have shown promising results on a broad spectrum of applications. Most empirical studies of GNNs directly take the observed graph as input, assuming the observed structure perfectly depicts the accurate and complete relations between nodes. However, graphs in the real-world are inevitably noisy or incomplete, which could even exacerbate the quality of graph representations. In this work, we propose a novel Variational Information Bottleneck guided Graph Structure Learning framework, namely VIB-GSL, in the perspective of information theory. VIB-GSL advances the Information Bottleneck (IB) principle for graph structure learning, providing a more elegant and universal framework for mining underlying task-relevant relations. VIB-GSL learns an informative and compressive graph structure to distill the actionable information for specific downstream tasks. VIB-GSL deduces a variational approximation for irregular graph data to form a tractable IB objective function, which facilitates training stability. Extensive experimental results demonstrate that the superior effectiveness and robustness of VIB-GSL. Copyright © 2021, The Authors. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Multiple Pseudo-Local Feedbacks for Controlling High-Order Oscillatory Objects 15

Multiple Pseudo-Local Feedbacks for Controlling High-Order O...

引用

15th International Scientific-Technical Conference on Actual Problems of Electronic Instrument engineering, APEIE 2021

作者： Zhmud, V.A. Nosek, J. Mansurova, M.E. Semibalamut, V.M. Fomin, Yu. N. Stukach, O.V. Novosibirsk State Technical University Institute of Laser Physics Sb Ras Dept. of Automation Novosibirsk Russia Technical University of Liberec Inst. of Mechatronics and Computer Engineering Liberec Czech Republic Al-Farabi Kazakh National University Department of Artificial Intelligence and Big Data Almaty Kazakhstan Unified Geophysical Service of the Russian Academy of Sciences Siberian Branch of the Federal State Budgetary Institution of Science of the Federal Research Center Novosibirsk Russia Novosibirsk State Technical University Higher School of Economics Dept. of Information Defense Moscow Russia

ISBN: (纸本)9781665434089

Development of the Internet of things (IoT) technologies arises many additional problems as energy harvesting. In particular, a long-Time controlling object needs a device without an external power supply. The control of technical objects with a high order of mathematical model has a large difficulty if a feature of the object is a high tendency to oscillations due to the ratio of the coefficients in the model. In particular, the tendency to oscillations occurs if the object model has complex roots, or if the model has a transport delay. One such example is a model that consists of two oscillatory objects and a delay loop. Widespread controlling such an objects using a PID controller is very difficult since in the transient process in the resulting system there is a large overshoot and many oscillations. If such an object could be stabilized with additional local feedbacks, the control task would be greatly simplified, but the object does not have corresponding outputs and inputs, therefore local feedbacks cannot be used. The pseudo-local feedback approach assumes the use of virtual fragments of the object's mathematical model in the controller to form such connections that the system perceives as local ones. This paper proposed the use of several pseudo-local feedbacks to control an object with elements that increased its tendency to oscillate. The effectiveness of the proposed approach is confirmed by modeling. © 2021 IEEE.

关键词： Feedback

来源：评论

学校读者我要写书评

暂无评论

Dynamic neural network approach to human emotion: an analysis based on sliding time windows

Dynamic neural network approach to human emotion: an analysi...

引用

IEEE International Conference on Cognitive Informatics

作者： Jingqi Wang Gen Shi Ning Ma Yang Sun Xuesong Li Jie Sui School of Computer Science and Technology Beijing Institute of Technology Beijing China Department of Echocardiography Big Data and Engineering Research Center Beijing Children&#x2019 s Hospital Capital Medical University Beijing China School of Educational Science Shenyang Normal University Shenyang China School of Psychology University of Aberdeen Aberdeen UK

ISBN: (纸本)9781665421201

Emotion is a key motivational factor of a person strivings for health and well-being. Understanding neural networks supporting different types of emotion bears far-reaching implications for mental health. Recent studies suggest that emotional processing is associated with a large number of brain regions. However, the precise functional connectivity (FC) of these regions in investigations of emotional processing are largely unknown. To address this issue, we recruited 359 participants who completed emotional-related measures including the Positive and Negative Affect Schedule (PANAS) the Self-Compassion Scale, while scanned with resting-state functional magnetic resonance images (fMRI). Here, we proposed a novel psychological characteristics analysis framework by using a dynamic sliding window method to characterize the nature of resting-state functional connectivity in the human brain, in relation to the static FC method. The comparison results showed that the dynamic FC method produced the better performance, compared to the static FC method. The global network analyses across all 6 possible connectivity matrices further demonstrated that the dynamically hemispheric asymmetry best predicted emotional processing. The dynamic FC method was evaluated on the three emotional labels - positive emotion, negative emotion, self-compassion and the best prediction performance was consistently observed in the dynamically hemispheric asymmetric FC.

关键词： Schedules Computational modeling Magnetic resonance Network analyzers Mental health Machine learning Functional magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

FedMood: Federated learning on mobile health data for mood detection

arXiv

引用

arXiv 2021年

作者： Xu, Xiaohang Peng, Hao Sun, Lichao Bhuiyan, Md Zakirul Alam Liu, Lianzhong He, Lifang School of Cyber Science and Technology Beihang University Beijing100083 China Beijing Advanced Innovation Center for Big Data and Brain Computing Beijing100083 China Department of Computer Science University of Illinois at Chicago Chicago United States Department of Computer and Information Sciences Fordham University JMH 334 E Fordham Road BronxNY10458 United States Department of Computer Science and Engineering Lehigh University BethlehemPA18015 United States

Depression is one of the most common mental illness problems, and the symptoms shown by patients are not consistent, making it difficult to diagnose in the process of clinical practice and pathological research. Although researchers hope that artificial intelligence can contribute to the diagnosis and treatment of depression, the traditional centralized machine learning needs to aggregate patient data, and the data privacy of patients with mental illness needs to be strictly confidential, which hinders machine learning algorithms clinical application. To solve the problem of privacy of the medical history of patients with depression, we implement federated learning to analyze and diagnose depression. First, we propose a general multi-view federated learning framework using multi-source data,which can extend any traditional machine learning model to support federated learning across different institutions or parties. Secondly, we adopt late fusion methods to solve the problem of inconsistent time series of multi-view data. Finally, we compare the federated framework with other cooperative learning frameworks in performance and discuss the related results. Copyright © 2021, The Authors. All rights reserved.

关键词： data privacy

来源：评论

学校读者我要写书评

暂无评论

Co-Designed Communication and Computing for data Reliability in Industrial Cyber-Physical Systems with Cloud-Fog Automation

引用

IEEE Journal on Selected Areas in Communications 2025年

作者： Fan, Xiaoxuan Deng, Xianjun Liu, Shenghao Zhu, Chenlu Zhou, Xinlei Yi, Lingzhi Wu, Libing Park, Jong Hyuk Huazhong University of Science and Technology Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering China Wuhan Research Institute of Posts and Telecommunications China Zhongnan University of Economics and Law School of Information Engineering China Wuhan University School of Cyber Science and Engineering China Seoul National University of Science and Technology Department of Computer Science and Engineering Korea Republic of

The Cloud-Fog Automation is a newly proposed digital industrial automation architecture aimed at accelerating the integration and collaboration of communication, computing, and control towards next-generation cyber-physical systems (CPSs). data reliability is one of the key considerations for achieving Cloud-Fog Automation. Sensor nodes serve as infrastructures for data collection within industrial CPSs and are essential for maintaining ultra-high data reliability. However, the underlying sensor nodes communicate frequently, are damage-prone and difficult to identify, which dramatically shortens the network lifetime and poses great challenges to data reliability. Motivated by this fact, this paper co-designs communication architecture, algorithms, and computing models for next-generation industrial CPSs with Cloud-Fog Automation to ensure data reliability and functional security. First, a four-layer energy-efficient communication architecture is proposed and a cluster head computing algorithm based on double deep Q-learning (CH-DDQ) is designed inside the architecture. Besides, a 2-stage hyBrid fault detection scheme (2-Brain) is proposed for underlying sensor nodes. 2-Brain first incorporates the Obstacle Triple Jump Protocol (OTP) and OTP packets to improve hard fault detection performance. Then, an unsupervised sensor reading soft fault detection model (SR-SFD) based on contrastive learning, momentum, and tensor is adopted to learn discriminative representations of sensor readings and identify soft faults. Simulations and a case study in the nuclear power industry manifest CH-DDQ improves the network lifetime by 5.4%484.3% compared to three peer methods, and OTP performs better than baselines by 33.1% on average. Additionally, SR-SFD exhibits high efficiency in sensor soft fault detection and other application scenarios. © 1983-2012 IEEE.

关键词： Cluster computing

来源：评论

学校读者我要写书评

暂无评论

µVulDeePecker: A deep learning-based system for multiclass vulnerability detection

arXiv

引用

arXiv 2020年

作者： Zou, Deqing Wang, Sujuan Xu, Shouhuai Li, Zhen Jin, Hai National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab Big Data Security Engineering Research Center School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan430074 China Shenzhen Huazhong University of Science and Technology Research Institute Shenzhen518057 China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab Big Data Security Engineering Research Center School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China Department of Computer Science University of Texas at San Antonio San AntonioTX78249 United States

Fine-grained software vulnerability detection is an important and challenging problem. Ideally, a detection system (or detector) not only should be able to detect whether or not a program contains vulnerabilities, but also should be able to pinpoint the type of a vulnerability in question. Existing vulnerability detection methods based on deep learning can detect the presence of vulnerabilities (i.e., addressing the binary classification or detection problem), but cannot pinpoint types of vulnerabilities (i.e., incapable of addressing multiclass classification). In this paper, we propose the first deep learning-based system for multiclass vulnerability detection, dubbed µVulDeePecker. The key insight underlying µVulDeePecker is the concept of code attention, which can capture information that can help pinpoint types of vulnerabilities, even when the samples are small. For this purpose, we create a dataset from scratch and use it to evaluate the effectiveness of µVulDeePecker. Experimental results show that µVulDeePecker is effective for multiclass vulnerability detection and that accommodating control-dependence (other than data-dependence) can lead to higher detection capabilities. Copyright © 2020, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

CT Scan Synthesis for Promoting computer-Aided Diagnosis Capacity of COVID-19 16th

CT Scan Synthesis for Promoting Computer-Aided Diagnosis Cap...

引用

16th International Conference on Intelligent Computing, ICIC 2020

作者： Li, Heng Hu, Yan Li, Sanqian Lin, Wenjun Liu, Peng Higashita, Risa Liu, Jiang School of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China Big Data Research Center University of Electronic Science and Technology of China Chengdu611731 China Tomey Corporation Nagoya451-0051 Japan Department of Computer Science and Engineering Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation Southern University of Science and Technology Shenzhen518055 China Ningbo Institute of Industrial Technology Chinese Academy of Sciences Ningbo China

ISBN: (纸本)9783030608019

Nowadays, with the rapid spread of Corona Virus Disease 2019 (COVID-19), this epidemic has become a threatening risk for global public health. Medical workers and researchers all over the world are struggling against the novel coronavirus in the front line. Because the computed tomography (CT) images from infected patients exposure characteristic abnormalities, automatic CT analyzers based on AI-based algorithms are extensively employed as effective weapons to aid clinicians. However, unbalanced data and lack of annotations obstruct AI-based algorithms applying in aided diagnosis because of their low performance. Therefore, in order to solve the above problems, a general-purpose solution is proposed to synthesize COVID-19 CT scans from non-COVID-19 data for providing high-quality negative-positive paired CT scans. Particularly, we introduce an elastic registration algorithm of CT images to manufacture paired training data. Then, a conditional Generative Adversarial Networks (GANs) based image-to-image translation model is implemented to synthesize COVID-19 CT scans from non-COVID-19 data. The effectiveness of our proposed algorithm used in COVID-19 aided diagnosis is verified in the experiments, and the identification and detection capacities of the classification models have been enhanced with the generated CT scans. Specifically, the precise lesion location is achieved by the generated data with a weakly supervised algorithm of class activation mapping (CAM). The model and code of this paper are publicly available at https://***/lihengbit/Synthesis-of-COVID-19-CT-Scan. © 2020, Springer Nature Switzerland AG.

关键词： computer aided diagnosis

来源：评论

学校读者我要写书评

暂无评论

A Correlation Visual Analytics System for Air Quality

引用

Chinese Journal of Electronics 2018年第5期27卷 920-926页

作者： DU Yi Abish Malik ZHOU Lianke ZHOU Yuanchun Department of Big Data Technology and Application Development Computer Network Information CenterChinese Academy of Sciences Davista Technologies College of Computer Science and Technology at Harbin Engineering University

A visual analytics system is proposed to reveal the lead/lag correlation when air pollution is detected. In this system, an Overview + Detail approach is utilized for analyzing the correlation of air quality under both the spatial and temporal dimensions and different spatial-temporal scales. An annular container is proposed to preserve the context spatial information while the zoom level of the map changes. Based on the annular container, several analysis techniques such as STL decomposition view and correlation algorithm are integrated.

关键词： Spatial-temporal visualization Time series visualization Correlation analysis Air pollution

来源：评论

学校读者我要写书评

暂无评论

Spatial fuzzy C-means clustering and deep belief network for change detection in synthetic aperture radar images 5

Spatial fuzzy C-means clustering and deep belief network for...

引用

IET International Radar Conference 2020, IET IRC 2020

作者： Qi, Wenwen Wu, Lin Guo, Zhengwei Huang, Dan College of Computer and Information Engineering Henan University Kaifeng475004 China Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng475004 China Henan Engineering Research Center of Intelligent Technology and Application Henan University Kaifeng475004 China College of Environment and Planning Henan University Kaifeng475004 China Department of Laboratory and Equipment Management Henan University Kaifeng475004 China

ISBN: (纸本)9781839535635

In this study, spatial fuzzy c-means (SFCM) clustering and deep belief network (DBN) method is presented for change detection in SAR images. There are three primary steps of this approach, they are given as follows: 1) Difference Image (DI) is firstly obtained by calculating the similarity of gray levels between multitemporal SAR images. 2) SFCM clustering is used to analyze DI, which combines the spatial information factor and the fuzzy cluster membership function, thus can effectively eliminate the interference of speckle noise. 3) DBN, a powerful data processing methodology that integrates deep learning techniques to extract underlying features and structures of complicated data, is trained to classify pixels to be changed or unchanged. The effectiveness and robustness of the proposed method are verified by experimental results with the Ottawa dataset. © 2020 Institution of engineering and Technology. All rights reserved.

关键词： Membership functions

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：