检索结果-内蒙古大学图书馆

Event detection and evolution in multi-lingual social streams

Frontiers of Computer Science 2020年第5期14卷 213-227页

作者： Yaopeng Liu Hao Peng Jianxin Li Yangqiu Song Xiong Li Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang UniversityBeijing100083China State Key Laboratory of Software Development Environment Beihang UniversityBeijing100083China Department of Computer Science and Engineering HKUSTHong Kong99907China National Computer Network Emergency Response Technical Team/Coordination Center of China Beijing100029China

Real-life events are emerging and evolving in social and news *** methods have succeeded in capturing designed features of monolingual events,but lack of interpretability and multi-lingual *** this end,we propose a multi-lingual event mining model,namely MLEM,to automatically detect events and generate evolution graph in multilingual hybrid-length text streams including English,Chinese,French,German,Russian and ***,we merge the same entities and similar phrases and present multiple similarity measures by incremental word2vec *** propose an 8-tuple to describe event for correlation analysis and evolution graph *** evaluate the MLEM model using a massive human-generated dataset containing real world *** results show that our new model MLEM outperforms the baseline method both in efficiency and effectiveness.

关键词： event detection event evolution stream processing multi-lingual anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Research on Vehicle Forward Pedestrian Recognition Based on Multi-line LIDAR

Research on Vehicle Forward Pedestrian Recognition Based on ...

引用

Chinese Intelligent Systems Conference, CISC 2019

作者： Guo, Chenyang Yu, Guizhen Zhang, Li Niu, Huan Zhou, Bin Wang, Zhangyu Li, Da 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

ISBN: (纸本)9789813296978

Pedestrians are one of the most important elements in traffic scenes. In autopilot system, pedestrians need to be accurately detected. We found the latest research that 3D light detection and ranging (LIDAR) sensors can provide more accurate pedestrian location information. In this paper, the AdaBoost algorithm is used to improve the accuracy of the support vector machine (SVM) and high-accuracy pedestrian detection based on real-time 3D point cloud data. The first step is to process 3D points to 2D grid, followed by using k-means clustering algorithm to extract candidate points of the pedestrian. Next, nine features are chosen to train the SVM, the AdaBoost iterative process is used to reduce the further error rate to meet the classification requirements. This method has achieved significant progress in our experiment, the average classification accuracy has been improved to 92.4% per scan. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Adaptive boosting

来源：评论

学校读者我要写书评

暂无评论

A Vision-Based Method for Vehicle Forward Collision Warning

A Vision-Based Method for Vehicle Forward Collision Warning

引用

Chinese Intelligent Systems Conference, CISC 2019

作者： Zhang, Yanfei Wang, Zhangyu Zhou, Bin Yu, Guizhen Hu, Chaowei Zhang, Li 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

ISBN: (纸本)9789813296978

Forward Collision Warning (FCW) system can automatically measure the distance between obstacles and provide early warning, which can effectively provide safety guarantee for vehicle travel and reduce the probability of traffic accidents. The vision-based approaches are always popular because vision sensors have the characteristics of low cost and rich image information. In this paper, a vision-based forward collision warning method is proposed. The method contains three main stages: (1) detect obstacle based on multi-feature fusion using convolution neural networks (CNN), (2) estimate the relative distance, relative velocity from vehicles and collision time, (3) design obstacles hazard level discrimination strategy for different road scenarios. The algorithm is tested on our own dataset and the experiment results showed that the method has good feasibility and robustness. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Hazards

来源：评论

学校读者我要写书评

暂无评论

Penetration trajectory optimization for the hypersonic gliding vehicle encountering two interceptors

arXiv

引用

arXiv 2022年

作者： Shen, Zhipeng Yu, Jianglong Dong, Xiwang Hua, Yongzhao Ren, Zhang School of Automation Science and Electrical Engineering Science and Technology on Aircraft Control Laboratory Beihang University Beijing100191 China Institute of Artificial Intelligence Beihang University Beijing100191 China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100191 China

The penetration trajectory optimization problem for the hypersonic gliding vehicle (HGV) encountering two interceptors is investigated. The HGV penetration trajectory optimization problem considering the terminal target area is formulated as a nonconvex optimal control problem. The nonconvex optimal control problem is transformed into a second-order cone programming (SOCP) problem, which can be solved by state-of-the-art interior-point methods. In addition, a penetration strategy that only requires the initial line-of-sight angle information of the interceptors is proposed. The convergent trajectory obtained by the proposed method allows the HGV to evade two interceptors and reach the target area successfully. Furthermore, a successive SOCP method with a variable trust region is presented, which is critical to balancing the trade-off between time consumption and optimality. Finally, the effectiveness and performance of the proposed method are verified by numerical simulations. Copyright © 2022, The Authors. All rights reserved.

关键词： Numerical methods

来源：评论

学校读者我要写书评

暂无评论

Mdpnet:A Dual-Pathway Parallel Fusion Network for Multi-Modal MRI Glioma Genotyping

SSRN

引用

SSRN 2024年

作者： Wang, Huaizhi Liu, Haichao Du, Fang Wang, Di Song, Lijuan School of Information Engineering Ningxia University Ningxia Hui Autonomous Region Yinchuan750021 China School of Advanced Interdisciplinary Studies Ningxia University Ningxia Hui Autonomous Region Zhongwei755000 China Ningxia Key Laboratory of Artificial Intelligence and Information Security for Channeling Computing Resources from the East to the West Ningxia Yinchuan750021 China Collaborative Innovation Center for Ningxia Big Data and Artificial Intelligence Co-founded by Ningxia Municipality and Ministry Ningxia Yinchuan750021 China

Glioblastomas have become the most lethal brain tumors in humans, and accurate diagnosis of gliomas is crucial for patient treatment and prognosis. Magnetic Resonance Imaging (MRI) is widely used due to its non-invasiveness and convenience. However, due to the significant heterogeneity of gliomas, even experienced neuroradiologists find it challenging to accurately differentiate glioma types based on imaging phenotypes. According to the WHO classification of central nervous system tumors, the types of gliomas can be determined based on the status of IDH, 1p/19q, and ATRX genetic markers. Current research is mostly limited to the analysis of a single molecular marker, either IDH or 1p/19q, lacking a comprehensive model to simultaneously evaluate these three critical molecular markers. Moreover, the lesion information embedded in T2 and FLAIR modalities has not been fully utilized, thus limiting the accuracy of glioma *** address this issue, we designed a dual-pathway parallel fusion network for multi-modal MRI glioma genotyping (MDPNet), which can simultaneously genotype IDH, 1p/19q, and ATRX genetic markers. MDPNet mainly consists of two parts: attention-guided asymmetric dual-pathway feature extraction (ADFE) and inter-gene relationship-guided genotyping (IGT). ADFE integrates CNN and attention mechanisms to capture both global and local information, enhancing the information from T2 and FLAIR modalities and extracting complex feature information through two parallel pathways. IGT constructs a complex classifier based on the interrelations among genes to simultaneously predict IDH mutation status, 1p/19q co-deletion status, and ATRX mutation *** evaluated our model on public datasets, and experimental results showed that our proposed method exhibited excellent performance. Ablation experiments demonstrated that utilizing the typing information of IDH and ATRX not only improved the network's performance in typing the 1p/19q gene molecule but also furt

关键词： Genes

来源：评论

学校读者我要写书评

暂无评论

Stabilization of Continuous-Time Markov/Semi-Markov Jump Linear Systems Via Finite data-Rate Feedback

SSRN

引用

SSRN 2022年

作者： Wang, Jingyi Feng, Jianwen Xu, Chen Wu, Xiaoqun Lü, Jinhu College of Mathematics and Statistics Shenzhen University Shenzhen518060 China School of Mathematics and Statistics Hubei Key Laboratory of Computational Science Wuhan University Wuhan China State Key Laboratory of Software Development Environment School of Automation Science and Electrical Engineering Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing China

This letter investigates almost sure exponential stabilization of continuous-time Markov jump linear systems (MJLSs) under communication data-rate constraints by introducing sampling and quantization into the feedback control. Different from previous works, the sampling times and the jump times are independent of each other in this letter. The quantization is recursively adjusted on the sampling time, and its updating strategy does not depend on the switching in a sampling interval. In other words, the explicit value of the switching signal in a sampling interval is not necessary. The numerically testable condition is developed to ensure almost sure exponential stabilization of MJLSs under the proposed communication and control protocols. We also drop the assumption of stabilizability of all individual modes required in previous works about the switched systems. Moreover, we extend the result to the case of continuous-time semi-Markov jump linear systems (semi-MJLSs) via the semi-Markov kernel approach. Finally, some numerical examples are presented to illustrate the effectiveness on stabilization of the proposed communication and control protocols. © 2022, The Authors. All rights reserved.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

PreZ-DGGAN: A Drug Graph GAN Based on Pre-Learning of Implicit Variables 2nd

PreZ-DGGAN: A Drug Graph GAN Based on Pre-Learning of Implic...

引用

2nd International Conference on Applied Intelligence, ICAI 2024

作者： Liu, Yixin Fan, Yueqin Li, Zhipeng Zhang, Qinhu Big Data and Intelligent Computing Research Center Guangxi Academy of Science Nanning530007 China School of Mechanical Engineering Guangxi University Nanning530004 China Ningbo Institute of Digital Twin Eastern Institute of Technology Ningbo315201 China Institute for Regenerative Medicine Medical Innovation Center and State Key Laboratory of Cardiology School of Medicine Shanghai East Hospital Tongji University Shanghai200123 China College of Advanced Agricultural Sciences Zhejiang Agriculture and Forestry University Hangzhou311300 China

ISBN: (纸本)9789819619061

In the field of drug discovery and development, deep learning techniques have become a powerful tool to accelerate the discovery and development of new drugs. In the design and optimization of lead molecules, generative adversarial network and graph neural network are one of the prime techniques for accelerating research and development, because the former is based on the idea of two-player game to learn drug features to generate effective molecules, while the unstructured inputs of the latter are well-suited for the analysis of molecular data. Therefore, this study develops a new graph generative adversarial model, called PreZ-DGGAN, by inserting the graph neural network layer into the generative adversarial network. Within PreZ-DGGAN, the latent variable input of the generator is pre-learned by an improved graph variational autoencoder, which effectively avoids the mode collapse of the generative adversarial network, whereas the hidden layer of the discriminator is graph neural network layer, which is able to better learn the real molecules and judge the generated molecules as true or false. Experiments on two molecule datasets show that the molecules generated by PreZ-DGGAN have higher validity (100% on average) and uniqueness (91.5% on average), and the generated molecules are more diverse in structure. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Hyper-IIoT: A Smart Contract-inspired Access Control Scheme for Resource-constrained Industrial Internet of Things

IEEE Transactions on Sustainable Computing

引用

IEEE Transactions on Sustainable computing 2025年

作者： Li, Dun Li, Hongzhi Crespi, Noel Minerva, Roberto Li, Ming Liang, Wei Li, Kuan-Ching Tsinghua University Department of Industrial Engineering China Institut Polytechnique de Paris Samovar Telecom SudParis Palaiseau91120 France Chizhou University College of Big Data and Artificial Intelligence Chizhou247100 China The Hong Kong Polytechnic University Research Institute for Advanced Manufacturing Hung Hom Hong Kong Hunan University of Science and Technology School of Computer Science and Engineering Hunan University of Science and Technology Sanya Research Institute Hunan Key Laboratory for Service Computing and Novel Software Technology China Providence University Dept. of Computer Science and Information Engineering Taiwan

In recent years, the refinements in industrial processes and the increasing complexity of managing privacy-sensitive data in Industrial Internet of Things (IIoT) devices have highlighted the need for secure, robust, and adaptive data management solutions. In this work, we propose a smart contract-assisted access control scheme for IIoT, which employs the Attribute-Based Access Control (ABAC) model to set access permissions for different industrial components. Besides, we defined a storage model and data format for private data by designing and deploying smart contracts to manage system operations and access policies. In addition, the bloom filter component is deployed to optimize the efficiency of contract management and system performance. Experimental results show that in real-world simulations, Hyper-IIoT demonstrates excellent contract execution time control, stable system throughput, and rapid consensus processes that are capable of handling high throughput and efficient consensus in distributed systems, even in large-scale request scenarios. © 2016 IEEE.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

Robust optimization for quantum reinforcement learning control using partial observations

引用

Physical Review A 2022年第6期105卷 062443-062443页

作者： Chen Jiang Yu Pan Zheng-Guang Wu Qing Gao Daoyi Dong State Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and Control College of Control Science and Engineering Zhejiang University Hangzhou 310027 China The School of Automation Science and Electrical Engineering and Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing 100191 China The School of Engineering and Information Technology University of New South Wales Canberra Australian Capital Territory 2600 Australia

The current quantum reinforcement learning control models often assume that the quantum states are known a priori for control optimization. However, full observation of the quantum state is experimentally infeasible due to the exponential scaling of the number of required quantum measurements on the number of qubits. In this paper, we investigate a robust reinforcement learning method using partial observations to overcome this difficulty. This control scheme is compatible with near-term quantum devices, where the noise is prevalent and predetermining the dynamics of the quantum state is practically impossible. We show that this simplified control scheme can achieve similar or even better performance when compared to the conventional methods relying on full observation. We demonstrate the effectiveness of this scheme on examples of quantum state control and the quantum approximate optimization algorithm (QAOA). It has been shown that high-fidelity state control can be achieved even if the noise amplitude is at the same level as the control amplitude. Besides, an acceptable level of optimization accuracy can be achieved for a QAOA with a noisy control Hamiltonian. This robust control optimization model can be trained to compensate for the uncertainties in practical quantum computing.

关键词： Machine learning Quantum control Quantum engineering

来源：评论

学校读者我要写书评

暂无评论

Neuromodulated Meta-Learning

arXiv

引用

arXiv 2024年

作者： Wang, Jingyao Guo, Huijie Qiang, Wenwen Li, Jiangmeng Zheng, Changwen Xiong, Hui Hua, Gang University of Chinese Academy of Sciences Beijing China National Key Laboratory of Space Integrated Information System Institute of Software Chinese Academy of Sciences Beijing China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing China Thrust of Artificial Intelligence Hong Kong University of Science and Technology Guangzhou China Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong Wormpex AI Research LLC BellevueWA98004 United States

Humans excel at adapting perceptions and actions to diverse environments, enabling efficient interaction with the external world. This adaptive capability relies on the biological nervous system (BNS), which activates different brain regions for distinct tasks. Meta-learning similarly trains machines to handle multiple tasks but relies on a fixed network structure, not as flexible as BNS. To investigate the role of flexible network structure (FNS) in meta-learning, we conduct extensive empirical and theoretical analyses, finding that model performance is tied to structure, with no universally optimal pattern across tasks. This reveals the crucial role of FNS in meta-learning, ensuring meta-learning to generate the optimal structure for each task, thereby maximizing the performance and learning efficiency of meta-learning. Motivated by this insight, we propose to define, measure, and model FNS in meta-learning. First, we define that an effective FNS should possess frugality, plasticity, and sensitivity. Then, to quantify FNS in practice, we present three measurements for these properties, collectively forming the structure constraint with theoretical supports. Building on this, we finally propose Neuromodulated Meta-Learning (NeuronML) to model FNS in meta-learning. It utilizes bi-level optimization to update both weights and structure with the structure constraint. Extensive theoretical and empirical evaluations demonstrate the effectiveness of NeuronML on various tasks. Code is publicly available at https://***/WangJingyao07/NeuronML. Copyright © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning

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：