检索结果-内蒙古大学图书馆

8th International Conference on Digital Home, ICDH 2020

作者： Huang, Wenming Zhang, Juan Xiao, Yannan Han, Zheng Deng, Zhenrong Guilin University of Electronic Technology School of Computer Science and Information Security Guilin China Key Laboratory of Intelligent Processing of Computer Image and Graphics Guilin China Guilin Bank Guilin China

ISBN: (纸本)9781728192345

Chinese named entity recognition (CNER) in the judicial domain is an important basic task for intelligent analysis and processing of massive documents. This domain entity has more complicated structure than the common named entity, and its entity category is more abundant. However, the general method can not solve the problem of domain specific identification. In this paper, we combine self-attention mechanism and iteration dilated convolution neural network (IDCNN) for CNER in judicial domain. The bidirectional gate recurrent unit (BiGRU) model is used to automatically learn the context semantic information of the text and solve the long-distance dependence of the sequence. The model introduce the IDCNN to extract the key features of context semantic information, and capture finer-grained semantic information in underlying texts. The self-attention mechanism is used to analyze the relationship between characters, and the problem of long sequence semantic dilution is effectively solved by means of dynamic weight, and the optimal tag sequence is calculated by integrating conditional random fields (CRF), which further improves the recognition ability of the model. Finally, by analyzing the characteristics of legal documents, the new data set is annotated and the fine-grained named entity recognition is realized. The experimental results on our corpus show that the proposed method can effectively identify the entities in legal documents, and improve performance in the judicial field. © 2020 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Autocorrelation Invariance Property of Chaos for Wireless Communication

arXiv

引用

arXiv 2022年

作者： Yin, Hui-Ping Ren, Hai-Peng Grebogi, Celso Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi'an University of Technology Xi'An710048 China Institute for Complex Systems and Mathematical Biology University of Aberdeen AB24 3UE United Kingdom

A new feature of the chaotic signal generated by chaotic shape-forming filter (CSF) is uncovered in this work. We find that, the autocorrelation function (ACF) of the transmitting signal generated by CSF keeps the same as that of the base function of CSF, no matter what information is encoded. We derive the analytical equation to describe the relation between the ACF of the received signal and the wireless channel parameters using the ACF of the transmitted signal as prior knowledge revealed by the finding in this work. This new property can be utilized together with different wireless communication systems to improve the system performance. Specially, to demonstrate the improvement, channel state information (CSI) is identified using the chaotic baseband wireless communication as a paradigm. Two significant benefits by using the new property are 1) the CSI can be identified without the probe information known to the receiver as done in the conventional wireless communication systems, which improves the bandwidth efficiency, especially in the time-varying channel;2) the correlation operation is insensitive to the channel noise, which improves the identification accuracy as compared to the commonly used methods. Copyright © 2022, The Authors. All rights reserved.

关键词： Channel state information

来源：评论

学校读者我要写书评

暂无评论

Optimizing Neural Network image Classification with Fractional Order Gradient Methods

SSRN

引用

SSRN 2023年

作者： Zhao, Haiming Chen, Jiejie Jiang, Ping Zeng, Zhigang Fan, Rui Yang, Honggang School of Computer and Information Engineering Hubei Normal University Huangshi435000 China School of Automation Wuhan University of Technology Wuhan430000 China School of Computer Hubei PolyTechnic University Huangshi435000 China Faculty of Artificial Intelligence Education Central China Normal University Wuhan430000 China School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430000 China Key Laboratory of Image Information Processing and Intelligent Control Ministry of Education of China Wuhan430000 China

As deep learning technology increasingly permeates various fields, the significance of optimization algorithms in neural network training has become more prominent. Typically, the training of deep learning networks relies on gradient descent optimizers based on calculus computations. Traditional integer-order calculus optimizers often fall short when dealing with complex and subtle data. To overcome these limitations, we innovatively utilized the Grünwald-Letnikov and Caputo definitions of fractional calculus to develop two new optimization algorithms: Fractional Order Adagrad (FAdagrad) and Fractional Order Adam (FAdam). These algorithms have been proven to converge to extremal points.A key advantage of our methods is their capability in handling complex, high-dimensional tasks, such as artistic painting image classification, where they exhibit exceptional performance in recognizing and processing subtle differences. The robustness and adaptability of these algorithms were further validated through experiments on the CIFAR-100 dataset. The results demonstrate the efficacy of fractional order optimizers in enhancing training efficiency and accuracy. © 2023, The Authors. All rights reserved.

关键词： image classification

来源：评论

学校读者我要写书评

暂无评论

Residual 3D Scene Flow Learning with Context-Aware Feature Extraction

arXiv

引用

arXiv 2021年

作者： Wang, Guangming Hu, Yunzhe Wu, Xinrui Wang, Hesheng Department of Automation Key Laboratory of System Control Information Processing of Ministry of Education Key Laboratory of Marine Intelligent Equipment and System Ministry of Education Shanghai Engineering Research Center of Intelligent Control and Management Shanghai Jiao Tong University Shanghai200240 China

Scene flow estimation is the task to predict the point-wise or pixel-wise 3D displacement vector between two consecutive frames of point clouds or images, which has important application in fields such as service robots and autonomous driving. Although many previous works have explored greatly on scene flow estimation based on point clouds, there are two problems that have not been noticed or well solved before: 1) Points of adjacent frames in repetitive patterns may be wrongly associated due to similar spatial structure in their neighbourhoods;2) Scene flow between adjacent frames of point clouds with long-distance movement may be inaccurately estimated. To solve the first problem, a novel context-aware set convolution layer is proposed in this paper to exploit contextual structure information of Euclidean space and learn soft aggregation weights for local point features. This design is inspired by human perception of contextual structure information during scene understanding with repetitive patterns. The context-aware set convolution layer is incorporated in a context-aware point feature pyramid module of 3D point clouds for scene flow estimation. For the second problem, an explicit residual flow learning structure is proposed in the residual flow refinement layer to cope with long-distance movement. The experiments and ablation study on FlyingThings3D and KITTI scene flow datasets demonstrate the effectiveness of each proposed component. The qualitative results show that the problems of ambiguous inter-frame association and long-distance movement estimation are well handled. Quantitative results on both FlyingThings3D and KITTI scene flow datasets show that the proposed method achieves state-of-the-art performance, surpassing all other previous works to the best of our knowledge by at least 25%. Copyright © 2021, The Authors. All rights reserved.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Topology Inference for Networked Dynamical Systems: A Causality and Correlation Perspective

Topology Inference for Networked Dynamical Systems: A Causal...

引用

IEEE Conference on Decision and control

作者： Yushan Li Jianping He Shanghai Engineering Research Center of Intelligent Control and Management Shanghai Jiao Tong University the Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai China

ISBN: (纸本)9781665436601

Networked dynamical systems (NDSs) have gained considerable attention in recent years, where the networked agents cooperate to accomplish the common task through the interaction topology. In this paper, we focus on the topology inference problem of NDSs. Different from traditional methods, we aim to infer the internal interaction topology from the perspective of node causality and correlation, covering both directed/undirected topology structures and the asymptotic/marginal stabilities of NDSs. Specifically, we propose a causality-based method that takes the noise characteristic into account and asymptotically approaches the real interaction topology structure, with only single round observations over the dynamical process. When the observation number is small, we further design a correlation-based modification to effectively alleviate the influence of noises. We demonstrate the close relation between the proposed method and the traditional Granger estimator and ordinary least square (OLS) estimator in terms of observation rounds and horizon. We further prove the equivalence conditions of the proposed method with the two estimators from the system stability and noise characteristic. The proposed causality-correlation combined method enjoys analogous asymptotic inference performance with Granger estimator of multiple observation rounds, and outperforms OLS estimator in single observation round, verified by extensive simulations.

关键词： Degradation Asymptotic stability Correlation Network topology Conferences Stability analysis Topology

来源：评论

学校读者我要写书评

暂无评论

intelligent intersection scheduling based on vehicle traffic priority

Intelligent intersection scheduling based on vehicle traffic...

引用

第40届中国控制会议

作者： Zhengxin Ruan Sicong Chen Yuanlong Li Liangren Shi Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Engineering Research Center of Intelligent Control and Management

This paper proposes an intelligent intersection management method based on the vehicle dynamic priority. By the information interaction between the autonomous vehicles（AVs） and the infrastructure equipment, the vehicle position and posture information is obtained in real time, and the priority of the vehicles passing through the conflict points in the scene is determined according to the order of the vehicles driving through the crossroads. Subsequently, to track the planned trajectory, we use the model predictive control（MPC） algorithm minimize the intersection delay with collision-free constraints. This guarantees the vehicles to drive through the intersection safely in the scene. Simulation experiments demonstrate the reliability and efficiency of the proposed algorithm.

关键词： Autonomous vehicle Intersection management system Vehicle-to-infrastructure communication Dynamic priority Model predictive control

来源：评论

学校读者我要写书评

暂无评论

An Accelerated Gossip-Based Distributed Gradient Method

An Accelerated Gossip-Based Distributed Gradient Method

引用

第40届中国控制会议

作者： Xiaoxing Ren Dewei Li Yugeng Xi Haibin Shao Department of Automation Shanghai Jiao Tong UniversityKey Laboratory of System Control and Information ProcessingMinistry of Education of ChinaShanghai Engineering Research Center of Intelligent Control and Management

This paper studies distributed optimization over the multi-agent network. We develop and analyze a novel accelerated distributed gradient descent method, termed as G-DGDlm, for gossip communication protocol. G-DGDlm uses gradient tracking technique and local memory. Specifically, each agent stores two past variables, namely, an estimate of the average gradient and an estimate of the optimal solution. G-DGDlm achieves linear convergence for strongly convex and smoot√h functions when the related works, we remove the dependence of θ on global parameters and G-DGDlm is applicable to gossip communication protocol. Numerical experiments of distributed estimation in sensor networks show the faster convergence speed of G-DGDlm in comparison with the state-of-the-art methods.

关键词： Distributed convex optimization gossip communication first-order methods

来源：评论

学校读者我要写书评

暂无评论

Bearing-only Formation control of Nonholonomic Agents with Unknown Dynamic Leaders

Bearing-only Formation Control of Nonholonomic Agents with U...

引用

Chinese Automation Congress (CAC)

作者： Haifan Su Ziwen Yang Shanying Zhu Cailian Chen Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai Jiao Tong University Shanghai China

ISBN: (纸本)9781665426480

In this paper, the problem of bearing-only formation tracking control of multiple nonholonomic agents is studied. A leader-follower structure is adopted, where the leaders are moving at an unknown constant linear velocity and time-varying orientation. To solve the problem using bearing-only measurements, a finite-time estimator is firstly proposed to estimate the leaders’ orientation information. Then, an adaptation law for estimating the leaders’ linear velocity is proposed, based on which control inputs for tracking the leaders in a predefined bearing-based formation are designed, so that formation tracking can be achieved asymptotically. Rigorous theoretical analysis of the closed-loop system is given. It is proved that both the estimation errors and formation errors converge to zero under the connectivity of the communication graph and conditions for bearing rigidity. Numerical simulations are presented to testify the effectiveness of the proposed method.

关键词： Estimation error Automation Simulation Numerical simulation Rigidity Velocity measurement Closed loop systems

来源：评论

学校读者我要写书评

暂无评论

Exploiting Distilled Learning for Deep Siamese Tracking

Exploiting Distilled Learning for Deep Siamese Tracking

引用

International Conference on Pattern Recognition

作者： Chengxin Liu Zhiguo Cao Wei Li Yang Xiao Shuaiyuan Du Angfan Zhu Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China Queen Mary University of London

Existing deep siamese trackers are typically built on off-the-shelf CNN models for feature learning, with the demand for huge power consumption and memory storage. This limits current deep siamese trackers to be carried on resource-constrained devices like mobile phones, given factor that such a deployment normally requires cost-effective considerations. In this work, we address this issue by presenting a novel Distilled Learning Framework(DLF) for siamese tracking, which aims at learning tracking model with efficiency and high accuracy. Specifically, we propose two simple yet effective knowledge distillation strategies, denote as point-wise distillation and pairwise distillation, which are designed for transferring knowledge from a more discriminative teacher tracker into a compact student tracker. In this way, cost-effective and high performance tracking could be achieved. Extensive experiments on several tracking benchmarks demonstrate the effectiveness of our proposed method.

关键词： Power demand Pipelines Memory management Benchmark testing Mobile handsets Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Bearing-based Formation Tracking of Nonholonomic Agents in the Leader’s Local Frame

Bearing-based Formation Tracking of Nonholonomic Agents in t...

引用

Chinese Automation Congress (CAC)

作者： Ke Lv Ziwen Yang Shanying Zhu Lin Wang Shanghai Engineering Research Center of Intelligent Control and Management Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai China

ISBN: (纸本)9781665426480

This paper investigates the formation tracking control problem of nonholonomic agents in the leader’s local frame, based on bearing measurements. Most of existing works on formation tracking are aimed at tracking a given formation in the global frame, which cannot meet the needs of many applications such as a fleet of cars driving on the highway. In this case, if the cars cannot keep a fixed formation in the leader’s local frame, they may drive off the highway. Thus we propose an integrated approach consisting of a bearing-based estimator and a tracking controller, to track a given formation in the leader’s local frame. In order to eliminate the estimation error in formation tracking, a persistently exciting leader is characterized by conditions. The stability of the integrated method is proved rigorously. Simulation results prove the effectiveness of the proposed approach.

关键词： Road transportation Estimation error Automation Simulation Stability analysis Robustness Trajectory

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：