检索结果-南通市图书馆

Scene text recognition via dual character counting-aware visual and semantic modeling network

在线全文

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2024年第3期67卷 313-314页

作者： Ke XIAO Anna ZHU Brian Kenji IWANA Cheng-Lin LIU School of Computer Science and artificial intelligence Wuhan University of Technology Human Interface Laboratory Kyushu University State Key Laboratory of Multimodal artificial intelligence Systems Institute of AutomationChinese Academy of Sciences School of artificial intelligence University of Chinese Academy of Sciences

Scene text recognition(STR) is drawing increasing attention nowadays due to its wide application in real life. Character counting information, as auxiliary information, has been shown to be effective in boosting text ... 详细信息

关键词： Decoding

A Bio-Inspired Integration Model of Basal Ganglia and Cerebellum for Motion Learning of a Musculoskeletal Robot

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Journal of Systems Science & Complexity 2024年第1期37卷 82-113页

作者： ZHANG Jinhan CHEN Jiahao ZHONG Shanlin QIAO Hong State Key Laboratory of Multimodal artificial intelligence Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China School of artificial intelligence University of Chinese Academy of SciencesBeijing 100049China.

It is a significant research direction for highly complex musculoskeletal robots that how to develop the ability of motion learning and generalization.The cooperations of multiple brain regions are crucial to improving motion performance.Inspired by the neural mechanisms of structures,functions,and interconnections of basal ganglia and cerebellum,a biologically inspired integration model for motor learning of musculoskeletal robots is proposed.Based on the neural characteristics of the basal ganglia,the basal ganglia actor network,which mainly simulates the dorsal striatum,outputs motion commands,and the basal ganglia critic network,which simulates the ventral striatum,estimates actionstate values.Their network parameters are updated using the soft actor-critic method.Based on the sensorimotor prediction mechanism of the cerebellum,the cerebellum network evaluates the state feature extraction quality of the basal ganglia actor network and then updates the weights of its feature layer.This learning method is proven to converge to the optimal policy.Furthermore,drawing on the mechanism of dopaminergic dynamic regulation in the basal ganglia,the adaptive adjustment of target entropy and the dopaminergic experience replay are proposed to further improve the integration model,which contributes to the exploration-exploitation trade-off of motor learning.The bio-inspired integration model is validated on a musculoskeletal system.Experimental results indicate that this model can effectively control the musculoskeletal robot to accomplish the motion task from random starting locations to random target positions with high precision and robustness.

关键词： Basal ganglia and cerebellum bio-inspired integration model motion learning musculoskeletal robot reinforcement learning.

Equilibrium Strategy of the Pursuit-Evasion Game in Three-Dimensional Space

在线全文

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2024年第2期11卷 446-458页

作者： Nuo Chen Linjing Li Wenji Mao School of artificial intelligence University of Chinese Academy of SciencesBeijing 100049 institute of Automation Chinese Academy of SciencesBeijing 100190China

The pursuit-evasion game models the strategic interaction among players, attracting attention in many realistic scenarios, such as missile guidance, unmanned aerial vehicles, and target defense. Existing studies mainly concentrate on the cooperative pursuit of multiple players in two-dimensional pursuit-evasion games. However, these approaches can hardly be applied to practical situations where players usually move in three-dimensional space with a three-degree-of-freedom control. In this paper,we make the first attempt to investigate the equilibrium strategy of the realistic pursuit-evasion game, in which the pursuer follows a three-degree-of-freedom control, and the evader moves freely. First, we describe the pursuer's three-degree-of-freedom control and the evader's relative coordinate. We then rigorously derive the equilibrium strategy by solving the retrogressive path equation according to the Hamilton-Jacobi-Bellman-Isaacs(HJBI) method, which divides the pursuit-evasion process into the navigation and acceleration phases. Besides, we analyze the maximum allowable speed for the pursuer to capture the evader successfully and provide the strategy with which the evader can escape when the pursuer's speed exceeds the threshold. We further conduct comparison tests with various unilateral deviations to verify that the proposed strategy forms a Nash equilibrium.

关键词： Differential game equilibrium strategy pursuit-evasion game threedegree-of-freedom control

A Knowledge-enhanced Two-stage Generative Framework for Medical Dialogue Information Extraction

在线全文

学校读者我要写书评

暂无评论

Machine intelligence Research 2024年第1期21卷 153-168页

作者： Zefa Hu Ziyi Ni Jing Shi Shuang Xu Bo Xu School of artificial intelligence University of Chinese Academy of SciencesBeijing 100049China institute of Automation Chinese Academy of SciencesBeijing 100190China

This paper focuses on term-status pair extraction from medical dialogues(MD-TSPE),which is essential in diagnosis dia-logue systems and the automatic scribe of electronic medical records(EMRs).In the past few years,works on MD-TSPE have attracted increasing research attention,especially after the remarkable progress made by generative methods.However,these generative methods output a whole sequence consisting of term-status pairs in one stage and ignore integrating prior knowledge,which demands a deeper un-derstanding to model the relationship between terms and infer the status of each term.This paper presents a knowledge-enhanced two-stage generative framework(KTGF)to address the above challenges.Using task-specific prompts,we employ a single model to com-plete the MD-TSPE through two phases in a unified generative form:We generate all terms the first and then generate the status of each generated term.In this way,the relationship between terms can be learned more effectively from the sequence containing only terms in the first phase,and our designed knowledge-enhanced prompt in the second phase can leverage the category and status candidates of the generated term for status generation.Furthermore,our proposed special status"not mentioned"makes more terms available and en-riches the training data in the second phase,which is critical in the low-resource setting.The experiments on the Chunyu and CMDD datasets show that the proposed method achieves superior results compared to the state-of-the-art models in the full training and low-re-sourcesettings.

关键词： Medical dialogue understanding information extraction text generation knowledge-enhanced prompt low-resource setting dataaugmentation

XMe - Xiamen Molecular Electronics Code:An Intelligent and Open-Source Data Analysis Tool for Single-Molecule Conductance Measurements

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Chemistry 2024年第3期42卷 317-329页

作者： Zhichao Pan Gang Dong Chi Shang Ruihao Li Tengyang Gao Luchun Lin Huicong Duan Xiaohui Li Jie Bai Yilin Lai Wenfeng Wu Jia Shi Junyang Liu Wenjing Hong State Key Laboratory of Physical Chemistry of Solid Surfaces College of Chemistry and Chemical Engineering & Institute of Artificial IntelligenceXiamen UniversityXiamenFujian361005 China School of artificial intelligence Guilin University of Electronic TechnologyGuilinGuangxi541004 China

Charge transport characterization of single-molecule junctions is essential for the fundamental research of single-molecule physical chemistry and the development towards single-molecule electronic devices and circuits. Among the single-molecule conductance characterization techniques,the single-molecule break junction technique is widely used in tens of worldwide research laboratories which can generate a large amount of experimental data from thousands of individual measurement cycles. However,data interpretation is a challenging task for researchers with different research backgrounds,and the different data analysis approaches sometimes lead to the misunderstanding of the measurement data and even reproducibility issues of the measurement. It is thus a necessity to develop a user-friendly all-in-one data analysis tool that automatizes the basic data analysis in a standard and widely accepted way. In this work,we present the XMe Code (Xiamen Molecular Electronics Code),an intelligent all-in-one data analysis tool for the comprehensive analysis of single-molecule break junction data. XMe code provides end-to-end data analysis that takes in the original experimental data and returns electronic characteristics and even charge transport mechanisms. We believe that XMe Code will promote the transparency of the data analysis in single-molecule electronics and the collaborations among scientists with different research backgrounds.

关键词： Molecular electronics Single-molecule studies Break junction Data science Software

Grasp Detection with Hierarchical Multi-Scale Feature Fusion and Inverted Shuffle Residual

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Tsinghua Science and Technology 2024年第1期29卷 244-256页

作者： Wenjie Geng Zhiqiang Cao Peiyu Guan Fengshui Jing Min Tan Junzhi Yu State Key Laboratory of Multimodal artificial intelligence Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China School of artificial intelligence University of Chinese Academy of SciencesBeijing 100049China Department of Advanced Manufacturing and Robotics College of EngineeringPeking UniversityBeijing 100871China

Grasp detection plays a critical role for robot manipulation.Mainstream pixel-wise grasp detection networks with encoder-decoder structure receive much attention due to good accuracy and efficiency.However,they usually transmit the high-level feature in the encoder to the decoder,and low-level features are neglected.It is noted that low-level features contain abundant detail information,and how to fully exploit low-level features remains unsolved.Meanwhile,the channel information in high-level feature is also not well mined.Inevitably,the performance of grasp detection is degraded.To solve these problems,we propose a grasp detection network with hierarchical multi-scale feature fusion and inverted shuffle residual.Both low-level and high-level features in the encoder are firstly fused by the designed skip connections with attention module,and the fused information is then propagated to corresponding layers of the decoder for in-depth feature fusion.Such a hierarchical fusion guarantees the quality of grasp prediction.Furthermore,an inverted shuffle residual module is created,where the high-level feature from encoder is split in channel and the resultant split features are processed in their respective branches.By such differentiation processing,more high-dimensional channel information is kept,which enhances the representation ability of the network.Besides,an information enhancement module is added before the encoder to reinforce input information.The proposed method attains 98.9%and 97.8%in image-wise and object-wise accuracy on the Cornell grasping dataset,respectively,and the experimental results verify the effectiveness of the method.

关键词： grasp detection hierarchical multi-scale feature fusion skip connections with attention inverted shuffle residual

Non-Deterministic Liveness-Enforcing Supervisor Tolerant to Sensor-Reading Modification Attacks

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2024年第1期11卷 240-248页

作者： Dan You Shouguang Wang IEEE the School of Information and Electronic Engineering Sussex Artificial Intelligence InstituteZhejiang Gongshang UniversityHangzhou 310018China

In this paper, we study the supervisory control problem of discrete event systems assuming that cyber-attacks might occur. In particular, we focus on the problem of liveness enforcement and consider a sensor-reading modification attack(SM-attack) that may disguise the occurrence of an event as that of another event by intruding sensor communication channels. To solve the problem, we introduce non-deterministic supervisors in the paper, which associate to every observed sequence a set of possible control actions offline and choose a control action from the set randomly online to control the system. Specifically, given a bounded Petri net(PN) as the reference formalism and an SMattack, an algorithm that synthesizes a liveness-enforcing nondeterministic supervisor tolerant to the SM-attack is proposed for the first time.

关键词： Cyber-attacks cyber-physical system(CPS) liveness non-deterministic supervisors Petri net(PN)

Adaptive interaction driven by the learning effect in the spatial prisoner's dilemma

在线全文

学校读者我要写书评

暂无评论

Chinese Physics B 2024年第3期33卷 160-169页

作者：李佳奇张建磊刘群 institute of Intelligent Information Hexi UniversityGansu 734000China College of artificial intelligence Nankai UniversityTianjin 300350China

We propose a computing model in which individuals can automatically adjust their interaction intensity with their mentor according to the learning effect.This model is designed to investigate the cooperative dynamics of the spatial prisoner's dilemma.More specifically,when the cumulative payoff of a learner is more than his reference earning,he will strengthen his interaction with his mentor;otherwise,he will reduce it.The experimental results indicate that this mechanism can improve the emergence of cooperation in a networked population and that the driving coefficient of interaction intensity plays an important role in promoting cooperation.Interestingly,under a certain social dilemma condition,there exists a minimal driving coefficient that leads to optimal cooperation.This occurs due to a positive feedback effect between the individual's satisfaction frequency and the number of effective neighbors.Moreover,we find that the experimental results are in accord with theoretical predictions obtained from an extension of the classical pair-approximation method.Our conclusions obtained by considering relationships with mentors can provide a new perspective for future investigations into the dynamics of evolutionary games within structured populations.

关键词： self-adapting interaction evolutionary game mentor spatial prisoner's dilemma

Global output feedback control of feedforward nonlinear time-delay systems with unknown growth rate and unknown measurement sensitivity

在线全文

学校读者我要写书评

暂无评论

Control Theory and Technology 2024年第1期22卷 122-134页

作者： Weiyong Yu Keao Gao Hongbing Zhou Qiang Liu Academy of artificial intelligence Beijing Institute of Petrochemical TechnologyBeijing102617China School of Mathematics and Statistics Nanyang Normal UniversityNanyang473061HenanChina

This paper discusses the problem of global state regulation via output feedback for a class of feedforward nonlinear time-delay systems with unknown measurement sensitivity. Different from previous works, the nonlinear terms are dominated by upper triangular linear unmeasured (delayed) states multiplied by unknown growth rate. The unknown growth rate is composed of an unknown constant, a power function of output, and an input function. Furthermore, due to the measurement uncertainty of the system output, it is more difficult to solve this problem. It is proved that the presented output feedback controller can globally regulate all states of the nonlinear systems using the dynamic gain scaling technique and choosing the appropriate Lyapunov–Krasovskii functionals.

关键词： Adaptive control Dynamic gain controllers Feedforward time-delay systems Measurement sensitivity Output feedback