检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Lv, Guoqing Li, Jiang Wang, Xiaoping Zeng, Zhigang The School of Artificial Intelligence and Automation The Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China The Hubei Key Laboratory of Brain-inspired Intelligent Systems Huazhong University of Science and Technology Wuhan430074 China

Current approaches to empathetic response generation typically encode the entire dialogue history directly and put the output into a decoder to generate friendly feedback. These methods focus on modelling contextual information but neglect capturing the direct intention of the speaker. We argue that the last utterance in the dialogue empirically conveys the intention of the speaker. Consequently, we propose a novel model named InferEM for empathetic response generation. We separately encode the last utterance and fuse it with the entire dialogue through the multi-head attention based intention fusion module to capture the speaker’s intention. Besides, we utilize previous utterances to predict the last utterance, which simulates human’s psychology to guess what the interlocutor may speak in advance. To balance the optimizing rates of the utterance prediction and response generation, a multitask learning strategy is designed for InferEM. Experimental results demonstrate the plausibility and validity of InferEM in improving empathetic expression. Copyright © 2022, The Authors. All rights reserved.

关键词： Encoding (symbols)

来源：评论

学校读者我要写书评

暂无评论

Short-Term Hybrid Prognostics of Fuel Cells: A Comparative and Improvement Study

SSRN

引用

SSRN 2024年

作者： Sheng, Chuang Fu, Jun Zu, YanMin Deng, ZhongHua Li, Xi School of Artificial Intelligence and Automation Key Laboratory of Image Processing and Intelligent Control Education Ministry Huazhong University of Science and Technology Wuhan430074 China Shenzhen Huazhong University of Science and Technology Research Institute Shenzhen518055 China School of Electronic Information Engineering Jingchu University of Technology Jingmen448000 China

Accurately predicting the performance degradation trend of fuel cells helps take measures in advance and prolong the service life of the stack, which led to the creation of a novel hybrid forecasting approach. The first grey model prediction method based on residual exponential smoothing optimization (ES-R-GM) can capture the voltage deterioration trend. The integration of two different ES techniques, specifically the double ES (ES2) and cubic ES (ES3), is explored to investigate their effect on improving the predictive accuracy of the GM model. The second method of the adaptive network fuzzy inference system (ANFIS) can characterize local nonlinear behaviour. The simulated annealing (SA) algorithm is utilized to optimize ANFIS results under different fuzzy rule selection strategies. The outcomes of the two types of prediction methods mentioned above are combined to create a hybrid prediction using the data fusion method and the moving window technique. Different hybrid methods are evaluated under general conditions and further detailed optimization. The proposed hybrid framework is verified by the data obtained from the experimental platform. Moreover, when applied to consistent public datasets, the hybrid approach maintains its robustness and accuracy compared with other prognostic methods. © 2024, The Authors. All rights reserved.

关键词： Simulated annealing

来源：评论

学校读者我要写书评

暂无评论

Fuzzy Sandwich control of Some Nonlinear Systems with a Number of Stochastically Occurring Impulses 13

Fuzzy Sandwich Control of Some Nonlinear Systems with a Numb...

引用

13th International Conference on information Science and Technology, ICIST 2023

作者： Onasanya, Babatunde Oluwaseun Dai, Xiangguang Feng, Yuming Zhang, Wei School of Computer Science and Engineering Chongqing Three Gorges University Chongqing Wanzhou404100 China Department of Mathematics University of Ibadan Ibadan200284 Nigeria Chongqing Engineering Research Center of Internet of Things and Intelligent Control Technology Chongqing Three Gorges University Chongqing Wanzhou404100 China Three Gorges Institute of Artificial Intelligence Chongqing Three Gorges University Chongqing Wanzhou404100 China Key Laboratory of Intelligent Information Processing and Control Chongqing Three Gorges University Chongqing Wanzhou404100 China

ISBN: (纸本)9798350313925

In this paper, rather than have a fixed constant matrix in the sandwich control of the nonlinear system, a fuzzy control matrix was used. In addition, simple inequalities that do not require additional computational time and skills in computer programming were used rather than the usual LMI. The result of this method is that the period T required in the control process is shorter and the control time is also reached much faster or reduced compared to the existing sandwich methods that used constant matrices. In other words, the control time of this method is shorter than the control time achieved when using constant matrices. Besides, this method also can be used to control more nonlinear chaotic systems such as Lorenz's, Rössler's and Chen's systems. Numerical simulations were used to demonstrate the effectiveness of this method. © 2023 IEEE.

关键词： Nonlinear systems

来源：评论

学校读者我要写书评

暂无评论

Hybrid Data-Free Knowledge Distillation

arXiv

引用

arXiv 2024年

作者： Tang, Jialiang Chen, Shuo Gong, Chen School of Computer Science and Engineering Nanjing University of Science and Technology China Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education China Jiangsu Key Laboratory of Image and Video Understanding for Social Security China Center for Advanced Intelligence Project RIKEN Japan Department of Automation Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University China

Data-free knowledge distillation aims to learn a compact student network from a pre-trained large teacher network without using the original training data of the teacher network. Existing collection-based and generation-based methods train student networks by collecting massive real examples and generating synthetic examples, respectively. However, they inevitably become weak in practical scenarios due to the difficulties in gathering or emulating sufficient real-world data. To solve this problem, we propose a novel method called Hybrid Data-Free Distillation (HiDFD), which leverages only a small amount of collected data as well as generates sufficient examples for training student networks. Our HiDFD comprises two primary modules, i.e., the teacher-guided generation and student distillation. The teacher-guided generation module guides a Generative Adversarial Network (GAN) by the teacher network to produce high-quality synthetic examples from very few real-world collected examples. Specifically, we design a feature integration mechanism to prevent the GAN from overfitting and facilitate the reliable representation learning from the teacher network. Meanwhile, we drive a category frequency smoothing technique via the teacher network to balance the generative training of each category. In the student distillation module, we explore a data inflation strategy to properly utilize a blend of real and synthetic data to train the student network via a classifier-sharing-based feature alignment technique. Intensive experiments across multiple benchmarks demonstrate that our HiDFD can achieve state-of-the-art performance using 120 times less collected data than existing methods. Code is available at https://***/tangjialiang97/HiDFD. Copyright © 2024, The Authors. All rights reserved.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

A Secure Parameter Self-Tuning control Scheme for Vehicle Platoons Under DoS Attacks

A Secure Parameter Self-Tuning Control Scheme for Vehicle Pl...

引用

IEEE International Conference on Cyber Technology in Automation, control, and intelligent Systems

作者： Qiaoni Han Guowen Cheng Zhenning Tang Chang Liu Tianjin Key Laboratory of Intelligent Unmanned Swarm Technology and System School of Electrical and Information Engineering Tianjin University Tianjin China Key Laboratory of System Control and Information Processing Ministry of Education Shanghai Center for Biomedical Engineering School of Information Science and Technology Fudan University Shanghai China

In order to mitigate the adverse impact of denial of service (DoS) attacks, this work designs a parameter self-tuning controller based on fuzzy rules for vehicle platoons with vehicle-to-vehicle (V2V) communications. Aiming at achieving the cooperative adaptive cruise control (CACC) of the vehicles with a required inter-vehicle distance and the same velocity, while considering the possible DoS attacks, we propose a parameter self-tuning longitudinal controller combining linear control and fuzzy control to enhance the stability and resilience of the platoon systems. Firstly, by analyzing the dynamic characteristics of vehicles and the mechanism of DoS attacks, we establish the dynamic model of vehicle platoons and model the impact of random DoS attacks as a constant data transmission delay, whose probability distribution can be defined using the Bernoulli random variable. Then, a linear controller based on fuzzy control is designed for longitudinal control to guarantee that the platoon keeps a reference velocity and the specified inter-vehicle distance under DoS attacks. Finally, thorough simulations are performed and the detailed results show the performance of the secure longitudinal control scheme for vehicle platoons in terms of stability and security.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Entity Representation Learning with Multimodal Neighbors for Link Prediction in Knowledge Graph 7

Entity Representation Learning with Multimodal Neighbors for...

引用

7th International Conference on Computer and Communications, ICCC 2021

作者： Liu, Wenxuan Duan, Hao Li, Zeng Liu, Jingdong Huo, Hong Fang, Tao Shanghai Jiao Tong University Department of Automation China Key Laboratory of System Control and Information Processing Ministry of Education of China China Shanghai Engineering Research Center of Intelligent Control and Management China

ISBN: (纸本)9781665409506

Entity representation learning is both fundamental and crucial for link prediction in knowledge graph. Existing entity representation learning approaches mainly focus on learning from knowledge triples with single modal text data which could only describe the things or concepts in words. However, multimodal data commonly exists in the real worlds and may describe things or concepts from different aspects. Therefore, multimodal entities have emerged in knowledge graph in recent years, which greatly enrich the knowledge graph by different information. This paper focuses on how to learn more robust and comprehensive representations of multimodal entities for better link prediction. A new representation learning method for multimodal entities is proposed, called Graph Attention with Bi-pooling Representation Learning (GBRL), where multimodal fusion and knowledge embedding are combined for learning representations of an entity with consideration of its multimodal neighbors. Firstly, feature vectors are obtained by pre-trained models for each modality. Then, the bilinear pooling is utilized for combining feature vectors of multimodal entities into multimodal feature vectors. A two-layer graph attention module is followed to generate multimodal representations of an entity from its multimodal neighbors. Finally, the inception decoder uses multimodal knowledge embedding to calculate scores for link prediction. The experimental results have shown that the proposed method performs well on link prediction by consideration of multimodal entities comparing with traditional methods that using only single modal text data. © 2021 IEEE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Event-Triggered Consensus on Matrix-weighted Networks

Event-Triggered Consensus on Matrix-weighted Networks

引用

2021 China Automation Congress, CAC 2021

作者： Pan, Lulu Wang, Chongzhi Shao, Haibin Li, Dewei Xi, Yugeng The 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 Shanghai200240 China

ISBN: (纸本)9781665426473

In this work, we consider the consensus problem of the multi-agent system over matrix-weighted networks using an event-triggered mechanism. An event-triggered coordination strategy is proposed to steer this generalized category of multi-agent systems towards the bipartite consensus state. The triggering condition is periodically checked and distributed in the sense that the event detector only uses neighbors' information and local computation at discrete sampling instants. Moreover, it is shown that the triggering condition is closely related to the spectrum of matrix-valued weights corresponding to the edges in the matrix-weighted network. In the meantime, the Zeno phenomenon can be avoided automatically under the proposed event trigger approach. © 2021 IEEE

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

An Integrated Scheduling Algorithm of Satellite Observation and Data Download Based on Multi-Agent Deep Reinforcement Learning

An Integrated Scheduling Algorithm of Satellite Observation ...

引用

Chinese Automation Congress (CAC)

作者： Kang Chen Shaochong Du Hong Huo Tao Fang Department of Automation Shanghai Jiao Tong University Shanghai China Key Laboratory of System Control and Information Processing Ministry of Education Shanghai China Shanghai Engineering Research Centre of Intelligent Control and Management Shanghai China

The earth observation satellite scheduling has always been critical for the maximum use of limited satellite resources, which basically includes scheduling ground target observation and observation data downloading. Due to the complexity of the mathematical model and its NP-hardness, current research usually splits it into two problems to simplify the model. In this paper, we propose a model of the integrated scheduling problem of satellite observation and data downloading (ISP-SODD) based on the decentralized partially observable Markov decision process (Dec-POMDP), treating each satellite as an agent with autonomous decision-making capability. A multi-agent deep reinforcement learning-based (MADRL-based) algorithm is proposed to solve it. A series of simulation experiments of different scales validate the effectiveness of the method and its advantages compared with the traditional heuristic algorithms. To the best of our knowledge, this study is the first attempt to apply multi-agent reinforcement learning to a multi-satellite scheduling scenario with downloading considerations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Track Association Algorithm Based on Transitive Closure Fuzzy Clustering

A Track Association Algorithm Based on Transitive Closure Fu...

引用

International Conference on Guidance, Navigation and control, ICGNC 2020

作者： Huang, Yinghao Zhang, Kaihua Wang, Jing Cai, Yunze Department of Automation Shanghai Jiao Tong University Shanghai200240 China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai200240 China Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education Shanghai Jiao Tong University Shanghai200240 China Shanghai Academy of Spaceflight Technology Shanghai201100 China

ISBN: (纸本)9789811581540

Aiming at track association before and after multi-target track interruption, a track associating method on the basis of transitive closure fuzzy clustering is proposed. Firstly, the method converts the traditional track fuzzy similarity matrix into a fuzzy equivalent matrix by squaring method, and split sub-blocks of the equivalent matrix. Then the method calculates final track correlation matrix based on correlating threshold function related to track interruption duration, and obtains correct track association by the correlation matrix. The simulation proves that, the proposed method improves association accuracy comparing with other association algorithms based on fuzzy theory, and presents a more significant advantage in the case that targets maneuver and tracks cross. © 2022, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Fuzzy clustering

来源：评论

学校读者我要写书评

暂无评论

Nonlinear Active Disturbance Rejection control for Vehicle Active Suspension System

Nonlinear Active Disturbance Rejection Control for Vehicle A...

引用

Electronic information Engineering and Computer Science (EIECS), 2021 International Conference on

作者： Xianglian Dai Chunzhe Zhao Rong Xu School of Electronics and Information Engineering Chongqing Three Gorges University Wanzhou China Chongqing Engineering Research Center of Internet of Things and Intelligent Control Technology Key Laboratory of Intelligent Information Processing and Control of Chongqing Municipal Institutions of Higher Education Chongqing Three Gorges University Wanzhou China

Nonlinear active disturbance rejection control (ADRC) is designed for the suspension system of the quarter vehicle model with the two-degree freedom. It is compared with other active suspension systems based on PID and linear ADRC scheme. The variance of the errors reveals that the nonlinear ADRC suspension system promotes the vehicle acceleration, the suspension dynamic disturbance, and wheel dynamic load.

关键词：

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：