检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Yan, Tijin Zhou, Tong Zhan, Yufeng Xiaa, Yuanqing Key Laboratory of Intelligent Control Decision of Complex Systems School of Automation Beijing Institute of Technology Beijing100081 China

With the development of AIoT, data-driven attack detection methods for cyber-physical systems (CPSs) have attracted lots of attention. However, existing methods usually adopt tractable distributions to approximate data distributions, which are not suitable for complex systems. Besides, the correlation of the data in different channels does not attract sufficient attention. To address these issues, we use energy-based generative models, which are less restrictive on functional forms of the data distribution. In addition, graph neural networks are used to explicitly model the correlation of the data in different channels. In the end, we propose TFDPM, a general framework for attack detection tasks in CPSs. It simultaneously extracts temporal pattern and feature pattern given the historical data. Then extract features are sent to a conditional diffusion probabilistic model. Predicted values can be obtained with the conditional generative network and attacks are detected based on the difference between predicted values and observed values. In addition, to realize real-time detection, a conditional noise scheduling network is proposed to accelerate the prediction process. Experimental results show that TFDPM outperforms existing state-of-the-art attack detection methods. The noise scheduling network increases the detection speed by three times. Copyright © 2021, The Authors. All rights reserved.

关键词： Embedded systems

来源：评论

学校读者我要写书评

暂无评论

Image Captioning on Fine Art Paintings via Virtual Paintings

Image Captioning on Fine Art Paintings via Virtual Paintings

引用

Digital Twins and Parallel Intelligence (DTPI), IEEE International Conference on

作者： Yue Lu Chao Guo Xingyuan Dai Fei-Yue Wang The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China

Machine learning in fine art paintings is attracting increasing attention recently. Image captioning of paintings is of great importance for painting analysis, but it is rarely studied. The paintings have abstract expressions and lack annotated datasets, leading to the data-hungry problem in painting captioning. Thus, painting captioning has more significant challenges than photographic image captioning. This paper makes a novel attempt at generating content descriptions of paintings. We generate virtual paintings using the style transfer technique to deal with the data-hungry problem, then train the painting captioning model via a two-step manner. We evaluate our method on an annotated small-scale painting captioning dataset and demonstrate our improvements.

关键词： Art Digital twin Conferences Machine learning Task analysis Painting

来源：评论

学校读者我要写书评

暂无评论

Memory Mechanisms Based Few-Shot Continual Learning Railway Obstacle Detection

Memory Mechanisms Based Few-Shot Continual Learning Railway ...

引用

Chinese automation Congress (CAC)

作者： Zhiyuan Li Di Shang Zongru Ma Yiqing Liu Yanfeng Lu State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Science (CASIA) University of Chinese Academy of Sciences (UCAS) Beijing China Traffic Control Technology Co. Ltd. Beijing China

Efficient and accurate railway track obstacle detection is crucial for ensuring travel safety. In order to solve the problem of small amount of track obstacle data and variable types of obstacles, we introduce the concept of few-shot continual learning into the object detection algorithm. This paper introduces a novel memory mechanisms-based multi-Domain few-shot continual learning algorithm. By simulating working memory and long-term memory processes, our method combines few-shot learning with continual adaptation to varying obstacles. The proposed double-loop approach reduces catastrophic forgetting, enhances model generalization, and improves detection accuracy. This innovation holds promise for advancing railway safety through effective obstacle detection. The proposed method showcases remarkable efficiency and accuracy in the detection of railway obstacles. Our experimental results demonstrate significant improvements compared to other methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Benchmarking lane-changing decision-making for deep reinforcement learning

arXiv

引用

arXiv 2021年

作者： Wang, Junjie Zhang, Qichao Zhao, Dongbin The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China College of Artificial Intelligence University of Chinese Academy of Sciences Beijing China

The development of autonomous driving has attracted extensive attention in recent years, and it is essential to evaluate the performance of autonomous driving. However, testing on the road is expensive and inefficient. Virtual testing is the primary way to validate and verify self-driving cars, and the basis of virtual testing is to build simulation scenarios. In this paper, we propose a training, testing, and evaluation pipeline for the lane-changing task from the perspective of deep reinforcement learning. First, we design lane change scenarios for training and testing, where the test scenarios include stochastic and deterministic parts. Then, we deploy a set of benchmarks consisting of learning and non-learning approaches. We train several state-of-the-art deep reinforcement learning methods in the designed training scenarios and provide the benchmark metrics evaluation results of the trained models in the test scenarios. The designed lane-changing scenarios and benchmarks are both opened to provide a consistent experimental environment for the lane-changing task. Copyright © 2021, 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

Adaptive Takagi-Sugeno Fuzzy Model for Pneumatic Artificial Muscles

Adaptive Takagi-Sugeno Fuzzy Model for Pneumatic Artificial ...

引用

International Workshop on Advanced Computational Intelligence (IWACI)

作者： Xiuze Xia Long Cheng School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China

Pneumatic artificial muscle (PAM) usually exhibits strong hysteresis nonlinearity and time-varying features that bring PAM modeling and control difficulties. In this paper, an adaptive Takagi-Sugeno (T-S) fuzzy model is established based on nonlinear auto-regression moving average with exogenous input (NARMAX) structure to describe PAM's characteristics. Experiments show that compared with other phenomenology-based models, the presented model has lower predictive error and better adaptability. Finally, a model predictive controller is designed and validated to verify the adaptive T-S fuzzy model's practicability.

关键词： Adaptation models Computational modeling Force Predictive models Muscles Jitter Takagi-Sugeno model

来源：评论

学校读者我要写书评

暂无评论

Exploring Painting Synthesis with Diffusion Models

Exploring Painting Synthesis with Diffusion Models

引用

Digital Twins and Parallel Intelligence (DTPI), IEEE International Conference on

作者： Da Yi Chao Guo Tianxiang Bai The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China

As a significant composition of art, fine art painting is becoming a research hotspot in machine learning community. With unique aesthetic value, paintings have quite different representations from natural images, making them irreplaceable. Meanwhile, the lack of training data is common in painting-related machine learning tasks. Therefore, the synthesis of fine art painting is meaningful and challenging work. There are two main types of generative models for image synthesis: generative adversarial networks (GANs) and likelihood-based models. GAN-based models can obtain high-quality samples but usually sacrifice diversity and training stability. Diffusion models are a class of likelihood-based models and have recently been shown to achieve state-of-the-art quality on the image synthesis tasks. In this paper, we explore generating fine art paintings by using diffusion models. We carried out the experiments on the partial impression paintings from the Wikiart dataset. The results demonstrate that the diffusion model can generate high-quality samples, and it is easy to train to cover more target distribution than the GAN-based methods.

关键词： Training Art Image synthesis Digital twin Training data Machine learning Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Differential evolution algorithm based on entropy weight method to determine the weight to optimize the configuration of wind, solar, and diesel microgrid 6

Differential evolution algorithm based on entropy weight met...

引用

2021 6th International Symposium on Advances in Electrical, Electronics and Computer Engineering, ISAEECE 2021

作者： Xing, Yongchen Duan, Qing Zhang, Guobao Ma, Chunyan Liu, Wen Long Key Laboratory of Measurement and Control of Complex Systems of Engineering School of Automation Southeast University Nanjing210096 China China Electric Power Research Institute Co. Ltd. Beijing100192 China State Grid Shanghai Energy Interconnection Research Institute Co. Ltd. Shanghai201203 China

In order to enhance the stable operation of the multi-energy complementary microgrid for wind, solar, and diesel storage, reduce operating costs, and solve the problems of large randomness, low accuracy, and slow convergence of traditional microgrid optimization multi-objective decision-making, a differential evolution based on the entropy weight method to determine the weight is proposed. Firstly, we establish a microgrid integrated energy model from the perspectives of system operation stability, economy and environmental protection;combined with the Pareto optimal solution set, multi-objectives are weighted according to the entropy weight method, and the multi-objective optimization problem is transformed into single-objective optimization The problem is to avoid artificial setting of weight factors;the calculation example shows that this method is more economical and reasonable in optimization results, and provides an economic, reliable and environmentally friendly microgrid configuration strategy for users to increase power capacity. © Published under licence by IOP Publishing Ltd.

关键词： Pareto principle

来源：评论

学校读者我要写书评

暂无评论

A New Constrained Cost Value Iteration for Optimal control of Discrete-Time Nonlinear systems

A New Constrained Cost Value Iteration for Optimal Control o...

引用

Chinese automation Congress (CAC)

作者： Tao Li Qinglai Wei The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781665426480

In this paper, a new constrained cost value iteration (CCVI) adaptive dynamic programming (ADP) algorithm is developed to solve optimal control problems with constrained cost function. The CCVI algorithm is initialized by a feasible control law, and the cost function of this initial feasible control constitutes the constraint condition in the policy update step. The convergence and optimality of the CCVI are analyzed. Furthermore, the feasibility of any iterative control law and the on-line evolving control law are proven. It is emphasized that the feasibility of any iterative control law and the on-line evolving control law guarantee that the CCVI algorithm can be used in situations where the cost function constraint is extremely important. Finally, a simulation example is given to verify the effect of the developed algorithm.

关键词： Costs automation Heuristic algorithms Simulation Optimal control Cost function Iterative algorithms

来源：评论

学校读者我要写书评

暂无评论

Accident Prediction in Mesoscopic View: A CPSS-Based Social Transportation Approach

Accident Prediction in Mesoscopic View: A CPSS-Based Social ...

引用

Digital Twins and Parallel Intelligence (DTPI), IEEE International Conference on

作者： Chen Sun Ruichen Tan Jie Deng Rui Zhou Long Chen Fei-Yue Wang Dongpu Cao University of Waterloo Waterloo Canada Waytous Inc. Qingdao China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China

In modern society, traffic accidents are becoming an essential social safety issue that cannot be ignored. Along with the convenience of the high-speed development of modernization, the prosperity of vehicles has also led to severe traffic accidents, which cause massive loss of lives and properties every year. Accident analysis and prediction based on big data have become increasingly important in social transportation. However, the traditional data analysis and prediction methods only focused on either macroscope(transportation) or microscope(vehicle), and the relationships between the two layers are missing. This paper proposes a novel analysis framework by introducing the mesoscopic factors to bridge the transportation and vehicle operation domain under the parallel driving setting. The feature aggregation and mesoscopic factors extraction are included in the proposed prediction strategy to improve the performance of various commonly used decision tree-based classifiers. Methods are compared under the most recent 5-year accident database, which stores over three million records. Insights are discussed based on the future application of connected autonomous vehicles and intelligent road infrastructures.

关键词： Databases Roads Microscopy Digital twin Transportation Prediction methods Feature extraction

来源：评论

学校读者我要写书评

暂无评论

A Convolutional Neural Network With Multi-scale Kernel and Feature Fusion for sEMG-based Gesture Recognition

A Convolutional Neural Network With Multi-scale Kernel and F...

引用

IEEE International Conference on Robotics and Biomimetics

作者： Lijun Han Yongxiang Zou Long Cheng State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781665405362

The sEMG-based gesture recognition has great potential in human-computer interaction. However, the current approaches are far from optimal. In this paper, a novel convolutional neural network which combines the multi-scale kernal and feature fusion (MKFF-CNN) is proposed. This model could extract multi-scale features and make full use of these feature maps. One dataset called “gForce dataset” is recorded in this work, comprising 13 able-bodied participants. To verify the effectiveness of the proposed model, evaluations on both the gForce dataset and the Ninapro DB6 are conducted. The experimental results demonstrate that, MKFF-CNN achieves an accuracy of 97.65% on the gForce dataset, which is 1.39% higher than that of the subnetwork without early fusion, and at least 6.54% higher than that of the subnetwork with single-scale convolution kernel. On the Ninapro DB6, MKFF-CNN achieves 98.52% accuracy, which is 1.3% higher than the state-of-the-art works, showing the superiority of the proposed model.

关键词： Human computer interaction Convolution Conferences Biomimetics Biological system modeling Gesture recognition Feature extraction

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：