检索结果-内蒙古大学图书馆

第43届中国控制会议

作者： Kanglin Zhu Hongfu Xiang Guohui Xiang Han Wu Xi Li School of Artificial Intelligence and Automation Key Laboratory of Image Processing and Intelligent Control of Education MinistryHuazhong University of Science and Technology Shenzhen Huazhong University of Science and Technology Research Institute

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

Solid oxide fuel cell(SOFC) is a new energy power supply device that has been highly popular in recent years. It has the advantages of high efficiency, quietness, and no pollution. However, due to the long-term operation of the SOFC system in a high-temperature environment, various faults are inevitable, which will affect the normal operation of the system. Therefore,this paper mainly focuses on the rupture fault of the heat exchanger and the hydrogen shortage fault that occur during the operation of the SOFC. A novel method(PCA-RF) for SOFC system fault diagnosis is established by combining principal component analysis and random forest algorithm. This method not only has a simple process but also has high ***, this algorithm can well help researchers accurately identify whether there is a fault in the actual use scenario of the SOFC, so as to reduce or recover unnecessary losses.

关键词： SOFC Data-driven PCA RF Fault diagnosis

来源：评论

学校读者我要写书评

暂无评论

Vision Transformer Off-the-Shelf: A Surprising Baseline for Few-Shot Class-Agnostic Counting

arXiv

引用

arXiv 2023年

作者： Wang, Zhicheng Xiao, Liwen Cao, Zhiguo Lu, Hao Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China

Class-agnostic counting (CAC) aims to count objects of interest from a query image given few exemplars. This task is typically addressed by extracting the features of query image and exemplars respectively and then matching their feature similarity, leading to an extract-then-match paradigm. In this work, we show that CAC can be simplified in an extract- and-match manner, particularly using a vision transformer (ViT) where feature extraction and similarity matching are executed simultaneously within the self-attention. We reveal the rationale of such simplification from a decoupled view of the self-attention. The resulting model, termed CACViT, simplifies the CAC pipeline into a single pretrained plain ViT. Further, to compensate the loss of the scale and the order-of-magnitude information due to resizing and normalization in plain ViT, we present two effective strategies for scale and magnitude embedding. Extensive experiments on the FSC147 and the CARPK datasets show that CACViT significantly outperforms state-of-the-art CAC approaches in both effectiveness (23.60% error reduction) and generalization, which suggests CACViT provides a concise and strong baseline for CAC. Code will be available. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Alzheimer’s Disease Diagnosis Based on Collaborative Learning Augmented Algorithms 18th

Alzheimer’s Disease Diagnosis Based on Collaborative Learn...

引用

18th Chinese intelligent Systems Conference, CISC 2022

作者： Gao, Libin Hu, Zhongyi Li, Zuoyong Lu, Xingjin Li, Rui Tong, Yinsheng Lin, Dehou College of Computer Science and Aritificial Intelligence Wenzhou University Wenzhou325035 China Key Laboratory of Intelligent Image Processing and Analysis Wenzhou325035 China College of Computer and Control Engineering Minjiang University Fuzhou350108 China

ISBN: (纸本)9789811962028

In this study, a novel training method is innovatively proposed to address the problem of poor generalisation of trained models due to imbalance in Alzheimer’s disease (AD) data. The method alternates AD image data with dog and cat data from natural images for collaborative learning training across datasets, enhancing the generalisation ability of the models. At the same time, inspired by current work related to attention mechanisms under the field of computer vision, the model is reconstructed and an attention module is added to the model to further improve the accuracy of the model. The experimental results show that the method has good classification performance and provides new ideas for the diagnosis of other brain diseases. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Distributed impulsive control for secure consensus of nonlinear dynamical networks with node delay under denial-of-service attacks

Distributed impulsive control for secure consensus of nonlin...

引用

作者： Shi, Yu-Lun Liu, Zhi-Wei School of Artificial Intelligence and Automation Huazhong University of Science and Technology Huazhong University of Science and Technology Wuhan China Key Laboratory of Image Processing and Intelligent Control Ministry of Education Huazhong University of Science and Technology Wuhan China

This paper investigates secure consensus problems of nonlinear dynamical networks (NDNs) with node delay under denial-of-service (DoS) attacks, which can cause a break in communication links. It will lead to packet loss. To ensure the secure consensus in this scenario, we propose an effective impulsive control which only based on sampled information from neighbor nodes. Based on the Lyapunov stability theory and the impulsive comparison principle, an upper bound of the average impulse interval is derived to ensure the exponential consensus of NDNs under DoS attacks, and the convergence rate can be estimated. Finally, a numerical example is provided to check the theory results. © 2021 Chinese Automatic control Society and John Wiley & Sons Australia, Ltd.

关键词： Time delay

来源：评论

学校读者我要写书评

暂无评论

Spatiality-Aligned Graph Convolution Hashing for Unsupervised Cross-Modal Retrieval

Spatiality-Aligned Graph Convolution Hashing for Unsupervise...

引用

Signal, information and Data processing (ICSIDP), IEEE International Conference on

作者： Fang Li Liulian Dai Rushi Lan Rui Yang Xiaonan Luo Center for Applied Mathematics of Guangxi(GUET) Guangxi Key Laboratory of Image and Graphic Intelligent Processing School of Computer Science and Information Security Guilin University of Electronic Technology Guilin China

ISBN: (数字)9798331515669

ISBN: (纸本)9798331515676

Unsupervised cross-modal retrieval leveraging hash learning has attracted a lot of interest from academics, primarily due to its minimal storage requirements, swift retrieval speeds, and label-free nature, making it a prime candidate for real-world applications. Nevertheless, the inherent "heterogeneous differences" and "semantic gap" within cross-modal data features pose significant challenges. Despite various attempts by scholars to address these issues, the existing solutions often fall short in terms of effectiveness. This can be attributed to several reasons: Firstly, image features, in contrast to text features, possess a plethora of attributes, making it challenging to extract features that possess strong expressive capabilities. Secondly, each modality of data exhibits not only inter-node correlations but also intricate relationships between individual nodes and their neighboring nodes. Consequently, a straightforward semantic correlation matrix is inadequate in capturing the intricate structural relationships within the data. Thirdly, the neglect of internal structural associations results in insufficient representation capabilities of binary hash codes in the Hamming space, hampering the learning of effective hash functions. To address these limitations, we introduce a Spatiality-Aligned Graph Convolution Hashing (SAGCH) algorithm. Extensive experiments demonstrate that our SAGCH method excels in both "image-to-text retrieval" and "text-to-image retrieval" tasks.

关键词： Hash functions Correlation Codes Convolution Graph convolutional networks Semantics Text to image Feature extraction Data processing Cross modal retrieval

来源：评论

学校读者我要写书评

暂无评论

Defocus to focus: photo-realistic bokeh rendering by fusing defocus and radiance priors

arXiv

引用

arXiv 2023年

作者： Luo, Xianrui Peng, Juewen Xian, Ke Wu, Zijin Cao, Zhiguo Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China

We consider the problem of realistic bokeh rendering from a single all-in-focus image. Bokeh rendering mimics aesthetic shallow depth-of-field (DoF) in professional photography, but these visual effects generated by existing methods suffer from simple flat background blur and blurred in-focus regions, giving rise to unrealistic rendered results. In this work, we argue that realistic bokeh rendering should i) model depth relations and distinguish in-focus regions, ii) sustain sharp in-focus regions, and iii) render physically accurate Circle of Confusion (CoC). To this end, we present a Defocus to Focus (D2F) framework to learn realistic bokeh rendering by fusing defocus priors with the all-in-focus image and by implementing radiance priors in layered fusion. Since no depth map is provided, we introduce defocus hallucination to integrate depth by learning to focus. The predicted defocus map implies the blur amount of bokeh and is used to guide weighted layered rendering. In layered rendering, we fuse images blurred by different kernels based on the defocus map. To increase the reality of the bokeh, we adopt radiance virtualization to simulate scene radiance. The scene radiance used in weighted layered rendering reassigns weights in the soft disk kernel to produce the CoC. To ensure the sharpness of in-focus regions, we propose to fuse upsampled bokeh images and original images. We predict the initial fusion mask from our defocus map and refine the mask with a deep network. We evaluate our model on a large-scale bokeh dataset. Extensive experiments show that our approach is capable of rendering visually pleasing bokeh effects in complex scenes. In particular, our solution receives the runner-up award in the AIM 2020 Rendering Realistic Bokeh Challenge. © 2023, CC BY-NC-ND.

关键词： image fusion

来源：评论

学校读者我要写书评

暂无评论

A Fast-trained and Generalized Spiking Neural Network for Robotic Gas Source Localization

A Fast-trained and Generalized Spiking Neural Network for Ro...

引用

International Conference on Advanced Robotics and Mechatronics (ICARM)

作者： Chiyang Liu Xinxing Chen Jian Huang Hubei Key Laboratory of Brain-inspired Intelligent Systems and the Key Laboratory for Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China Guangdong Provincial Key Laboratory of Human-Augmentation and Rehabilitation Robotics in Universities Southern University of Science and Technology Shenzhen China

ISBN: (数字)9798350385724

ISBN: (纸本)9798350385731

Mobile robots for Gas Source Localization (GSL) tasks are a safer alternative than human and animal rescuers in hazardous scenarios. Existing research primarily concentrates on rule-based algorithms or conventional artificial neural networks (ANNs). However, these approaches are either inapplicable in cluttered environments or undeployable due to their high energy consumption and the demand for substantial computational resources. This paper introduces the application of energy-efficient spiking neural networks (SNNs) to address robotic GSL tasks. A pipeline is proposed to train SNNs with deep Q learning and a pretrain-finetune paradigm. To facilitate the training process, a small dataset of gas dispersion is generated utilizing openFoam and GADEN, a high-fidelity simulator for gas dispersion. Data from a simplified plume model are leveraged to pretrain an ANN, the activation function of which gradually transitions from a bounded rectified linear unit (bReLU) to a step function. Subsequently, an SNN initialized with the ANN parameters undergoes finetuning on the GADEN-based dataset. The training pipeline significantly reduces training time compared to direct training of SNNs. The trained SNN is validated within the GADEN simulation environment and compared to three different models, demonstrating promising performance and superior generalization despite limited training data.

关键词： Training Location awareness Q-learning Mechatronics Pipelines Training data Spiking neural networks Data models Mobile robots Dispersion

来源：评论

学校读者我要写书评

暂无评论

Multiple Unmanned Surface Vehicle Coverage control in Dynamic Environments

Multiple Unmanned Surface Vehicle Coverage Control in Dynami...

引用

Neuromorphic Computing (ICNC), International Conference on

作者： Hong Chen Dingxin He Huantao Mao Yong Yang Zhi-Wei Liu School of Artificial Intelligence and Automation Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China Huazhong University of Science and Technology Wuhan China

This paper investigates the area coverage problem for multiple Unmanned Surface Vehicles (USVs) in dynamic environments. Multiple USVs are employed to execute the coverage task using the Voronoi Partition method for task allocation. Parameter adaptive laws are employed to estimate the parameters of the sensing function and the Voronoi cell centroids for updating the target positions in dynamic environments. Additionally, considering the influence of water surface disturbances, a nonholonomic underactuated model analysis is conducted for the USV under non-full constraints, resulting in a motion strategy for USVs. This enables the multiple USVs to effectively cover the task area. Finally, simulation results are presented to validate the effectiveness of the coverage scheme designed in this paper and the ability of USVs to effectively cover dynamic environments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Modified RC and Diode Co-Triggered ESD Clamp Circuit 1

A Modified RC and Diode Co-Triggered ESD Clamp Circuit

引用

1st Annual International EOS/ESD Symposium on Design and System, IEDS 2020

作者： Yang, Zhaonian Zhang, Yibo Mao, Pan Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi'an University of Technology Xi'an710048 China

ISBN: (纸本)9781585373284

This paper presents a new ESD clamp circuit which is co-triggered by RC and diode. It is immune to the false triggering caused by fast power-up events due to the diode detection mechanism. With the addition of a common source amplifier, the detection signal is enhanced, and the clamp device is turned on more quickly. The proposed circuit is designed in a 0.18 μm 1.8-V CMOS process and verified by numerical simulation. The characteristics and improvements of the new circuit are discussed. © 2021 EOS/ESD ASSOCIATION INC.

关键词： Diodes

来源：评论

学校读者我要写书评

暂无评论

Relative-Posture-Fixed Model Predictive Human-Following control with Visibility Constraints in Obstacle Environments 8

Relative-Posture-Fixed Model Predictive Human-Following Cont...

引用

8th IEEE International Conference on Advanced Robotics and Mechatronics, ICARM 2023

作者： Zhang, Yikun Huang, Jian Yu, Jinqi Zhu, Yaonan Hasegawa, Yasuhisa School of Artificial Intelligence and Automation Huazhong University of Science and Technology Key Laboratory for Image Processing and Intelligent Control Wuhan430074 China Shenzhen Huazhong University of Science and Technology Research Institute ShenZhen518060 China Nagoya University Department of Micronano Mechanical Science and Engineering Nagoya464-8603 Japan

ISBN: (纸本)9798350300178

The relative-posture-fixed human following is critical for the human-robot interaction and cooperation in daily scenes such as domestic service and healthcare. However, few of previous researches have discussed the difficulties faced by mobile robots in the real world, including the limitation of sensing range and hindrance from obstacles. For practicality, in this paper we investigate the relative-posture-fixed following control with collision avoidance and visibility constraints. The control task is formulated as a receding-horizon optimization problem and solved under the Nonlinear Model Predictive control (NMPC) framework, while an Extended Kalman Filter (EKF) based human trajectory predict algorithm is integrated into the robot controller. The effectiveness of the proposed algorithm is verified in a simulation, and the results demonstrate a promising performance of our controller for the human-following task in complicated environments. © 2023 IEEE.

关键词： Human robot interaction

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：