检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2024年第4期5卷 1658-1668页

作者： Zhang, Chunjie Zheng, Xiaolong Beijing Jiaotong University Institute of Information Science Beijing100044 China Beijing Jiaotong University Beijing Key Laboratory of Advanced Information Science and Network Technology Beijing100044 China University of Chinese Academy of Sciences State Key Laboratory of Multimodal Artificial Intelligence Systems The State of Key Laboratory of Management and Control for Complex System Institute of Automation Chinese Academy of Sciences School of Artificial Intelligence Beijing100190 China

Most image classification methods are designed to either boost the classification accuracies with abundant supervision, or cope with the shortage of supervision information. This is often achieved by using the visual and semantic information of other sources. However, these methods use the visual and semantic information within the same class independently, leaving their intrinsic correlations unconsidered. Objects and disturbing components as well as noise exist on the same image. Besides, semantic representations also contain noisy information. To solve the problems mentioned above, we propose a novel method for both fully supervised image classification and few-shot image classification by decomposing visual and semantic correlations. We jointly explore the intrinsic correlations of visual and semantic information of images within the same class. For each class, we decompose its visual and semantic correlations using low-rank and sparse constraint respectively. The decomposed low-rank parts character the intrinsic correlations of images can be used in a linear transformation way. Using the decomposed parts of each class, Classification can be achieved by reconstruction error minimization. We conduct experiments on several datasets for both fully supervised image classification and few-shot image classification. Experimental results well show the effectiveness of the proposed method. © 2020 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Semi-supervised learning with GAN for Semantic Segmentation of Wood Defect image

Semi-supervised learning with GAN for Semantic Segmentation ...

引用

2024 China Automation Congress, CAC 2024

作者： Zheng, Kunxin Zheng, Song Xu, Zhezhuang Lin, Ye Zhu, Yuhang College of Electrical Engineering and Automation Fuzhou University Key Laboratory of Industrial Automation Control Technology and Information Processing Education Department of Fujian Province Fuzhou350000 China

ISBN: (纸本)9798350368604

Automatic defect detection on wood surface is essential for ensuring product quality. Semantic segmentation methods have shown outstanding performance in wood defect detection. However, it is costly to acquire correct pixel-level labels of wood surface defects due to the complicated characteristics. To mitigate the cost of acquiring high-quality datasets, this study proposes a semi-supervised defect detection approach based on generative adversarial networks, which contains a generator and a discriminator. The generator is utilized to generate pixel-level segmentation results of wood defect images. To improve the segmentation performance, the discriminator learns against the generator by judging the goodness of the prediction results and generates supervised signals for the prediction results of unlabeled images. With this learning model, the proposed method can enhance segmentation performance using unlabeled images and alleviate the burden of data annotation. We validate the effectiveness of the proposed approach on a collected dataset of wood defects. Experimental results demonstrate the remarkable performance of our method even when utilizing only a small amount of annotated data. © 2024 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Pointer Meter Reading under Noise Based on Virtual Data Generation

Pointer Meter Reading under Noise Based on Virtual Data Gene...

引用

2024 China Automation Congress, CAC 2024

作者： Zhu, Jinyang Xu, Zhezhuang Lin, Ye College of Electrical Engineering and Automation Fuzhou University Key Laboratory of Industrial Automation Control Technology and Information Processing Education Department of Fujian Province Fuzhou350000 China

ISBN: (纸本)9798350368604

Using machine vision for meter reading significantly enhances the efficiency of industrial monitoring. However, meters in outdoor environment are often subject to the noise such as rain and fog, which affect the accuracy of meter readings. Additionally, the meter images and labels under noise are hard to obtain. To address these challenges, We propose a method for pointer meter reading under noise based on virtual data generation. Firstly, We utilize Unity to construct an industrial meter scene, which generates the images of meter under noise and theri labels. Secondly, we develop a U-Net network with an ASPP module, which expands the receptive field of network and enhances the ability of segmentation network to capture global semantic information under noise. Finally, the angular method is used to calculate the meter readings. Experimental results show that this method can effectively read meters under noise in outdoor environments. © 2024 IEEE.

关键词： Virtual addresses

来源：评论

学校读者我要写书评

暂无评论

NeFF: Semantic information Learning In 3D Space Using Neural Feature Field

NeFF: Semantic Information Learning In 3D Space Using Neural...

引用

2024 China Automation Congress, CAC 2024

作者： Yang, Yimu Chen, Cailian Department of Automation Shanghai Jiao Tong University Shanghai200240 China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai200240 China

ISBN: (数字)9798350368604

ISBN: (纸本)9798350368604

Inferring a 3D space with partial observation requires prior knowledge from previous experience, and deep learning offers an intuitive solution. Prior knowledge can be categorized into two extremes Global and Local. Global prior uses input image as a clue to retrieve seen intact 3D objects yielding 3D consistent inference with fewer details. In contrast, Local prior takes advantage of closeby views’ overlapping areas and propagates input image cues to their vicinity via geometry transformation directly, producing realistic inferences around the reference views yet inconsistent inferences away from the reference views. We propose Neural feature field, an implicit 3D neural representation that combines the strength of the Global and Local prior. We represent each 3D scene with a latent embedding, then we perform a global scene-level prior to local view-specific feature prior with the neural feature field and volume rendering technique. Our model learns general scene properties across a category. Given a single input image at test time, the scene latent code is acquired via a two-round optimization process. Experiments on the SRN benchmark show that NeFF generalizes well to unseen objects within the same object category and is capable of producing 3D consistent inferences with sharp details from a single observation. © 2024 IEEE.

关键词： 3D reconstruction

来源：评论

学校读者我要写书评

暂无评论

Design Technology of Multi-AGV Warehouse Intelligent Scheduling Optimization control System 15th

Design Technology of Multi-AGV Warehouse Intelligent Schedul...

引用

15th International Conference on Genetic and Evolutionary Computing, ICGEC 2023

作者： Pan, YanPeng Zhang, XueTing Zhang, FuQuan Tan, LiLi Yang, LiJie Ma, Jun China Academy of Launch Vehicle Technology Beijing100076 China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou350121 China

ISBN: (纸本)9789819700677

Different from the traditional warehousing system, in the multi-AGV warehouse scheduling control system, the constraints of poor connectivity of the conveying track have led to the emergence of urgent problems such as vehicle conflicts in the task, low efficiency of multitasking concurrency, difficulty of delineating the conditions for entering the transporting area and so on. This paper proposes a design of multi-AGV warehouse intelligent scheduling optimized control system, which takes multitask scheduling research as an entry point, designs the warehouse layout and vehicle operation rules assumptions and modeling, studies the scheduling solution of Monorail Vehicles in multiple tasks, designs a scheduling optimization method based on the algorithm of Time Window, solves conflicts between key process and operation task process and optimize the scheduling, so as to effectively enhance the efficient scheduling capability of multi-AGV warehouse intelligent scheduling optimized control system. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Warehouses

来源：评论

学校读者我要写书评

暂无评论

Dual-type Hyperspectral Microscopic Imaging System based on Fourier Transform Imaging Spectrometer 15

Dual-type Hyperspectral Microscopic Imaging System based on ...

引用

15th International Conference on information Optics and Photonics, CIOP 2024

作者： Wei, Zhanqi Wu, Kaijie Qin, Yuheng Cheng, Hao Gu, Chaochen Department of Automation Shanghai Jiao Tong University Shanghai200240 China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai200240 China

ISBN: (数字)9781510686175

ISBN: (纸本)9781510686168

This article proposes a hyperspectral microscopic imaging system based on Fourier transform interferometer to broaden the spectral range and obtain more types of spectral information under large field of view. Through stage scanning and light sources switching, transmission and fluorescence spectral images can be obtained successively. The system was validated using fibre tissues imaging. The spectral range covers 300-800 nm, and the spectral resolution is approximately 5 nm. It can be effectively applied to pathology and cytogenetics, obtaining morphological and spectral information to study the structure of the object and observe the similarities and differences of components in different positions. © 2024 SPIE.

关键词： Spectral resolution

来源：评论

学校读者我要写书评

暂无评论

Uncertainty-Aware Reactive control for Signal Temporal Logic with Unknown Obstacles 14

Uncertainty-Aware Reactive Control for Signal Temporal Logic...

引用

14th Asian control Conference, ASCC 2024

作者： Chen, Chen Li, Shaoyuan Yin, Xiang Shanghai Jiao Tong University Department of Automation Shanghai200240 China The Ministry of Education of China Key Laboratory of System Control and Information Processing Shanghai200240 China

ISBN: (纸本)9789887581598

In this paper, we investigate the challenge of con-trol synthesis for Signal Temporal Logic (STL) specifications within workspaces harboring unknown obstacles. We consider a sensing-based control setting, where robots are equipped with sensors with a limited sensing range to acquire obstacle locations with prior information. The objective is to synthesize a control strategy that maximize the robustness degree of the STL tasks while simultaneously minimizing the probability of collisions with obstacles during its operation. To address this, we present a receding horizon reactive control framework, tackling the problem by solving an uncertainty-aware optimal planning problem at each time instant. A key aspect of our approach is the avoidance of explicit computation of collision probability. Instead, we transform the uncertainty-aware synthesis problem into a non-probabilistic optimization problem, and the results of which still provide probabilistic guarantees. Simulation results are provided to illustrate the effectiveness of our approach. © 2024 Asian control Association.

关键词： Temporal logic

来源：评论

学校读者我要写书评

暂无评论

Safe Deep Learning-Based Offset-Free MPC for Green Hydrogen Injected PEMFC systems

Safe Deep Learning-Based Offset-Free MPC for Green Hydrogen ...

引用

2023 China Automation Congress, CAC 2023

作者： Wang, Han Li, Longyan Ning, Chao Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Department of Automation Shanghai China

ISBN: (纸本)9798350303759

Safe and stable operation of a proton exchange membrane fuel cell (PEMFC) system requires stringent control of oxygen excess ratio (OER). However, the OER regulation in PEMFC is challenging due to frequent fluctuations of current, various modeling nonlinearities, constrained manipulated variable, and real-time requirements. Offset-free model predictive control (MPC) provides a useful means for controlling systems with disturbances and constraints, but suffers from the heavy computational burden of repeatedly solving an optimization problem in real time. Such computational issue precludes the possibility of meeting the real-time requirements of PEMFC. In this paper, a PEMFC cathode gas supply model is firstly established. Next, we develop a safe deep learning-based offset-free MPC algorithm. Based on the nominal offset-free MPC, the proposed MPC not only reserves the ability of disturbance rejection, but also leverages deep neural networks for approximating the explicit solution to the MPC problem to greatly reduce online computational time. Furthermore, a gauge map is used to guarantee the satisfaction of safe constraints regarding compressor voltage. The simulation results show that the proposed MPC is an order of magnitude faster than the nominal offset-free MPC. © 2023 IEEE.

关键词： Model predictive control

来源：评论

学校读者我要写书评

暂无评论

Deterministic Message Flow Scheduling in Industrial Internet: Message Middleware Use Case 24

Deterministic Message Flow Scheduling in Industrial Internet...

引用

24th IEEE International Conference on Communication Technology, ICCT 2024

作者： Wang, Xin Zhou, Chonghan Jiang, Jing Key Laboratory of Information and Communication Systems Ministry of Information Industry Key Laboratory of Modern Measurement & Control Technology Ministry of Education Beijing China State Grid Economic and Technological Research Institute co. Ltd Beijing China

ISBN: (纸本)9798350363760

This article mainly focuses on message flow scheduling for industrial message middleware in the integration of deterministic network with industrial internet, which is to find the optimal matching between telecom operator and message requests from industrial users. However, current deterministic network is limited to two or three layers, and the whole transmission reliability and latency involving industrial networking and service layers cannot be guaranteed, resulting in uncontrollable message scheduling reliability, deterministic latency, low channel resource utilization etc. To this end, an integer linear programming (ILP) model is formulated for message flow scheduling issue, with multi-objectives optimization of resource utilization and profit under customized message sending latencies, and deterministic reliability. A heuristic algorithm is also proposed. Furthermore, we present a Deep Reinforcement Learning based Message Flow Scheduling algorithm (DRL-MFS), which not only solves complex message flow scheduling problems, but also achieves the self-optimization automatically. Proposed message flow scheduling approaches are simulated based on data from real cloud messaging service platforms. Simulations results prove that proposed DRL-MFS is superior to heuristic, and is close to ILP model in multi-objective optimization under three urgency levels of message sending. The reliability of three methods is proven to be deterministic. © 2024 IEEE.

关键词： Middleware

来源：评论

学校读者我要写书评

暂无评论

Provably Safe Deep Learning-Based Offset-Free Model Predictive control and its Application to Safety-Critical Autonomous Driving 6

Provably Safe Deep Learning-Based Offset-Free Model Predicti...

引用

6th International Conference on Robotics, control and Automation Engineering, RCAE 2023

ISBN: (纸本)9798350315301

Offset-free model predictive control (MPC) provides a useful means for controlling systems with uncertainties and constraints, but suffers from the heavy computational burden of repeatedly solving an optimization problem in real time. Such computational issue precludes the possibility of its application in systems requiring high realtime requirements, such as autonomous driving system. To address this problem, we develop a provably safe deep learning-based offset-free MPC framework. Based on the nominal offset-free MPC, the proposed MPC not only reserves the ability of disturbance rejection, but also leverages deep neural networks for approximating the explicit MPC solution to greatly reduce online computational time. Furthermore, a gauge map is used to guarantee the satisfaction of safe constraints. The proposed MPC is used in trajectory tracking control for smart autonomous driving. The simulation results show that the proposed MPC is an order of magnitude faster than the nominal offset-free MPC in safety-critical systems. © 2023 IEEE.

关键词： Model predictive control

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：