检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Zhu, Yuting Xue, Shibei Ju, Fangfang Yuan, Haidong Department of Automation Shanghai Jiao Tong University Shanghai200240 China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai200240 China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai200240 China Department of Mechanical and Automation Engineering The Chinese University of Hong Kong Shatin Hong Kong School of Physics and Electronics Hunan Normal University Changsha410081 China

Recent progress shows that a surface-acoustic-wave (SAW) cavity can not only induce quantum acoustic dynamics but also can form optomechanical-like systems. Its operating frequencies in the microwave band make it resistant to the thermal noise of surrounding environments, while its radiation-pressure couplings make it susceptible to weak forces. Based on these advantages, we propose a gyroscope comprising coupled microwave-SAW cavities. In this paper, we systematically consider the three indices including range, signal-to-noise ratio, and sensitivity, which are the most important to gyroscopes but only partially considered in existing works. Additionally, we establish the fundamental limits of sensitivity when the quantum input is in the vacuum state and the squeezed vacuum state. We find that squeezing improves sensitivity and can surpass the standard quantum limit. However, this improvement can only reach up to √2/2 even as the squeezed parameter approaches infinity, which is rarely noted in recent works. Finally, we also offer analytical constraints for cooperativity and squeezed parameters. These constraints can be utilized to design gyroscopes based on coupled cavities in experiments. Copyright © 2024, The Authors. All rights reserved.

关键词： Gyroscopes

来源：评论

学校读者我要写书评

暂无评论

Thought expression analysis of english essays combining opinion and sentiment

引用

Journal of Computers (Taiwan) 2021年第3期32卷 43-56页

作者： Wang, Yabing Huang, Guimin Zhang, Xiaowei Li, Yiqun Li, Maolin Li, Hui Li, Jun Guangxi Key Laboratory of Image and Graphic Intelligent Processing School of Computer Science and Information Security Guilin University of Electronic Technology Guilin541004 China

With the rapid development of science, technology and the gradual information of education, the automatic English essays correction system has received more and more attention. The existing automatic English essays correction system can provide feedback on vocabulary and grammar, but it has a lack of thought expression analysis of English essays. Therefore, it is impossible to comprehensively evaluate whether opinion of English essays is relevant and expression of sentiment is clear. To solve this problem, we propose to analyze the thought expression of English essays by combining sentiment analysis and opinion analysis. Through experiment analysis and verification from the aspects of relevance degree of opinion, sentiment tendency, and thought expression of English essays, the results show the proposed method has a good performance in analyzing thought expression of English essays. © 2021 Computer Society of the Republic of China. All rights reserved.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Lite-HRPE: A 6DoF Object Pose Estimation Method for Resource-Limited Platforms

Lite-HRPE: A 6DoF Object Pose Estimation Method for Resource...

引用

International Conference on control and Automation (ICCA)

作者： Xin Liu Qi Guan Shibei Xue Dezong Zhao Department of Automation Shanghai Jiao Tong University Shanghai P. R. China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai P. R. China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai P. R. China James Watt School of Engineering University of Glasgow Glasgow U.K.

ISBN: (数字)9798350354409

ISBN: (纸本)9798350354416

Accurately estimating the six-degree-of-freedom pose of objects is essential for intelligent robotics. Although significant progress has been made in this area, most studies fail to account for specific hardware limitations for model deployment, which remains a major challenge for resource-constrained scenarios. To address this issue, we propose Lite-HRPE, a lightweight RGB-based pose estimation method, which leverages a multi-branch parallel structure to extract spatial and semantic information of key points for pose estimation. Additionally, Lite-HRPE adopts the G-block and G-neck modular structure and streamlines the original feature extraction network to realize a compact network structure. This allows Lite-HRPE to strike a balance between pose estimation accuracy, parameter count, computational load, and runtime speed. Our evaluation on public datasets shows that Lite-HRPE achieves a 95.7% accuracy with only 10.8% of the number of parameters and 11.8% of the FLOPs compared to Hybridpose.

关键词： Training Accuracy Runtime Pose estimation Semantics Feature extraction Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Few-Shot Classification with Task-Adaptive Semantic Feature Learning

SSRN

引用

SSRN 2022年

作者： Pan, Mei-Hong Xin, Hong-Yi Xia, Chun-Qiu Shen, Hong-Bin Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai200240 China University of Michigan Shanghai Jiao Tong University Joint Institute Shanghai Jiaotong University Shanghai200240 China

Few-shot classification aims to learn a classifier that categorizes objects of unseen classes with limited samples. One general approach is to mine as much information as possible from limited samples. This can be achieved by incorporating data from multiple modals. However, existing multi-modality methods only use additional modality in support samples while adhering to a single modal in query samples. Such approach could lead to information imbalance between support and query samples, which confounds model generalization from support to query samples. Towards this problem, we propose a task-adaptive semantic feature learning mechanism to incorporate semantic features for both support and query samples. The semantic feature learner is trained episodic-wisely by regressing from the feature vectors of the support samples. It is utilized to predict semantic features for the query samples. Such method maintains a consistent training scheme between support and query samples and enables direct model transfer from support to query data, which significantly improves model generalization. We conduct extensive experiments on four benchmarks in both inductive and tranductive settings. Results show that the proposed TasNet outperforms state-of-the-art methods with an improvement of 1% to 5% in classification accuracy, demonstrating the superiority of our method. The exhaustive ablation studies further validate the effectiveness of our framework. © 2022, 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

Neural Network-Based Prescription of Chinese Herbal Medicines 11

Neural Network-Based Prescription of Chinese Herbal Medicine...

引用

11th International Conference on information Technology in Medicine and Education, ITME 2021

作者： Zhao, Wen Lu, Weikai Zhou, Chang'en Li, Zuoyong Fan, Haoyi Lin, Xuejuan Yang, Zhaoyang Li, Candong Fujian University of Traditional Chinese Medicine School of Traditional Chinese Medicine Fuzhou350122 China Minjiang University Fujian Provincial Key Laboratory of Information Processing and Intelligent Control College of Computer and Control Engineering Fuzhou350121 China Harbin University of Science and Technology School of Computer Science and Technology Harbin150080 China

ISBN: (纸本)9781665406796

Objective: To develop a neural network model that recommends traditional Chinese medicine (TCM) herbal prescriptions. Methods: We constructed a new dataset of diagnosis and treatment knowledge from the Treatise on Febrile Diseases. Based on TCM's logical principles of 'syndrome differentiation' and 'state recognition', a back-propagation neural network model is proposed that simulates clinical diagnosis and treatment. Results: The proposed model is a four-layer BP neural network. Experiments on the constructed dataset show that the proposed method achieved the best precision, recall, and F1-scores. Conclusion: The proposed method provides much more accurate herbal prescription recommendations than logistic regression. © 2021 IEEE.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

image Definition Evaluation Function Based on Improved Maximum Local Variation and Focusing Window Selection 1

引用

6th International Conference on Data Mining and Big Data, DMBD 2021

作者： Li, Shiyun Chen, Jian Wan, Jiaze Li, Zuoyong Lin, Li School of Electronic Electrical Engineering and Physics Fujian University of Technology Xueyuan Road Fujian Fuzhou350118 China College of Computer and Control Engineering Minjiang University No. 200 Xiyuangong Road Fujian Fuzhou350121 China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou350121 China

ISBN: (数字)9789811675027

ISBN: (纸本)9789811675010

Aiming at the problem that commonly used image definition evaluation functions in the focusing process are sensitive to noise, we propose a new image definition evaluation function based on improved maximum local variation and focusing window selection. Firstly, the focusing window is selected by gradient accumulation of a 4-directional Scharr operator in order to reduce the calculation complexity and improve the accuracy of evaluation results. Secondly, an improved 3-neighbors method based on the maximum local variation is proposed to decrease the change in scores for noisy images. Finally, the standard deviation of the improved maximum local variation distribution is used as the measure of clarity. The experimental results show that compared with the method using maximum local variation, the proposed method has better unbiasedness and sensitivity. Compared with the commonly used evaluation functions, the proposed method has better noise immunity and high sensitivity. Compare with other no-reference image quality assessment algorithms, it has better monotonicity, unimodality, unbiasedness, sensitivity and real-time performance as well. The proposed method is suitable for the fine focusing stage with high real-time performance. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Streaming-Data-Driven Distributionally Robust Joint Operation of Multi-Microgrids and Off-Site Hydrogen Refueling Stations under Uncertainties

Streaming-Data-Driven Distributionally Robust Joint Operatio...

引用

IEEE Innovative Smart Grid Technologies - Asia (ISGT Asia)

作者： Longyan Li Chao Ning Haifeng Qiu Department of Automation Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai Jiao Tong University Shanghai China School of Electrical & Electronic Engineering Nanyang Technological University Singapore

ISBN: (纸本)9798350399677

This paper proposes a novel online-learning-enabled hierarchical distributionally robust energy management framework for multi-microgrids (MMGs) with off-site hydrogen refueling stations (HRSs). The proposed framework integrates day-ahead scheduling, intra-day rescheduling and real-time control. The day-ahead scheduling is implemented via a central energy management system for optimal joint scheduling of the MMG systems and off-site HRSs, then the intra-day rescheduling is carried out to optimize the real-time operation and to generate the reference for local controllers. To adequately characterize the statistical properties of renewable and load uncertainties from data streams, we leverage a Dirichlet process mixture model to construct an online-update ambiguity set, which encodes multimodality and local moment information. Based upon this ambiguity set, an online-learning distributionally robust model predictive control (OL-DRMPC) is developed to enhance the tracking performance of energy storage references and to reduce conservatism while guaranteeing probabilistic operational constraints. Its effectiveness is verified in a case study.

关键词： Renewable energy sources Uncertainty Hydrogen Asia Mixture models Probabilistic logic Real-time systems

来源：评论

学校读者我要写书评

暂无评论

OadTR: Online action detection with transformers

arXiv

引用

arXiv 2021年

作者： Wang, Xiang Zhang, Shiwei Qing, Zhiwu Shao, Yuanjie Zuo, Zhengrong Gao, Changxin Sang, Nong Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology China DAMO Academy Alibaba Group China

Most recent approaches for online action detection tend to apply Recurrent Neural Network (RNN) to capture long-range temporal structure. However, RNN suffers from non-parallelism and gradient vanishing, hence it is hard to be optimized. In this paper, we propose a new encoder-decoder framework based on Transformers, named OadTR, to tackle these problems. The encoder attached with a task token aims to capture the relationships and global interactions between historical observations. The decoder extracts auxiliary information by aggregating anticipated future clip representations. Therefore, OadTR can recognize current actions by encoding historical information and predicting future context simultaneously. We extensively evaluate the proposed OadTR on three challenging datasets: HDD, TVSeries, and THUMOS14. The experimental results show that OadTR achieves higher training and inference speeds than current RNN based approaches, and significantly outperforms the state-of-the-art methods in terms of both mAP and mcAP. Code is available at https://***/wangxiang1230/OadTR. Copyright © 2021, The Authors. All rights reserved.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Robust Simultaneous Tracking and Local Dense Structured Mapping at Scenes lack of Geometric Features

Robust Simultaneous Tracking and Local Dense Structured Mapp...

引用

International Conference on Mechatronics and Machine Vision in Practice (M2VIP)

作者： Yueling Shen Zhijian Qiao Xu Wang Hesheng Wang Key Laboratory of System Control and Information Processing of Ministry of Education Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education Shanghai Engineering Research Center of Intelligent Control and Management Shanghai Jiao Tong University Shanghai China

ISBN: (纸本)9781665431545

In this paper, we present a simultaneous tracking and dense structured mapping method aimed at robotic tasks including obstacle avoidance, path planning and manipulation. This is achieved through (1) sparse-to-dense pose estimation with both keypoints and dense vertex images for keeping robust at scenes lack of geometric features, (2) dense local map algorithm, which clears map outside the neighborhood of the robot for the consistency of the system at large-scale scenes, (3) structured analysis to obtain elevation and norms of surfaces, (4) the proposed dynamic mode for ghosting-free mapping in dynamic scenes. Experiments are conducted to evaluate each part of the system. The effectiveness and efficiency are proved by quantitative experiments.

关键词： Meters Surface reconstruction Three-dimensional displays Mechatronics Heuristic algorithms Pose estimation Path planning

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Learning of 3D Scene Flow from Monocular Camera^*

Unsupervised Learning of 3D Scene Flow from Monocular Camera...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Guangming Wang Xiaoyu Tian Ruiqi Ding Hesheng Wang Shanghai Engineering Research Center of Intelligent Control and Management Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing of Ministry of Education Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education Shanghai China

Scene flow represents the motion of points in the 3D space, which is the counterpart of the optical flow that represents the motion of pixels in the 2D image. However, it is difficult to obtain the ground truth of scene flow in the real scenes, and recent studies are based on synthetic data for training. Therefore, how to train a scene flow network with unsupervised methods based on real-world data shows crucial significance. A novel unsupervised learning method for scene flow is proposed in this paper, which utilizes the images of two consecutive frames taken by monocular camera without the ground truth of scene flow for training. Our method realizes the goal that training scene flow network with real-world data, which bridges the gap between training data and test data and broadens the scope of available data for training. Unsupervised learning of scene flow in this paper mainly consists of two parts: (i) depth estimation and camera pose estimation, and (ii) scene flow estimation based on four different loss functions. Depth estimation and camera pose estimation obtain the depth maps and camera pose between two consecutive frames, which provide further information for the next scene flow estimation. After that, we used depth consistency loss, dynamic-static consistency loss, Chamfer loss, and Laplacian regularization loss to carry out unsupervised training of the scene flow network. To our knowledge, this is the first paper that realizes the unsupervised learning of 3D scene flow from monocular camera. The experiment results on KITTI show that our method for unsupervised learning of scene flow meets great performance compared to traditional methods Iterative Closest Point (ICP) and Fast Global Registration (FGR). The source code is available at: https://***/IRMVLab/3DUnMonoFlow.

关键词： Training Three-dimensional displays Laser radar Laplace equations Pose estimation Training data Cameras

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：