检索结果-内蒙古大学图书馆

5th International Conference on Data Science and information Technology, DSIT 2022

作者： Jia, Hong Weng, Yubin Shenzhen Institute of Artificial Intelligence and Robotics for Society College of Electronics and Information Engineering Shenzhen University Guangdong Key Laboratory of Intelligent Information Processing Shenzhen China

ISBN: (数字)9781665498685

ISBN: (纸本)9781665498685

The purpose of feature selection is to obtain a feature subset from the original data to realize dimension reduction, and at the same time, improve the performance of following machine learning task. Due to the lack of label information, unsupervised feature selection is more challenging. In this paper, the idea of sample clustering is applied to feature space. Clustering the features makes the similarity between features in the same cluster high and that from different clusters low. Subsequently, representative features are selected from each cluster to form the final feature subset. Along this way, an unsupervised feature selection algorithm which considers both the similarity and relevance of different features is proposed. Experiments in comparison with both traditional and novel algorithms on benchmark data sets are performed. The results show the superiority of the proposed method. © 2022 IEEE.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Chinese image captioning via double decoding based on visual prompts 5

Chinese image captioning via double decoding based on visual...

引用

5th International Conference on Computer Vision and Data Mining, ICCVDM 2024

作者： Tan, Weiguo Xiao, Yannan Wen, Yayuan Deng, Zhenrong Huang, Wenming School of Computer Science and Information Security Guilin University of Electronic Technology Guangxi Guilin541004 China Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guangxi Guilin China College of Electronic Engineering Guangxi Normal University Guangxi Guilin China

ISBN: (纸本)9781510682863

The significant progress of vision-language pre-trained models (VLMs) and large language models (LLMs) have provided a feasible new mode for image captioning, which relies on VLMs to process images and then utilizes LLMs to generate captions, simplifying the caption generation process and making it lighter. Based on this mode, to address the issues of deviation between the generated captions and the content of image expressions, incomplete descriptive information, and resource hungry in previous Chinese image captioning models, we propose a Chinese image captioning model via double decoding based on Visual Prompts, DDVP. This model employs the CLIP model as the encoder, the GPT2 model as the decoder, and introduces Visual Prompts, which are keywords related to image content. The model adopts a double decoding approach, first decoding to generate Visual Prompts and then decoding to generate the final captions based on the Visual Prompts. Through evaluation, we have demonstrated that our model achieves competitive results on the AIC-ICC dataset, and while maintaining fluency, the generated captions of DDVP can also cover the information in the image more comprehensively and accurately. © 2024 SPIE.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

A Four-arm Archimedean Spiral Antenna with Multi-mode Orbital Angular Momentum 5

A Four-arm Archimedean Spiral Antenna with Multi-mode Orbita...

引用

5th IEEE International Conference on Electronic information and Communication Technology, ICEICT 2022

作者： Qian, Sixian Meng, Lulu Huang, Zhixiang Li, Yingsong Yang, Lixia School of Electronic and Informationn Engineering Anhui University Hefei230601 China Anhui Province Key Laboratory of Target Recognition and Feature Extraction LuAn230088 China Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education China

ISBN: (数字)9781665472111

ISBN: (纸本)9781665472111

A four-arm Archimedean spiral multi-mode OAM (Orbital Angular Momentum) antenna with bandwidth of 1.34GHz-9.53GHz is presented and analyzed. The bandwidth of traditional OAM antenna is dramatically improved by utilizing the self-complementarity between the arms of Archimede spiral. Comparing to the dual arm helical antenna, the vortex electromagnetic wave phase for the proposed scheme shows better continuity and purity, simultaneously more modes are realized. The reflector is arranged under the ground to make the antenna achieve unidirectional radiation characteristics and reduce backward radiation. The mode for l= 0, l= 1, l= 2 and mixed mode l= 1.2 are realized by controlling phase of the four different feed ports. Finally, the effects about the rotation radius for the Archimede spiral on the patterns with various arm width is investigated and discussed. The results are significant consistency with the design, and concurrently superb vortex characteristics are achieved in different modes. © 2022 IEEE.

关键词： Spiral antennas

来源：评论

学校读者我要写书评

暂无评论

Towards Label-Efficient Deep Learning for Myopic Maculopathy Classification 1

引用

Myopic Maculopathy Analysis Challenge, MMAC 2023, which was a part of the 26th International Conference on Medical Image Computing and Computer Assisted Intervention, MICCAI 2023

作者： Hou, Junlin Xu, Jilan Xiao, Fan Zhang, Bo Xu, Yiqian Zhang, Yuejie Zou, Haidong Feng, Rui School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing Fudan University Shanghai China Academy for Engineering and Technology Fudan University Shanghai China Department of Ophthalmology Shanghai General Hospital School of Medicine Shanghai Jiao Tong University Shanghai China

ISBN: (数字)9783031548574

ISBN: (纸本)9783031548567

Myopic Maculopathy is the leading cause of legal blindness in patients with pathologic myopia. Automated myopic maculopathy diagnosis is of vital importance to early treatment and progression slowdown. However, the scarcity of labeled fundus images with myopic maculopathy makes it challenging to improve diagnostic performance via deep learning models. In this paper, we construct a label-efficient deep learning framework for myopic maculopathy classification. In specific, we exploit two categories of pre-training methods, i.e., vision-language pre-training and self-supervised visual representation learning, to alleviate the overfitting problem caused by the limited number of training images. Moreover, we adopt a semi-supervised learning technique, namely pseudo labeling, to leverage a large number of unlabeled fundus images from external datasets. We also investigate the impact of other key components in model training for better performance, including backbone architecture, input resolution, and loss function. Our method is evaluated in the MICCAI 2023 Myopic Maculopathy Analysis Challenge (MMAC). Among 17 participating teams, our ensembled model ranked 1st on the leaderboard with an average score of 0.8752. The code will be publicly available at https://***/FDU-VTS/MMAC. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Learning Hierarchical Robot Skills Represented by Behavior Trees from Natural Language 29th

Learning Hierarchical Robot Skills Represented by Behavior ...

引用

29th International Conference on Cooperative information Systems, CoopIS 2023

作者： Wang, Kaiyi Zhao, Yongjia Dai, Shuling Yang, Minghao He, Yichen Zhang, Ning State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China Jiangxi Research Institute Beihang University Jiangxi China Institute of Automation Chinese Academy of Sciences Beijing China Institute of Intelligent Information Processing Beihang University Beijing China

ISBN: (纸本)9783031468452

Learning from natural language is a programming-free and user friendly teaching method that allows users without programming knowledge or demonstration capabilities to instruct robots, which has great value in industry and daily life. The manipulation skills of robots are often hierarchical skills composed of low-level primitive skills, so they can be conveniently represented by behavior trees (BTs). Based on this idea, we propose NL2BT, a framework for generating behavior trees from natural language and controlling robots to complete hierarchical tasks in real time. The framework consists of two language processing stages, an initial behavior tree library composed of primitive skill subtrees, and a BT-Generation algorithm. To validate the effectiveness of NL2BT, we use it to build a Chinese natural language system for instructing robots in performing 3C assembly tasks, which is a significant application of Industry 4.0. We also discuss the positive impact of real-time teaching, visual student models, and the synonymous skill module in the framework. In addition to the demonstrated application, NL2BT can be easily migrated to other languages and hierarchical task learning scenarios. © 2024, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Robot programming

来源：评论

学校读者我要写书评

暂无评论

A L2 Band LHCP Antenna with Combination of Unequal Slots and Arc-Shaped Protruding Patches 5

A L2 Band LHCP Antenna with Combination of Unequal Slots and...

引用

5th IEEE International Conference on Electronic information and Communication Technology, ICEICT 2022

作者： Meng, Lulu Qian, Sixian Li, Yingsong Huang, Zhixiang Yang, Lixia School of Electronic and Informationn Engineering Anhui University Hefei230601 China Anhui Province Key Laboratory of Target Recognition and Feature Extraction LuAn230088 China Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education China

ISBN: (数字)9781665472111

ISBN: (纸本)9781665472111

A microstrip circular polarization (CP) patch antenna with a combination of unequal slots and arc-shaped protruding patches is proposed and designed, which can work for L2 band of GPS. The antenna is composed of ground plane, dielectric and radiation patch, where two unequal slots and arc-shaped protruding patches are loaded on the patch and placed along the diagonal. By adjusting the radius of arc-shape slots and protruding patches, Left-handed circular polarization (LHCP) is realized. Simulation and optimization results show that the CP antenna achieves axial ratio bandwidth of 10MHz and impedance bandwidth of 40MHz, providing a potential application for GPS. © 2022 IEEE.

关键词： Circular polarization

来源：评论

学校读者我要写书评

暂无评论

Distributed Secondary Control of DC Microgrids with Operation Loss Reduction

Distributed Secondary Control of DC Microgrids with Operatio...

引用

第43届中国控制会议

作者： Maoxiang Qiu Zhicheng Zhang Zhiqiang Zuo Yijing Wang Tianjin Key Laboratory of Intelligent Unmanned Swarm Technology and System School of Electrical and Information Engineering Tianjin University Key Laboratory of System Control and Information Processing Ministry of Education

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

In DC microgrids, current sharing and voltage regulation are two main objectives for real-time control, while the operation loss reduction is typically achieved by steady-state optimization. However, the ratio of current sharing is generally determined by the result of the centralized optimization in the classical hierarchical control framework of DC microgrids. Such an issue brings insufficient capability in respond to the changes of photovoltaic power and stored energy in the solar-powered energy systems. To handle this, this work proposes a distributed control scheme for single-bus DC microgrids. Under the proposed controller, the objectives of current sharing, bus voltage regulation and the total operation loss(converter loss and line loss) reduction can be guaranteed simultaneously. Moreover, the constraints on line currents and bus voltage are tackled as ***, simulations verify the performance of the proposed control scheme.

关键词： DC Microgrids Current Sharing Voltage Regulation Operation Loss Reduction Distributed Secondary Control

来源：评论

学校读者我要写书评

暂无评论

Metasurface-Loaded Circularly Polarized Dual-Band MIMO Cellphone Frame Antenna for Mobile Communication Applications

引用

IEEE Antennas and Wireless Propagation Letters 2025年

作者： Meng, Yanfeng Ren, Aidi Wang, Chao Xu, Guanghui Zhao, Luyu Li, Yingsong Yang, Lixia Huang, Zhi-Xiang Anhui University Information Materials and Intelligent Sensing Laboratory of Anhui Province Hefei230039 China Anhui University School of Electronic and Information Engineering Hefei230601 China Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Hefei230039 China Anhui Province Key Laboratory of Target Recognition and Feature Extraction Anhui237010 China Anhui University Key Laboratory of Electromagnetic Environment al Sensing of Anhui Higher Education Institutes Hefei230039 China

In this letter, a set of circularly polarized (CP) multiple-input multiple-output (MIMO) cellphone frame antennas for mobile communication applications is proposed. The planar inverted-F antenna (PIFA) and monopole antenna operate at frequencies of 3.5 GHz and 5.5 GHz with impedance and axial ratio (AR) bandwidths overlapping at 11.4% (3.3-3.7 GHz) and 7.3% (5.2-5.6 GHz), respectively. To reduce the electromagnetic coupling between the two antennas, the V-shaped mental fence is added and different rectangular metasurface (RMS) arrays are adopted to enhance the CP radiation performances. This design not only covers 5G communication, LTE, and the 5 GHz Wi-Fi band. It also provides a communication strategy for future direct satellite communication from cellphones, enhancing efficient switching between satellite and cellular networks. © 2002-2011 IEEE.

关键词： Monopole antennas

来源：评论

学校读者我要写书评

暂无评论

QH-Bird: A Fine-Grained Bird Visual Dataset and Hierarchical Consistency Denoising Method 3

QH-Bird: A Fine-Grained Bird Visual Dataset and Hierarchical...

引用

3rd International Conference on Artificial Intelligence, Internet of Things and Cloud Computing Technology, AIoTC 2024

作者： Song, Wenjing Geng, Shengling Zhang, Dan School of Computer Science Qinghai Normal University China Academy of Plateau Science and Sustainability People's Government of Qinghai Province Beijing Normal University China Qinghai Normal University The State Key Laboratory of Tibetan Intelligent Information Processing and Application Xining China

ISBN: (纸本)9798331530280

To address the lack of bird image datasets in the field of fine-grained image recognition, this paper introduces a new fine-grained bird image dataset and a deep learning-based denoising method. The dataset encompasses 50,000 images across 200 species. Initially, we constructed an initial bird image dataset by sourcing and compiling images from specialized books and online resources. Subsequently, we employed image deduplication methods based on difference hashing (dHash) and structural similarity index (SSIM) to clean duplicate images from the dataset. Following this, we applied a deep learning-based hierarchical consistency learning method to identify noisy web images, using classification loss and semantic consistency prediction. To further enhance the dataset's diversity and balance, we expanded the number of images for each bird species using data augmentation techniques such as rotation, mirroring, random cropping, and adjustments in brightness and contrast. Ultimately, we constructed a high-quality, balanced, and diverse bird image dataset, named QH-Bird, which serves as a valuable resource for research and applications in fine-grained image recognition. We evaluated our dataset using four deep learning models: VGG-16, ResNet-50, EfficientNet, and HCLNet, achieving accuracies of 87.17%, 88.59%, 90.28%, and 91.59%, respectively. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Distributed Neighbor Selection on Matrix-weighted Networks 38

Distributed Neighbor Selection on Matrix-weighted Networks

引用

38th Youth Academic Annual Conference of Chinese Association of Automation, YAC 2023

作者： Wei, Haoyu Pan, Lulu Shao, Haibin Li, Dewei 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 Department of Automation Shanghai200240 China

ISBN: (纸本)9798350303636

This paper explores distributed neighbor selection in matrix-weighted networks, where a matrix-valued weight captures the interdependencies among agents' states. We demonstrate the feasibility of preserving and, in certain cases, improving the convergence rate of matrix-weighted networks by having agents exclusively engage with a subset of their neighbors. Leveraging the inherent monotonicity of Laplacian matrix eigenvectors, we introduce a novel neighbor selection criterion that reduces network connections while enhancing convergence rates. Existing neighbor selection strategies often require acquiring information from all nodes before making decisions. In order to propose a distributed neighbor selection strategy for matrix-weighted networks, we establish a numerical relationship between Laplacian eigenvectors and a locally measurable metric. In essence, this paper extends prior findings from scalar-weighted networks to matrix-weighted networks. © 2023 IEEE.

关键词： convergence rate Distributed neighbor selection Laplacian matrix matrix-weighted networks

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：