检索结果-内蒙古大学图书馆

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Kirill Ivanov Gonzalo Ferrer Anastasiia Kornilova Skolkovo Institute of Science and Technology (Skoltech) Center for AI Technology (CAIT) Software Engineering Department Saint Petersburg State University

Lines are interesting geometrical features commonly seen in indoor and urban environments. There is missing a complete benchmark where one can evaluate lines from a sequential stream of images in all its stages: Line detection, Line Association and Pose error. To do so, we present a complete and exhaustive benchmark for visual lines in a SLAM front-end, both for RGB and RGBD, by providing a plethora of complementary metrics. We have also labeled data from well-known SLAM datasets in order to have all in one poses and accurately annotated lines. In particular, we have evaluated 17 line detection algorithms, 5 line associations methods and the resultant pose error for aligning a pair of frames with several combinations of detector-association. We have packaged all methods and evaluations metrics and made them publicly available on web-page 3 3 https://***/evolin/.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Improving Medical Predictions with Label Noise Tolerant Classification 4

Improving Medical Predictions with Label Noise Tolerant Clas...

引用

4th International Conference on Advances in Computing, Communication Control and Networking, ICAC3N 2022

作者： Vernekar, Shivam Ayyar, Arun Rajagopalan, Arun Kumar, Bijendra Mishra, Vivek Kumar Evive Software Analytics Pvt. Ltd. Bengaluru India Santa Fe Research Pvt Ltd Chennai India Evive Software Analytics Pvt. Ltd. Data Science Bengaluru India Galgotia College of Engineering and Technology Electrical and Electronics Engineering Greater Noida India

ISBN: (纸本)9781665474368

Supervised machine learning algorithms depend crucially on availability of a large pool of correctly labelled instances. However many real world datasets may contain noisy features and label values. This is even more problematic for medical datasets since noise can be asymmetric (class dependent) due to imprecise class definitions or subjective human biases during data collection. There is easy availability of a large pool of unlabelled instances which can't be directly used for training, for example raw data from medical devices like fitness trackers, data from health surveys etc. Labelling them (with respect to certain task) with the help of human experts might be a time consuming and a costly process. Besides, learning algorithms trained on noisy datasets can reduce the quality of future inferences making them unsuitable for business use-cases. In this paper we propose a semi-supervised learning based approach where we combine information embedded in unlabelled and incorrectly labelled instances with a very small set of correctly labelled instances. To the best of our knowledge this is the first work based on semi-supervised learning for reducing the noise in generated predictions using imperfect datasets. It is demonstrated through extensive experimentation using a medical diagnostic diabetes dataset, that by using only a fraction of correctly labelled instances, we are able to generate high quality predictions on unseen data. © 2022 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

A high-resolution numerical investigation of unsteady wake vortices for coaxial rotors in hover

引用

Chinese Journal of Aeronautics 2024年第11期37卷 278-299页

作者： Shaoqiang HAN Wenping SONG Zhonghua HAN Jianhua XU Tianfu Engineering-oriented Numerical&Software Innovation Center College of Computer ScienceSichuan UniversityChengdu 610065China National Key Laboratory of Science and Technology on Aerodynamic Design and Research School of AeronauticsNorthwestern Polytechnical UniversityXi’an 710072China

High-resolution numerical simulations for wake vortical flows have long been a challenge in rotor aerodynamics.A novel spectrum-optimized sixth-order Weighted Essentially NonOscillatory(WENO)scheme is proposed to discretize inviscid fluxes on moving overset grids,and the Improved Delayed Detached Eddy Simulation(IDDES)is employed to resolve turbulent *** integration of these methods facilitates a comprehensive numerical investigation into the unsteady vortical flows over coaxial rotors in *** results highlight the substantial improvement in numerical resolution,in terms of both spatial structure and temporal evolution of unsteady multiscale wake *** rotors in hover manifest three primary scales of wake vortex structures:(A)the helical evolution of primary blade tip vortices and the periodic occurrence of strong Blade-Vortex Interactions(BVI);(B)the continuous shedding of small-scale horseshoeshaped vortices from the trailing edges of rotor blades,forming the vortex sheets;(C)the emergence of small-scale secondary vortex braids induced by interactions between rotor tip vortices and the vortex *** vortex structures and their interactions cause high-frequency oscillations in rotor disk loads and induce unsteady perturbations in the local flow *** among these primary vortices,coupled with the generation of secondary vortices,result in the dissipation,distortion,and breakup of the rotor tip vortices,ultimately forming a vortex ***,a substantial quantity of seemingly weak small-scale secondary vortex braids significantly contribute to energy dissipation during the evolution of wake vortices for coaxial rotors in hover.ó2024 Chinese Society of Aeronautics and *** and hosting by Elsevier *** is an open access article under the CC BY-NC-ND license(http://***/licenses/by-nc-nd/4.0/).

关键词： Coaxial rotor Blade tip vortex Secondary vortex High-order scheme IDDES Moving overset grid

来源：评论

学校读者我要写书评

暂无评论

A Weighted Topic Modeling Approach Based on Word Embedding

A Weighted Topic Modeling Approach Based on Word Embedding

引用

International Conference on Artificial Intelligence and Computer Information technology (AICIT)

作者： Conghui Yuan Shengnan Zhang Information Science and Engineering School Shenyang University of Technology Shenyang China Software School Shenyang University of Technology Shenyang China

Topic modeling is commonly used to discover potential semantic structures in different domain corpora, and it is an essential tool for semantic retrieval, feature extraction, and target classification of large amounts of text. As a widely used probabilistic topic generation model, Latent Dirichlet Allocation (LDA) is powerful in extracting salient topics, but LDA makes assumptions based on bag-of-words model, which ignores the semantic information implied between words, makes inter-word disorder in the process of topic extraction, and results in poor quality of generated topics. In this paper, we propose a weighted topic modeling method based on word embedding, which first constructs the directed semantic graph between feature words, calculates weight values of nodes, and then improves LDA topic model by combining word embedding. The experimental results show that the presented method can effectively enhance the contextual semantic association and improve the distinction between topics compared with TF-LDA and ETM.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SHT-based public auditing protocol with error tolerance in FDL-empowered IoVs

引用

Digital Communications and Networks 2024年第1期10卷 142-149页

作者： Kui Zhu Yongjun Ren Jian Shen Pandi Vijayakumar Pradip Kumar Sharma School of Computer and Software Nanjing University of Information Science&TechnologyNanjing210044China Peng Cheng Laboratory Shenzhen518000China Department of Computer Science and Engineering University College of Engineering TindivanamTamil Nadu604001India Department of Computing Science University of AberdeenAberdeenAB243UEUK

With the intelligentization of the Internet of Vehicles(lovs),Artificial Intelligence(Al)technology is becoming more and more essential,especially deep *** Deep Learning(FDL)is a novel distributed machine learning technology and is able to address the challenges like data security,privacy risks,and huge communication overheads from big raw data ***,FDL can only guarantee data security and privacy among multiple clients during data *** the data sets stored locally in clients are corrupted,including being tampered with and lost,the training results of the FDL in intelligent IoVs must be negatively *** this paper,we are the first to design a secure data auditing protocol to guarantee the integrity and availability of data sets in FDL-empowered ***,the cuckoo filter and Reed-Solomon codes are utilized to guarantee error tolerance,including efficient corrupted data locating and *** addition,a novel data structure,Skip Hash Table(SHT)is designed to optimize data ***,we illustrate the security of the scheme with the Computational Diffie-Hellman(CDH)assumption on bilinear *** theoretical analyses and performance evaluations demonstrate the security and efficiency of our scheme for data sets in FDL-empowered IoVs.

关键词： Internet of vehicles Federated deep learning Data security Data auditing Data locating and recovery

来源：评论

学校读者我要写书评

暂无评论

Optimization design of highway tunnel lighting entrance section for safety and energy saving

Optimization design of highway tunnel lighting entrance sect...

引用

第35届中国控制与决策会议

作者： Lunhui Xu Runnan Xu Mengyao Zhu Guangdong University of Science and Technology School of computer Jiangxi University of Science and Technology School of Electrical Engineering and Automation Software Engineering Institute of Guangzhou Department of electronics

In order to solve the contradiction between over-luminance and under-luminance in the highway tunnel lighting system,an entrance section luminance curve optimization design method is proposed to the purpose of traffic safety and energy consumption ***,under the constraints of the Rules and Guidelines,the objective function of luminance curves optimization considering over-luminance and under-luminance is constructed,and the four-step optimization model and design parameters of the entrance section luminance curve are *** the luminance curve optimization model is evaluated and analyzed in terms of comfort,safety and energy saving ***,combined with the actual tunnel,it is verified that compared with the Rule method,the proposed design method reduces the maximum luminance ratio of adjacent sections by 26.5%,and the lighting step curve in the second half of the entrance section is reduced by 95.7% compared with the adaptive *** power consumption was reduced by 6.1% and 6.3% for HPS and LED lights,respectively,compared to the design method considering only traffic safety.

关键词： Tunnel lighting Optimized design Tunnel security Energy saving and Consumption reduction

来源：评论

学校读者我要写书评

暂无评论

ACDR-CRAFF Net: A Multi-Scale Network Based on Adaptive Channel and Coordinate Relational Attention Network for Remote Sensing Scene Classification

引用

IET Image Processing 2025年第1期19卷

作者： Dai, Wei Xu, Haixia Shi, Furong Yuan, Liming Wang, Xinyu Wen, Xianbin School of Computer Science and Engineering Tianjin University of Technology Tianjin China Key Laboratory of Computer Vision and System Ministry of Education Tianjin University of Technology Tianjin China Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology Tianjin University of Technology Tianjin China

Accurate classification of remote sensing scene images is crucial for diverse applications, from environmental monitoring to urban planning. While convolutional neural networks (CNNs) have dramatically improved classification accuracy, challenges remain due to the complex distribution of small objects, varied spatial configurations, and intra-class multimodality in remote sensing images. In this work, we make three key contributions to address these challenges. (1) We propose the adaptive channel and coordinate relational attention network (ACDR-CRAFF), a novel multi-scale feature fusion framework designed to enhance feature representation across scales. (2) We introduce two innovative modules: the adaptive channel dimensionality reduction (ACDR) module, which dynamically adjusts channel representations to retain essential low-dimensional features, and the coordinate relational attention multi-scale feature fusion (CRAFF) module, which effectively captures and transfers spatial information between feature levels. (3) By integrating ACDR and CRAFF, our model achieves a progressive fusion of local to global features, ensuring robust feature expressiveness at multiple scales. Experimental results on four widely used benchmark datasets demonstrate that ACDR-CRAFF consistently outperforms several state-of-the-art methods, achieving significant improvements in classification accuracy and setting a new benchmark for complex remote sensing scene classification tasks. These results underscore the effectiveness of our approach in addressing the limitations of existing methods and advancing the state of the art in remote sensing image analysis. © 2025 The Author(s). IET Image Processing published by John Wiley & Sons Ltd on behalf of The Institution of engineering and technology.

关键词： Photointerpretation

来源：评论

学校读者我要写书评

暂无评论

SEARCHING FRAME-RECURRENT ATTENTIVE DEFORMABLE NETWORK FOR REAL-TIME VIDEO DERAINING

SEARCHING FRAME-RECURRENT ATTENTIVE DEFORMABLE NETWORK FOR R...

引用

2021 IEEE International Conference on Multimedia and Expo, ICME 2021

作者： Xue, Xinwei Meng, Xiangyu Ma, Long Wang, Yi Liu, Risheng Fan, Xin International School of Information Science and Engineering Dalian University of Technology China School of Software Technology Dalian University of Technology China Key Laboratory for Ubiquitous Network Service Software of Liaoning Province China

ISBN: (纸本)9781665438643

Video deraining has become an issue of great interest since rain streaks inevitably affect video quality. Most of the existing works focus on heuristically designing the network architecture to integrate available information derived from the temporal dimension. However, their inferences take a long time, so that the practicability is somewhat ignored. To solve this problem, we develop a real-time video deraining network in a frame-recurrent manner. It includes a fast attentive deformable alignment module and an automatically-discovered spatial-temporal reconstruction module. In which, the alignment is composed of a single newly-built deformable convolution under the channel attention mechanism to keep the accurate motion consistency and reduce time-consuming by a wide margin. The reconstruction part for the first time introduces the architecture search technique for video deraining to automatically discover a high-effective architecture by designing an effective and compact search space. Experimental results demonstrate remarkable superiority both in computational efficiency and actual performance compared to other state-of-the-art approaches. © 2021 IEEE

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

Remote Sensing Image Scene Classification Based on Multidimensional Attention and Feature Enhancement

IAENG International Journal of Computer Science

引用

IAENG International Journal of Computer Science 2023年第4期50卷 1337页

作者： Liu, Chengrui Dai, Hong Wang, Shuang Chen, Junhong University of Science and Technology Liaoning Liaoning CO Anshan114051 China Computer Science and Software Engineering University of Science and Technology Liaoning Liaoning Anshan China

Remote sensing image scene classification is a challenging task that involves automatically assigning labels to remote sensing images based on predefined categories. The inherent intra-class diversity and inter-class similarity of remote sensing images make it difficult for classification models to capture the discriminative key information necessary for accurate labeling, resulting in classification confusion. This paper proposes a novel method called Multidimensional Attention and Feature Enhancement (MA-FE) to address this issue. The proposed MA-FE method comprehensively captures essential features in different dimensions of channel and position through the Multidimensional Attention (MA) module, which integrates and combines the captured features. The Feature Enhancement (FE) module then amplifies the dis- criminative features to suppress the interference of useless information, thus improving the representation ability of the model. We conducted detailed experiments on three public remote sensing datasets and performed a comparative e- valuation with multiple remote sensing scene classification methods proposed in recent years. The overall accuracies of the proposed MA-FE method on these datasets were 99.66%, 95.68%, and 93.21%, respectively. Our experimental results demonstrate that the proposed MA-FE method is more effective in extracting complex features in remote sensing images than other methods, thereby proving its effectiveness. © 2023, International Association of Engineers. All rights reserved.

关键词： Remote sensing

来源：评论

学校读者我要写书评

暂无评论

Decoupled 2S-AGCN Human Behavior Recognition Based on New Partition Strategy 13th

Decoupled 2S-AGCN Human Behavior Recognition Based on New Pa...

引用

13th EAI International Conference on Mobile Networks and Management, MONAMI 2023

作者： Qiuming, Liu Longping, Chen Da, Wang He, Xiao Yang, Zhou Dong, Wu School of Software Engineering Jiangxi University of Science and Technology Nanchang330013 China Nanchang Key Laboratory of Virtual Digital Factory and Cultural Communications Nanchang330013 China Information and Communication Branch of Jiangxi Electric Power Co. Ltd. Nanchang330095 China

ISBN: (纸本)9783031554704

Human skeleton point data has better environmental adaptability and motion expression ability than RGB video data. Therefore, the action recognition algorithm based on skeletal point data has received more and more attention and research. In recent years, skeletal point action recognition models based on graph convolutional networks (GCN) have demonstrated outstanding performance. However, most GCN-based skeletal action recognition models use three stable spatial configuration partitions, and manually set the connection relationship between each skeletal joint point. Resulting in an inability to better adapt to varying characteristics of different actions. And all channels of the input X features use the same graph convolution kernel, resulting in coupling aggregation. Contrary to the above problems, this paper proposes a new division strategy, which can better extract the feature information of neighbor nodes of nodes in the skeleton graph and adaptively obtain the connection relationship of joint nodes. And introduce Decoupled Graph Convolution (DC-GCN) to each partition to solve the coupled aggregation problem. Experiments on the NTU-RGB+D dataset show that the proposed method can achieve higher action recognition accuracy than most current methods. © ICST Institute for Computer Sciences, Social Informatics and Telecommunications engineering 2024.

关键词： Convolution

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：