检索结果-内蒙古大学图书馆

5th Asian Conference on Pattern Recognition, ACPR 2019

作者： Xu, Qin Li, Linyang Chen, Qian Luo, Bin Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Hefei230601 China

ISBN: (纸本)9783030414030

Fine-grained visual classification is a challenging task because of intra-class variation and inter-class similarity. Most fine-grained models predominantly focus on discriminative region localization which can effectively solve the intra-class variation, but ignore global information and the problem of inter-class similarity which easily leads to overfitting on specific samples. To address these issues, we develop an end-to-end model based on selecting discriminative features for fine-grained visual classification without the help of part or bounding box annotations. In order to accurately select discriminative features, we integrate effective information from different receptive fields to enhance the quality of features, then the features of discriminative regions detected by anchors and the whole image’s feature are jointly processed for classification. Besides, we propose a new loss function to optimize the model to find discriminative regions and prevent overfitting in the particular sample, which can simultaneously solve the problems of intra-class variation and inter-class similarity. Comprehensive experiments show that the proposed approach is superior to the state-of-the-art methods on CUB-200-2011, Stanford Cars and FGVC-Aircraft datasets. © Springer Nature Switzerland AG 2020.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Manifold feature extraction for video based on locally linear embedding

Manifold feature extraction for video based on locally linea...

引用

International Conference on Computer Science and education

作者： Fu, Maosheng Xu, Qin Kong, Min Luo, Bin Key Lab. of Intelligent Computing and Signal Processing Ministry of Education Anhui University Hefei230039 China Department of Computer Science and Technology West Anhui University Anhui Lu'an 237012 China

ISBN: (纸本)9781424460052

Locally linear embedding (LLE) is an elegant nonlinear method for feature extraction and manifold learning, which attempt to project the original data into a lower dimensional feature space by preserving the local neighborhood structure. However, LLE algorithm fails when it is directly applied to video with multi-shot. In this paper, video manifold feature is defined firstly, and then using LLE we extract video manifold feature through adding virtual frames on an enriched set. The proposed manifold feature extraction method is applied to shot transition and video trajectories. The video manifold feature description gives a new tool for video analysis. ©2010 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Few-Shot Object Detection in SAR images via Gaussian Flow Class-Balanced Differential Aggregation 2

Few-Shot Object Detection in SAR images via Gaussian Flow Cl...

引用

2nd IEEE International Conference on signal, Information and Data processing, ICSIDP 2024

作者： Zhao, Po Chen, Jie Zhang, Chaochen Ma, Ke Anhui University Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Electronics and Information Engineering Hefei230601 China

ISBN: (纸本)9798331515669

Currently, few-shot object detection (FSOD) methods for synthetic aperture radar (SAR) images are severely understudied. The high confidentiality and scarcity of SAR data, coupled with the susceptibility of targets in SAR images to significant changes in orientation, make existing models sensitive to variations in novel class examples. This sensitivity leads to challenges in extracting class prototypes and accurately estimating class centers for novel classes. To solve the above issues, we propose a few-shot object detection algorithm for SAR images via Gaussian Flow Class-Balanced Differential Aggregation. Specifically, we first design a class-balanced difference feature aggregation module to solve the problems of difficult class distribution estimation and inaccurate class center estimation of novel classes in SAR images. Second, the contextual information perception module is designed to extract the most representative support features into fine-grained prototypes and aggregate them with the query features using the matching paradigm to solve the imbalance between foreground targets and background in SAR images. Finally, experimental results on MSAR-AIR dataset indicate that our model realizes the best detection properties on SAR images compared to existing models. © 2024 IEEE.

关键词： few-shot learning object detection synthetic aperture radar variational feature learning

来源：评论

学校读者我要写书评

暂无评论

A NEW HIGH ACCURACY RETRIEVAL MODEL BASED ON QUOTIENT SPACE

A NEW HIGH ACCURACY RETRIEVAL MODEL BASED ON QUOTIENT SPACE

引用

2007中国宁波国际计算机科学与技术学术大会

作者： Yang Weimin Li Longshu Key Lab.of Intelligent Computing & Signal Processing Anhui University Ministry of Education Department of Computer Science and Engineering Anhui University

ISBN: (纸本)9780972147903

The effectiveness of ad-hoc retrieval systems appears to have reached a *** the research community is investigating an assortment of variables that will help them develop increasingly accurate retrieval *** paper presents a new method of high accuracy retrieval of document,which is based on quotient *** describes the problem space from different granularity:sentence,paragraph and document,and studies the relations among different granularities.

关键词： Quotient space High accuracy retrieval Granularity analysis Rough set

来源：评论

学校读者我要写书评

暂无评论

Non-intrusive Load Monitoring Based Data-Free Incremental Electrical Appliance Identification 8th

Non-intrusive Load Monitoring Based Data-Free Incremental El...

引用

8th International Conference on Energy and Environmental Science, ICEES 2024

作者： Zhou, Rui Fang, Xiaohan The Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Electrical Engineering and Automation Anhui University Hefei230601 China

ISBN: (纸本)9783031639005

In the realm of modern energy management systems, Non-Intrusive Load Monitoring (NILM) technology provides an innovative solution for power suppliers. It allows for remote monitoring and analysis of users’ electricity consumption patterns without requiring direct access to each device. This technology works by collecting comprehensive energy data at the user’s meter entry point and using algorithms to differentiate and identify the energy consumption characteristics of each device. However, with the increasing number of smart devices used by residential and commercial users, traditional NILM methods face the challenge of dealing with more complex and diverse electricity usage patterns. To address these challenges, we propose a novel incremental NILM framework. This framework has the ability to independently learn new load categories without load data, which is crucial for adapting in real-time to the changing variety of load devices, while also effectively addressing user privacy concerns. We introduce a VI-SCRM for extracting V-I trajectory features, incorporating a reconstruction convolution module. This method reduces the redundancy of V-I trajectory features and eliminates insignificant features, thereby improving algorithm efficiency. Additionally, this approach streamlines the model training process and prevents the model from ‘forgetting’ previously acquired knowledge. By implementing this framework in NILM, the system can continually adjust to new types of devices. Our experimental results confirm the effectiveness of this approach and highlight its potential advantages in practical applications. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

A novel approch for clustering of Chinese text based on concept hierarchy

A novel approch for clustering of Chinese text based on conc...

引用

IEEE International Conference on Cognitive Informatics

作者： Zhao, Peng Geng, Huan-Tong Cai, Qing-Sheng Department of Computer Science and Technology University of Science and Technology of China Hefei 230027 China Key Lab. of Intelligent Computing and Signal Processing of Ministry of Education Anhui University Hefei 230039 China

ISBN: (纸本)9781424404759

After analyzing the disadvantages of traditional text clustering method based on keywords set, a novel approach for clustering of Chinese text based on concept hierarchy is presented. It introduces a Chinese topic classify dictionary as background knowledge to clustering of Chinese text. It adopts a hierarchical coding system which reflects concept relevance among different words and uses Vector Space Model based on concept hierarchy to represent Chinese text. The experimental results show this approach is more effective than traditional text clustering method based on keywords set. © 2006 IEEE.

关键词： Cluster analysis

来源：评论

学校读者我要写书评

暂无评论

Evolutionary Multi-Objective Neural Architecture Search for Generalized Cognitive Diagnosis Models 5

Evolutionary Multi-Objective Neural Architecture Search for ...

引用

5th International Conference on Data-Driven Optimization of Complex Systems, DOCS 2023

作者： Yang, Shangshang Zhen, Cheng Tian, Ye Ma, Haiping Liu, Yuanchao Zhang, Panpan Zhang, Xingyi School of Artificial Intelligence Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Hefei China Institutes of Physical Science and Information Technology Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Hefei China Automation for Process Industries Northeastern University State Key Laboratory of Synthetical Shenyang China

ISBN: (纸本)9798350393521

Cognitive diagnosis models (CDMs) with high generalization are essential for intelligent education systems to reveal students' knowledge states in multiple datasets. However, existing CDMs' architectures are designed dependent on researcher expertise and experience from observing and summarizing partial students' learning behaviors, which makes handcrafted models not cover all learning behaviors well and thus limits their generalization. To develop generalized CDMs, this paper proposes an evolutionary neural architecture search to design CDMs' architectures effective on multiple datasets automatically. Specifically, we first formulate the search task as a multi-objective optimization problem (MOP), which maximizes model performance on multiple datasets containing learning behaviors as many as possible to ensure model generalization. Then, an expressive search space is devised to contain as many potential architectures as possible, where each architecture is denoted by a unified form, taking three given inputs and integrating them in a linear or no-linear manner for prediction. Finally, an evolutionary algorithm with a tailored deduplication strategy is employed to solve the MOP, where each architecture is further represented by a single-root computation tree for easy optimization. Experiments on multiple datasets demonstrate the generalization and effectiveness of the best architecture searched by the proposed approach, and the searched architecture also holds as good interpretability as handcrafted architectures. © 2023 IEEE.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

A full-rate wireless cooperative relay transmission scheme with low detection complexity

引用

Journal of Computational Information Systems 2012年第13期8卷 5279-5285页

作者： Zhang, Hongwei Liu, Yanru Zhang, Ye Li, Xiaohui Key Lab. of Intelligent Computing and Signal Processing of Ministry of Education Anhui University Hefei 230039 China

To achieve low detection complexity and full-rate wireless cooperative transmissions, pre-coding and cyclic delay diversity (CDD) techniques are fully considered and properly combined for a two-path successive relay network with multiple relay nodes in this paper. Firstly, the symbols to be transmitted at source node are encoded with linear complex field coding methods, and then these coded symbols are divided into two data streams. Both streams are transmitted to two groups of relay nodes respectively during two consecutive time slots. After having been amplified and forwarded by relay nodes using CDD ways, all transmit signals are received by the destination node finally. At receiver, only two symbols are needed to be jointly detected in each transmission process, the complexity is low. Simulation results show that the proposed scheme can achieve full-rate cooperative relay transmissions and obtain high diversity gains of the distributed wireless systems. © 2011 by Binary Information Press.

关键词： Orthogonal frequency division multiplexing

来源：评论

学校读者我要写书评

暂无评论

Elimination of Interference Analysis for RIS Element Demage 7

Elimination of Interference Analysis for RIS Element Demage

引用

7th IEEE International Conference on Electronic Information and Communication Technology, ICEICT 2024

作者： Min, Sipei Yu, Canping Li, Liping Li, Yingsong Zlatanov, Nikola Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education China Innopolis University Faculty of Computer and Engineering Sciences Russia

ISBN: (纸本)9798350384437

This paper aims to investigate the ability of reconfigurable intelligent surfaces (RIS) damaged in multi-user environments to eliminate interference. Our research found that even if the RIS is damaged, interference can still be eliminated in the absence of a direct path and when the number of RIS is sufficient. In order to solve interference cancellation, we adopted the alternating projection algorithm, which ensures local convergence and good convergence speed. © 2024 IEEE.

关键词： Interference suppression

来源：评论

学校读者我要写书评

暂无评论

A novel anonymous secret sharing scheme based on BP Artificial Neural Network

A novel anonymous secret sharing scheme based on BP Artifici...

引用

2012 8th International Conference on Natural Computation, ICNC 2012

作者： Zhong, Hong Wei, Xiaodong Shi, Runhua Key Laboratory of Intelligent Computing and Signal Processing Anhui University Ministry of Education China School of Computer Science and Technology Anhui University China

ISBN: (纸本)9781457721311

In an anonymous secret sharing scheme, the secret can be reconstructed without knowledge of which participant hold which share. That is, in such scheme the secret can be recovered from the shares without the identities of shareholders. However, the previous anonymous schemes are not very efficient and the existing bounds make optimization work difficult. In this paper, we present a novel anonymous secret sharing scheme by using BP Artificial Neural Network. The scheme can ensure that the shareholders' identities are completely anonymous when the secret is recovered. Unlike previous schemes, our scheme is an ideal (t, n) threshold scheme which parameter t doesn't have lower bounds and need less storage space. Furthermore, the shares can be chosen by shareholders and the communication between dealer and participants doesn't need secure channel. In addition, the participants can verify the correctness of their shares and the secret S. © 2012 IEEE.

关键词： Neural 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：