检索结果-内蒙古大学图书馆

Asia Communications and Photonics Conference and Exhibition (ACP)

作者： Lei Yu Le Cheng Jinli Zhang Hongna Zhu Xiaorong Gao Southwest Jiaotong University Chengdu China National Key Laboratory of Science and Technology on Blind Signal Processing Chengdu China

Semi-supervised learning is adopted for fine-grained image classification with convolutional networks. Compared with the traditional approach of distillation, we obtain accuracy improvement of ~3 percent points under ... 详细信息

ISBN: (纸本)9781943580705

关键词： Training Data models Image classification Semisupervised learning Pattern recognition Diseases Conferences

来源：评论

学校读者我要写书评

暂无评论

Challenge-aware U-net for breast lesion segmentation in ultrasound images

引用

Pattern Recognition 2025年 168卷

作者： Dengdi Sun Changxu Dong Yuchen Yan Bo Jiang Yayang Duan Zhengzheng Tu Chaoxue Zhang Key Laboratory of Intelligent Computing & Signal Processing (ICSP) Ministry of Education School of Artificial Intelligence Anhui University China Institute of Artificial Intelligence Hefei Comprehensive National Science Center China Anhui Provincial Key Laboratory of Multimodal Cognitive Computing School of Computer Science and Technology Anhui University China Department of Ultrasound the First Affiliated Hospital of Anhui Medical University China

Deep learning methods can enhance the efficiency of tumor segmentation in breast ultrasound (BUS) images. However, noise interference, small tumors, and blurred boundaries can reduce segmentation accuracy. We design a three-branch challenge-aware U-net (CAU-net) to address these main challenges in BUS images. Our CAU-net extracts the features from three challenge-aware encoders in parallel first. Secondly, we propose an adaptive aggregation layer (AAL) to merge the multi-scale features of three challenging branches, enabling the network to adaptively handle different breast lesion samples with these main challenges. To further enhance the accuracy of segmentation, we introduce the graph reasoning module (GRM) to the network to model the correlation between the channels of the features and acquire the global information in the features. The result of our experiment on two datasets demonstrates the superiority of CAU-net over the advanced medical image segmentation methods. Our code can be downloaded from https://***/tzz-ahu .

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhanced Discriminant Analysis Based Fault Diagnosis Scheme for Marine Diesel Engines 11

Enhanced Discriminant Analysis Based Fault Diagnosis Scheme ...

引用

11th IEEE Data Driven Control and Learning Systems Conference, DDCLS 2022

作者： Zhong, Kai Wang, Jiayi Pan, Donghui Institutes of Physical Science and Information Technology Anhui University Key Laboratory of Intelligent Computing and Signal Processing of the Ministry of Education Anhui Hefei230601 China School of Mathematical Science Anhui University Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Anhui Hefei230601 China

ISBN: (数字)9781665496759

ISBN: (纸本)9781665496759

Since the marine diesel engine is one of the most popular power equipments for modern shipping, accurate and timely diagnose the faults occurred in diesel engine is extraordinary important for long service life and high reliability. Note that Fisher discriminant analysis (FDA) has been widely applied in fault diagnosis field. However, it is quite susceptible to the small sample size (SSS) problem, which is very common in the running process of diesel engine. In response to the problem, this study pro-poses a new fault classification criterion based exponential discriminant analysis (EDA) scheme for diesel engine fault diagnosis, in which the exponential transformation is carried out first to enlarge the margin between different classes, thus the different fault classes are further separated and the diagnosis capability is enhanced. In addition, the theorems of matrix exponential guarantee that the matrix exp (Sw) is always full-rank, even though the Sw is singular. That means, the novel methodology is still appli-cable when confronts with the SSS problem. Finally, based on the more reasonable fault classification criterion, the simulation results on a real-world two-stroke six-cylinder low-speed marine diesel engine indicate that the EDA based diagnosis scheme achieves higher fault diagnosis accuracy with good robustness and practicability in real-world engineering applications. © 2022 IEEE.

关键词： Failure analysis

来源：评论

学校读者我要写书评

暂无评论

A cross-layer design and ant-colony optimization based load-balancing routing protocol for ad-hoc networks

引用

Frontiers of Electrical and Electronic Engineering in China 2007年第2期2卷 219-229页

作者： ZHENG Xiangquan GUO Wei GE Lijia LIU Renting Key Laboratory of Digital Communication and Signal Processing Chongqing Communication CollegeChongqing 400035China National Key Laboratory of Communication University of Electronic Science and Technology of ChinaChengdu 610054China

In order to periodically reassess the status of the alternate path route(APR)set and to improve the efficiency of alternate path construction existing in most current alter-nate path routing protocols,we present a cross-layer design and ant-colony optimization based load-balancing routing protocol for ad-hoc networks(CALRA)in this *** CALRA,the APR set maintained in nodes is aged and reas-sessed by the inherent mechanism of pheromone evaporation of ant-colony optimization algorithm,and load balance of network is achieved by ant-colony optimization combining with cross-layer synthetic *** efficiency of APR set construction is improved by bidirectional and hop-by-hop routing update during routing discovery and routing maintenance ***,ants in CALRA deposit simulated pheromones as a function of multiple parameters corresponding to the information collected by each layer of each node visited,such as the distance from their source node,the congestion degree of the visited nodes,the current pheromones the nodes possess,the velocity of the nodes,and so on,and provide the information to the visiting nodes to update their pheromone tables by endowing the different parameters corresponding to different information and different weight values,which provides a new method to improve the congestion problem,the shortcut problem,the convergence rate and the heavy overheads commonly existed in existing ant-based routing protocols for ad-hoc *** performance of the algorithm is measured by the packet delivery rate,good-put ratio(routing overhead),and end-to-end *** results show that CALRA performs well in decreasing the route overheads,balancing traffic load,as well as increasing the packet delivery rate,etc.

关键词： cross-layer design ant-colony optimization load-balancing routing protocol APR

来源：评论

学校读者我要写书评

暂无评论

Research on Automatic Decoding of Morse Code Based on Deep Learning

Research on Automatic Decoding of Morse Code Based on Deep L...

引用

International Conference on Intelligent Computing, Automation and Systems (ICICAS)

作者： Weihao Li Keren Wang Information Engineering University Zhengzhou China National Key Laboratory of Science and Technology on Blind Signal Processing Chengdu China

ISBN: (数字)9781728161068

ISBN: (纸本)9781728161075

The current automatic decoding method of the Morse telegram has limited accuracy, and can't adapt to signal distortion and code length deviation of the manual telegram. This paper introduces the deep learning method and constructs an automatic decoding model, which integrates feature extraction, sequence modeling and transcription into an end-to-end training neural network. The time-frequency diagrams of signals are used for training and testing. Experimental results show that the decoding system has strong adaptability to manual deviation and frequency drift, and is robust in a noisy environment.

关键词： decoding feature extraction learning (artificial intelligence) neural nets telecommunication computing telegraphy Telegraphies DECODING telecommunication computing Neural network Feature extraction Noisy environment Morse code Frequency drift manual

来源：评论

学校读者我要写书评

暂无评论

Zernike moments and histogram of oriented gradient descriptors for face recognition from video sequence 2

Zernike moments and histogram of oriented gradient descripto...

引用

2nd World Conference on Complex Systems, WCCS 2014

作者： Chelali, Fatma Zohra Djeradi, Amar Speech communication and signal processing Laboratory Faculty of electronics and computer science University of science and technology Houari Boumedienne USTHB Box No 32 Algiers16111 Algeria

ISBN: (纸本)9781479946471

The aim of our work is to investigate the use of two powerful feature descriptor known as Zernike moments and histogram of oriented gradient (HOG) for facial images extracted from a video sequence uttered ten times by four speakers where MLP neural network classifier is used to identify the correct speaker. We've demonstrated good recognition rate obtained for both Zernike moments and HOG descriptors. © 2014 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Dynamic clustering algorithm in mobile wireless sensor network

引用

Journal of Information and Computational science 2015年第13期12卷 4897-4907页

作者： Wang, Bingting Liang, Hui Lin, Qibin Zhang, Yangyi Wang, Yujie Hong, Peilin Hu, Yanjun Department of Electronic and Electrical Engineering Chuzhou University Chuzhou China Department of Electronic Engineering and Information Science University of Science and Technology of China Hefei China Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University Hefei China

In this paper, we analyzed the blindness of traditional clustering algorithms, which select cluster head based on residual energy. Then we proposed the Dynamic Clustering Algorithm (DCA) in Mobile Wireless Sensor Network, which takes into consideration residual buffer level when selecting cluster heads and allots time slots dynamically base on the occupied buffer level. We analyzed the energy model of the proposed DCA algorithm and calculated the optimal distance between cluster heads. Simulation results show that our DCA clustering algorithm has good performances in terms of residual energy, data transmission and network lifetime by comparing it with LEACH and LEACH-CI. ©, 2015, Journal of Information and Computational science. All right reserved.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Person re-identification with density-distance unsupervised salience learning 8th

Person re-identification with density-distance unsupervised ...

引用

8th International Conference on Image and Graphics, ICIG 2015

作者： Zhou, Baoliang Zheng, Aihua Jiang, Bo Li, Chenglong Tang, Jin Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology AnHui University Hefei China Key Laboratory of Industry Image Processing and Analysis in Anhui Province Hefei China

ISBN: (纸本)9783319219684

Human salience of pedestrians images is distinctive and has been shown importantly in person re-identification (or pedestrians identification) problem. Thus, how to obtain the salient area of pedestrian images is important for this salience based pedestrians identification problem. In this paper, we first show that this kind of salient area detection can be formulated as a kind of outlier detection problem, and then propose a novel unsupervised salience learning method using a local outlier-detection technique for person re-identification task. The main feature of the proposed salience computation method is that it exploits both distance and density information simultaneously. Experimental results on several datasets show the effectiveness of the proposed salience based person re-identification method. © Springer International Publishing Switzerland 2015.

关键词： Statistics

来源：评论

学校读者我要写书评

暂无评论

Attention Mechanism Based Technical Phrase Extraction for Patent Text 8

Attention Mechanism Based Technical Phrase Extraction for Pa...

引用

8th International Conference on Intelligent Computing and signal processing, ICSP 2023

作者： Jiang, Xin Zhou, Peng Zhao, Shu Guo, Yufeng Anhui University School of Computer Science and Technology Hefei China Anhui University Key Laboratory of Intelligent Computing and Signal Processing Hefei China

ISBN: (纸本)9798350302455

Technological innovation is becoming one of the critical factors in promoting social development all over the world. The vigorous development of patent applications in recent years provides an opportunity to reveal the inherent laws of innovation, but it also puts forward higher requirements for patent mining technology. An essential step in patent text mining is to build a technical portrait for each patent, that is, to identify the technical phrases involved, which can summarize and represent the patent from a technical perspective. Previous technical phrase extraction methods thoroughly used technical phrases' characteristics and the relationship between technical phrases. Regarding our observations, the relationship between patent texts and technical phrases is also essential. Specifically, critical technical phrases are more relevant to the patent text and can be discovered by the attention mechanism. Motivated by this, we propose an unsupervised technical phrase extraction method based on the attention mechanism named UTESC. Self-attention captures the importance of technical phrases in sentences, and cross-attention captures the relevance between technical phrases and patents. Extensive experiments and algorithm comparisons on patent datasets have proven the effectiveness of our algorithm. © 2023 IEEE.

关键词： Patents and inventions

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：