检索结果-内蒙古大学图书馆

Adaptive nonlinear auto-associative modeling through manifold learning

9th Pacific-Asia Conference on Advances in Knowledge Discovery and Data Mining, PAKDD 2005

作者： Zhang, Junping Li, Stan Z. Intelligent Information Processing Laboratory Department of Computer Science and Engineering Fudan University Shanghai 200433 China Key Laboratory of Complex Systems and Intelligence Science Chinese Academy of Sciences China National Laboratory of Pattern Recognition Center for Biometrics and Security Research Institute of Automation Beijing 100080 China

ISBN: (纸本)3540260765

We propose adaptive nonlinear auto-associative modeling (ANAM) based on Locally Linear Embedding algorithm (LLE) for learning intrinsic principal features of each concept separately and recognition thereby. Unlike traditional supervised manifold learning algorithm, the proposed ANAM algorithm has several advantages: 1) it implicitly embodies discriminant information because the suboptimal parameters of ANAM are determined based on error rate of the validation set. 2) it avoids the curse of dimensionality without loss accuracy because recognition is completed in the original space. Experiments on character and digit databases show that the advantages of the proposed ANAM algorithm. © Springer-Verlag Berlin Heidelberg 2005.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Geometrical probability covering algorithm

Geometrical probability covering algorithm

引用

2nd International Conference on Fuzzy systems and Knowledge Discovery, FSKD 2005

作者： Zhang, Junping Li, Stan Z. Wang, Jue Shanghai Key Laboratory of Intelligent Information Processing Department of Computer Science and Engineering Fudan University Shanghai 200433 China Key Laboratory of Complex Systems and Intelligence Science Institute of Automation Chinese Academy of Sciences Beijing 100080 China National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing 100080 China

ISBN: (纸本)9783540283126

In this paper, we propose a novel classification algorithm, called geometrical probability covering (GPC) algorithm, to improve classification ability. On the basis of geometrical properties of data, the proposed algorithm first forms extended prototypes through computing means of any two prototypes in the same class. Then Gaussian kernel is employed for covering the geometrical structure of data and used as a local probability measurement. By computing the sum of the probabilities that a new sample to be classified to the set of prototypes and extended prototypes, the classified criterion based on the global probability measurement is achieved. The proposed GPC algorithm is simple but powerful, especially, when training samples are sparse and small size. Experiments on several databases show that the proposed algorithm is promising. Also, we explore other potential applications such as outlier removal with the proposed GPC algorithm. © Springer-Verlag Berlin Heidelberg 2005.

关键词： Algorithms

来源：评论

学校读者我要写书评

暂无评论

Learning reference-based representation for image categorization

引用

Journal of Information and Computational Science 2012年第15期9卷 4261-4269页

作者： Li, Qun Zhang, Honggang Guo, Jun Bhanu, Bir Pattern Recognition and Intelligent System Laboratory Beijing University of Posts and Telecommunications Beijing 100876 China Center for Research in Intelligent Systems University of California Riverside CA 92521 United States

This paper develops a reference-based representation method for image categorization and shows that this representation has favorable performance characteristics for multi-class problems. We learn a reconstructive dictionary by associating the reference-set with training data to form a unified objective function. The optimal solution is efficiently obtained using the K-SVD algorithm. After dictionaries are generated, Locality-constrained Linear Coding (LLC) features are extracted. Then, the image feature vector is reconstructed to a histogram-like descriptor by all the image features in the reference-set with a regularization term, leading to a significant reduction of the dimensionality in the feature space. Experimental results show that the proposed method achieves or outperforms results on several benchmarks. © 2012 by Binary Information Press.

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

ANALYSIS AND RESEARCH OF ASSOCIATION pattern BETWEEN NETWORK PERFORMANCES AND FAULTS IN VOIP NETWORK

ANALYSIS AND RESEARCH OF ASSOCIATION PATTERN BETWEEN NETWORK...

引用

2009 IEEE International Conference on Network Infrastructure and Digital Content(2009年IEEE网络基础设施与数字内容国际会议 IEEE IC-NIDC2009)

作者： Jun Guo Chuanmei Wang Bin Zhang Guohui Li Jin Zhou Pattern Recognition and Intelligent System Laboratory Beijing University of Posts and Telecommunica IBM China Research Laboratory Beijing University of Posts and Telecommunications Beijing

ISBN: (纸本)9781424448999

The paper focuses on implementation of association pattern between the network performances and the general network faults. We use network simulation tool, OPNET, to accomplish network simulations of different network faults and different situations based on VoIP. Network performance parameters such as end-to-end delay, jitter, traffic dropped, queuing delay, link throughout, link utilization are monitored and collected. The simulation results are processed using data mining software, Weka, to discover the association pattern.

关键词： VoIP Network Performances Network Faults OPNET Data Mining Weka

来源：评论

学校读者我要写书评

暂无评论

Mining top-K Frequent and Flexible pattern from sequences

Mining top-K Frequent and Flexible Pattern from sequences

引用

2013 IEEE Conference Anthology, ANTHOLOGY 2013

作者： Junyan, Zhang Fan, Min Information Science and Technology College Chengdu University China University Key Laboratory of Pattern Recognition and Intelligent Information Processing Sichuan Province Chengdu China School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China

ISBN: (纸本)9781479916603

pattern Mining is a popular issue in biological sequence analysis. With the introduction of wildcard gaps, more interesting patterns can be mined. In this paper, we propose a new definition related to pattern frequency, under which the Apriori property holds. We define a pattern mining problem called Ming top-K Frequent patterns (MFP), where gaps are mined instead of specified. Compared with existing problems, MFP does not require any domain knowledge of the user. However, theoretical analysis and experimental results show that MFP favors inflexible patterns. We then define another problem where the flexibility threshold of each gap is specified by the user. The problem is called Mining top-K Frequent and Flexible patterns (MF2P). We develop algorithm with polynomial complexities for both problems. patterns can grow from both sides. Some interesting biological patterns mined by our algorithms are discussed. © 2013 IEEE.

关键词： Bioinformatics

来源：评论

学校读者我要写书评

暂无评论

Matching Image with Multiple Local Features

Matching Image with Multiple Local Features

引用

International Conference on pattern recognition

作者： Yudong Cao Honggang Zhang Yanyan Gao Xiaojun Xu Jun Guo Pattern Recognition and Intelligent System Laboratory Beijing University of Posts and Telecommunications Beijing China Liaoning University of Technology Jinzhou China

In this paper, we present the fusional feature composed of Affine-SIFT, MSER and color moment invariants. The fusional feature is more robust and distinctive than a single local feature. Instead of adding three local features together simply, an efficient two-level matching strategy is devised with the fusional feature, which speeds up the establishment of the local correspondences. To remove partial false positives, an affine transformation is estimated with the weighted RANSAC which decreases iteration times. The experimental results show that our approach can achieve more accurate correspondence. We prospect to apply the fusional feature and match strategy to image retrieval in the end.

关键词： Geometry pattern recognition Image color analysis Nearest neighbor searches Robustness Computer vision Stereo vision

来源：评论

学校读者我要写书评

暂无评论

Mixture Loss Function-based Classification Network for Few-shot Learning

Mixture Loss Function-based Classification Network for Few-s...

引用

Computing, Robotics and system Sciences (ICRSS), International Conference on

作者： Yansha Zhang Feng Pan Jie Wang Lin Wang College of Date Science and Information Engineering GuiZhou Minzu University Guiyang China Key Laboratory of Pattern Recognition and Intelligent System of Guizhou Province Guiyang China

Data augmentation technology can effectively solve the problem of few-shot image classification, but many approaches based on data augmentation generated sample have poor discriminability, which negatively affects the classifier and classification accuracy needs to be improved. In this regard, based on the TFFCN, a mixture loss function-based classification network for few-shot learning (MLFCN) is proposed. First of all, for the prototype tensor features with a simple mean representation, ignoring the different contributions of the sample features of support set for per class to the class prototype tensor features, so that the generated prototype tensor features can not well represent sample features of per class, affecting the discriminability of the generated samples. Introduce the improved adaptively spatial feature fusion module, it uses the convolution, considers the support set of different sample features on the prototype tensor, adaptively assign weights, then weighted and summed to obtain a more representative prototype tensor feature; secondly, aiming at the blurred classification boundary of similar categories in the generated sample features, a mixture loss function is proposed. The loss function is to add the inter-class mean squared error term to the mean square error loss, and stretches the inter-class distance of the generated tensor feature, so that the classification boundary is clearer, so as to train a better classifier. Experimental results show that the improved adaptively spatial feature fusion and the mixing loss function can augment the discriminability of the generated tensor features and further improve the classification accuracy.

关键词： Training Tensors Convolution Prototypes Mean square error methods Feature extraction Generators

来源：评论

学校读者我要写书评

暂无评论

A MIL-based interactive approach for hotspot segmentation from bone scintigraphy

A MIL-based interactive approach for hotspot segmentation fr...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Shijie Geng Jingyang Ma Xiaoguang Niu Shaoyong Jia Yu Qiao Jie Yang Institute of Image Processing and Pattern Recognition The Key Laboratory of System Control and Information Processing Ministry of Education China

ISBN: (纸本)9781479999897

Bone scintigraphy is widely used to diagnose bone diseases. Accurate hotspot segmentation is a critical task for tumor metastasis diagnosis. In this paper, we propose an interactive approach to detect and extract hotspots in thoracic region based on a new multiple instance learning (MIL) method called EM-MILBoost. We convert the segmentation problem to a multiple instance learning task by constructing positive and negative bags according to the input bounding box. In order to be robust against noisy input, we train a region-level hotspot classifier with EM-MILBoost and develop several segmentation strategies based on it. The experimental results demonstrate that our method outperforms other methods and is robust against various noisy input.

关键词： Image segmentation Noise measurement Bones Training Indexes Belts Standards

来源：评论

学校读者我要写书评

暂无评论

Deep facial expression recognition: A survey

arXiv

引用

arXiv 2018年

作者： Li, Shan Deng, Weihong Pattern Recognition and Intelligent System Laboratory School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing100876 China

With the transition of facial expression recognition (FER) from laboratory-controlled to challenging in-the-wild conditions and the recent success of deep learning techniques in various fields, deep neural networks have increasingly been leveraged to learn discriminative representations for automatic FER. Recent deep FER systems generally focus on two important issues: overfitting caused by a lack of sufficient training data and expression-unrelated variations, such as illumination, head pose and identity bias. In this paper, we provide a comprehensive survey on deep FER, including datasets and algorithms that provide insights into these intrinsic problems. First, we introduce the available datasets that are widely used in the literature and provide accepted data selection and evaluation principles for these datasets. We then describe the standard pipeline of a deep FER system with the related background knowledge and suggestions of applicable implementations for each stage. For the state of the art in deep FER, we review existing novel deep neural networks and related training strategies that are designed for FER based on both static images and dynamic image sequences, and discuss their advantages and limitations. Competitive performances on widely used benchmarks are also summarized in this section. We then extend our survey to additional related issues and application scenarios. Finally, we review the remaining challenges and corresponding opportunities in this field as well as future directions for the design of robust deep FER systems. Copyright © 2018, The Authors. All rights reserved.

关键词： Surveys

来源：评论

学校读者我要写书评

暂无评论

Dynamic round robin scheduling algorithm for μc/OS-III

Boletin Tecnico/Technical Bulletin

引用

Boletin Tecnico/Technical Bulletin 2017年第7期55卷 8-15页

作者： Zhang, Chunhong Ren, Jianqiang Luo, Ping College of Mathematics and Information Langfang Teachers University Langfang Hebei065000 China Institute of Pattern Recognition and Intelligent System Langfang Teachers University Langfang Hebei065000 China Langfang Key Laboratory of Intelligent Transportation System Langfang Hebei065000 China

In μC/OS-III, the traditional round robin algorithm is inefficient for tasks with the same priority. To solve this problem, this paper proposes a dynamic round robin scheduling algorithm based on the shortest remaining time first, called SRTFDRR. The algorithm determines the scheduling order according to the submission time and the remaining execution time of each task;For tasks with the same priority, set up multiple ready queues, each queue calculates the time slice independently based on the average value of the remaining execution time of the task;The ready task is inserted into the ready queue RQ1 of the corresponding priority in the order of burst time increments;If the priority of the queue task is the current highest priority, the SRTFDRR algorithm runs the task in the queue RQ1;If the time slice expires, there is a task in RQ1 that has not yet finished, and the remaining execution part moves into queue RQ2 waiting for scheduling again, and so on until all tasks are finished. A multi-level queue is formed during the scheduling process. Simulation results show that, compared with the traditional RR algorithm, the SRTFDRR algorithm reduces the average turnaround time, average waiting time, average response time and switching times. It performs well in performance, overhead, and fairness of scheduling.

关键词： Scheduling

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：