检索结果-内蒙古大学图书馆

arXiv 2018年

作者： Yu, Hong Ma, Zhanyu Pattern Recognition and Intelligent System Laboratory Beijing University of Posts and Telecommunications Beijing China

Many researches demonstrated that the DNA methylation, which occurs in the context of a CpG, has strong correlation with diseases, including cancer. There is a strong interest in analyzing the DNA methylation data to find how to distinguish different subtypes of the tumor. However, the conventional statistical methods are not suitable for analyzing the highly dimensional DNA methylation data with bounded support. In order to explicitly capture the properties of the data, we design a deep neural network, which composes of several stacked binary restricted Boltzmann machines, to learn the low dimensional deep features of the DNA methylation data. Experiments show these features perform best in breast cancer DNA methylation data cluster analysis, comparing with some state-of-the-art methods. Copyright © 2018, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Sparse feature representation for visual tracking

Sparse feature representation for visual tracking

引用

International Conference on systems and Informatics (ICSAI)

作者： Yifei Liu Zhenjun Han Qixiang Ye Jianbin Jiao Ce Li Pattern Recognition and Intelligent System Development Laboratory Chinese Academy of Sciences Beijing China

In this paper, a novel sparse feature representation method for object tracking is proposed. The method is on the observation that a tracked object can be dynamically and compactly represented by a few features (sparse representation) from a large feature set (the improved histogram of oriented gradient and color, HOGC). Based on the HOGC features, the sparse representation can be learned online from the constructed training samples during the tracking procedure by exploiting the L1-norm minimization principle, which can also be called feature selection procedure, ensuring the tracking can adapt to the appearance variations of either foreground or background. Experiments with comparisons demonstrate the effectiveness of the proposed method.

关键词： Feature extraction Humans Image color analysis Tracking Visualization Training Minimization

来源：评论

学校读者我要写书评

暂无评论

A Confusion Network Based Confidence Measure for Active Learning in Speech recognition

A Confusion Network Based Confidence Measure for Active Lear...

引用

The 2008 IEEE International Conference on Natural Language Processing and Knowledge Engineering(IEEE NLP-KE 2008)(2008IEEE自然语言处理与知识工程国际会议)

作者： Wei CHEN Gang LIU Jun GUO Pattern Recognition and Intelligent System Laboratory Beijing University of Posts and TelecommunicationsBeijingChina

Speech recognition systems are usually trained using tremendous transcribed utterances, and training data preparation is intensively time-consuming and costly. Aiming at reducing the number of training examples to be labeled, active learning is used in acoustic modeling of speech recognition, this learning scheme iteratively inspects the unlabeled samples, selects the most informative samples corresponding to a certain criterion, then annotates them, and adds the newly transcribed samples to the training set to update the acoustic model. Concerning about the importance of the criterion to select the most informative samples, we proposed a confidence measure computed by confusion network, and used this measure as the criterion for sample selection to improve the efficiency of active learning in acoustic modeling. Our experiments show that active learning, which adopts the proposed confidence measure, can achieve 31％ maximum reduction of labeled data compared with random selection method.

关键词： Active learning Confusion network Confidence Measure

来源：评论

学校读者我要写书评

暂无评论

Structural fingerprint based hierarchical filtering in song identification

Structural fingerprint based hierarchical filtering in song ...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Qiang Wang Gang Liu Zhiyuan Guo Jun Guo Xiaoyu Chen Pattern Recognition and Intelligent System Laboratory Beijing University of Posts and Telecommunications Beijing China

ISBN: (纸本)9781612843483

Automatic song identification has long been a research focus. In this paper, a novel structural fingerprint based hierarchical filtering method is proposed and it consists of two parts: one is the generation of fingerprint with both long structural information and low collision, and the other is an efficient searching algorithm based on a set of selective 2-level filters. Experiments conducted on a database of 10,000 songs show that our approach is fast enough and can achieve the accuracy of 99.7% on 5 second clips with the SNR at 0db comparable to the state-of-the-art.

关键词： Fingerprint recognition Filtering Filtering algorithms Indexes Robustness Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Multi-parameter frequency warping based on LDA

Multi-parameter frequency warping based on LDA

引用

International Conference on Fuzzy systems and Knowledge Discovery (FSKD)

作者： Gang Liu Boce Chu Ruchao Fan Pattern Recognition and Intelligent System Laboratory Beijing University of Posts and Telecommunications Beijing China

The difference between speakers will blur the semantic information, leading to the mismatch between training and decoding, which means the reduction of the performance of speech recognition. This paper presents a novel method to combine subglottic parameter, glottis parameter and supraglottic parameter based on Linear Discriminant Analysis (LDA). Estimating warped factor from multiple parameters using LDA is efficient to extract more stable individual difference information. Experimental results show that the proposed algorithm has better performance than the conventional methods.

关键词： Resonant frequency Semantics Frequency estimation Data mining Maximum likelihood estimation Couplings

来源：评论

学校读者我要写书评

暂无评论

Oscillation resolution for massive cell phone traffic data 1

Oscillation resolution for massive cell phone traffic data

引用

1st Workshop on Mobile Data, MobiData 2016, co-located with MobiSys 2016

作者： Qi, Ling Qiao, Yuanyuan Abdesslem, Fehmi Ben Ma, Zhanyu Yang, Jie Center for Data Science Beijing Key Laboratory of Network System Architecture and Convergence Beijing Laboratory of Advanced Information Network BUPT Beijing China Decisions Networks and Analytics Laboratory SICS Stockholm Sweden Center for Data Science Pattern Recognition and Intelligent System Lab BUPT Beijing China

ISBN: (纸本)9781450343275

Cellular towers capture logs of mobile subscribers whenever their devices connect to the network. When the logs show data traffic at a cell tower generated by a device, it reveals that this device is close to the tower. The logs can then be used to trace the locations of mobile subscribers for different applications, such as studying customer behaviour, improving location-based services, or helping urban planning. However, the logs often suffer from an oscillation phenomenon. Oscillations may happen when a device, even when not moving, does not only connect to the nearest cell tower, but is instead unpredictably switching between multiple cell towers because of random noise, load balancing, or simply dynamic changes in signal strength. Detecting and removing oscillations are a challenge when analyzing location data collected from the cellular network. In this paper, we propose an algorithm called SOL (Stable, Oscillation, Leap periods) aimed at discovering and reducing oscillations in the collected logs. We apply our algorithm on real datasets which contain about 18.9 TB of traffic logs generated by more than 3 million mobile subscribers covering about 21000 cell towers and collected during 27 days from both GSM and UMTS networks in northern China. Experimental results demonstrate the ability and effectiveness of SOL to reduce oscillations in cellular network logs. © 2016 ACM.

关键词： Location based services

来源：评论

学校读者我要写书评

暂无评论

Classification of EEG signal based on non-Gaussian neutral vector

arXiv

引用

arXiv 2018年

作者： Ma, Zhanyu Pattern Recognition and Intelligent System Laboratory Beijing University of Posts and Telecommunications Beijing China

In the design of brain-computer interface systems, classification of Electroencephalogram (EEG) signals is the essential part and a challenging task. Recently, as the marginalized discrete wavelet transform (mDWT) representations can reveal features related to the transient nature of the EEG signals, the mDWT coefficients have been frequently used in EEG signal classification. In our previous work, we have proposed a super-Dirichlet distribution-based classifier, which utilized the nonnegative and sum-to-one properties of the mDWT coefficients. The proposed classifier performed better than the state-of-the-art support vector machine-based classifier. In this paper, we further study the neutrality of the mDWT coefficients. Assuming the mDWT vector coefficients to be a neutral vector, we transform them non-linearly into a set of independent scalar coefficients. Feature selection strategy is proposed on the transformed feature domain. Experimental results show that the feature selection strategy helps improving the classification accuracy. Copyright © 2018, The Authors. All rights reserved.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

INTEGRATIVE LABELING BASED STATISTICAL COLOR MODELS WITH APPLICATION TO SKIN DETECTION

INTEGRATIVE LABELING BASED STATISTICAL COLOR MODELS WITH APP...

引用

IEEE International Conference on Image Processing

作者： Mingzhi Dong Liang Yin Jun Guo Weihong Deng Weiran Xu Pattern Recognition and Intelligent System Laboratory Beijing University of Posts and Telecommunications Beijing China

To alleviate the workload of labeling before estimating certain color distributions, integrative labeling is introduced, which merely needs to figure out whether a picture contains positive-class regions or not and then all pixels of the picture are treated as positive or negative class training samples. Integrative labeling, however, results in heavy mixture of training samples. Thus traditional generative density estimation methods can't be used directly in that they perform poorly with heavily polluted training samples. In this paper, by utilizing the prior knowledge of high separability between positive and negative class color distributions, a discriminative learning based GMM(DiscGMM) is proposed for integrative labeling. Besides generating the polluted positive-class samples with comparatively high probability, optimal parameters found by DiscGMM also enjoy a comparatively low probability of generating negative-class samples. The parameter learning problem is solved by a modified Expectation Maximization (EM) algorithm. In an integrative labeling experiment of skin detection, DiscGMM is testified to enjoy much better performance than generative density estimation methods and shows qualified results.

关键词： Labeling Training Skin Image color analysis Histograms Estimation Linear programming

来源：评论

学校读者我要写书评

暂无评论

Simplified Local Binary pattern Descriptor for Character recognition of Vehicle License Plate

Simplified Local Binary Pattern Descriptor for Character Rec...

引用

International Conference on Computer Graphics, Imaging and Visualization, CGIV

作者： Lixia Liu Honggang Zhang Aiping Feng Xinxin Wan Jun Guo Pattern Recognition and Intelligent System Laboratory Beijing University of Posts and Telecommunications Beijing China

Local Binary pattern (LBP) is a powerful texture descriptor for its tolerance against illumination changes and its computational simplicity. The basic LBP encodes 256 feature patterns in a 3×3 neighborhood, but not all the patterns are effective for classification. In this paper, we propose a simplified LBP(S-LBP) which produces optimal patterns by using the best coding principle for classification. Meanwhile, we combine S-LBP and Mahalonobis distance in solving the practical problem of character recognition in Chinese license plate. Experimental results demonstrate the effectiveness of our method for vehicle license recognition comparing with other popular methods.

关键词： Licenses Pixel Character recognition Feature extraction Histograms Vehicles

来源：评论

学校读者我要写书评

暂无评论

A Modified system for Weblog Topic Relevance Retrieval

A Modified System for Weblog Topic Relevance Retrieval

引用

International Seminar on Future Information Technology and Management Engineering, FITME

作者： Si Li Lei Du Weiran Xu Jun Guo Pattern Recognition and Intelligent System Laboratory Beijing University of Posts and Telecommunications Beijing China

Weblog is widely used, and the number of users is increasing rapidly. Weblog reflects every aspect of the society, such as politics, economy and culture, so the topic relevance retrieval research on Weblog becomes necessary. Because of a lot of noise in the corpus and it is usually difficult to obtain the appropriate query, the common methods sometimes fail to reach an acceptable precision. We design a Modified Topic Relevance Retrieval system (MTRRS) containing query formulation and a combination model. To design the query, manual adjustment and machine learning are used. During the machine learning processing, we define a center word list which helps to generate a novel distance feature. The result can be improved 22.97% on MAP by query formulation. The results of document retrieval model and passage retrieval model are combined. 33.55% increase on MAP can be received. Also by using the combination model, the retrieval result of the semi-machine learning query is closely approaching the manually adjusted result.

关键词： Internet Information services Web sites Machine learning Feedback Information retrieval Search engines Content based retrieval Information technology Conference management

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：