检索结果-内蒙古大学图书馆

International Conference on computer Modeling and Simulation, ICCMS

作者： Bo Pu Shuang Liang Yongming Xie Zhang Yi Pheng-Ann Heng School of Computer Science and Engineering University of Electronic Science and Technology Chengdu China Department of Computer Science and Engineering Chinese University of Hong Kong Hong Kong China Machine Intelligence Laboratory Sichuan University Chengdu China

The active shape model (ASM) has been widely used to recognize and track a face from a video sequence. However, it is usually limited to frontal view or the cases of small-scale head movement, as its accuracy may greatly degrade in conditions of quick movement, large rotation and temporary occlusion. We propose an enhanced ASM and predicted mean shift algorithm to meet these challenges, which combines the context information and predicted mean shift to obtain multi-angle start shapes for ASM searching and the best result shape is chosen based on a matching evaluation. Extensive experiments demonstrate the flexibility and accuracy of the proposed method.

关键词： Facial features Active shape model Tracking Active appearance model Face detection Predictive models computer science Face recognition Video sequences Head

来源：评论

学校读者我要写书评

暂无评论

Deep Spatiotemporal Feature Learning with Application to Image Classification

Deep Spatiotemporal Feature Learning with Application to Ima...

引用

International Conference on machine Learning and Applications (ICMLA)

作者： Thomas P. Karnowski Itamar Arel Derek Rose Image Science and Machine Vision Group Oak Ridge National Laboratory Oak Ridge TN USA Department of Electrical Engineering and Computer Science University of Tennessee Knoxville TN USA

Deep machine learning is an emerging framework for dealing with complex high-dimensionality data in a hierarchical fashion which draws some inspiration from biological sources. Despite the notable progress made in the field, there remains a need for an architecture that can represent temporal information with the same ease that spatial information is discovered. In this work, we present new results using a recently introduced deep learning architecture called Deep Spatio-Temporal Inference Network (DeSTIN). DeSTIN is a discriminative deep learning architecture that combines concepts from unsupervised learning for dynamic pattern representation together with Bayesian inference. In DeSTIN the spatiotemporal dependencies that exist within the observations are modeled inherently in an unguided manner. Each node models the inputs by means of clustering and simple dynamics modeling while it constructs a belief state over the distribution of sequences using Bayesian inference. We demonstrate that information from the different layers of this hierarchical system can be extracted and utilized for the purpose of pattern classification. Earlier simulation results indicated that the framework is highly promising, consequently in this work we expand DeSTIN to a popular problem, the MNIST data set of handwritten digits. The system as a preprocessor to a neural network achieves a recognition accuracy of 97.98% on this data set. We further show related experimental results pertaining to automatic cluster adaptation and termination.

关键词： computer architecture Training Artificial neural networks Measurement Pixel machine learning Feature extraction

来源：评论

学校读者我要写书评

暂无评论

A comparative study on two large-scale hierarchical text classification tasks' solutions

A comparative study on two large-scale hierarchical text cla...

引用

International Conference on machine Learning and Cybernetics

作者： Zhang, Jian Zhao, Hai Lu, Bao-Liang Department of Computer Science and Engineering Center for Brain-Like Computing and Machine Intelligence Shanghai Jiao Tong University 800 Dong Chuan Road Shanghai 200240 China MOE-Microsoft Key Laboratory for Intelligent Computing and Intelligent Systems Shanghai Jiao Tong University 800 Dong Chuan Road Shanghai 200240 China

ISBN: (纸本)9781424465262

Patent classification is a large scale hierarchical text classification (LSHTC) task. Though comprehensive comparisons, either learning algorithms or feature selection strategies, have been fully made in the text categorization field, few work was done for a LSHTC task due to high computational cost and complicated structural label characteristics. For the first time, this paper compares two popular learning frameworks, namely hierarchical support vector machine (SVM) and k nearest neighbor (k-NN) that are applied to a LSHTC task. Experiment results show that the latter outperforms the former in this LSHTC task, which is quite different from the usual results for normal text categorization tasks. Then this paper does a comparative study on different similarity measures and ranking approaches in k-NN framework for LSHTC task. Conclusions can be drawn that k-NN is more appropriate for the LSHTC task than hierarchical SVM and for a specific LSHTC task. BM25 outperforms other similarity measures and List Weak gains a better performance than other ranking approaches. We also find an interesting phenomenon that using all the labels of the retrieved neighbors can remarkably improve classification performance over only using the first label of the retrieved neighbors. © 2010 IEEE.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Discretization of continuous-valued attributes in decision tree generation

Discretization of continuous-valued attributes in decision t...

引用

International Conference on machine Learning and Cybernetics (ICMLC)

作者： Wen-Liagn Li Rui-Hua Yu Xi-Zhao Wang Key Laboratory of Machine Learning and Computational Intelligence College of Mathematics and Computer Science Hebei University Baoding China Department of Information Technology Baoding University Baoding China

Decision tree is one of the most popular and widely used classification models in machine learning. The discretization of continuous-valued attributes plays an important role in decision tree generation. In this paper, we improve Fayyad's discretization method which uses the average class entropy of candidate partitions to select boundaries for discretization. Our method can reduce the number of candidate boundaries further. Here we also propose a generalized splitting criterion for cut point selection and prove that the cut points are always on boundaries when using this criterion. Along with the formal proof, we present empirical results that the decision trees generated by using such criteria are similar on several datasets from the UCI machine Learning Repository.

关键词： Entropy machine learning Impurities Indexes Classification tree analysis

来源：评论

学校读者我要写书评

暂无评论

An Empirical Study on Development Set Selection Strategy for machine Translation Learning∗ 5

An Empirical Study on Development Set Selection Strategy for...

引用

Joint 5th Workshop on Statistical machine Translation and MetricsMATR, WMT 2010 at the 48th Conference of the Associationfor Computational Linguistics, ACL 2010

作者： Hui, Cong Zhao, Hai Song, Yan Lu, Bao-Liang Center for Brain-Like Computing and Machine Intelligence Department of Computer Science and Engineering Shanghai Jiao Tong University China MOE-Microsoft Key Laboratory for Intelligent Computing and Intelligent Systems Shanghai Jiao Tong University 800 Dong Chuan Rd. Shanghai 200240 China Department of Chinese Translation and Linguistics City University of Hong Kong Hong Kong

ISBN: (纸本)9781932432718

This paper describes a statistical machine translation system for our participation for the WMT10 shared task. Based on MOSES, our system is capable of translating German, French and Spanish into English. Our main contribution in this work is about effective parameter tuning. We discover that there is a significant performance gap as different development sets are adopted. Finally, ten groups of development sets are used to optimize the model weights, and this does help us obtain a stable evaluation result. © 2010 Association for Computational Linguistics

关键词： machine translation

来源：评论

学校读者我要写书评

暂无评论

SFSSClass: An integrated approach for miRNA based tumor classification

SFSSClass: An integrated approach for miRNA based tumor clas...

引用

8th Asia-Pacific Bioinformatics Conference, APBC 2010

作者： Mitra, Ramkrishna Bandyopadhyay, Sanghamitra Maulik, Ujjwal Zhang, Michael Q. Machine Intelligence Unit Indian Statistical Institute Kolkata India Department of Computer Science and Engineering Jadavpur University Kolkata India Watson School of Biological Sciences Cold Spring Harbor Laboratory Cold Spring Harbor NY 11724 United States MOE Key Laboratory of Bioinformatics and Bioinformatics Division TNLIST Tsinghua University Beijing 100084 China

Background: MicroRNA (miRNA) expression profiling data has recently been found to be particularly important in cancer research and can be used as a diagnostic and prognostic tool. Current approaches of tumor classification using miRNA expression data do not integrate the experimental knowledge available in the literature. A judicious integration of such knowledge with effective miRNA and sample selection through a biclustering approach could be an important step in improving the accuracy of tumor classification. Results: In this article, a novel classification technique called SFSSClass is developed that judiciously integrates a biclustering technique SAMBA for simultaneous feature (miRNA) and sample (tissue) selection (SFSS), a cancer-miRNA network that we have developed by mining the literature of experimentally verified cancer-miRNA relationships and a classifier uncorrelated shrunken centroid (USC). SFSSClass is used for classifying multiple classes of tumors and cancer cell lines. In a part of the investigation, poorly differentiated tumors (PDT) having non diagnostic histological appearance are classified while training on more differentiated tumor (MDT) samples. The proposed method is found to outperform the best known accuracy in the literature on the experimental data sets. For example, while the best accuracy reported in the literature for classifying PDT samples is ∼76.5%, the accuracy of SFSSClass is found to be ∼82.3%. The advantage of incorporating biclustering integrated with the cancer-miRNA network is evident from the consistently better performance of SFSSClass (integration of SAMBA, cancer-miRNA network and USC) over USC (eg., ∼70.5% for SFSSClass versus ∼58.8% in classifying a set of 17 MDT samples from 9 tumor types, ∼91.7% for SFSSClass versus ∼75% in classifying 12 cell lines from 6 tumor types and ∼82.3% for SFSSClass versus ∼41.2% in classifying 17 PDT samples from 11 tumor types). Conclusion: In this article, we develop the SFSSClass algori

关键词： Tumors

来源：评论

学校读者我要写书评

暂无评论

A novel method of fingerprint minutiae extraction based on Gabor phase

A novel method of fingerprint minutiae extraction based on G...

引用

IEEE International Conference on Image Processing

作者： Xin Gao Xiaoguang Chen Jia Cao Zirui Deng Chongjin Liu Jufu Feng Key Laboratory of Machine Perception MOE Department of Machine Intelligence School of Electronics Engineering and Computer Science Peking University Beijing China Institute of Image Processing and Pattern Recognition North-China University of Technology Beijing China

In this paper, a novel method of fingerprint minutiae extraction on grey-scale images is proposed based on the Gabor phase field. The novelty of our approach is that the proposed algorithm is performed on the transform domain, i.e. the Gabor phase field of the fingerprint image. This is different from most existing minutiae extraction methods, in which the minutiae are usually extracted from the binarized and thinned fingerprint image. Experimental results on benchmark data sets demonstrate that the proposed algorithm has promising performances.

关键词： Pixel Feature extraction Image quality Fingerprint recognition Detectors Frequency estimation Software algorithms

来源：评论

学校读者我要写书评

暂无评论

Cooperative Co-evolution for large scale optimization through more frequent random grouping

Cooperative Co-evolution for large scale optimization throug...

引用

Congress on Evolutionary Computation

作者： Mohammad Nabi Omidvar Xiaodong Li Zhenyu Yang Xin Yao Evolutionary Computing and Machine Learning Group (ECML) the School of Computer Science and IT RMIT University Melbourne VIC Australia Nature Inspired Computation and Application Laboratory Department of Computer Science and Technology University of Science and Technology Hefei Anhui China Centre of Excellence of Research in Computational Intelligence and Applications (CERCIA) School of Computer Science University of Binningham Birmingham UK

In this paper we propose three techniques to improve the performance of one of the major algorithms for large scale continuous global function optimization. Multilevel Cooperative Co-evolution (MLCC) is based on a Cooperative Co-evolutionary framework and employs a technique called random grouping in order to group interacting variables in one subcomponent. It also uses another technique called adaptive weighting for co-adaptation of subcomponents. We prove that the probability of grouping interacting variables in one subcomponent using random grouping drops significantly as the number of interacting variables increases. This calls for more frequent random grouping of variables. We show how to increase the frequency of random grouping without increasing the number of fitness evaluations. We also show that adaptive weighting is ineffective and in most cases fails to improve the quality of found solution, and hence wastes considerable amount of CPU time by extra evaluations of objective function. Finally we propose a new technique for self-adaptation of the subcomponent sizes in CC. We demonstrate how a substantial improvement can be gained by applying these three techniques.

关键词： Optimization Probability computer science Electronic mail Space exploration Computational modeling Software

来源：评论

学校读者我要写书评

暂无评论

Hybrid uniform distribution of particle swarm optimizer

引用

IEICE Transactions on Fundamentals of Electronics, Communications and computer sciences 2010年第10期E93-A卷 1782-1791页

作者： Zhang, Junqi Tan, Ying Ni, Lina Xie, Chen Tang, Zheng Department of Computer Science and Technology Key Laboratory of Embedded System and Service Computing Ministry of Education Qingdao China Tongji University Shanghai 200092 China Key Laboratory of Machine Perception Ministry of Education Qingdao China Department of Machine Intelligence School of Electronics Engineering and Computer Science Peking University Beijing 100871 China College of Info Sci and Engi Shandong University of Science and Technology Qingdao China Department of Intellectual Information Systems Engineering University of Toyama Toyama-shi 930-8555 Japan

Particle swarm optimizer (PSO) is a stochastic global optimization technique based on a social interaction metaphor. Because of the complexity, dynamics and randomness involved in PSO, it is hard to theoretically analyze the mechanism on which PSO depends. Statistical results have shown that the probability distribution of PSO is a truncated triangle, with uniform probability across the middle that decreases on the sides. The "truncated triangle" is also called the "Maya pyramid" by Kennedy. However, very little is known regarding the sampling distribution of PSO in itself. In this paper, we theoretically analyze the "Maya pyramid" without any assumption and derive its computational formula, which is actually a hybrid uniform distribution that looks like a trapezoid and conforms with the statistical results. Based on the derived density function of the hybrid uniform distribution, the search strategy of PSO is defined and quantified to characterize the mechanism of the search strategy in PSO. In order to show the significance of these definitions based, on the derived hybrid uniform distribution, the comparison between the defined search strategies of the classical, linear decreasing weight based PSO and the canonical constricted PSO suggested by Clerc is illustrated and elaborated. Copyright © 2010 The Institute of Electronics, Information and Communication Engineers.

关键词： Probability distributions

来源：评论

学校读者我要写书评

暂无评论

A new instance selection algorithm based on contribution for nearest neighbour classification

A new instance selection algorithm based on contribution for...

引用

International Conference on machine Learning and Cybernetics (ICMLC)

作者： Yong-Hua Cai Bo Wu Yu-Lin He Ye Zhang Department of Mathematics and Computer Science Hebei Normal University of Nationalities Chengde Hebei China Automation Department Chengdu Iron & Steel Branch Hebei Iron and Steel Group Company Limited Chengde Hebei China Key Laboratory of Machine Learning and Computational Intelligence College of Mathematics and Computer Science Hebei University Baoding Hebei China

Nearest Neighbor Classifier is one of the most classical lazy learning schemes. The basic nearest neighbor classifiers suffer from the common problem that the instances used to train the classifier are all stored indiscriminately, and as a result, the required memory storage is huge and response time becomes slow with a large database. In this paper, a new Instances Selection algorithm based on Classification Contribution Function shortly named ISCC is presented. In this algorithm, a function is introduced to evaluate the classification ability of the instances. For each instance, the function considers its contribution to the neighbor instances not only with same class but also with different class. Then an instance with the highest value of Classification Contribution Function is added to the condensed subset and the instances which can be classified correctly are deleted in each iteration. This process is repeated until the subset is no longer getting larger. The time complexity of ISCC is O (in 2 ). The experimental results on two artificial databases and some real databases demonstrate the effectiveness and the feasibility of the proposed algorithm. Compared to traditional methods, such as MCS, ICF and ENN, the condensed sets obtained by ISCC is superior in storage and classification accuracy.

关键词： Classification algorithms Nearest neighbor searches Training machine learning Accuracy Noise Learning

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：