A method of 3D modeling and codec

3D modeling and codec of real objects are hot issues in the field of virtual reality. In this paper, we propose an automatic registration two range images method and a cycle based automatic global registration algorithm for rapidly and automatically registering all range images and constructing a realistic 3D model. Besides, to meet the requirement of huge data transmission over Internet, we present a 3D mesh encoding/decoding method for encoding geometry, topology and attribute data with high compression ratio and supporting progressive transmission. The research results have already been applied successfully in digital museum. Supported by the National Natural Science Foundation of China (Grant Nos. 60533070, 60773153), the Key Grant Project of Chinese Ministry of Education (Grant No. 308004), the Project of Chinese Ministry of Science and Technology (Grant No. 2006BAK12B09), and the Project of Beijing Municipal Science and Technology Commission (Grant No. Z07000100560714)     

A Rectangular Finite Volume Element Method for a Semilinear Elliptic Equation

In this paper we extend the idea of interpolated coefficients for semilinear problems to the finite volume element method based on rectangular partition. At first we introduce bilinear finite volume element method with interpolated coefficients for a boundary value problem of semilinear elliptic equation. Next we derive convergence estimate in H ¹-norm and superconvergence of derivative. Finally an example is given to illustrate the effectiveness of the proposed method. This work is supported by Program for New Century Excellent Talents in University of China State Education Ministry, National Science Foundation of China, the National Basic Research Program under the Grant (2005CB321703), the key project of China State Education Ministry (204098), Scientific Research Fund of Hunan Provincial Education Department, China Postdoctoral Science Foundation (No. 20060390894) and China Postdoctoral Science Foundation (No. 20060390894).     

A moving object segmentation algorithm for static camera via active contours and GMM

Moving object segmentation is one of the most challenging issues in computer vision. In this paper, we propose a new algorithm for static camera foreground segmentation. It combines Gaussian mixture model (GMM) and active contours method, and produces much better results than conventional background subtraction methods. It formulates foreground segmentation as an energy minimization problem and minimizes the energy function using curve evolution method. Our algorithm integrates the GMM background model, shadow elimination term and curve evolution edge stopping term into energy function. It achieves more accurate segmentation than existing methods of the same type. Promising results on real images demonstrate the potential of the presented method. Supported by National Basic Research Program of China (Grant No. 2006CB303105), the Chinese Ministry of Education Innovation Team Fund Project (Grant No. IRT0707), the National Natural Science Foundation of China (Grant Nos. 60673109 and 60801053), Beijing Excellent Doctoral Thesis Program (Grant No. YB20081000401), Beijing Municipal Natural Science Foundation (Grant No. 4082025), and Doctoral Foundation of China (Grant No. 20070004037)     

Multivariable direct adaptive decoupling controller using multiple models and a case study

In this paper, a multivariable direct adaptive controller using multiple models without minimum phase assumption is presented to improve the transient response when the parameters of the system jump abruptly. The controller is composed of multiple fixed controller models, a free-running adaptive controller model and a re-initialized adaptive controller model. The fixed controller models are derived from the corresponding fixed system models directly. The adaptive controller models adopt the direct adaptive algorithm to reduce the design calculation. At every instant, the optimal controller is chosen out according to the switching index. The interaction of the system is viewed as the measured disturbance which is eliminated by the choice of the weighing polynomial matrix. The global convergence is obtained. Finally, several simulation examples in a wind tunnel experiment are given to show both effectiveness and practicality of the proposed method. The significance of the proposed method is that it is applicable to a non-minimum phase system, adopting direct adaptive algorithm to overcome the singularity problem during the matrix calculation and realizing decoupling control for a multivariable system. Supported by the National Natural Science Foundation of China (Grant Nos. 60504010, 60864004), the National High-Tech Research and Development Program of China (Grant No. 2008AA04Z129), the Key Project of Chinese Ministry of Education (Grant No. 208071), and the Natural Science Foundation of Jiangxi Province (Grant No. 0611006)     

Energy-based adaptive orthogonal FRIT and its application in image denoising

Efficient representation of linear singularities is discussed in this paper. We analyzed the relationship between the “wrap around” effect and the distribution of FRAT (Finite Radon Transform) coefficients first, and then based on study of some properties of the columnwisely FRAT reconstruction procedure, we proposed an energy-based adaptive orthogonal FRIT scheme (EFRIT). Experiments using nonlinear approximation show its superiority in energy concentration over both Discrete Wavelet Transform (DWT) and Finite Ridgelet Transform (FRIT). Furthermore, we have modeled the denoising problem and proposed a novel threshold selecting method. Experiments carried out on images containing strong linear singularities and texture components with varying levels of addictive white Gaussian noise show that our method achieves prominent improvement in terms of both SNR and visual quality as compared with that of DWT and FRIT.     

Modeling selected real-time database concurrency control protocols in Uppaal

Real-time database management systems (RTDBMS) are recently subject of an intensive research. Model checking algorithms and verification tools are of great concern as well. In this paper, we show some possibilities of using a verification tool Uppaal on some variants of pessimistic and optimistic concurrency control protocols used in real-time database management systems. We present some possible models of such protocols expressed as nets of timed automata, which are a modeling language of Uppaal. M. Kot acknowledges the support by the Czech Ministry of Education, Grant No. 1M0567.     

中文矛盾语块数据集构建和边界识别研究

文本矛盾是自然语言理解的一项基础性问题。目前的研究大多针对矛盾识别任务,而深入文本内部探究矛盾产生原因的工作较少,且缺乏专门的中文矛盾数据集。该文在前人矛盾研究基础上,提出矛盾语块的概念,将其划分为7种类型,并根据标注规范构建了包含16 224条数据的中文矛盾语块(CCB)数据集。基于此数据集,利用序列标注及抽取式阅读理解类模型开展矛盾语块边界识别实验,以检验模型对矛盾内部语义信息的理解能力,结果显示阅读理解类模型在该任务上的性能优于序列标注模型。该文通过三个角度对影响语块边界识别的因素进行分析,为文本矛盾后续研究工作提供可靠的数据集和基线模型。     

GSAM: A deep neural network model for extracting computational representations of Chinese addresses fused with geospatial feature

Addresses are one of the most important geographical reference systems in natural languages. In China, due to the relatively backward address planning, there are a large number of non-standard addresses. This kind of unstructured text makes the management and application of Chinese addresses much more difficult. However, by extracting the computational representations of addresses, it can be structured and its related applications can be extended more conveniently. Therefore, this paper utilizes a deep neural language model from natural language processing (NLP) to automatically extract computational representations through an unsupervised address language model (ALM), which is trained in an unsupervised way and is suitable for a large-scale address corpus. We propose a solution to fuse addresses and geospatial features and construct a geospatial-semantic address model (GSAM) that supports a variety of downstream tasks. Our proposed GSAM constructing process consists of three phases. First, we build an ALM using bidirectional encoder representations from Transformers (BERT) to learn the addresses' semantic representations. Then, the fusion clustering results of the semantic and geospatial information are obtained by a high-dimensional clustering algorithm. Finally, we construct the GSAM based on the fused clustering results using novel fine-tuning techniques. Furthermore, we apply the extracted computational representation from GSAM to the address location prediction task. The experimental results indicate that the target task accuracy of the ALM is 90.79%, and the result of semantic geospatial fusion clustering strongly correlates with fine-grained urban neighbourhood area division. The GSAM can accurately identify clustering labels and the values of evaluation metrics are all above 0.96. We also demonstrate that our model outperforms purely ALM-based and word2vec-based models by address location prediction task.     

Modeling plants with sensor data

Sensor data, typically images and laser data, are essential to modeling real plants. However, due to the complex geometry of the plants, the measurement data are generally limited, thereby bringing great difficulties in classifying and constructing plant organs, comprising leaves and branches. The paper presents an approach to modeling plants with the sensor data by detecting reliable sharp features, i.e. the leaf apexes of the plants with leaves and the branch tips of the plants without leaves, on volumes recovered from the raw data. The extracted features provide good estimations of correct positions of the organs. Thereafter, the leaves are reconstructed separately by simply fitting and optimizing a generic leaf model. One advantage of the method is that it involves limited manual intervention. For plants without leaves, we develop an efficient strategy for decomposition-based skeletonization by using the tip features to reconstruct the 3D models from noisy laser data. Experiments show that the sharp feature detection algorithm is effective, and the proposed plant modeling approach is competent in constructing realistic models with sensor data. Supported in part by the National Basic Research Program of China (Grant No. 2004CB318000), the National High-Tech Research & Development Program of China (Grant Nos. 2006AA01Z301, 2006AA01Z302, 2007AA01Z336), Key Grant Project of Chinese Ministry of Education (Grant No. 103001)     

Online short text clustering using infinite extensions of discrete mixture models

Short text clustering is one of the fundamental tasks in natural language processing. Different from traditional documents, short texts are ambiguous and sparse due to their short form and the lack of recurrence in word usage from one text to another, making it very challenging to apply conventional machine learning algorithms directly. In this article, we propose two novel approaches for short texts clustering: collapsed Gibbs sampling infinite generalized Dirichlet multinomial mixture model infinite GSGDMM) and collapsed Gibbs sampling infinite Beta-Liouville multinomial mixture model (infinite GSBLMM). We adopt two flexible and practical priors to the multinomial distribution where in the first one the generalized Dirichlet distribution is integrated, while the second one is based on the Beta-Liouville distribution. We evaluate the proposed approaches on two famous benchmark datasets, namely, Google News and Tweet. The experimental results demonstrate the effectiveness of our models compared to basic approaches that use Dirichlet priors. We further propose to improve the performance of our methods with an online clustering procedure. We also evaluate the performance of our methods for the outlier detection task, in which we achieve accurate results.     

基于多通道BERT的跨语言属性级情感分类方法

属性级情感分类是情感分析领域中一个细粒度的情感分类任务,旨在判断文本中针对某个属性的情感极性.现有的属性级情感分类方法大多是使用同一种语言的标注文本进行模型的训练与测试,而现实中很多语言的标注文本规模并不足以训练一个高性能的模型,因此跨语言属性级情感分类是一个亟待解决的问题.跨语言属性级情感分类是指利用源语言文本的语义...     

An approach for constructing complex discriminating surfaces based on Bayesian interference of the maximum entropy

In this paper we present a comprehensive Maximum Entropy (MaxEnt) procedure for the classification tasks. This MaxEnt is applied successfully to the problem of estimating the probability distribution function (pdf) of a class with a specific pattern, which is viewed as a probabilistic model handling the classification task. We propose an efficient algorithm allowing to construct a non-linear discriminating surfaces using the MaxEnt procedure. The experiments that we carried out shows the performance and the various advantages of our approach.     

Neural Network Algorithm for Designing FIR Filters Utilizing Frequency-Response Masking Technique

This paper presents a new joint optimization method for the design of sharp linear-phase finite-impulse response (FIR) digital filters which are synthesized by using basic and multistage frequency-response-masking(FRM) techniques.The method is based on a batch back-propagation neural network algorithm with a variable learning rate mode.We propose the following two-step optimization technique in order to reduce the complexity.At the first step,an initial FRM filter is designed by alternately optimizing th...     

GA, MR, FFNN, PNN and GMM based models for automatic text summarization

This work proposes an approach to address the problem of improving content selection in automatic text summarization by using some statistical tools. This approach is a trainable summarizer, which takes into account several features, including sentence position, positive keyword, negative keyword, sentence centrality, sentence resemblance to the title, sentence inclusion of name entity, sentence inclusion of numerical data, sentence relative length, Bushy path of the sentence and aggregated similarity for each sentence to generate summaries. First, we investigate the effect of each sentence feature on the summarization task. Then we use all features in combination to train genetic algorithm (GA) and mathematical regression (MR) models to obtain a suitable combination of feature weights. Moreover, we use all feature parameters to train feed forward neural network (FFNN), probabilistic neural network (PNN) and Gaussian mixture model (GMM) in order to construct a text summarizer for each model. Furthermore, we use trained models by one language to test summarization performance in the other language. The proposed approach performance is measured at several compression rates on a data corpus composed of 100 Arabic political articles and 100 English religious articles. The results of the proposed approach are promising, especially the GMM approach.     

A weighted LS-SVM approach for the identification of a class of nonlinear inverse systems

In this paper, a weighted least square support vector machine algorithm for identification is proposed based on the T-S model. The method adopts fuzzy c-means clustering to identify the structure. Based on clustering, the original input/output space is divided into several subspaces and submodels are identified by least square support vector machine (LS-SVM). Then, a regression model is constructed by combining these submodels with a weighted mechanism. Furthermore we adopt the method to identify a class of inverse systems with immeasurable state variables. In the process of identification, an allied inverse system is constructed to obtain enough information for modeling. Simulation experiments show that the proposed method can identify the nonlinear allied inverse system effectively and provides satisfactory accuracy and good generalization. Supported by the National Natural Science Foundation of China (Grant No. 60874013) and the Doctoral Project of the Ministry of Education of China (Grant No. 20070286001)     

AE1: An extension matrix approximate method for the general covering problem

A new approach, the extension matrix approach, is introduced and used to show that some optimization problems in general covering problem areNP-hard. Approximate solutions for these problems are given. Combining these approximate solutions, this paper presents an approximately optimal covering algorithm,AE1. Implementation shows thatAE1 is efficient and gives optimal or near optimal results.This research was supported in part by the National Science Foundation under Grant DCR 84-06801, Office of Naval Research under Grant N00014-82-K-0186, Defense Advanced Research Project Agency under Grant N00014-K-85-0878, and Education Ministry of the People's Republic of China.On leave from Harbin Institute of Technology, Harbin, China.     

A writer identification system for on-line whiteboard data

In this paper we address the task of writer identification of on-line handwriting captured from a whiteboard. Different sets of features are extracted from the recorded data and used to train a text and language independent on-line writer identification system. The system is based on Gaussian mixture models (GMMs) which provide a powerful yet simple means of representing the distribution of the features extracted from the handwritten text. The training data of all writers are used to train a universal background model (UBM) from which a client specific model is obtained by adaptation. Different sets of features are described and evaluated in this work. The system is tested using text from 200 different writers. A writer identification rate of 98.56% on the paragraph and of 88.96% on the text line level is achieved.     

Orthogonal Methods Based Ant Colony Search for Solving Continuous Optimization Problems

Research into ant colony algorithms for solving continuous optimization problems forms one of the most significant and promising areas in swarm computation. Although traditional ant algorithms are designed for combinatorial optimization, they have shown great potential in solving a wide range of optimization problems, including continuous optimization. Aimed at solving continuous problems effectively, this paper develops a novel ant algorithm termed ＂continuous orthogonal ant colony＂ （COAC）, whose pheromone deposit mechanisms would enable ants to search for solutions collaboratively and effectively. By using the orthogonal design method, ants in the feasible domain can explore their chosen regions rapidly and efficiently. By implementing an ＂adaptive regional radius＂ method, the proposed algorithm can reduce the probability of being trapped in local optima and therefore enhance the global search capability and accuracy. An elitist strategy is also employed to reserve the most valuable points. The performance of the COAC is compared with two other ant algorithms for continuous optimization -API and CACO by testing seventeen functions in the continuous domain. The results demonstrate that the proposed COAC algorithm outperforms the others.     

A word-building method based on neural network for text classification

Text classification is a foundational task in many natural language processing applications. All traditional text classifiers take words as the basic units and conduct the pre-training process (like word2vec) to directly generate word vectors at the first step. However, none of them have considered the information contained in word structure which is proved to be helpful for text classification. In this paper, we propose a word-building method based on neural network model that can decompose a Chinese word to a sequence of radicals and learn structure information from these radical level features which is a key difference from the existing models. Then, the convolutional neural network is applied to extract structure information of words from radical sequence to generate a word vector, and the long short-term memory is applied to generate the sentence vector for the prediction purpose. The experimental results show that our model outperforms other existing models on Chinese dataset. Our model is also applicable to English as well where an English word can be decomposed down to character level, which demonstrates the excellent generalisation ability of our model. The experimental results have proved that our model also outperforms others on English dataset.     

面向汉语作为第二语言学习的个性化语法纠错

语法纠错任务旨在通过自然语言处理技术自动检测并纠正文本中的语序、拼写等语法错误。当前许多针对汉语的语法纠错方法已取得较好的效果,但往往忽略了学习者的个性化特征,如二语等级、母语背景等。因此,该文面向汉语作为第二语言的学习者,提出个性化语法纠错,对不同特征的学习者所犯的错误分别进行纠正,并构建了不同领域汉语学习者的数据集进行实验。实验结果表明,将语法纠错模型适应到学习者的各个领域后,性能得到明显提升。