Search

Salient feature extraction is an important task in image classification and recognition. Although classification techniques focus on the bright part of an image, many pixels of the image are of similar saliency. To address the issue, this paper proposes the logarithmic function-based novel representation algorithm (LFNR) to apply a novel representation for each image. The original and novel representations were fused to improve the classification accuracy. Experimental results show that, thanks to the simultaneous use of original and novel representations, the test samples could be better classified. The classification algorithms coupled with the LFNR all witnessed lower error rates than the original algorithms. In particular, the collaboration representation-based classification coupled with the LFNR significantly outperformed the other sparse representation algorithms, such as homotopy, primal augmented Lagrangian method (PALM), and sparse reconstruction by separable approximation algorithm (SpaRSA). The no-parameter property of the LFNR is also noteworthy.

Description and classification of face images is a significant task of computer vision, machine learning and pattern recognition communities. In the past, researchers have made tremendous efforts in this task. Previous researchers always seek high-resolution face images for better image classification. However, with this paper, we present and demonstrate a new opinion that in some cases the use of alternative representations of facial images are very useful for face recognition and properly reducing the image resolution might be beneficial to better classification of face images. This may be attributed to the deformable property of faces and the fact that the proposed alternative representations can in some extent reduce the within-class difference of facial images. Also, the presented idea appear to be useful for helping people to improve face recognition techniques in real worlds.

Thyroid disease is a frequent occurrence in clinical practice and the computerized analysis of ultrasonography has been becoming the most prospective tool for thyroid disease automatic diagnosis. However, the accuracy of vision-based diagnostic analysis is often reduced because the quality of ultrasound image is easily corrupted by the speckle noise. Thus, noise suppression is imperative and significant for the thyroid ultrasonography image preprocessing to increase the reliability of subsequent analysis. In this paper, we propose a novel weighted image averaging method based on anisotropic diffusion filters combination to remove speckle noise and enhance the details of the image at the same time. The method first denoises the image separately by two filters with different performances. The speckle reducing anisotropic diffusion filter can enhance the details of the image, and the anisotropic diffusion filter can better suppress the speckle noise in the image. In order to integrate the advantages of the two filters and reduce the mutual interference meanwhile, an adaptive weighted image averaging method is further proposed to combine the pixels of the two denoised images. The experimental results indicate that the proposed method can achieve promising performance on the template images with various noise levels by considering PSNR and SSIM. What's more, it is not only superior to other methods in automatic segmentation, but also can obtain better visual effect for thyroid images.

There is large and growing amounts of textual data that contains information about human activities. Mining interesting knowledge from this textual data is a challenging task because it consists of unstructured or semistructured text that are written in natural language. In the field of artificial intelligence, event-oriented techniques are helpful in addressing this problem, where information retrieval (IR), information extraction (IE) and graph methods (GMs) are three of the most important paradigms in supporting event-oriented processing. In recent years, due to information explosions, textual event detection and recognition have received extensive research attention and achieved great success. Many surveys have been conducted to retrospectively assess the development of event detection. However, until now, all of these surveys have focused on only a single aspect of IR, IE or GMs. There is no research that provides a complete introduction or a comparison of IR, IE, and GMs. In this article, a survey about these techniques is provided from a broader perspective, and a convenient and comprehensive comparison of these techniques is given. The hallmark of this article is that it is the first survey that combines IR, IE and GMs in a single frame and will therefore benefit researchers by acting as a reference in this field.

Biomedical named entity recognition (BNER) is an important task in biomedical natural language processing, in which neologisms (new terms, words) are coined constantly. Most of the existing work can only identify biomedical named entities with flattened structures and ignore nested biomedical named entities and discontinuous biomedical named entities. Because biomedical domains often use nested structures to represent semantic information of named entities, existing methods fail to utilize abundant information when processing biomedical texts. This paper focuses on identifying nested biomedical named entities using a boundary assembly (BA) model, which is a cascading framework consisting of three steps. First, start and end named entity boundaries are identified and then assembled into named entity candidates. Finally, a classifier is implemented for filtering false named entities. Our approach is effective in handling nesting and discontinuous problems in biomedical named entity recognition tasks. It improves the performance considerably, achieving an F1-score of 81.34% on the GENIA dataset.

Mining a document structure from multiple data sources in terms of their underlying topics has become an important task of document clustering. The traditional document clustering approach cannot be applied directly to the multi-source document clustering problem. There are three typical difficulties: 1) The topics of different data sources are related but not the same. 2) Usually, each data source has its own focus on topics. 3) The number of clusters of the data sources are not necessarily the same and are not known beforehand. In this paper, based on our previous research, we design a novel multi-source document clustering model, namely, the hierarchical Dirichlet multinomial allocation (HDMA) model, to solve all the above problems. The HDMA model is investigated with a two-step hierarchical topic generation process. Topics are learnt to share their general characteristics across data source, while at the same time preserve the local characteristics of the data source. Each data source is applied with an exclusive topic partition to learn the source-level topic emphasis. A Gibbs sampling algorithm is then used to learn the number of clusters for each data source as well as the parameters of the HDMA model at the same time. Experimental results demonstrate that the HDMA model is effective.

The task to recognize named entities is often modeled as a sequence labeling process, which selects a label path whose probability is maximum for an input sentence. Because it makes the assumption that the input sentence has a flattened structure, it often fails to recognize nested named entities. In our previous work, a boundary assembling (BA) model was proposed. It is a cascading framework, which identifies named entity boundaries first, and then assembles them into entity candidates for further assessment. This model is effective to recognize nested named entities, but still suffers from poor performance caused by the sparse feature problem. In this article, the BA model is remodeled with the advancement of neural networks, which enables the model to capture semantic information of a sentence by using word embeddings pretrained in external resources. In our experiments, it shows an impressive improvement on the final performance, outperforming the state of the art more than 17% in F-score.

The context of a sentence is composed of a limited number of words. This leads to the feature sparsity problem whereby the sentence's meaning is easily influenced by language phenomena such as polysemy, ambiguity and puns. To resolve these problems, the set space model (SSM) uses language characteristics to group features of a sentence into different sets. Afterwards, the proposed feature calculus is used to capture the structural information of the sentence. Experiments have shown that this approach to the relation recognition task is effective. However, at least three weaknesses remain. First, due to the lack of a probabilistic explanation, several aspects of SSM (e.g., filter selection) have not yet been covered. Second, the existing studies have only provided an outline of SSM, and many issues remain unclear. To understand this approach, it is necessary to discuss a suitable example in detail. Third, SSM has been applied only to the task of relation recognition. Case studies of more typical topics (e.g., named entity recognition) will help illustrate the use of SSM's methodology to manipulate features. This paper develops SSM to cover these problems. It describes a systematic and novel approach to manipulating features of a sentence. In the experimental part, two typical information extraction tasks are performed to demonstrate SSM's capabilities. Two case studies are considered, and favorable improvements are observed. All of the obtained results surpass those of compared approaches. The experiments also show the influence of sentence structural information on information extraction.

Relation extraction aims to extract semantic relationships between two specified named entities in a sentence. Because a sentence often contains several named entity pairs, a neural network is easily bewildered when learning a relation representation without position and semantic information about the considered entity pair. In this paper, instead of learning an abstract representation from raw inputs, task-related entity indicators are designed to enable a deep neural network to concentrate on the task-relevant information. By implanting entity indicators into a relation instance, the neural network is effective for encoding syntactic and semantic information about a relation instance. Organized, structured and unified entity indicators can make the similarity between sentences that possess the same or similar entity pair and the internal symmetry of one sentence more obviously. In the experiment, a systemic analysis was conducted to evaluate the impact of entity indicators on relation extraction. This method has achieved state-of-the-art performance, exceeding the compared methods by more than 3.7%, 5.0% and 11.2% in F1 score on the ACE Chinese corpus, ACE English corpus and Chinese literature text corpus, respectively.

Making full use of semantic and structure information in a sentence is critical to support entity relation extraction. Neural networks use stacked neural layers to perform designated feature transformations and can automatically extract high-order abstract feature representations from raw inputs. However, because a sentence usually contains several pairs of named entities, the networks are weak when encoding semantic and structure information of a relation instance. In this paper, we propose a neuralized feature engineering approach for entity relation extraction. This approach enhances the neural network by manually designed features, which have the advantage of using prior knowledge and experience developed in feature-based models. Neuralized feature engineering encodes manually designed features into distributed representations to increase the discriminability of a neural network. Experiments show that this approach considerably improves the performance compared to that of neural networks or feature-based models alone, exceeding state-of-the-art performance by more than 8% and 16.5% in terms of F1-score on the ACE corpus and the Chinese literature text corpus, respectively.

A key to dictionary learning is to attain a robust dictionary, which enables difference between test samples and training samples of the same class to be alleviated. Owing to this factor, the dictionary can bring proper representations of test samples and produce better classification results for them. For face recognition, because of varying facial appearance caused by changeable illuminations, poses and facial expressions, a robust dictionary is definitely preferred. In this paper, we propose a robust dictionary learning method for face recognition. Robustness is attained in a two-fold way. First, auxiliary faces are produced via original face images. Second, the scheme to attain the dictionary under the condition that label coefficients can deviate from sample coefficients is designed. Auxiliary faces express possible variations of faces. Moreover, it seems that difference between auxiliary faces and original training samples of the same class somewhat reflects difference between test samples and training samples, thus use of auxiliary faces is beneficial to improve robustness of the method. The scheme to attain the dictionary further enhances robustness.

The kernel method is a very effective and popular method to extract features from data such as images. A novel method is presented to enhance traditional kernel method for face image representation in this paper, which is very suitable to treat the high-dimensional datasets. The proposed method is called weighted kernel representation-based method (WKRBM) in this paper. WKRBM assumes that the test sample can be expressed by all the training samples and linear solution in the mapping space. It uses the obtained linear combination to recognize face images. In particular, the coefficients of a linear combination can be set as the optimal weight that is an important factor to obtain better performance for image classification. The rationale, characteristics, and advantages of the proposed method are presented. The analysis describes that WKRBM outperforms collaborative representation-based kernel method for image recognition. Extensive experimental results illustrate that WKRBM has partial properties of sparsity, which is effective to recognize images.

On-line load balancing is one of the most important problems for applications with resource allocation. It aims to assign tasks to suitable machines and balance the load among all of the machines, where the tasks need to be assigned to a machine upon arrival. In practice, tasks are not always required to be assigned to machines immediately. In this paper, we propose a novel on-line load balancing model with task buffer, where the buffer can temporarily store tasks as many as possible. Three algorithms, namely LPTCP1_α, LPTCP2_α, and LPTCP3_β, are proposed based on the Longest Processing Time (LPT) algorithm and a variety of planarization algorithms. The planarization algorithms are proposed for reducing the difference among each element in a set. Experimental results show that our proposed algorithms can effectively solve the on-line load balancing problem and have good performance in large scale experiments.

Chinese characters are composed of radicals, and their radicals have the distinction between "shaped parts" (representing semantics) and "sound parts" (representing speech). As a hieroglyph, many radicals of Chinese characters have certain semantic information, which can effectively improve the performance of Chinese named entity recognition. In the Chinese named entity recognition, many related studies use Bi-LSTM to extract the semantic features from radicals. However, the LSTM-based model cannot effectively extract the semantic information of radicals due to ambiguity in partitioning the granularity of radicals and weak dependency between Chinese radicals. Therefore, this paper presents a radical neural network method RCBC (Radical CNN-BiLSTM-CRF). The experimental results on SIGHAN 2006 Bakeoff MSRA dataset and Peking University's People's Daily dataset in 1998 indicate that this model can effectively extract the semantic information of Chinese radicals and improve the performanceof Chinese named entity recognition compared with the traditional model.

Due to the influence of germs and viruses, plants often show various symptoms of diseases and insect pests during the growth process, which leads to a large economic loss of fruit farmers. It also brings a certain economic loss to our society, so prevent earlier and advise growers about plant diseases and insect pests have important value and significance. In this case, this paper proposes a detection method which is based on the combination of HOG, LBP and CSS features with Support Vector Machine (SVM) classifier. This method extracts the histogram of oriented gradients, texture, and color self-similar features of potato leaves, and then training samples with SVM classifier to detect late blight as early as possible in the early stages of potato growth. In addition, this paper proposes a method to increase virtual samples, that is, generating symmetrical samples according to the original samples. Due to the limitation of the number of collected samples, increasing symmetrical samples can expand the diversity of samples. The results show that this method can obtain a detection rate of 92.7%, and has better detection and recognition performance in practical application.

The frequency of phrases is important to discover key phrases. A high occurrence gives more contexts to assess them while many meaningful rare phrases are ignored. In this paper, we address the problem by exploring the semantic structure of rare phrases. An unsupervised method is presented to discover key phrases that occurs even only one time in a corpus. Comparing with related methods, the experiment shows an effective result. Moreover, a relation extraction task is conducted to evaluate the utilization of rare phrases for supporting NLP applications.

Topic modeling has been widely used to mine topics. However, users' individual needs are seldom considered, which is against the trend that individuation becomes more and more important. In this work, we propose a user-oriented probabilistic topic model based on Latent Dirichlet Allocation. Interested and uninterested words are used as supervised information to take users' preferences into account. A self-learning algorithm increasing the quantity of supervised information effectively are also presented. As a semi-supervised model, data with or without supervised information attached are treated differently. In the parameters inference, we integrate the Polya urn model into the Gibbs sampling process to utilize different kinds of supervised information efficiently. Experiments conducted on real datasets show the model outperforms the state-of-the-art models.

Semi-supervised text clustering, as a research branch of the text clustering, aims at employing limited priori knowledge to aid unsupervised text clustering process, and helping users get improved clustering results. Because labeled data are difficult, expensive and time-consuming to obtain, it is important to use the supervised information effectively to improve the performance of clustering significantly. This paper proposes a semi-supervised LDA text clustering algorithm based on the weights of word distribution (WWDLDA). By introducing the coefficients of word distribution obtained from labeled data, LDA model can be used in the field of semi-supervised clustering. In the process of clustering, coefficients always adjust the word distribution to change the clustering results. Our experimental results on real data sets show that the proposed semi-supervised text clustering algorithm can get better clustering results than constrained mixmnl, where mixmnl stands for multinomial model-based EM algorithm. Introduction Text clustering, as an important method of knowledge discovery, is a procedure and an unsupervised method of automatic text classification. By analyzing the relationship between documents, text clustering makes the same theme articles classified as a class. Without the training process and prior category label, text clustering is provided with higher ability of automatic processing and flexibility, which is widely used in data mining, information retrieval and theme testing. Research on text clustering is demonstrated in [1-3]. Traditional document clustering algorithm is an unsupervised learning method that processes unlabeled documents. In practical applications, however, people can get limited priori knowledge of the data, including class labels and documentation division of constraints conditions (such as pairwise constraints) [4]. Semi-supervised text clustering is a text clustering research branch. It utilizes priori labeled data to guide unsupervised text clustering process on the basis of the traditional text clustering method, and gets better clustering results. Semi-supervised text clustering has recently become a topic of significant interest. The complexity of document corpora has led to considerable interest in applying hierarchical statistical models based on what are called topic. Topic model could reduce data dimension by changing the document representation from by words to by topic, and achieve new document representation. Among topic models, Latent Dirichlet allocation (LDA) [5] is one of the simplest, most popular models and arguably most important probabilistic models in widespread use today. While cluster documents according to topic, the obtained distribution of topic helps us get clustering results. Therefore LDA can be applied on text clustering. LDA is a unsupervised learning algorithm. This paper puts forward a new semi-supervised text clustering algorithm, which embed weights of words distribution to LDA. The coefficient guides the clustering process by updating the word item distribution, and then enhances the clustering performance. The semi-supervised LDA text clustering algorithm based on the weights of word distribution (WWDLDA) is experimented on real data sets. The experimental results show that WWDLDA has a better performance than the constrained mixmnl algorithm [6]. International Conference on Education Technology and Information System (ICETIS 2013) © 2013. The authors Published by Atlantis Press 1024 Latent Dirichlet Allocation Latent Dirichlet allocation (LDA) presented by Blei is a topic model and a generative probabilistic model of a corpus. A document consisting of a large number of words might be concisely modeled as deriving from a smaller number of topics. A topic is a probability distribution over words. The basic idea of LDA is that documents are represented as random mixtures over latent topics, where each topic is characterized by a distribution over words. Fig.1. Graphical model representation of LDA. According to the graphical model representation shown in Figure 1, LDA assumes the following generative process for a document: first, choose a variableθ ,whereθ is the random variable parameter of a multinomial over topics and θ follows Dirichlet distribution; secondly choose a topic n z and then choose a word n w from a multinomial probability conditioned on the topic n z ; last repeated choosing topic and word N times. The probability of a corpus is obtained. ( ) ( ) ( ) ( ) 1 1 p | , | | | , d

Good assessment and evaluation of ERP is very important for us to know the effect of implement ERP. In this paper, we bring forward evaluation module architecture of chemical enterprises ERP based the actual situation of some chemical enterprise. Enterprises can make comprehensive assessment and evaluation of ERP through the module including six evaluation indicators.

Web search engines have become one of the absolutely necessary tools for us in the use of the Internet. They are receiving keen appreciation from the broad masses of network users because of the ability of quick search and the navigation service. However, the current used search engines do not take the actual situation and actual need of users into account, users may meet the topic drift problems in the searching process. Based on the PageRank algorithm, taking the human factor into consideration, we introduce page belief recommendation mechanism and bring forward a balanced rank algorithm based on PageRank and page belief recommendation. This algorithm attaches importance into the subjective needs of the users, it can effectively avoid topic drift problems.