检索结果-南通市图书馆

Text Detection in Natural Scene Images Using Morphological Component Analysis and Laplacian Dictionary

在线全文

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2020年第1期7卷 214-222页

作者： Shuping Liu Yantuan Xian Huafeng Li zhengtao yu School of Information Engineering and Automation and Key Laboratory of Intelligent Information Processing Kunming University of Science and Technology

Text in natural scene images usually carries abundant semantic information. However, due to variations of text and complexity of background, detecting text in scene images becomes a critical and challenging task. In this paper, we present a novel method to detect text from scene images. Firstly, we decompose scene images into background and text components using morphological component analysis(MCA), which will reduce the adverse effects of complex backgrounds on the detection *** order to improve the performance of image decomposition,two discriminative dictionaries of background and text are learned from the training samples. Moreover, Laplacian sparse regularization is introduced into our proposed dictionary learning method which improves discrimination of dictionary. Based on the text dictionary and the sparse-representation coefficients of text, we can construct the text component. After that, the text in the query image can be detected by applying certain heuristic rules. The results of experiments show the effectiveness of the proposed method.

关键词： Dictionary learning Laplacian sparse regularization morphological component analysis(MCA) sparse representation text detection

Detecting micro-blog user interest communities through the integration of explicit user relationship and implicit topic relations

在线全文

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2017年第9期60卷 64-77页

作者： yu QIN zhengtao yu Yanbing WANG Shengxiang GAO Linbin SHI Institute of Information Engineering and Automation Kunming University of Science and Technology Key Laboratory of Intelligent Information Processing Kunming University of Science and Technology

In order to effectively utilize the explicit user relationship and implicit topic relations for the detection of micro-blog user interest communities, a micro-blog user interest community(MUIC) detection approach is proposed. First, through the analysis of the follow relationship between users, we have defined three types of such relationships to construct the user follow-ship network. Second, taking the semantic correlation between user tags into account, we construct the user interest feature vectors based on the concept of feature mapping to build a user tag based interest relationship network. Third, user behaviors, such as reposting, commenting, replying, and receiving comments from others, are able to provide certain guidance for the extraction of micro-blog topics. Hence, we propose to integrate the four mentioned user behaviors that are considered to provide guidance information for the traditional latent Dirichlet allocation(LDA) model. Thereby, in addition to the construction of a topic-based interest relationship network, a guided topic model can be built to extract the topics in which the user is interested. Finally, with the integration of the afore-mentioned three types of relationship network, a micro-blog user interest relationship network can be created. Meanwhile, we propose a MUIC detection algorithm based on the contribution of the neighboring nodes. The experiment result proves the effectiveness of our approach in detecting MUICs.

关键词： feature mapping implicit topic guided topic model contribution of the neighboring nodes

A Novel Dual Pointer Approach for Entity Mention Extraction

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2021年第1期30卷 127-133页

作者： LIU Jie PANG Yihe ZHANG Kai LIU Lizhen yu zhengtao Department of Information Engineering Capital Normal University Research Center for Language Intelligence Capital Normal University Department of Information Engineering and Automation Kunming University of Science and Technology

The named entity extraction task aims to extract entity mentions from the unstructured text,including names of people, places, institutions and so on. It plays an important role in many Natural language processing(NLP) tasks, such as knowledge bases construction, automatic question answering system and information extraction. Most of the existing entity extraction studies are based on the long text data, which are easier to annotate due to the sufficient contextual information. Extracting entities from short texts such as search queries, conversations is still a challenging *** paper proposes a dual pointer approach for entity mention extraction, it extracts one entities by two position pointers of the input sentence. The end-to-end deep neural networks model based on the proposed approach can extract the entities by serially generating the dual *** evaluation results on the Chinese public dataset show that the model achieves the state-of-the-art results over the baseline models.

关键词： entity mention extraction novel dual pointer approach Chinese public dataset text analysis deep learning (artificial intelligence) long text data end-to-end deep neural networks model natural language processing automatic question answering system named entity extraction task unstructured text question answering (information retrieval) natural language processing tasks query processing knowledge bases construction knowledge based systems information extraction

Structural, Anisotropic and Thermodynamic Properties of Imm2-BCN

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Journal of Wuhan University of Technology(Materials Science) 2016年第6期31卷 1272-1279页

作者：邢孟江 li binhua yu zhengtao chen qi Faculty of Information Engineering & Automation Kunming University of Science and Technology Kunming 650051 China

Structural, anisotropic, and thermodynamic properties of Imm2-BCN were studied based on density function theory with the ultrasoft psedopotential scheme in the frame of the generalized gradient approximation（GGA）. The elastic constants were confirmed that the predicted Imm2-BCN is mechanically stable. The anisotropy of elastic properties were also studied systematically. The anisotropy studies of Young＇s modulus, shear modulus, linear compressibility, and Poisson＇s ratio show that the Imm2-BCN exhibits a large anisotropy. Through the quasi-harmonic Debye model, the relations between the equilibrium volume V, thermal expansion α, the heat capacity C_V and CP, the Grüneisen parameter γ, and the Debye temperature Θ_D with pressure P and temperature T were also studied systematically.

关键词： anisotropic properties thermodynamic properties the quasi-harmonic Debye model BCN

Semantic-aware entity alignment for low resource language knowledge graph

在线全文

学校读者我要写书评

暂无评论

Frontiers of Computer Science 2024年第4期18卷 97-106页

作者： Junfei TANG Ran SONG yuxin HUANG Shengxiang GAO zhengtao yu Faculty of Information Engineering and Automation Kunming University of Science and TechnologyKunming 650500China yunnan Key Laboratory of Artificial Intelligence Kunming University of Science and TechnologyKunming 650500China

Entity alignment(EA)is an important technique aiming to find the same real entity between two different source knowledge graphs(KGs).Current methods typically learn the embedding of entities for EA from the structure of KGs for *** EA models are designed for rich-resource languages,requiring sufficient resources such as a parallel corpus and pre-trained language ***,low-resource language KGs have received less attention,and current models demonstrate poor performance on those low-resource ***,researchers have fused relation information and attributes for entity representations to enhance the entity alignment performance,but the relation semantics are often *** address these issues,we propose a novel Semantic-aware Graph Neural Network(SGNN)for entity ***,we generate pseudo sentences according to the relation triples and produce representations using pre-trained ***,our approach explores semantic information from the connected relations by a graph neural *** model captures expanded feature information from *** results using three low-resource languages demonstrate that our proposed SGNN approach out performs better than state-of-the-art alignment methods on three proposed datasets and three public datasets.

关键词： graph neural network knowledge graph entity alignment low-resource language

Discrimination of Motor Imagery Patterns by Electroencephalogram Phase Synchronization Combined With Frequency Band Energy

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2017年第3期4卷 551-557页

作者： Chuanwei Liu yunfa Fu Jun Yang Xin Xiong Huiwen Sun zhengtao yu Faculty of Information Engineering and Automation Kunming University Science and Technology Shanghai Micro Electronics Equipment Co. Ltd. (SMEE)

Central nerve signal evoked by thoughts can be directly used to control a robot or prosthetic devices without the involvement of the peripheral nerve and *** is a new strategy of human-computer interaction.A method of electroencephalogram(EEG) phase synchronization combined with band energy was proposed to construct a feature vector for pattern recognition of brain-computer interaction based on EEG induced by motor imagery in this paper,rhythm and beta rhythm were first extracted from EEG by band pass filter and then the frequency band energy was calculated by the sliding time window;the instantaneous phase values were obtained using Hilbert transform and then the phase synchronization feature was calculated by the phase locking value(PLV) and the best time interval for extracting the phase synchronization feature was searched by the distribution of the PLV value in the time ***,discrimination of motor imagery patterns was performed by the support vector machine(SVM).The results showed that the phase synchronization feature more effective in4s-7s and the correct classification rate was 91.4%.Compared with the results achieved by a single EEG feature related to motor imagery,the correct classification rate was improved by 3.5 and4.3 percentage points by combining phase synchronization with band *** indicate that the proposed method is effective and it is expected that the study provides a way to improve the performance of the online real-time brain-computer interaction control system based on EEG related to motor imagery.

关键词： Brain-computer interaction(BCI) electroencephalogram(EEG) frequency band energy motor imagery phase synchronization

Expert Evidence Document Recognition Integrating Relationship of Expert

在线全文

学校读者我要写书评

暂无评论

Expert Evidence Document Recognition Integrating Relationshi...

Review Expert Collaborative Recommendation Algorithm Based on Topic Relationship

第25届中国控制与决策会议

作者： Meng Wang Tao Shen zhengtao yu School of Information Engineering and Automation Kunming University of Science and Technology School of Material Science and Engineering Kunming University of Science and Technology

ISBN: (纸本)9781467355339

Focus on the issue that the existing expert evidence document recognition method is not effective use of the relationship between experts, this paper proposed a method to recognize the expert evidence documents which integrate the feature of webpage content and the complex relationship between the experts. First of all, the method analyses characteristics of expert evidence document, to select Coauthors and organization as relationship feature, and then extracts feature values. Secondly, select 10130 expert evidence pages, and build data sets which integrate the feature values of and webpage content and the relationship, and then select different learning algorithms to build recognition model. Finally, experiment of expert evidence document recognition is carried out in the field of information processing. The experimental results shows that the proposed method achieves a good recognition effect. Using relationship can effectively improve the accuracy of the evidence document recognition. Its accuracy is improved by 4% compared to method using the page content feature recognition only.

关键词： Expert evidence document recognition Relationship feature Content feature Adaboost algorithm

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2015年第4期2卷 403-411页

作者： Shengxiang Gao zhengtao yu Linbin Shi Xin Yan Haixia Song School of Information Engineering and Automation and Key Laboratory of Intelligent Information Processing Kunming University of Science and Technology

The project review information plays an important role in the recommendation of review experts. In this paper, we aim to determine review expert's rating by using the historical rating records and the final decision results on the previous projects, and by means of some rules, we construct a rating matrix for projects and experts. For the data sparseness problem of the rating matrix and the 'cold start' problem of new expert recommendation, we assume that those projects/experts with similar topics have similar feature vectors and propose a review expert collaborative recommendation algorithm based on topic relationship. Firstly, we obtain topics of projects/experts based on latent Dirichlet allocation (LDA) model, and build the topic relationship network of projects/experts. Then, through the topic relationship between projects/experts, we find a neighbor collection which shares the largest similarity with target project/expert, and integrate the collection into the collaborative filtering recommendation algorithm based on matrix factorization. Finally, by learning the rating matrix to get feature vectors of the projects and experts, we can predict the ratings that a target project will give candidate review experts, and thus achieve the review expert recommendation. Experiments on real data set show that the proposed method could predict the review expert rating more effectively, and improve the recommendation effect of review experts. © 2014 Chinese Association of Automation.

关键词： Algorithms Collaborative filtering Factorization Rating Statistics

Linguistic feature template integration for Chinese-Vietnamese neural machine translation

在线全文

学校读者我要写书评

暂无评论

Frontiers of Computer Science 2022年第4期16卷 223-225页

作者： Zhiqiang yu Yantuan XIAN zhengtao yu yuxin HUANG Junjun GUO Faculty of Information Engineering and Automation Kunming University of Science and TechnologyKunming 650500China School of Mathematics and Computer Science Yunnan Minzu UniversityKunming 650500China yunnan Key Laboratory of Artificial Intelligence Kunming University of Science and TechnologyKunming 650500China

1 Introduction and main contributions Template-based approaches have achieved significant progress in low-resource neural machine translation(NMT)recently[1],such as the efficient works,NMT-GTM[2],SoftPrototype[3],***,most previous works only retrieve target sentence as template to generate translation,neglecting the utilization of linguistic feature that contained in the source sentence and template.

关键词： translation template such

同方期刊数据库