Search scope:
排序: Display mode:
一种易用的实体识别消歧系统评测框架 Article
辉 陈,宝刚 魏,一鸣 李,Yong-huai LIU,文浩 朱
Frontiers of Information Technology & Electronic Engineering 2017, Volume 18, Issue 2, Pages 195-205 doi: 10.1631/FITEE.1500473
Keywords: 实体识别消歧;评测框架;信息抽取
Disambiguating named entitieswith deep supervised learning via crowd labels Article
Le-kui ZHOU,Si-liang TANG,Jun XIAO,Fei WU,Yue-ting ZHUANG
Frontiers of Information Technology & Electronic Engineering 2017, Volume 18, Issue 1, Pages 97-106 doi: 10.1631/FITEE.1601835
Keywords: Named entity disambiguation Crowdsourcing Deep learning
A review on cyber security named entity recognition Review Article
Chen Gao, Xuan Zhang, Mengting Han, Hui Liu,zhxuan@ynu.edu.cn
Frontiers of Information Technology & Electronic Engineering 2021, Volume 22, Issue 9, Pages 1153-1168 doi: 10.1631/FITEE.2000286
Keywords: 命名实体识别(NER);信息抽取;网络空间安全;机器学习;深度学习
A network security entity recognition method based on feature template and CNN-BiLSTM-CRF Research Papers
Ya QIN, Guo-wei SHEN, Wen-bo ZHAO, Yan-ping CHEN, Miao YU, Xin JIN
Frontiers of Information Technology & Electronic Engineering 2019, Volume 20, Issue 6, Pages 872-884 doi: 10.1631/FITEE.1800520
By network security threat intelligence analysis based on a security knowledge graph (SKG), multi-source threat intelligence data can be analyzed in a fine-grained manner. This has received extensive attention. It is difficult for traditional named entity recognition methods to identify mixed security entities in Chinese and English in the field of network security, and there are difficulties in accurately identifying network security entities because of insufficient features extracted. In this paper, we propose a novel FT-CNN-BiLSTM-CRF security entity recognition method based on a neural network CNN-BiLSTM-CRF model combined with a feature template (FT). The feature template is used to extract local context features, and a neural network model is used to automatically extract character features and text global features. Experimental results showed that our method can achieve an F-score of 86% on a large-scale network security dataset and outperforms other methods.
Keywords: Network security entity Security knowledge graph (SKG) Entity recognition Feature template Neural network
A Face Recognition Based on Fusion Features Extraction From Two Kinds of Projection
Zhang Shengliang,Xu Yong,Yang Jian,Yang Jingyu
Strategic Study of CAE 2006, Volume 8, Issue 8, Pages 50-55
A novel face recognition algorithm based on two kinds of projection is presented in this paper. First, the two dimension principal component analysis (2DPCA) is used to extract one group of features, denoted by α. Second, the fisher linear discriminant analysis (LDA) , or fisherfaces, is used for extracting another group of features, denoted by β.After being standardized, the two kinds of features are combined together in the form of the complex vector α+iβ. Then the fusion features in the complex feature space is extracted by using complex PCA (CPCA). The proposed algorithm is evaluated by using the FERET face database at three different resolutions. The experimental results indicate that the proposed method can achieve about 10% higher recognition accurate rate than 2DPCA and LDA, while only using 28 features for each sample.
Keywords: feature fusion linear discriminant analysis (LDA) feature extraction face recognition
Learning to select pseudo labels: a semi-supervised method for named entity recognition Research Articles
Zhen-zhen Li, Da-wei Feng, Dong-sheng Li, Xi-cheng Lu,lizhenzhen14@nudt.edu.cn,davyfeng.c@gmail.com,dsli@nudt.edu.cn,xclu@nudt.edu.cn
Frontiers of Information Technology & Electronic Engineering 2020, Volume 21, Issue 6, Pages 809-962 doi: 10.1631/FITEE.1800743
Keywords: 命名实体识别;无标注数据;深度学习;半监督学习方法
A Study on the Essence of Optimal Statistical Uncorrelated Discriminant Vectors
Wu Xiaojun,Yang Jingyu,Wang Shitong,Liu Tongming,Josef Kittler
Strategic Study of CAE 2004, Volume 6, Issue 2, Pages 44-47
A study has been made on the essence of optimal set of uncorrelated discriminant vectors in this paper. A whitening transform has been constructed on the basis of the eigen decomposition of population scatter matrix, which makes the population scatter matrix an identity matrix in the transformed sample space. Thus, the optimal discriminant vectors solved by conventional LDA methods are statistical uncorrelated. The research indicates that the essence of the statistical uncorrelated discriminant transform is the whitening transform plus conventional linear discriminant transform. The distinguished characteristic of the proposed method is that the obtained optimal discriminant vectors are orthogonal and statistical uncorrelated. The proposed method suits for all the problems of algebraic feature extraction. The numerical experiments on facial database of ORL show the effectiveness of the proposed method.
Keywords: pattern recognition feature extraction disciminant analysis generalized optimal set of discriminant vectors face recognition
Both-Branch Fuzzy Decision and Problems on Decision Discernment
Shi Kaiquan,Li Qiqiang
Strategic Study of CAE 2001, Volume 3, Issue 1, Pages 71-77
This paper proposes the concept of both-branch fuzzy decision on X, which contains neutral universe(X*≠{x}), and the optimal decision analysis model. In addition, the paper proposes decision judgement theorem, decision discernment theorem, decision surplusage-discarding theorem and hole-digging principle on decision factors universe X. Both-branch fuzzy decision has such characteristics as decision two-direction dependence character, decision piling-synthesis character, decision branch-separating character, decision branch-degeneration character, and decision non-fault character. The research results have found application.
Keywords: both-branch fuzzy decision decision model judgement theorem discernment theorem surplusage-discarding theorem hole-digging principle
High-Temperature Target Recognition Based on Spectral Radiation Information
Fan Xueliang,Cheng Xiaofang,Xu Jun
Strategic Study of CAE 2004, Volume 6, Issue 6, Pages 57-62
Based on the principles of optics and radiometry, the imaging mathematical model is established and the factors of the contrast (signal-noise-ratio) of high-temperature target and the scenery are given. By analyzing not only the differences in spectral properties between objects in the scene, but also the CCD spectral response theoretically, a new method of enhancement of contrast is given. By optimizing the initial image capture stage, using liquid crystal light valve to make a simple modification of the imaging system, the goal of high object recognition is achieved. The experimental results agree with the theoretical predicts.
Keywords: video image object recognition radiation information liquid crystal light valve
DDUC: an erasure-coded system with decoupled data updating and coding Research Article
Xiang LI, Yibing LI, Chunrui TANG, Yingsong LI,chunruitang@126.com
Frontiers of Information Technology & Electronic Engineering 2023, Volume 24, Issue 5, Pages 742-758 doi: 10.1631/FITEE.2200253
Keywords: Signal noise elimination Deep adaptive threshold learning network Multi-scale feature fusion Modulation recognition
A Framework of Knowledge Theory: Toward a Unified Theory of Information, Knowledge and Intelligence
Zhong Yixin
Strategic Study of CAE 2000, Volume 2, Issue 9, Pages 50-64
Knowledge has been very important wealth to the mankind but there has not a knowledge theory existed yet till the present time. An attempt is thus made in the paper to present a framework of knowledge theory that includes two parts: fundamentals and the main body of knowledge theory. The first part is to deal with a series of basic issues such as the related concepts and definitions, the methods of representation, the measurements, the reasoning and decision rules. The second part is to explore the mechanism of knowledge formation based on information processing and the mechanism of intelligence formation based on the activation of knowledge. It is believed that the establishment of the knowledge theory will lay a solid foundation to the unified theory of information, knowledge, and intelligence and will greatly facilitate the effective utilization of information and knowledge, leading to the growth of the research in the field of intelligent machines.
Keywords: knowledge amount of knowledge knowledge formation knowledge activation unified theory of information-knowledge-intelligence
Algorithm Design for Improving Feature Extraction Efficiency Based on KPCA
Xu Yong,Yangjingyu,Lu Jianfeng
Strategic Study of CAE 2005, Volume 7, Issue 10, Pages 38-42
KPCA (kernel PCA) is derived from PCA. It can extract nonlinear feature components of samples. However, feature extraction for one sample requires that kernel functions between training samples and the sample be calculated in advance. So, the size of training sample set affects the efficiency of feature extraction. It is supposed that in feature space the eigenvectors may be linearly expressed by a part of training samples, called nodes. According to the supposition, an improved KPCA (IKPCA) algorithm is developed. IKPCA extracts feature components of one sample efficiently, only based on kernel functions between nodes and the sample. Experimental results show that IKPCA is very close to KPCA in performance, while with higher efficiency.
Keywords: KPCA(Kernel PCA) IKPCA(Improved KPCA) feature extraction feature space
Improving entity linking with two adaptive features Research Article
Hongbin ZHANG, Quan CHEN, Weiwen ZHANG
Frontiers of Information Technology & Electronic Engineering 2022, Volume 23, Issue 11, Pages 1620-1630 doi: 10.1631/FITEE.2100495
(EL) is a fundamental task in natural language processing. Based on neural networks, existing systems pay more attention to the construction of the , but ignore latent semantic information in the and the acquisition of effective information. In this paper, we propose two , in which the first adaptive feature enables the local and s to capture latent information, and the second adaptive feature describes effective information for embeddings. These can work together naturally to handle some uncertain information for EL. Experimental results demonstrate that our EL system achieves the best performance on the AIDA-B and MSNBC datasets, and the best average performance on out-domain datasets. These results indicate that the proposed , which are based on their own diverse contexts, can capture information that is conducive for EL.
Keywords: Entity linking Local model Global model Adaptive features Entity type
Shahab POURTALEBI,Imre HORVÁTH
Frontiers of Information Technology & Electronic Engineering 2016, Volume 17, Issue 9, Pages 862-884 doi: 10.1631/FITEE.1600997
Keywords: Cyber-physical systems Software toolbox Pre-embodiment design System manifestation features (SMFs) Warehouses Database schemata SMF genotypes SMF phenotypes SMF instances Information schema constructs
Yin Zhiping,Liu Aihua,Pan Renming
Strategic Study of CAE 2008, Volume 10, Issue 7, Pages 90-95
Extinguishing concentration measurement experiments in the cup burner on two kinds of superfine ammonium phosphate extinguishing agents with different particle sizes had been done by means of filtering and weighing method combined with laser attenuation measurement. The fitting curves of particle concentration with laser attenuation rate and the extinguishing concentration of superfine particle agents had been got. The extinguishing mass concentration of two super fine agents were measured in cup burner. The results showed that when the median particle size of two kinds of extinguishing agents were 6.0 μm and 13.7μm, their laser absorption coefficients were 0.353 m2/g and 0.257 3 m2/g respectively and their mean extinguishing concentration were 32.9 g/m3 and 41.6 g/m3 respectively. Extinguishing ability of the former was 25 % to 30 % higher than that of the latter. The laser attenuation measurement relative errors were less when the former agent was used in experiment.
Keywords: laser attenuation measurement filtering and weighing method superfine particle extinguishing agent extinguishing concentration
Title Author Date Type Operation
Disambiguating named entitieswith deep supervised learning via crowd labels
Le-kui ZHOU,Si-liang TANG,Jun XIAO,Fei WU,Yue-ting ZHUANG
Journal Article
A review on cyber security named entity recognition
Chen Gao, Xuan Zhang, Mengting Han, Hui Liu,zhxuan@ynu.edu.cn
Journal Article
A network security entity recognition method based on feature template and CNN-BiLSTM-CRF
Ya QIN, Guo-wei SHEN, Wen-bo ZHAO, Yan-ping CHEN, Miao YU, Xin JIN
Journal Article
A Face Recognition Based on Fusion Features Extraction From Two Kinds of Projection
Zhang Shengliang,Xu Yong,Yang Jian,Yang Jingyu
Journal Article
Learning to select pseudo labels: a semi-supervised method for named entity recognition
Zhen-zhen Li, Da-wei Feng, Dong-sheng Li, Xi-cheng Lu,lizhenzhen14@nudt.edu.cn,davyfeng.c@gmail.com,dsli@nudt.edu.cn,xclu@nudt.edu.cn
Journal Article
A Study on the Essence of Optimal Statistical Uncorrelated Discriminant Vectors
Wu Xiaojun,Yang Jingyu,Wang Shitong,Liu Tongming,Josef Kittler
Journal Article
Both-Branch Fuzzy Decision and Problems on Decision Discernment
Shi Kaiquan,Li Qiqiang
Journal Article
High-Temperature Target Recognition Based on Spectral Radiation Information
Fan Xueliang,Cheng Xiaofang,Xu Jun
Journal Article
DDUC: an erasure-coded system with decoupled data updating and coding
Xiang LI, Yibing LI, Chunrui TANG, Yingsong LI,chunruitang@126.com
Journal Article
A Framework of Knowledge Theory: Toward a Unified Theory of Information, Knowledge and Intelligence
Zhong Yixin
Journal Article
Algorithm Design for Improving Feature Extraction Efficiency Based on KPCA
Xu Yong,Yangjingyu,Lu Jianfeng
Journal Article
Improving entity linking with two adaptive features
Hongbin ZHANG, Quan CHEN, Weiwen ZHANG
Journal Article
Information schema constructs for defining warehouse databases of genotypes and phenotypes of system manifestation features
Shahab POURTALEBI,Imre HORVÁTH
Journal Article