Search | Engineering

Subscribe Submit

Home Journals Focus Achievement Fronts About Us 中文版

Resource Type

Journal Article 187

Year

2023 24

2022 19

2021 11

2020 7

2019 4

2018 16

2017 10

2016 10

2015 2

2014 2

2013 7

2012 12

2011 2

2010 5

2009 3

2008 5

2007 6

2006 4

2005 9

2004 10

open ︾

Keywords

DX pile 8

COVID-19 2

Colloids 2

Dictionary learning 2

Representation learning 2

Sparse representation 2

automatic target recognition 2

cyberspace security 2

fire detection 2

guard mode 2

numerical analysis 2

performance evaluation 2

settlement 2

-10#emulsified diesel oil 1

2019-nCoV 1

3D printing 1

6G 1

In situ pyrolysis 1

ANFIS 1

open ︾

Search scope:

排序： Display mode:

MPIN: a macro-pixel integration network for light field super-resolution Research Articles

Xinya Wang, Jiayi Ma, Wenjing Gao, Junjun Jiang,wangxinya@whu.edu.cn,jyma2010@gmail.com,wenjinggao@whu.edu.cn,junjun0595@163.com

Frontiers of Information Technology & Electronic Engineering 2021, Volume 22, Issue 10, Pages 1299-1310 doi: 10.1631/FITEE.2000566

Abstract: Most existing (LF) (SR) methods either fail to fully use angular information or have an unbalanced performance distribution because they use parts of views. To address these issues, we propose a novel integration network based on for the LF SR task, named MPIN. Restoring the entire LF image simultaneously, we couple the spatial and angular information by rearranging the four-dimensional LF image into a two-dimensional macro-pixel image. Then, two special convolutions are deployed to extract spatial and angular information, separately. To fully exploit spatial-angular correlations, the integration resblock is designed to merge the two kinds of information for mutual guidance, allowing our method to be angular-coherent. Under the , an angular shuffle layer is tailored to improve the spatial resolution of the macro-pixel image, which can effectively avoid aliasing. Extensive experiments on both synthetic and real-world LF datasets demonstrate that our method can achieve better performance than the state-of-the-art methods qualitatively and quantitatively. Moreover, the proposed method has an advantage in preserving the inherent epipolar structures of LF images with a balanced distribution of performance.

Keywords：光场；超分辨率；宏像素表示

HTML PDF Collect

Uncertainty in Knowledge Representation

Li Deyi

Strategic Study of CAE 2000, Volume 2, Issue 10, Pages 73-79

Abstract:

Knowledge representation in AI has been a bottleneck for years. And the difficulty is uncertainty hidden in qualitative concepts, that is the randomness and fuzziness. At this junction, this paper presents a new concept of cloud models with three digital characteristics： expected value Ex, entropy En, and hyper entropy He. This methodology has effectively made mapping between quantitative and qualitative knowledge much easier at any time. A cloud drop, that is a quantitative value, representing the qualitative concept can be measured by contributions. A new explanation for the 24 solar terms in lunar calendar is given as well. The cloud models have been used in data mining, intelligent control, hopping frequency technique, system evaluation, and so on.

Keywords： knowledge representation qualitative concept uncertainty cloud model digital characteristics

HTML PDF Collect

Public key based bidirectional shadow image authentication without pixel expansion in image secret sharing Research Article

Xuehu YAN, Longlong LI, Jia CHEN, Lei SUN,publictiger@126.com

Frontiers of Information Technology & Electronic Engineering 2023, Volume 24, Issue 1, Pages 88-103 doi: 10.1631/FITEE.2200118

Abstract: (ISS) is gaining popularity due to the importance of digital images and its wide application to cloud-based distributed storage and multiparty secure computing. generally includes shadow image detection and identification, and plays an important role in ISS. However, traditional dealer-participatory methods, which suffer from significant or storing auxiliary information, authenticate the shadow image mainly during the decoding phase, also known as unidirectional authentication. The authentication of the shadow image in the distributing (encoding) phase is also important for the participant. In this study, we introduce a based bidirectional method in ISS without for a (k,n) threshold. When the dealer distributes each shadow image to a corresponding participant, the participant can authenticate the received shadow image with his/her private key. In the decoding phase, the dealer can authenticate each received shadow image with a secret key; in addition, the dealer can losslessly decode the secret image with any k or more shadow images. The proposed method is validated using theoretical analyses, illustrations, and comparisons.

Keywords： Image secret sharing Shadow image authentication Public key Pixel expansion Lossless decoding

HTML PDF Collect

Analyzing the Effect of the Intra-Pixel Position of Small PSFs for Optimizing the PL of Optical Subpixel Localization Article

Haiyang Zhan, Fei Xing, Jingyu Bao, Ting Sun, Zhenzhen Chen, Zheng You, Li Yuan

Engineering 2023, Volume 27, Issue 8, Pages 140-149 doi: 10.1016/j.eng.2023.03.009

Abstract:

Subpixel localization techniques for estimating the positions of point-like images captured by pixelated image sensors have been widely used in diverse optical measurement fields. With unavoidable imaging noise, there is a precision limit when estimating the target positions on image sensors, which depends on the detected photon count, noise, point spread function (PSF) radius, and PSF’s intra-pixel position. Previous studies have clearly reported the effects of the first three parameters on the precision limit but have neglected the intra-pixel position information. Here, we develop a localization precision limit analysis framework for revealing the effect of the intra-pixel position of small PSFs. To accurately estimate the precision limit in practical applications, we provide effective PSF (ePSF) modeling approaches and apply the Cramér-Rao lower bound. Based on the characteristics of small PSFs, we first derive simplified equations for finding the best precision limit and the best intra-pixel region for an arbitrary small PSF; we then verify these equations on real PSFs. Next, we use the typical Gaussian PSF to perform a further analysis and find that the final optimum of the precision limit is achieved at the pixel boundaries when the Gaussian radius is as small as possible, indicating that the optimum is ultimately limited by light diffraction. Finally, we apply the maximum likelihood method. Its combination with ePSF modeling allows us to successfully reach the precision limit in experiments, making the above theoretical analysis effective. This work provides a new perspective on combining image sensor position control with PSF engineering to make full use of information theory, thereby paving the way for thoroughly understanding and achieving the final optimum of the precision limit in optical localization.

Keywords： Optical measurement Subpixel localization Precision limit optimization Small point spread functions Centroiding Star sensors

HTML PDF Collect

Laplacian sparse dictionary learning for image classification based on sparse representation Article

Fang LI, Jia SHENG, San-yuan ZHANG

Frontiers of Information Technology & Electronic Engineering 2017, Volume 18, Issue 11, Pages 1795-1805 doi: 10.1631/FITEE.1600039

Abstract: Sparse representation is a mathematical model for data representation that has proved to be a powerful tool for solving problems in various fields such as pattern recognition, machine learning, and computer vision. As one of the building blocks of the sparse representation method, dictionary learning plays an important role in the minimization of the reconstruction error between the original signal and its sparse representation in the space of the learned dictionary. Although using training samples directly as dictionary bases can achieve good performance, the main drawback of this method is that it may result in a very large and inefficient dictionary due to noisy training instances. To obtain a smaller and more representative dictionary, in this paper, we propose an approach called Laplacian sparse dictionary (LSD) learning. Our method is based on manifold learning and double sparsity. We incorporate the Laplacian weighted graph in the sparse representation model and impose the l1-norm sparsity on the dictionary. An LSD is a sparse overcomplete dictionary that can preserve the intrinsic structure of the data and learn a smaller dictionary for each class. The learned LSD can be easily integrated into a classification framework based on sparse representation. We compare the proposed method with other methods using three benchmark-controlled face image databases, Extended Yale B, ORL, and AR, and one uncontrolled person image dataset, i-LIDS-MA. Results show the advantages of the proposed LSD algorithm over state-of-the-art sparse representation based classification methods.

Keywords： Sparse representation Laplacian regularizer Dictionary learning Double sparsity Manifold

HTML PDF Collect

Semantic composition of distributed representations for query subtopic mining None

Wei SONG, Ying LIU, Li-zhen LIU, Han-shi WANG

Frontiers of Information Technology & Electronic Engineering 2018, Volume 19, Issue 11, Pages 1409-1419 doi: 10.1631/FITEE.1601476

Abstract:

Inferring query intent is significant in information retrieval tasks. Query subtopic mining aims to find possible subtopics for a given query to represent potential intents. Subtopic mining is challenging due to the nature of short queries. Learning distributed representations or sequences of words has been developed recently and quickly, making great impacts on many fields. It is still not clear whether distributed representations are effective in alleviating the challenges of query subtopic mining. In this paper, we exploit and compare the main semantic composition of distributed representations for query subtopic mining. Specifically, we focus on two types of distributed representations: paragraph vector which represents word sequences with an arbitrary length directly, and word vector composition. We thoroughly investigate the impacts of semantic composition strategies and the types of data for learning distributed representations. Experiments were conducted on a public dataset offered by the National Institute of Informatics Testbeds and Community for Information Access Research. The empirical results show that distributed semantic representations can achieve outstanding performance for query subtopic mining, compared with traditional semantic representations. More insights are reported as well.

Keywords： Subtopic mining Query intent Distributed representation Semantic composition

HTML PDF Collect

Syntactic word embedding based on dependency syntax and polysemous analysis None

Zhong-lin YE, Hai-xing ZHAO

Frontiers of Information Technology & Electronic Engineering 2018, Volume 19, Issue 4, Pages 524-535 doi: 10.1631/FITEE.1601846

Abstract: Most word embedding models have the following problems: (1) In the models based on bag-of-words contexts, the structural relations of sentences are completely neglected; (2) Each word uses a single embedding, which makes the model indiscriminative for polysemous words; (3) Word embedding easily tends to contextual structure similarity of sentences. To solve these problems, we propose an easy-to-use representation algorithm of syntactic word embedding (SWE). The main procedures are: (1) A polysemous tagging algorithm is used for polysemous representation by the latent Dirichlet allocation (LDA) algorithm; (2) Symbols ‘+’ and ‘−’ are adopted to indicate the directions of the dependency syntax; (3) Stopwords and their dependencies are deleted; (4) Dependency skip is applied to connect indirect dependencies; (5) Dependency-based contexts are inputted to a word2vec model. Experimental results show that our model generates desirable word embedding in similarity evaluation tasks. Besides, semantic and syntactic features can be captured from dependency-based syntactic contexts, exhibiting less topical and more syntactic similarity. We conclude that SWE outperforms single embedding learning models.

Keywords： Dependency-based context Polysemous word representation Representation learning Syntactic word embedding

HTML PDF Collect

Principles and applications of high-speed single-pixelimaging technology Review

Qiang GUO, Yu-xi WANG, Hong-wei CHEN, Ming-hua CHEN, Si-gang YANG, Shi-zhong XIE

Frontiers of Information Technology & Electronic Engineering 2017, Volume 18, Issue 9, Pages 1261-1267 doi: 10.1631/FITEE.1601719

Abstract: Single-pixel imaging (SPI) technology has garnered great interestwithin the last decade because of its ability to record high-resolutionimages using a single-pixel detector. It has been applied to diversefields, such as magnetic resonance imaging (MRI), aerospace remotesensing, terahertz photography, and hyperspectral imaging. Comparedwith conventional silicon-based cameras, single-pixel cameras (SPCs)can achieve image compression and operate over a much broader spectralrange. However, the imaging speed of SPCs is governed by the responsetime of digital micromirror devices (DMDs) and the amount of compressionof acquired images, leading to low (ms-level) temporal resolution.Consequently, it is particularly challenging for SPCs to investigatefast dynamic phenomena, which is required commonly in microscopy.Recently, a unique approach based on photonic time stretch (PTS) toachieve high-speed SPI has been reported. It achieves a frame ratefar beyond that can be reached with conventional SPCs. In this paper,we first introduce the principles and applications of the PTS technique.Then the basic architecture of the high-speed SPI system is presented,and an imaging flow cytometer with high speed and high throughputis demonstrated experimentally. Finally, the limitations and potentialapplications of high-speed SPI are discussed.

Keywords： Compressive sampling Single-pixel imaging Photonic time stretch Imaging flow cytometry

HTML PDF Collect

Federated unsupervised representation learning Research Article

Fengda ZHANG, Kun KUANG, Long CHEN, Zhaoyang YOU, Tao SHEN, Jun XIAO, Yin ZHANG, Chao WU, Fei WU, Yueting ZHUANG, Xiaolin LI,fdzhang@zju.edu.cn,kunkuang@zju.edu.cn

Frontiers of Information Technology & Electronic Engineering 2023, Volume 24, Issue 8, Pages 1181-1193 doi: 10.1631/FITEE.2200268

Abstract: To leverage the enormous amount of unlabeled data on distributed edge devices, we formulate a new problem in called federated unsupervised (FURL) to learn a common representation model without supervision while preserving data privacy. FURL poses two new challenges: (1) data distribution shift (non-independent and identically distributed, non-IID) among clients would make local models focus on different categories, leading to the inconsistency of representation spaces; (2) without unified information among the clients in FURL, the representations across clients would be misaligned. To address these challenges, we propose the federated contrastive averaging with dictionary and alignment (FedCA) algorithm. FedCA is composed of two key modules: a dictionary module to aggregate the representations of samples from each client which can be shared with all clients for consistency of representation space and an alignment module to align the representation of each client on a base model trained on public data. We adopt the contrastive approach for local model training. Through extensive experiments with three evaluation protocols in IID and non-IID settings, we demonstrate that FedCA outperforms all baselines with significant margins.

Keywords： Federated learning Unsupervised learning Representation learning Contrastive learning

HTML PDF Collect

The Cryptographic Properties of Select Logic Functions

Liang Zeng,Li Shiqu

Strategic Study of CAE 2005, Volume 7, Issue 7, Pages 50-54

Abstract:

In this paper, the main results are concerned with the Walsh transform and the autocorrelation function of select logic functions. Select logic functions with large number of variables have perfect stability and can resist towards cryptanalysis of best affine approximation, but they can't resist towards differential cryptanalysis efficiently because of weak propagation property. By a linear transformation of coordinates, an explicit construction for functions satisfying the strict avalanche criterion or Being correlation immune is provided.

Keywords： select logic function Walsh transform autocorrelation function strict avalanche criterion correlation immune probability expressions

HTML PDF Collect

Dynamic parameterized learning for unsupervised domain adaptation Research Article

Runhua JIANG, Yahong HAN

Frontiers of Information Technology & Electronic Engineering 2023, Volume 24, Issue 11, Pages 1616-1632 doi: 10.1631/FITEE.2200631

Abstract: enables neural networks to transfer from a labeled source domain to an unlabeled target domain by learning domain-invariant representations. Recent approaches achieve this by directly matching the marginal distributions of these two domains. Most of them, however, ignore exploration of the dynamic trade-off between and learning, thus rendering them susceptible to the problems of negative transfer and outlier samples. To address these issues, we introduce the dynamic parameterized learning framework. First, by exploring domain-level semantic knowledge, the dynamic alignment parameter is proposed, to adaptively adjust the of and learning. Besides, for obtaining semantic-discriminative and domain-invariant representations, we propose to align training trajectories on both source and target domains. Comprehensive experiments are conducted to validate the effectiveness of the proposed methods, and extensive comparisons are conducted on seven datasets of three visual tasks to demonstrate their practicability.

Keywords： Unsupervised domain adaptation Optimization steps Domain alignment Semantic discrimination

HTML PDF Collect

Cyberspace Security Competition and Talent Management

Yu Xiangzhan,Zhang Hongli and Yu Haining、Tian Zhihong、Zhai Jianhong、Pan Zhuting

Strategic Study of CAE 2016, Volume 18, Issue 6, Pages 49-52 doi: 10.15302/J-SSCAE-2016.06.010

Abstract:

Competition of talents is fundamental to international cyberspace security, and the discovery and tracking of talents is one of the key links. First, we investigate the development status of domestic and international cyberspace security competition. Then, we analyze the main problems of cyberspace security competition in discovering and tracking talents. Finally, we propose a long-term policy to discover and track talents based on cyberspace competitions.

Keywords： cyberspace security competition talent-discovery talent-track

HTML PDF Collect

基于ARIMA和Kalman滤波的道路交通状态实时预测 Article

东伟徐,永东王,利民贾,勇秦,宏辉董

Frontiers of Information Technology & Electronic Engineering 2017, Volume 18, Issue 2, Pages 287-302 doi: 10.1631/FITEE.1500381

Abstract: 道路交通流预测不仅可以为出行者提供实时有效的信息，而且可以帮助他们选择最佳路径，减少出行时间，实现道路交通路径诱导，缓解交通拥堵。本文提出了一种基于ARIMA模型和Kalman滤波算法的道路交通流预测方法。首先，基于道路交通历史数据建立时间序列的ARIMA模型。其次，结合ARIMA模型和Kalman滤波法构建道路交通预测算法，获取Kalman滤波的测量方程和更新方程。然后，基于历史道路交通数据进行算法的参数设定。最后，以北京的四条路段作为案例，对所提出的方法进行了分析。实验结果表明，基于ARIMA模型和Kalman滤波的实时道路交通状态预测方法是可行的，并且可以获得很高的精度。

Keywords： ARIMA模型；Kalman滤波；建模；训练；预测

HTML PDF Collect

Development Strategy for China's Energy Conservation and Environmental Protection Industry

Feng Huijuan, Luo Hong, Pei Yingying, Xue Jie, Yang ZhanHong, Lv Lianhong

Strategic Study of CAE 2016, Volume 18, Issue 4, Pages 1-8 doi: 10.15302/J-SSCAE-2016.04.001

Abstract:

Developing the energy conservation and environmental protection industry—a new economic growth engine—is an important guarantee for the promotion of ecological civilization construction and the realization of green development in China. This paper proceeds from the development status of this industry to analyze the deep-seated problems affecting China’s energy conservation and environmental protection industry development, study and determine the new industrial development trends in the 13th Five-Year Plan period, and define the development objectives and key projects of this industry, thereby offering strategic suggestions for promoting the energy conservation and environmental protection industry development in China.

Keywords： energy saving environmental protection industry developmental strategy

HTML PDF Collect

A survey of malware behavior description and analysis Review

Bo YU, Ying FANG, Qiang YANG, Yong TANG, Liu LIU

Frontiers of Information Technology & Electronic Engineering 2018, Volume 19, Issue 5, Pages 583-603 doi: 10.1631/FITEE.1601745

Abstract: Behavior-based malware analysis is an important technique for automatically analyzing and detecting malware, and it has received considerable attention from both academic and industrial communities. By considering how malware behaves, we can tackle the malware obfuscation problem, which cannot be processed by traditional static analysis approaches, and we can also derive the as-built behavior specifications and cover the entire behavior space of the malware samples. Although there have been several works focusing on malware behavior analysis, such research is far from mature, and no overviews have been put forward to date to investigate current developments and challenges. In this paper, we conduct a survey on malware behavior description and analysis considering three aspects: malware behavior description, behavior analysis methods, and visualization techniques. First, existing behavior data types and emerging techniques for malware behavior description are explored, especially the goals, principles, characteristics, and classifications of behavior analysis techniques proposed in the existing approaches. Second, the inadequacies and challenges in malware behavior analysis are summarized from different perspectives. Finally, several possible directions are discussed for future research.

Keywords： Malware behavior Static analysis Dynamic Analysis Behavior data expression Behavior analysis Machine learning Semantics-based analysis Behavior visualization Malware evolution

HTML PDF Collect

Title Author Date Type Operation

MPIN: a macro-pixel integration network for light field super-resolution

Xinya Wang, Jiayi Ma, Wenjing Gao, Junjun Jiang,wangxinya@whu.edu.cn,jyma2010@gmail.com,wenjinggao@whu.edu.cn,junjun0595@163.com

Journal Article

Uncertainty in Knowledge Representation

Li Deyi

Journal Article

Public key based bidirectional shadow image authentication without pixel expansion in image secret sharing

Xuehu YAN, Longlong LI, Jia CHEN, Lei SUN,publictiger@126.com

Journal Article

Analyzing the Effect of the Intra-Pixel Position of Small PSFs for Optimizing the PL of Optical Subpixel Localization

Haiyang Zhan, Fei Xing, Jingyu Bao, Ting Sun, Zhenzhen Chen, Zheng You, Li Yuan

Journal Article

Laplacian sparse dictionary learning for image classification based on sparse representation

Fang LI, Jia SHENG, San-yuan ZHANG

Journal Article

Semantic composition of distributed representations for query subtopic mining

Wei SONG, Ying LIU, Li-zhen LIU, Han-shi WANG

Journal Article

Syntactic word embedding based on dependency syntax and polysemous analysis

Zhong-lin YE, Hai-xing ZHAO

Journal Article

Principles and applications of high-speed single-pixelimaging technology

Qiang GUO, Yu-xi WANG, Hong-wei CHEN, Ming-hua CHEN, Si-gang YANG, Shi-zhong XIE

Journal Article

Federated unsupervised representation learning

Fengda ZHANG, Kun KUANG, Long CHEN, Zhaoyang YOU, Tao SHEN, Jun XIAO, Yin ZHANG, Chao WU, Fei WU, Yueting ZHUANG, Xiaolin LI,fdzhang@zju.edu.cn,kunkuang@zju.edu.cn

Journal Article

The Cryptographic Properties of Select Logic Functions

Liang Zeng,Li Shiqu

Journal Article

Dynamic parameterized learning for unsupervised domain adaptation

Runhua JIANG, Yahong HAN

Journal Article

Cyberspace Security Competition and Talent Management

Yu Xiangzhan,Zhang Hongli and Yu Haining、Tian Zhihong、Zhai Jianhong、Pan Zhuting

Journal Article

基于ARIMA和Kalman滤波的道路交通状态实时预测

东伟徐,永东王,利民贾,勇秦,宏辉董