Resource Type

Journal Article 468

Year

2024 1

2023 53

2022 47

2021 59

2020 55

2019 37

2018 36

2017 31

2016 36

2015 10

2014 1

2013 3

2012 3

2011 5

2010 1

2009 5

2008 9

2007 11

2006 10

2005 14

open ︾

Keywords

neural network 16

Deep learning 12

Artificial intelligence 9

Neural network 8

Machine learning 7

Software-defined networking (SDN) 7

cyberspace 5

cyberspace security 5

6G 4

ANN 3

Attention mechanism 3

BP neural network 3

Boolean control networks 3

Network security 3

Optimization 3

fuzzy sets 3

5G 2

Accelerator 2

Artificial intelligence (AI) 2

open ︾

Search scope:

排序： Display mode:

Generative adversarial network based novelty detection usingminimized reconstruction error Article

Huan-gang WANG, Xin LI, Tao ZHANG

Frontiers of Information Technology & Electronic Engineering 2018, Volume 19, Issue 1,   Pages 116-125 doi: 10.1631/FITEE.1700786

Abstract: Generative adversarial network (GAN) is the most exciting machine learning breakthrough in recent years, and it trains the learning model by finding the Nash equilibrium of a two-player zero-sum game. GAN is composed of a generator and a discriminator, both trained with the adversarial learning mechanism. In this paper, we introduce and investigate the use of GAN for novelty detection. In training, GAN learns from ordinary data. Then, using previously unknown data, the generator and the discriminator with the designed decision boundaries can both be used to separate novel patterns from ordinary patterns. The proposed GAN-based novelty detection method demonstrates a competitive performance on the MNIST digit database and the Tennessee Eastman (TE) benchmark process compared with the PCA-based novelty detection methods using Hotelling’s and squared prediction error statistics.

Keywords： Generative adversarial network (GAN)     Novelty detection     Tennessee Eastman (TE) process    

HTML PDF Collect

Cantonese porcelain classification and image synthesis by ensemble learning and generative adversarial network Special Feature on Intelligent Design

Steven Szu-Chi CHEN, Hui CUI, Ming-han DU, Tie-ming FU, Xiao-hong SUN, Yi JI, Henry DUH

Frontiers of Information Technology & Electronic Engineering 2019, Volume 20, Issue 12,   Pages 1632-1643 doi: 10.1631/FITEE.1900399

Abstract: Accurate recognition of modern and traditional porcelain styles is a challenging issue in Cantonese porcelain management due to the large variety and complex elements and patterns. We propose a hybrid system with porcelain style identification and image recreation modules. In the identification module, prediction of an unknown porcelain sample is obtained by logistic regression of ensembled neural networks of top-ranked design signatures, which are obtained by discriminative analysis and transformed features in principal components. The synthesis module is developed based on a conditional generative adversarial network, which enables users to provide a designed mask with porcelain elements to generate synthesized images of Cantonese porcelain. Experimental results of 603 Cantonese porcelain images demonstrate that the proposed model outperforms other methods relative to precision, recall, area under curve of receiver operating characteristic, and confusion matrix. Case studies on image creation indicate that the proposed system has the potential to engage the community in understanding Cantonese porcelain and promote this intangible cultural heritage.

Keywords： Cantonese porcelain     Classification     Generative adversarial network     Creative arts    

HTML PDF Collect

Deep 3D reconstruction: methods, data, and challenges Review Article

Caixia Liu, Dehui Kong, Shaofan Wang, Zhiyong Wang, Jinghua Li, Baocai Yin,lcxxib@emails.bjut.edu.cn,wangshaofan@bjut.edu.cn

Frontiers of Information Technology & Electronic Engineering 2021, Volume 22, Issue 5,   Pages 615-766 doi: 10.1631/FITEE.2000068

Abstract: Three-dimensional (3D) reconstruction of shapes is an important research topic in the fields of computer vision, computer graphics, pattern recognition, and virtual reality. Existing 3D reconstruction methods usually suffer from two bottlenecks: (1) they involve multiple manually designed states which can lead to cumulative errors, but can hardly learn semantic features of 3D shapes automatically; (2) they depend heavily on the content and quality of images, as well as precisely calibrated cameras. As a result, it is difficult to improve the reconstruction accuracy of those methods. 3D reconstruction methods based on deep learning overcome both of these bottlenecks by automatically learning semantic features of 3D shapes from low-quality images using deep networks. However, while these methods have various architectures, in-depth analysis and comparisons of them are unavailable so far. We present a comprehensive survey of 3D reconstruction methods based on deep learning. First, based on different deep learning model architectures, we divide 3D reconstruction methods based on deep learning into four types, , , , and based methods, and analyze the corresponding methodologies carefully. Second, we investigate four representative databases that are commonly used by the above methods in detail. Third, we give a comprehensive comparison of 3D reconstruction methods based on deep learning, which consists of the results of different methods with respect to the same database, the results of each method with respect to different databases, and the robustness of each method with respect to the number of views. Finally, we discuss future development of 3D reconstruction methods based on deep learning.

Keywords： 深度学习模型；三维重建；循环神经网络；深度自编码器；生成对抗网络；卷积神经网络    

HTML PDF Collect

SmartPaint: a co-creative drawing system based on generative adversarial networks Special Feature on Intelligent Design

Lingyun SUN, Pei CHEN, Wei XIANG, Peng CHEN, Wei-yue GAO, Ke-jun ZHANG

Frontiers of Information Technology & Electronic Engineering 2019, Volume 20, Issue 12,   Pages 1644-1656 doi: 10.1631/FITEE.1900386

Abstract: Artificial intelligence (AI) has played a significant role in imitating and producing large-scale designs such as e-commerce banners. However, it is less successful at creative and collaborative design outputs. Most humans express their ideas as rough sketches, and lack the professional skills to complete pleasing paintings. Existing AI approaches have failed to convert varied user sketches into artistically beautiful paintings while preserving their semantic concepts. To bridge this gap, we have developed SmartPaint, a co-creative drawing system based on generative adversarial networks (GANs), enabling a machine and a human being to collaborate in cartoon landscape painting. SmartPaint trains a GAN using triples of cartoon images, their corresponding semantic label maps, and edge detection maps. The machine can then simultaneously understand the cartoon style and semantics, along with the spatial relationships among the objects in the landscape images. The trained system receives a sketch as a semantic label map input, and automatically synthesizes its edge map for stable handling of varied sketches. It then outputs a creative and fine painting with the appropriate style corresponding to the human’s sketch. Experiments confirmed that the proposed SmartPaint system successfully generates high-quality cartoon paintings.

Keywords： Co-creative drawing     Deep learning     Image generation    

HTML PDF Collect

Adversarial Attacks and Defenses in Deep Learning Feature Article

Kui Ren, Tianhang Zheng, Zhan Qin, Xue Liu

Engineering 2020, Volume 6, Issue 3,   Pages 346-360 doi: 10.1016/j.eng.2019.12.012

Abstract:

With the rapid developments of artificial intelligence (AI) and deep learning (DL) techniques, it is critical
to ensure the security and robustness of the deployed algorithms. Recently, the security vulnerability of
DL algorithms to adversarial samples has been widely recognized. The fabricated samples can lead to various
misbehaviors of the DL models while being perceived as benign by humans. Successful implementations
of adversarial attacks in real physical-world scenarios further demonstrate their practicality.
Hence, adversarial attack and defense techniques have attracted increasing attention from both machine
learning and security communities and have become a hot research topic in recent years. In this paper,
we first introduce the theoretical foundations, algorithms, and applications of adversarial attack techniques.
We then describe a few research efforts on the defense techniques, which cover the broad frontier
in the field. Several open problems and challenges are subsequently discussed, which we hope will provoke
further research efforts in this critical area.

Keywords： Machine learning     Deep neural network Adversarial example     Adversarial attack     Adversarial defense    

HTML PDF Collect

Wasserstein GAN-Based Small-Sample Augmentation for New-Generation Artificial Intelligence: A Case Study of Cancer-Staging Data in Biology Article

Yufei Liu, Yuan Zhou, Xin Liu, Fang Dong, Chang Wang, Zihong Wang

Engineering 2019, Volume 5, Issue 1,   Pages 156-163 doi: 10.1016/j.eng.2018.11.018

Abstract:

It is essential to utilize deep-learning algorithms based on big data for the implementation of the new generation of artificial intelligence. Effective utilization of deep learning relies considerably on the number of labeled samples, which restricts the application of deep learning in an environment with a small sample size. In this paper, we propose an approach based on a generative adversarial network (GAN) combined with a deep neural network (DNN). First, the original samples were divided into a training set and a test set. The GAN was trained with the training set to generate synthetic sample data, which enlarged the training set. Next, the DNN classifier was trained with the synthetic samples. Finally, the classifier was tested with the test set, and the effectiveness of the approach for multi-classification with a small sample size was validated by the indicators. As an empirical case, the approach was then applied to identify the stages of cancers with a small labeled sample size. The experimental results verified that the proposed approach achieved a greater accuracy than traditional methods. This research was an attempt to transform the classical statistical machine-learning classification method based on original samples into a deep-learning classification method based on data augmentation. The use of this approach will contribute to an expansion of application scenarios for the new generation of artificial intelligence based on deep learning, and to an increase in application effectiveness. This research is also expected to contribute to the comprehensive promotion of new-generation artificial intelligence.

Keywords： Artificial intelligence     Generative adversarial network     Deep neural network     Small sample size     Cancer    

HTML PDF Collect

Calculation of the Behavior Utility of a Network System: Conception and Principle Article

Changzhen Hu

Engineering 2018, Volume 4, Issue 1,   Pages 78-84 doi: 10.1016/j.eng.2018.02.010

Abstract:

The service and application of a network is a behavioral process that is oriented toward its operations and tasks, whose metrics and evaluation are still somewhat of a rough comparison. This paper describes scenes of network behavior as differential manifolds. Using the homeomorphic transformation of smooth differential manifolds, we provide a mathematical definition of network behavior and propose a mathematical description of the network behavior path and behavior utility. Based on the principle of differential geometry, this paper puts forward the function of network behavior and a calculation method to determine behavior utility, and establishes the calculation principle of network behavior utility. We also provide a calculation framework for assessment of the network’s attack-defense confrontation on the strength of behavior utility. Therefore, this paper establishes a mathematical foundation for the objective measurement and precise evaluation of network behavior.

Keywords： Network metric evaluation     Differential manifold     Network behavior utility     Network attack-defense confrontation    

HTML PDF Collect

A Geometric Understanding of Deep Learning Article

Na Lei, Dongsheng An, Yang Guo, Kehua Su, Shixia Liu, Zhongxuan Luo, Shing-Tung Yau, Xianfeng Gu

Engineering 2020, Volume 6, Issue 3,   Pages 361-374 doi: 10.1016/j.eng.2019.09.010

Abstract:

This work introduces an optimal transportation (OT) view of generative adversarial networks (GANs). Natural datasets have intrinsic patterns, which can be summarized as the manifold distribution principle: the distribution of a class of data is close to a low-dimensional manifold. GANs mainly accomplish two tasks: manifold learning and probability distribution transformation. The latter can be carried out using the classical OT method. From the OT perspective, the generator computes the OT map, while the discriminator computes the Wasserstein distance between the generated data distribution and the real data distribution; both can be reduced to a convex geometric optimization process. Furthermore, OT theory discovers the intrinsic collaborative—instead of competitive—relation between the generator and the discriminator, and the fundamental reason for mode collapse. We also propose a novel generative model, which uses an autoencoder (AE) for manifold learning and OT map for probability distribution transformation. This AE–OT model improves the theoretical rigor and transparency, as well as the computational stability and efficiency; in particular, it eliminates the mode collapse. The experimental results validate our hypothesis, and demonstrate the advantages of our proposed model.

Keywords： Generative     Adversarial     Deep learning     Optimal transportation     Mode collapse    

HTML PDF Collect

Anovel resource optimization scheme for multi-cellOFDMArelay network Article

Ning DU,Fa-sheng LIU

Frontiers of Information Technology & Electronic Engineering 2016, Volume 17, Issue 8,   Pages 825-833 doi: 10.1631/FITEE.1500294

Abstract: In cellular networks, users communicate with each other through their respective base stations (BSs). Conventionally, users are assumed to be in different cells. BSs serve as decode-and-forward (DF) relay nodes to users. In addition to this type of conventional user, we recognize that there are scenarios users who want to communicate with each other are located in the same cell. This gives rise to the scenario of intra-cell communication. In this case, a BS can behave as a two-way relay to achieve information exchange instead of using conventional DF relay. We consider a multi-cell orthogonal frequency division multiple access (OFDMA) network that comprises these two types of users. We are interested in resource allocation between them. Specifically, we jointly optimize subcarrier assignment, subcarrier pairing, and power allocation to maximize the weighted sum rate. We consider the resource allocation problem at BSs when the end users’ power is fixed. We solve the problem approximately through Lagrange dual decomposition. Simulation results show that the proposed schemes outperform other existing schemes.

Keywords： Intra-cell communication     Two-way relay     Subcarrier assignment     Subcarrier pairing    

HTML PDF Collect

Learning Rat-Like Behavior for a Small-Scale Biomimetic Robot

Zihang Gao, Guanglu Jia, Hongzhao Xie, Qiang Huang, Toshio Fukuda, Qing Shi

Engineering 2022, Volume 17, Issue 10,   Pages 232-243 doi: 10.1016/j.eng.2022.05.012

Abstract:

Existing biomimetic robots can perform some basic rat-like movement primitives (MPs) and simple behavior with stiff combinations of these MPs. To mimic typical rat behavior with high similarity, we propose parameterizing the behavior using a probabilistic model and movement characteristics. First, an analysis of fifteen 10min video sequences revealed that an actual rat has six typical behaviors in the open
field, and each kind of behavior contains different bio-inspired combinations of eight MPs. We used the softmax classifier to obtain the behavior-movement hierarchical probability model. Secondly, we specified the MPs using movement parameters that are static and dynamic. We obtained the predominant values of the static and dynamic movement parameters using hierarchical clustering and fuzzy C-means
clustering, respectively. These predominant parameters were used for fitting the rat spinal joint trajectory using a second-order Fourier series, and the joint trajectory was generalized using a back propagation neural network with two hidden layers. Finally, the hierarchical probability model and the generalized joint trajectory were mapped to the robot as control policy and commands, respectively. We implemented the six typical behaviors on the robot, and the results show high similarity when compared with the behaviors of actual rats.

Keywords： Biomimetic     Bio-inspired robot     Neural network learning system     Behavior generation    

HTML PDF Collect

Study of Topology Control Based on Genetic Algorithm in Wireless Sensor Networks

Liu Linfeng,zhuanyanyan,Liu Ye

Strategic Study of CAE 2008, Volume 10, Issue 2,   Pages 66-71

Abstract:

The chief objective of wireless sensor networks designing is to pr ol ong the lifetime of networks, and topology control is the basic support for the objective. Aiming at the defect is that high redundancy of connectivity or low r obu st of structure in traditional methods, the problem was transformed into a model of multi-criteria minimum spanning tree ultimately, and a genetic algorithm wa s designed to deal with the model. A topology control method based on genetic alg orithm was proposed in this paper. The result of simulations suggests a topology with low total power consumption, high robust structure and low contention amon g nodes can be obtained by this method, and the lifetime of networks can be prol onged on the topology.

Keywords： wireless sensor network     topology control     multi-criteria minimum spanning tree problems     genetic algorithm    

HTML PDF Collect

Trends and Management of Harmful Information around the World

Jia Yan1,Li Aiping and Li Yuxiao、Li Shudong、Tian Zhihong、Han Yi、Shi Jinqiao、Lin Bin

Strategic Study of CAE 2016, Volume 18, Issue 6,   Pages 94-98 doi: 10.15302/J-SSCAE-2016.06.019

Abstract:

In view of the management needs of all kinds of harmful information (including terrorism, rumor, fraud, violence, pornography, and subversion) in cyberspace, this paper summarizes the management situation of harmful information around the world. The paper first introduces the definition and classification of harmful information. It then proposes laws and regulations for the supervision of harmful information, and expounds the regulations that countries generally adopt in their legislative practice. Next, starting from network data monitoring, information filtering, and public opinion against network management, this paper introduces the technology and means of network governance over harmful information. Finally, this paper describes recent global internal Internet governance special action, and so forth.

Keywords： cyberspace     harmful information     information censorship     information filtering     confrontation of public opinion    

HTML PDF Collect

Brain Encoding and Decoding in fMRI with Bidirectional Deep Generative Models Review

Changde Du, Jinpeng Li, Lijie Huang, Huiguang He

Engineering 2019, Volume 5, Issue 5,   Pages 948-953 doi: 10.1016/j.eng.2019.03.010

Abstract:

Brain encoding and decoding via functional magnetic resonance imaging (fMRI) are two important aspects of visual perception neuroscience. Although previous researchers have made significant advances in brain encoding and decoding models, existing methods still require improvement using advanced machine learning techniques. For example, traditional methods usually build the encoding and decoding models separately, and are prone to overfitting on a small dataset. In fact, effectively unifying the encoding and decoding procedures may allow for more accurate predictions. In this paper, we first review the existing encoding and decoding methods and discuss
the potential advantages of a "bidirectional" modeling strategy. Next, we show that there are correspondences between deep neural networks and human visual streams in terms of the architecture and computational rules Furthermore, deep generative models (e.g., variational autoencoders (VAEs) and generative adversarial networks (GANs)) have produced promising results in studies on brain encoding and decoding. Finally, we propose that the dual learning method, which was originally designed for machine translation tasks, could help to improve the performance of encoding and decoding models by leveraging large-scale unpaired data.

Keywords： Brain encoding and decoding     Functional magnetic resonance imaging     Deep neural networks     Deep generative models     Dual learning    

HTML PDF Collect

A highly efficient reconfigurable rotation unit based on an inverse butterfly network Article

Chao MA, Zi-bin DAI, Wei LI, Hai-juan ZANG

Frontiers of Information Technology & Electronic Engineering 2017, Volume 18, Issue 11,   Pages 1784-1794 doi: 10.1631/FITEE.1601265

Abstract: We propose a reconfigurable control-bit generation algorithm for rotation and sub-word rotation operations. The algorithm uses a self-routing characteristic to configure an inverse butterfly network. In addition to being highly parallelized and inexpensive, the algorithm integrates the rotation-shift, bi-directional rotation-shift, and sub-word rotation-shift operations. To our best knowledge, this is the first scheme to accommodate a variety of rotation operations into the same architecture. We have developed the highly efficient reconfigurable rotation unit (HERRU) and synthesized it into the Semiconductor Manufacturing International Corporation (SMIC)’s 65-nm process. The results show that the overall efficiency (relative area×relative latency) of our HERRU is higher by at least 23% than that of other designs with similar functions. When executing the bi-directional rotation operations alone, HERRU occupies a significantly smaller area with a lower latency than previously proposed designs.

Keywords： Rotation operations     Self-routing     Control-bit generation algorithm     Inverse butterfly network    

HTML PDF Collect

Underwater Attack–Defense Confrontation System and Its Future Development

Xie Wei, Yang Meng, Gong Junbin

Strategic Study of CAE 2019, Volume 21, Issue 6,   Pages 71-79 doi: 10.15302/J-SSCAE-2019.06.014

Abstract:

As an important development direction of naval warfare, the underwater attack–defense confrontation system integrates underwater warning, scout, detection, attack, defense and a series of other operations. Currently, although underwater offensive and defensive weapons have developed rapidly, research on the capacity building, combat styles, and development priorities of the confrontation system still lacks. This paper first summarizes the status quo of underwater confrontation system construction in some military powers, and analyzes the functional composition and typical combat styles of the future underwater attack–defense confrontation system. Furthermore, it systematically studies the development directions of the future confrontation system, and proposes corresponding suggestions for the development of the underwater attack–defense system and equipment, including improving integrated perception and navigation, developing unified command and control, and promoting military-civilian integration.

Keywords： underwater attack and defense     confrontation system     coordinated combat     unmanned system    

HTML PDF Collect

Title Author Date Type Operation

Generative adversarial network based novelty detection usingminimized reconstruction error

Huan-gang WANG, Xin LI, Tao ZHANG

Journal Article

Cantonese porcelain classification and image synthesis by ensemble learning and generative adversarial network

Steven Szu-Chi CHEN, Hui CUI, Ming-han DU, Tie-ming FU, Xiao-hong SUN, Yi JI, Henry DUH

Journal Article

Deep 3D reconstruction: methods, data, and challenges

Caixia Liu, Dehui Kong, Shaofan Wang, Zhiyong Wang, Jinghua Li, Baocai Yin,lcxxib@emails.bjut.edu.cn,wangshaofan@bjut.edu.cn

Journal Article

SmartPaint: a co-creative drawing system based on generative adversarial networks

Lingyun SUN, Pei CHEN, Wei XIANG, Peng CHEN, Wei-yue GAO, Ke-jun ZHANG

Journal Article

Adversarial Attacks and Defenses in Deep Learning

Kui Ren, Tianhang Zheng, Zhan Qin, Xue Liu

Journal Article

Wasserstein GAN-Based Small-Sample Augmentation for New-Generation Artificial Intelligence: A Case Study of Cancer-Staging Data in Biology

Yufei Liu, Yuan Zhou, Xin Liu, Fang Dong, Chang Wang, Zihong Wang

Journal Article

Calculation of the Behavior Utility of a Network System: Conception and Principle

Changzhen Hu

Journal Article

A Geometric Understanding of Deep Learning

Na Lei, Dongsheng An, Yang Guo, Kehua Su, Shixia Liu, Zhongxuan Luo, Shing-Tung Yau, Xianfeng Gu

Journal Article

Anovel resource optimization scheme for multi-cellOFDMArelay network

Ning DU,Fa-sheng LIU

Journal Article

Learning Rat-Like Behavior for a Small-Scale Biomimetic Robot

Zihang Gao, Guanglu Jia, Hongzhao Xie, Qiang Huang, Toshio Fukuda, Qing Shi

Journal Article

Study of Topology Control Based on Genetic Algorithm in Wireless Sensor Networks

Liu Linfeng,zhuanyanyan,Liu Ye

Journal Article

Trends and Management of Harmful Information around the World

Jia Yan1,Li Aiping and Li Yuxiao、Li Shudong、Tian Zhihong、Han Yi、Shi Jinqiao、Lin Bin

Journal Article

Brain Encoding and Decoding in fMRI with Bidirectional Deep Generative Models

Changde Du, Jinpeng Li, Lijie Huang, Huiguang He

Journal Article

A highly efficient reconfigurable rotation unit based on an inverse butterfly network

Chao MA, Zi-bin DAI, Wei LI, Hai-juan ZANG

Journal Article

Underwater Attack–Defense Confrontation System and Its Future Development

Xie Wei, Yang Meng, Gong Junbin

Journal Article