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
Keywords: Generative adversarial network (GAN) Novelty detection Tennessee Eastman (TE) process
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
Keywords: Cantonese porcelain Classification Generative adversarial network Creative arts
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
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
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
Keywords: Co-creative drawing Deep learning Image generation
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
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
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
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
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
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
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
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
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
Keywords: Intra-cell communication Two-way relay Subcarrier assignment Subcarrier pairing
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
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
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
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
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
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
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
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
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
Keywords: Rotation operations Self-routing Control-bit generation algorithm Inverse butterfly network
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
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
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