Search scope:
排序: Display mode:
Dynamic value iteration networks for the planning of rapidly changing UAV swarms Research Articles
Wei Li, Bowei Yang, Guanghua Song, Xiaohong Jiang,li2ui2@zju.edu.cn,boweiy@zju.edu.cn,ghsong@zju.edu.cn,jiangxh@zju.edu.cn
Frontiers of Information Technology & Electronic Engineering 2021, Volume 22, Issue 5, Pages 615-766 doi: 10.1631/FITEE.1900712
Keywords: 动态值迭代网络;场景式Q学习;无人机自组网;NSGA-II;路径规划
Binary neural networks for speech recognition Regular Papers
Yan-min QIAN, Xu XIANG
Frontiers of Information Technology & Electronic Engineering 2019, Volume 20, Issue 5, Pages 701-715 doi: 10.1631/FITEE.1800469
Recently, deep neural networks (DNNs) significantly outperform Gaussian mixture models in acoustic modeling for speech recognition. However, the substantial increase in computational load during the inference stage makes deep models difficult to directly deploy on low-power embedded devices. To alleviate this issue, structure sparseness and low precision fixed-point quantization have been applied widely. In this work, binary neural networks for speech recognition are developed to reduce the computational cost during the inference stage. A fast implementation of binary matrix multiplication is introduced. On modern central processing unit (CPU) and graphics processing unit (GPU) architectures, a 5–7 times speedup compared with full precision floatingpoint matrix multiplication can be achieved in real applications. Several kinds of binary neural networks and related model optimization algorithms are developed for large vocabulary continuous speech recognition acoustic modeling. In addition, to improve the accuracy of binary models, knowledge distillation from the normal full precision floating-point model to the compressed binary model is explored. Experiments on the standard Switchboard speech recognition task show that the proposed binary neural networks can deliver 3–4 times speedup over the normal full precision deep models. With the knowledge distillation from the normal floating-point models, the binary DNNs or binary convolutional neural networks (CNNs) can restrict the word error rate (WER) degradation to within 15.0%, compared to the normal full precision floating-point DNNs or CNNs, respectively. Particularly for the binary CNN with binarization only on the convolutional layers, the WER degradation is very small and is almost negligible with the proposed approach.
Keywords: Speech recognition Binary neural networks Binary matrix multiplication Knowledge distillation Population count
The Forward Recurrent Method for Dynamic Programming
Zhang Zhao,Pei Yanling,Zhang Renbao
Strategic Study of CAE 2005, Volume 7, Issue 2, Pages 62-65
Backward recurrent method is usually adopted in seeking optimal solution by dynamic programming. A forward recurrent method to find optimal solution by dynamic programming is presented on the basis of an instance. The fundamental equation of dynamic programming and Millton-Jacobi's equation are also derived. It's an exploratory study on optimal solution of dynamic programming. An amount of work is reduced in calculating by using forward recurrent method, while applied range of the method is expanded.
Keywords: dynamic programming multi-level decision functional equation optimal solution
A novel multiple-outlier-robust Kalman filter Research Articles
Yulong HUANG, Mingming BAI, Yonggang ZHANG,heuedu@163.com,mingming.bai@hrbeu.edu.cn,zhangyg@hrbeu.edu.cn
Frontiers of Information Technology & Electronic Engineering 2022, Volume 23, Issue 3, Pages 422-437 doi: 10.1631/FITEE.2000642
Keywords: Kalman filtering Multiple statistical similarity measure Multiple outliers Fixed-point iteration State estimate
Asurvey on complex dynamical networkswith impulsive effects Review Articles
Xiu-ping HAN, Yong-shun ZHAO, Xiao-di LI
Frontiers of Information Technology & Electronic Engineering 2020, Volume 21, Issue 2, Pages 199-219 doi: 10.1631/FITEE.1900456
Keywords: Complex dynamical networks Synchronizing impulses Desynchronizing impulses Pinning control Time delay
Dynamic aspects of domination networks Personal View
Yu-xian LIU, Ronald ROUSSEAU
Frontiers of Information Technology & Electronic Engineering 2020, Volume 21, Issue 4, Pages 635-648 doi: 10.1631/FITEE.1800553
Keywords: Domination Power structure Digraphs Network dynamics
The Dynamic Functional Network Connectivity Analysis Framework
Zening Fu, Yuhui Du, Vince D. Calhoun
Engineering 2019, Volume 5, Issue 2, Pages 190-193 doi: 10.1016/j.eng.2018.10.001
Chenxi Li, Lei Guan, Huaqing Wu, Nan Cheng, Zan Li, Xuemin Sherman Shen
Engineering 2022, Volume 17, Issue 10, Pages 220-231 doi: 10.1016/j.eng.2021.04.019
Heterogeneous cellular networks (HCNs) are envisioned as a promising architecture to provide seamless wireless coverage and increase network capacity. However, the densified multi-tier network architecture introduces excessive intra- and cross-tier interference and makes HCNs vulnerable to eavesdropping attacks. In this article, a dynamic spectrum control (DSC)-assisted transmission scheme is proposed for HCNs to strengthen network security and increase the network capacity. Specifically, the proposed DSC-assisted transmission scheme leverages the idea of block cryptography to generate sequence families, which represent the transmission decisions, by performing iterative and orthogonal sequence transformations. Based on the sequence families, multiple users can dynamically occupy different frequency slots for data transmission simultaneously. In addition, the collision probability of the data transmission is analyzed, which results in closed-form expressions of the reliable transmission probability and the secrecy probability. Then, the upper and lower bounds of network capacity are further derived with given requirements on the reliable and secure transmission probabilities. Simulation results demonstrate that the proposed DSC-assisted scheme can outperform the benchmark scheme in terms of security performance. Finally, the impacts of key factors in the proposed DSC-assisted scheme on the network capacity and security are evaluated and discussed.
Keywords: Heterogeneous cellular networks Dynamic spectrum control Transmission security Efficient data transmission
Cyberspace Endogenous Safety and Security Article
Jiangxing Wu
Engineering 2022, Volume 15, Issue 8, Pages 179-185 doi: 10.1016/j.eng.2021.05.015
Uncertain security threats caused by vulnerabilities and backdoors are the most serious and difficult problem in cyberspace. This paper analyzes the philosophical and technical causes of the existence of so-called “dark functions” such as system vulnerabilities and backdoors, and points out that endogenous security problems cannot be completely eliminated at the theoretical and engineering levels; rather, it is necessary to develop or utilize the endogenous security functions of the system architecture itself. In addition, this paper gives a definition for and lists the main technical characteristics of endogenous safety and security in cyberspace, introduces endogenous security mechanisms and characteristics based on dynamic heterogeneous redundancy (DHR) architecture, and describes the theoretical implications of a coding channel based on DHR.
Keywords: Cyberspace endogenous security problem Uncertain threat Cyberspace endogenous safety and security Relative right axiom Dynamic heterogeneous redundant architecture
A creative concept for designing and simulating quaternary logic gates in quantum-dot cellular automata Research Articles
Alireza Navidi, Reza Sabbaghi-Nadooshan, Massoud Dousti,alireza.navidi@srbiau.ac.ir,r_sabbaghi@iauctb.ac.ir,m_dousti@srbiau.ac.ir
Frontiers of Information Technology & Electronic Engineering 2021, Volume 22, Issue 11, Pages 1441-1550 doi: 10.1631/FITEE.2000590
Keywords: 量子点细胞自动机(QCA);四值逻辑;量子点细胞自动模拟器(QCASim);四值QCA(QQCA);四值译码器;四值门
Minimax Q-learning design for H∞ control of linear discrete-time systems Research Articles
Xinxing LI, Lele XI, Wenzhong ZHA, Zhihong PENG,lixinxing_1006@163.com,xilele.bit@gmail.com,zhawenzhong@126.com,peng@bit.edu.cn
Frontiers of Information Technology & Electronic Engineering 2022, Volume 23, Issue 3, Pages 438-451 doi: 10.1631/FITEE.2000446
Keywords: H∞ control Zero-sum dynamic game Reinforcement learning Adaptive dynamic programming Minimax Q-learning Policy iteration
RCAnalyzer: visual analytics of rare categories in dynamic networks Research
Jia-cheng PAN, Dong-ming HAN, Fang-zhou GUO, Da-wei ZHOU, Nan CAO, Jing-rui HE, Ming-liang XU, Wei CHEN
Frontiers of Information Technology & Electronic Engineering 2020, Volume 21, Issue 4, Pages 491-506 doi: 10.1631/FITEE.1900310
Keywords: Rare category detection Dynamic network Visual analytics
Cyber Resilience Enabled by Endogenous Safety and Security: Vision, Techniques, and Strategies
Wu Jiangxing , Zou Hong , Xue Xiangyang , Zhang Fan , Shang Yuting
Strategic Study of CAE 2023, Volume 25, Issue 6, Pages 106-115 doi: 10.15302/J-SSCAE-2023.06.018
Cyber resiliency engineering is a technical approach embraced by countries and regions such as the United States and Europe to implement digital transformation and address network security challenges under new circumstances. It aims to keep the barriers to entry high for digital technologies based on the cyber resilience standard and to improve the digital infrastructure security capability of China from both the application service and device supply sides. This study focuses on the impact and challenges brought by the initiatives of cyber resiliency engineering in the United States and Europe on the development of new-generation network information technology in China. It starts from a concept introduction of resilience, cyber resilience, and cyber resiliency engineering. Subsequently, it elaborates on the application progress of cyber resiliency engineering in the United States and Europe in terms of policy drivers, strategic considerations, and development dilemmas. Moreover, the study goes further to propose a dynamic heterogeneous redundancy architecture based on an endogenous security and safety (ESS) theory. It describes and illustrates the intrinsic mechanism, basic concepts, and application methods of cyber resilience empowered by ESS. Furthermore, we propose that China should accelerate innovation to offset the combined effects of cyber resiliency engineering in developed countries, introduce a cyber resilience policy and law system with Chinese characteristics, establish corresponding regulatory systems to clarify the network security responsibilities, establish a quantifiable, verifiable, and credible testing and evaluation system, and boost the holistic implementation of cyber resilience with a multi-pronged approach including financial marketization, hoping to ystematically enhance the cyber resilience and strength of China.
Keywords: cyberspace endogenous safety and security cyber resilience structure encryption dynamic heterogeneous redundancy architecture
Yang CHEN, Hong-chao HU, Guo-zhen CHENG
Frontiers of Information Technology & Electronic Engineering 2019, Volume 20, Issue 2, Pages 238-252 doi: 10.1631/FITEE.1800516
Although the perimeter security model works well enough when all internal hosts are credible, it is becoming increasingly difficult to enforce as companies adopt mobile and cloud technologies, i.e., the rise of bring your own device (BYOD). It is observed that advanced targeted cyber-attacks usually follow a cyber kill chain; for instance, advanced targeted attacks often rely on network scanning techniques to gather information about potential targets. In response to this attack method, we propose a novel approach, i.e., an “isolating and dynamic” cyber defense, which cuts these potential chains to reduce the cumulative availability of the gathered information. First, we build a zero-trust network environment through network isolation, and then multiple network properties are maneuvered so that the host characteristics and locations needed to identify vulnerabilities cannot be located. Second, we propose a software-defined proactive cyber defense solution (SPD) for enterprise networks and design a general framework to strategically maneuver the IP address, network port, domain name, and path, while limiting the performance impact on the benign network user. Third, we implement our SPD proof-of-concept system over a software-defined network controller (OpenDaylight). Finally, we build an experimental platform to verify the system’s ability to prevent scanning, eavesdropping, and denial-of-service attacks. The results suggest that our system can significantly reduce the availability of network reconnaissance scan information, block network eavesdropping, and sharply increase the cost of cyber-attacks.
Keywords: Intranet defense Software-defined network Multi-dimensional maneuvering
Motion planning of a quadrotor robot game using a simulation-based projected policy iteration method Regular Papers
Li-dong ZHANG, Ban WANG, Zhi-xiang LIU, You-min ZHANG, Jian-liang AI
Frontiers of Information Technology & Electronic Engineering 2019, Volume 20, Issue 4, Pages 525-537 doi: 10.1631/FITEE.1800571
Making rational decisions for sequential decision problems in complex environments has been challenging researchers in various fields for decades. Such problems consist of state transition dynamics, stochastic uncertainties, long-term utilities, and other factors that assemble high barriers including the curse of dimensionality. Recently, the state-of-the-art algorithms in reinforcement learning studies have been developed, providing a strong potential to efficiently break the barriers and make it possible to deal with complex and practical decision problems with decent performance. We propose a formulation of a velocity varying one-on-one quadrotor robot game problem in the threedimensional space and an approximate dynamic programming approach using a projected policy iteration method for learning the utilities of game states and improving motion policies. In addition, a simulation-based iterative scheme is employed to overcome the curse of dimensionality. Simulation results demonstrate that the proposed decision strategy can generate effective and efficient motion policies that can contend with the opponent quadrotor and gather advantaged status during the game. Flight experiments, which are conducted in the Networked Autonomous Vehicles (NAV) Lab at the Concordia University, have further validated the performance of the proposed decision strategy in the real-time environment.
Keywords: Reinforcement learning Approximate dynamic programming Decision making Motion planning Unmanned aerial vehicle
Title Author Date Type Operation
Dynamic value iteration networks for the planning of rapidly changing UAV swarms
Wei Li, Bowei Yang, Guanghua Song, Xiaohong Jiang,li2ui2@zju.edu.cn,boweiy@zju.edu.cn,ghsong@zju.edu.cn,jiangxh@zju.edu.cn
Journal Article
The Forward Recurrent Method for Dynamic Programming
Zhang Zhao,Pei Yanling,Zhang Renbao
Journal Article
A novel multiple-outlier-robust Kalman filter
Yulong HUANG, Mingming BAI, Yonggang ZHANG,heuedu@163.com,mingming.bai@hrbeu.edu.cn,zhangyg@hrbeu.edu.cn
Journal Article
Asurvey on complex dynamical networkswith impulsive effects
Xiu-ping HAN, Yong-shun ZHAO, Xiao-di LI
Journal Article
The Dynamic Functional Network Connectivity Analysis Framework
Zening Fu, Yuhui Du, Vince D. Calhoun
Journal Article
Dynamic Spectrum Control-Assisted Secure and Efficient Transmission Scheme in Heterogeneous Cellular Networks
Chenxi Li, Lei Guan, Huaqing Wu, Nan Cheng, Zan Li, Xuemin Sherman Shen
Journal Article
A creative concept for designing and simulating quaternary logic gates in quantum-dot cellular automata
Alireza Navidi, Reza Sabbaghi-Nadooshan, Massoud Dousti,alireza.navidi@srbiau.ac.ir,r_sabbaghi@iauctb.ac.ir,m_dousti@srbiau.ac.ir
Journal Article
Minimax Q-learning design for H∞ control of linear discrete-time systems
Xinxing LI, Lele XI, Wenzhong ZHA, Zhihong PENG,lixinxing_1006@163.com,xilele.bit@gmail.com,zhawenzhong@126.com,peng@bit.edu.cn
Journal Article
RCAnalyzer: visual analytics of rare categories in dynamic networks
Jia-cheng PAN, Dong-ming HAN, Fang-zhou GUO, Da-wei ZHOU, Nan CAO, Jing-rui HE, Ming-liang XU, Wei CHEN
Journal Article
Cyber Resilience Enabled by Endogenous Safety and Security: Vision, Techniques, and Strategies
Wu Jiangxing , Zou Hong , Xue Xiangyang , Zhang Fan , Shang Yuting
Journal Article
Design and implementation of a novel enterprise network defense system bymaneuveringmulti-dimensional network properties
Yang CHEN, Hong-chao HU, Guo-zhen CHENG
Journal Article