Search scope:
排序: Display mode:
An artificial intelligence enhanced star identification algorithm
Hao Wang, Zhi-yuan Wang, Ben-dong Wang, Zhuo-qun Yu, Zhong-he Jin, John L. Crassidis,roger@zju.edu.cn
Frontiers of Information Technology & Electronic Engineering 2020, Volume 21, Issue 11, Pages 1535-1670 doi: 10.1631/FITEE.1900590
Keywords: 星敏感器;姿态失锁;星图识别;卷积神经网络
Marine target detection based on Marine-Faster R-CNN for navigation radar plane position indicator images Research Article
Xiaolong CHEN, Xiaoqian MU, Jian GUAN, Ningbo LIU, Wei ZHOU,cxlcxl1209@163.com,guanjian_68@163.com
Frontiers of Information Technology & Electronic Engineering 2022, Volume 23, Issue 4, Pages 630-643 doi: 10.1631/FITEE.2000611
Keywords: Marine target detection Navigation radar Plane position indicator (PPI) images Convolutional neural network (CNN) Faster R-CNN (region convolutional neural network) method
Recent advances in efficient computation of deep convolutional neural networks Review
Jian CHENG, Pei-song WANG, Gang LI, Qing-hao HU, Han-qing LU
Frontiers of Information Technology & Electronic Engineering 2018, Volume 19, Issue 1, Pages 64-77 doi: 10.1631/FITEE.1700789
Keywords: Deep neural networks Acceleration Compression Hardware accelerator
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
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
Fault Pattern Recognition of Rolling Bearing Based on Radial Basis Function Neural Networks
Lu Shuang,Zhang Zida,Li Meng
Strategic Study of CAE 2004, Volume 6, Issue 2, Pages 56-60
Radial basis function neural network is a type of three — layer feedforward network. It has many good properties, such as powerful ability for function approximation, classification and learning rapidly. In this paper, in the light of the merit of radial basis function neural network and on the basis of the feature analysis of vibration signal of rolling bearing, AR model is presented by using time series method. Radial basis function neural networks is established based on AR model parameters. In the light of the theory of radial basis function neural networks, fault pattern of rolling bearing is recognized correspondingly. Theory and experiment show that the recognition of fault pattern of rolling bearing based on radial basis function neural networks theory is available and its precision is high.
Keywords: rolling bearing vibration signal AR model RBF neural networks pattern recognition
Learning and Applications of Procedure Neural Networks
He Xingui,Liang Jiuzhen,Xu Shaohua
Strategic Study of CAE 2001, Volume 3, Issue 4, Pages 31-35
This paper deals with learning algorithms for procedure neural networks (PNN) and its applications in aggregation chemical reaction and seepage test in oil geology. Weight bases selection rules and pattern curve standard problems are also discussed. These examples show that PNN have extensive applications.
Keywords: procedure neural networks learning algorithm pattern recognition chemical reaction seepage
Current Source Active Power Filter Control UsingNeural Network Technologies
Wang Ping,Zhang Ke, Xu Huijun
Strategic Study of CAE 2007, Volume 9, Issue 1, Pages 40-43
In this paper,the application of neural network to power converter control is discussed.A new hysteresis comparator constructed by using neural network is introduced.Hysteresis band control is an effective and simple control method.It can easily run without many system parameters.But the switch frequency of system is not fixed.So it not only makes the system unstable but also may lessen the life span of the switches. The control method that combines the neural network technology with the hysteresis band technology has a high performance in response of current.Through training the neural network can learn the control rules by itself and can replace the real hysteresis comparator in power converter control.The computer simulation results are given in this paper and they can demonstrate the effectiveness of the proposed method.The neural network is realized by using DSP.
Keywords: source filter neural network hysteresis comparator
A partition approach for robust gait recognition based on gait template fusion Research Articles
Kejun Wang, Liangliang Liu, Xinnan Ding, Kaiqiang Yu, Gang Hu,heukejun@126.com,liuliangliang@hrbeu.edu.cn,dingxinnan@hrbeu.edu.cn,yukaiqiang@hrbeu.edu.cn,hugang@hrbeu.edu.cn
Frontiers of Information Technology & Electronic Engineering 2021, Volume 22, Issue 5, Pages 615-766 doi: 10.1631/FITEE.2000377
Hydrogeological Parameter Identification Based on the Radial Basis Function Neural Networks
Zhang Junyan,Wei Lianwei,Han Weixiu,Shao Jingli,Cui Yali,Zhang Jianli
Strategic Study of CAE 2004, Volume 6, Issue 8, Pages 74-78
The problem of hydrogeological parameter identification is actually a complex one. With the limit of identifying the parameter by traditional methods, the radial basis function neural networks (RBF) is applied into this area. Not only the parameter identification is automatically realized, but also th.e problem of local optimization is solved. The feasibility and effectiveness have been proved by the examples.
Keywords: groundwater hydrogeological parameter radial basis function (RBF) neural networks BP neural networks
A novel method based on convolutional neural networks for deriving standard 12-lead ECG from serial 3-lead ECG Regular Papers
Lu-di WANG, Wei ZHOU, Ying XING, Na LIU, Mahmood MOVAHEDIPOUR, Xiao-guang ZHOU
Frontiers of Information Technology & Electronic Engineering 2019, Volume 20, Issue 3, Pages 405-413 doi: 10.1631/FITEE.1700413
Reconstruction of a 12-lead electrocardiogram (ECG) from a serial 3-lead ECG has been researched in the past to satisfy the need for more wearing comfort and ambulatory situations. The accuracy and real-time performance of traditional methods need to be improved. In this study, we present a novel method based on convolutional neural networks (CNNs) for the synthesis of missing precordial leads. The results show that the proposed method receives better similarity and consumes less time using the PTB database. Particularly, the presented method shows outstanding performance in reconstructing the pathological ECG signal, which is crucial for cardiac diagnosis. Our CNN-based method is shown to be more accurate and time-saving for deployment in non-hospital situations to synthesize a standard 12-lead ECG from a reduced lead-set ECG recording. This is promising for real cardiac care.
Keywords: Convolutional neural networks (CNNs) Electrocardiogram (ECG) synthesis E-health
A Survey of Accelerator Architectures for Deep Neural Networks Review
Yiran Chen, uan Xie, Linghao Song, Fan Chen, Tianqi Tang
Engineering 2020, Volume 6, Issue 3, Pages 264-274 doi: 10.1016/j.eng.2020.01.007
Recently, due to the availability of big data and the rapid growth of computing power, artificial intelligence (AI) has regained tremendous attention and investment. Machine learning (ML) approaches have been successfully applied to solve many problems in academia and in industry. Although the explosion of big data applications is driving the development of ML, it also imposes severe challenges of data processing speed and scalability on conventional computer systems. Computing platforms that are dedicatedly designed for AI applications have been considered, ranging from a complement to von Neumann platforms to a “must-have” and standalone technical solution. These platforms, which belong to a larger category named “domain-specific computing,” focus on specific customization for AI. In this article, we focus on summarizing the recent advances in accelerator designs for deep neural networks (DNNs)—that is, DNN accelerators. We discuss various architectures that support DNN executions in terms of computing units, dataflow optimization, targeted network topologies, architectures on emerging technologies, and accelerators for emerging applications. We also provide our visions on the future trend of AI chip designs.
Keywords: Deep neural network Domain-specific architecture Accelerator
Processing and analysis of data from microwave humidity sounder onboard FY-3A satellite
He Jieying,Zhang Shengwei
Strategic Study of CAE 2013, Volume 15, Issue 10, Pages 47-53
Microwave humidity sounder (MWHS) is one of payloads on the Fengyun-3A (FY-3A) satellite. This paper introduces its structure, operation status and data receiving and processing. The paper constructs an inversion model using artificial neural network (ANN) algorithm, and makes comparison with advanced microwave sounding unit advanced microwave sounding unit-B(AMSU-B). The results demonstrate that the model can be operated successfully. Using the simulated brightness temperatures from MWHS from July to December in 2008 in Beijing, the paper derives water vapor density profiles and gives analysis of root mean square. Meanwhile, the paper focuses on brightness temperature values of different scanning lines when the typhoon comes. The paper demonstrates that FY-3A satellite MWHS can retrieve the water vapor density profiles, cloud liquid water and other related information. Also, in the process of monitoring the tropical typhoon and cyclone and judging the trend of them, FY-3A satellite MWHS also plays a very important role.
Keywords: MWHS FY-3A ANN water vapor density
Pattern Recognition With Fuzzy Central Clustering Algorithms
Zen Huanglin,Yuan Hui,Liu Xiaofang
Strategic Study of CAE 2004, Volume 6, Issue 11, Pages 33-37
Based on optimization of constrained nonlinear programming, an approach of clustering center and a fuzzy membership function of pattern classification are derived from an objective function of the constrained nonlinear programming. An unsupervised algorithm with recursive expression and a fuzzy central cluster neural network are suggested in this paper. The fuzzy central cluster neural network proposed here can realize crisp decision or fuzzy decision in pattern classification.
Keywords: fuzzy sets central cluster pattern recognition neural network
A Rough Fuzzy Neural Classifier
Zeng Huanglin,Wang Xiao
Strategic Study of CAE 2003, Volume 5, Issue 12, Pages 60-65
In this paper, the concepts of rough sets are used to define equivalence classes encoding input data sets, and eliminate redundant or insignificant attributes in data sets so that to reduce the complexity of system construction. In order to deal with ill-defined or real experimental data, an input object is represented as a fuzzy variable by fuzzy membership function, and the significant factor of the input feature corresponding to output pattern classification is incorporated to constitute a fuzzy inference so that to enhance nonlinear mapping classification. A new kind of rough fuzzy neural classifier and a learning algorithm with LSE are proposed in this paper. A integration of the merits of fuzzy and neural network technologies can not only accommodate overlapping classification and therefore increase the performance of nonlinear mapping classification, but ensure more efficiently to handle real life ambiguous and changing situations and to achieve tractability, robustness, and low-cost solutions.
Keywords: fuzzy sets rough sets neural networks pattern classification
Title Author Date Type Operation
An artificial intelligence enhanced star identification algorithm
Hao Wang, Zhi-yuan Wang, Ben-dong Wang, Zhuo-qun Yu, Zhong-he Jin, John L. Crassidis,roger@zju.edu.cn
Journal Article
Marine target detection based on Marine-Faster R-CNN for navigation radar plane position indicator images
Xiaolong CHEN, Xiaoqian MU, Jian GUAN, Ningbo LIU, Wei ZHOU,cxlcxl1209@163.com,guanjian_68@163.com
Journal Article
Recent advances in efficient computation of deep convolutional neural networks
Jian CHENG, Pei-song WANG, Gang LI, Qing-hao HU, Han-qing LU
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
Fault Pattern Recognition of Rolling Bearing Based on Radial Basis Function Neural Networks
Lu Shuang,Zhang Zida,Li Meng
Journal Article
Learning and Applications of Procedure Neural Networks
He Xingui,Liang Jiuzhen,Xu Shaohua
Journal Article
Current Source Active Power Filter Control UsingNeural Network Technologies
Wang Ping,Zhang Ke, Xu Huijun
Journal Article
A partition approach for robust gait recognition based on gait template fusion
Kejun Wang, Liangliang Liu, Xinnan Ding, Kaiqiang Yu, Gang Hu,heukejun@126.com,liuliangliang@hrbeu.edu.cn,dingxinnan@hrbeu.edu.cn,yukaiqiang@hrbeu.edu.cn,hugang@hrbeu.edu.cn
Journal Article
Hydrogeological Parameter Identification Based on the Radial Basis Function Neural Networks
Zhang Junyan,Wei Lianwei,Han Weixiu,Shao Jingli,Cui Yali,Zhang Jianli
Journal Article
A novel method based on convolutional neural networks for deriving standard 12-lead ECG from serial 3-lead ECG
Lu-di WANG, Wei ZHOU, Ying XING, Na LIU, Mahmood MOVAHEDIPOUR, Xiao-guang ZHOU
Journal Article
A Survey of Accelerator Architectures for Deep Neural Networks
Yiran Chen, uan Xie, Linghao Song, Fan Chen, Tianqi Tang
Journal Article
Processing and analysis of data from microwave humidity sounder onboard FY-3A satellite
He Jieying,Zhang Shengwei
Journal Article
Pattern Recognition With Fuzzy Central Clustering Algorithms
Zen Huanglin,Yuan Hui,Liu Xiaofang
Journal Article