Resource Type

Journal Article 521

Year

2024 1

2023 61

2022 59

2021 68

2020 60

2019 41

2018 36

2017 37

2016 36

2015 11

2014 4

2013 3

2012 6

2011 5

2010 1

2009 6

2008 12

2007 13

2006 10

2005 14

open ︾

Keywords

Deep learning 34

neural network 16

Artificial intelligence 15

Machine learning 9

Neural network 8

Software-defined networking (SDN) 7

cyberspace 5

cyberspace security 5

6G 4

ANN 3

Attention mechanism 3

Autonomous driving 3

BP neural network 3

Boolean control networks 3

Network security 3

fuzzy sets 3

5G 2

Accelerator 2

Additive manufacturing 2

open ︾

Search scope:

排序： Display mode:

Diffractive Deep Neural Networks at Visible Wavelengths Article

Hang Chen, Jianan Feng, Minwei Jiang, Yiqun Wang, Jie Lin, Jiubin Tan, Peng Jin

Engineering 2021, Volume 7, Issue 10,   Pages 1485-1493 doi: 10.1016/j.eng.2020.07.032

Abstract:

Optical deep learning based on diffractive optical elements offers unique advantages for parallel processing, computational speed, and power efficiency. One landmark method is the diffractive deep neural network (D2NN) based on three-dimensional printing technology operated in the terahertz spectral range. Since the terahertz bandwidth involves limited interparticle coupling and material losses, this paper
extends D2NN to visible wavelengths. A general theory including a revised formula is proposed to solve any contradictions between wavelength, neuron size, and fabrication limitations. A novel visible light D2NN classifier is used to recognize unchanged targets (handwritten digits ranging from 0 to 9) and targets that have been changed (i.e., targets that have been covered or altered) at a visible wavelength of 632.8 nm. The obtained experimental classification accuracy (84%) and numerical classification accuracy (91.57%) quantify the match between the theoretical design and fabricated system performance. The presented framework can be used to apply a D2NN to various practical applications and design other new applications.

Keywords： Optical computation     Optical neural networks     Deep learning     Optical machine learning     Diffractive deep neural networks    

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

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

Abstract:

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    

HTML PDF Collect

DAN: a deep association neural network approach for personalization recommendation Research Articles

Xu-na Wang, Qing-mei Tan,Xuna@nuaa.edu.cn,tanchina@nuaa.edu.cn

Frontiers of Information Technology & Electronic Engineering 2020, Volume 21, Issue 7,   Pages 963-980 doi: 10.1631/FITEE.1900236

Abstract: The collaborative filtering technology used in traditional systems has a problem of data sparsity. The traditional matrix decomposition algorithm simply decomposes users and items into a linear model of potential factors. These limitations have led to the low accuracy in traditional algorithms, thus leading to the emergence of systems based on . At present, s mostly use deep s to model some of the auxiliary information, and in the process of modeling, multiple mapping paths are adopted to map the original input data to the potential vector space. However, these deep algorithms ignore the combined effects of different categories of data, which can have a potential impact on the effectiveness of the . Aimed at this problem, in this paper we propose a feedforward deep method, called the deep association (DAN), which is based on the joint action of multiple categories of information, for implicit feedback . Specifically, the underlying input of the model includes not only users and items, but also more auxiliary information. In addition, the impact of the joint action of different types of information on the is considered. Experiments on an open data set show the significant improvements made by our proposed method over the other methods. Empirical evidence shows that deep, joint s can provide better performance.

Keywords： Neural network     Deep learning     Deep association neural network (DAN)     Recommendation    

HTML PDF Collect

Penetration Depth of Projectiles Into Concrete Using Artificial Neural Network

Li Jianguang,Li Yongchi,Wang Yulan

Strategic Study of CAE 2007, Volume 9, Issue 8,   Pages 77-81

Abstract:

In this article,  nonlinear mapping relation between input of 13 variables of lp and σyt/σyp etc. , and output of penetration depth is established by dimensional analysis and theory of artificial neural networks for problem of penetration depth of projectiles into concrete.  Moreover,  a satisfied output about penetration depth from RBF neural network is gotten by a group of input sets and corresponding output sets,  which comes from M.  J.  Forrestal 's document.

Keywords： neural networks     dimensional analysis     penetration depth of projectiles into concrete     nonlinear mapping relation     RBF neural networks    

HTML PDF Collect

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

Abstract: Deep neural networks have evolved remarkably over the past few years and they are currently the fundamental tools of many intelligent systems. At the same time, the computational complexity and resource consumption of these networks continue to increase. This poses a significant challenge to the deployment of such networks, especially in real-time applications or on resource-limited devices. Thus, network acceleration has become a hot topic within the deep learning community. As for hardware implementation of deep neural networks, a batch of accelerators based on a field-programmable gate array (FPGA) or an application-specific integrated circuit (ASIC) have been proposed in recent years. In this paper, we provide a comprehensive survey of recent advances in network acceleration, compression, and accelerator design from both algorithm and hardware points of view. Specifically, we provide a thorough analysis of each of the following topics: network pruning, low-rank approximation, network quantization, teacher–student networks, compact network design, and hardware accelerators. Finally, we introduce and discuss a few possible future directions.

Keywords： Deep neural networks     Acceleration     Compression     Hardware accelerator    

HTML PDF Collect

Associative affinity network learning for multi-object tracking Research Articles

Liang Ma, Qiaoyong Zhong, Yingying Zhang, Di Xie, Shiliang Pu,maliang6@hikvision.com,zhongqiaoyong@hikvision.com,zhangyingying7@hikvision.com,xiedi@hikvision.com,pushiliang.hri@hikvision.com

Frontiers of Information Technology & Electronic Engineering 2021, Volume 22, Issue 9,   Pages 1194-1206 doi: 10.1631/FITEE.2000272

Abstract: We propose a joint feature and metric learning architecture, called the associative affinity network (AAN), as an affinity model for (MOT) in videos. The AAN learns the associative affinity between tracks and detections across frames in an end-to-end manner. Considering flawed detections, the AAN jointly learns bounding box regression, classification, and affinity regression via the proposed multi-task loss. Contrary to networks that are trained with ranking loss, we directly train a binary classifier to learn the associative affinity of each track-detection pair and use a matching cardinality loss to capture information among candidate pairs. The AAN learns a discriminative affinity model for data association to tackle MOT, and can also perform single-object tracking. Based on the AAN, we propose a simple multi-object tracker that achieves competitive performance on the public MOT16 and MOT17 test datasets.

Keywords： 多目标跟踪；深度神经网络；相似度学习    

HTML PDF Collect

High-accuracy target tracking for multistatic passive radar based on a deep feedforward neural network Research Article

Baoxiong XU, Jianxin YI, Feng CHENG, Ziping GONG, Xianrong WAN,jessiexu@whu.edu.cn,jxyi@whu.edu.cn,cwing@whu.edu.cn

Frontiers of Information Technology & Electronic Engineering 2023, Volume 24, Issue 8,   Pages 1214-1230 doi: 10.1631/FITEE.2200260

Abstract: In radar systems, errors are mainly from motion models and nonlinear measurements. When we evaluate a tracking algorithm, its is the main criterion. To improve the , in this paper we formulate the tracking problem into a regression model from measurements to target states. A tracking algorithm based on a modified (MDFNN) is then proposed. In MDFNN, a is introduced to describe the temporal sequence relationship of the input measurement sequence, and the optimal measurement sequence size is analyzed. Simulations and field experimental data of the show that the accuracy of the proposed algorithm is better than those of extended Kalman filter (EKF), unscented Kalman filter (UKF), and recurrent neural network (RNN) based tracking methods under the considered scenarios.

Keywords： Deep feedforward neural network     Filter layer     Passive radar     Target tracking     Tracking accuracy    

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

Research on Tracing Evaluation System in Virtual Enterprise Based on Neural Network

Wang Shuo,Tang Xiaowo

Strategic Study of CAE 2003, Volume 5, Issue 4,   Pages 65-69

Abstract:

The paper designed tracing evaluation index system in virtual enterprise and established neural network trace evaluation model. As a result, it was simple and nicety than traditional method, so it had wider application foreground.

Keywords： virtual enterprise     neural network     trace evaluation     system    

HTML PDF Collect

Estimating Rainfall Intensity Using an Image-Based Deep Learning Model Article

Hang Yin, Feifei Zheng, Huan-Feng Duan, Dragan Savic, Zoran Kapelan

Engineering 2023, Volume 21, Issue 2,   Pages 162-174 doi: 10.1016/j.eng.2021.11.021

Abstract:

Urban flooding is a major issue worldwide, causing huge economic losses and serious threats to public safety. One promising way to mitigate its impacts is to develop a real-time flood risk management system; however, building such a system is often challenging due to the lack of high spatiotemporal rainfall data. While some approaches (i.e., ground rainfall stations or radar and satellite techniques) are available to measure and/or predict rainfall intensity, it is difficult to obtain accurate rainfall data with a desirable spatiotemporal resolution using these methods. This paper proposes an image-based deep learning model to estimate urban rainfall intensity with high spatial and temporal resolution. More specifically, a convolutional neural network (CNN) model called the image-based rainfall CNN (irCNN) model is developed using rainfall images collected from existing dense sensors (i.e., smart phones or transportation cameras) and their corresponding measured rainfall intensity values. The trained irCNN model is subsequently employed to efficiently estimate rainfall intensity based on the sensors' rainfall images. Synthetic rainfall data and real rainfall images are respectively utilized to explore the irCNN's accuracy in theoretically and practically simulating rainfall intensity. The results show that the irCNN model provides rainfall estimates with a mean absolute percentage error ranging between 13.5% and 21.9%, which exceeds the performance of other state-of-the-art modeling techniques in the literature. More importantly, the main feature of the proposed irCNN is its low cost in efficiently acquiring high spatiotemporal urban rainfall data. The irCNN model provides a promising alternative for estimating urban rainfall intensity, which can greatly facilitate the development of urban flood risk management in a real-time manner.

Keywords： Urban flooding     Rainfall images     Deep learning model     Convolutional neural networks (CNNs)     Rainfall intensity    

HTML PDF Collect

FlowDNN: a physics-informed deep neural network for fast and accurate flow prediction Research Articles

Donglin CHEN, Xiang GAO, Chuanfu XU, Siqi WANG, Shizhao CHEN, Jianbin FANG, Zheng WANG,chendonglin14@nudt.edu.cn,gaoxiang12@nudt.edu.cn,xuchuanfu@nudt.edu.cn

Frontiers of Information Technology & Electronic Engineering 2022, Volume 23, Issue 2,   Pages 207-219 doi: 10.1631/FITEE.2000435

Abstract: For flow-related design optimization problems, e.g., aircraft and automobile aerodynamic design, computational fluid dynamics (CFD) simulations are commonly used to predict flow fields and analyze performance. While important, CFD simulations are a resource-demanding and time-consuming iterative process. The expensive simulation overhead limits the opportunities for large design space exploration and prevents interactive design. In this paper, we propose FlowDNN, a novel (DNN) to efficiently learn flow representations from CFD results. FlowDNN saves computational time by directly predicting the expected flow fields based on given flow conditions and geometry shapes. FlowDNN is the first DNN that incorporates the underlying physical conservation laws of fluid dynamics with a carefully designed for steady . This approach not only improves the prediction accuracy, but also preserves the physical consistency of the predicted flow fields, which is essential for CFD. Various metrics are derived to evaluate FlowDNN with respect to the whole flow fields or regions of interest (RoIs) (e.g., boundary layers where flow quantities change rapidly). Experiments show that FlowDNN significantly outperforms alternative methods with faster inference and more accurate results. It speeds up a graphics processing unit (GPU) accelerated CFD solver by more than , while keeping the prediction error under 5%.

Keywords： Deep neural network     Flow prediction     Attention mechanism     Physics-informed loss    

HTML PDF Collect

Pressure in Gas-assisted Injection Molding

Ou Changjin

Strategic Study of CAE 2007, Volume 9, Issue 5,   Pages 27-32

Abstract:

In this study,  an effective control method and strategy based on fuzzy neural network has been developed for gas injection pressure accurate control in gas-assisted injection. A fuzzy neural network controller with five layers and its control algorithm are established.  The learning ability of neural network is used to optimize the rules of the fuzzy logic so as to improve the adaptability of system.  The simulation of the system capability and three segmental injected pressure control are carried out under the environment of MATLAB and the results show that this theoretic model is feasible, and the control system has good characteristics and control action.

Keywords： gas-assisted injection molding     fuzzy neural network     gas-injection pressure control    

HTML PDF Collect

Research on fuzzy neural network control method for high-frequency vacuum drying of wood

Jiang Bin,Sun Liping,Cao Jun and Zhou Zheng

Strategic Study of CAE 2014, Volume 16, Issue 4,   Pages 17-20

Abstract:

High- frequency vacuum combined wood drying is a kind of fast drying speed， low energy consumption，little environmental pollution of new drying technology. On the basis of theoretical analysis with high frequency in wood vacuum drying process，the fuzzy controller and fuzzy neural network controller of wood drying are designed in view of the neural network method to establish model of wood drying. The simulation experiment results show that fuzzy neural network control is better，such as the temperature rising fast，high control precision，good stability. The method to realize the automatic control of timber drying process has important research significance.

Keywords： high-frequency vacuum     wood drying     fuzzy neural network    

HTML PDF Collect

Simulation Algorithm of Flightdeck Airflow Based on Neural Network

Xun Wensheng,Lin Ming

Strategic Study of CAE 2003, Volume 5, Issue 5,   Pages 76-79

Abstract:

The airflow on the flightdeck is an important factor which influences helicopter flight safety. The airflow velocity distribution characteristics directly influences simulation accuracy of helicopter flight dynamics. Based on the Navier-Stokes equations, the method to determine the airflow velocity in real-time is discussed using BP neural network. This method can be used for flightdeck airflow real-time simulation, and it can improve helicopter flight simulation accuracy.

Keywords： flow     finite element     neural network    

HTML PDF Collect

Title Author Date Type Operation

Diffractive Deep Neural Networks at Visible Wavelengths

Hang Chen, Jianan Feng, Minwei Jiang, Yiqun Wang, Jie Lin, Jiubin Tan, Peng Jin

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

A Survey of Accelerator Architectures for Deep Neural Networks

Yiran Chen, uan Xie, Linghao Song, Fan Chen, Tianqi Tang

Journal Article

DAN: a deep association neural network approach for personalization recommendation

Xu-na Wang, Qing-mei Tan,Xuna@nuaa.edu.cn,tanchina@nuaa.edu.cn

Journal Article

Penetration Depth of Projectiles Into Concrete Using Artificial Neural Network

Li Jianguang,Li Yongchi,Wang Yulan

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

Associative affinity network learning for multi-object tracking

Liang Ma, Qiaoyong Zhong, Yingying Zhang, Di Xie, Shiliang Pu,maliang6@hikvision.com,zhongqiaoyong@hikvision.com,zhangyingying7@hikvision.com,xiedi@hikvision.com,pushiliang.hri@hikvision.com

Journal Article

High-accuracy target tracking for multistatic passive radar based on a deep feedforward neural network

Baoxiong XU, Jianxin YI, Feng CHENG, Ziping GONG, Xianrong WAN,jessiexu@whu.edu.cn,jxyi@whu.edu.cn,cwing@whu.edu.cn

Journal Article

Adversarial Attacks and Defenses in Deep Learning

Kui Ren, Tianhang Zheng, Zhan Qin, Xue Liu

Journal Article

Research on Tracing Evaluation System in Virtual Enterprise Based on Neural Network

Wang Shuo,Tang Xiaowo

Journal Article

Estimating Rainfall Intensity Using an Image-Based Deep Learning Model

Hang Yin, Feifei Zheng, Huan-Feng Duan, Dragan Savic, Zoran Kapelan

Journal Article

FlowDNN: a physics-informed deep neural network for fast and accurate flow prediction

Donglin CHEN, Xiang GAO, Chuanfu XU, Siqi WANG, Shizhao CHEN, Jianbin FANG, Zheng WANG,chendonglin14@nudt.edu.cn,gaoxiang12@nudt.edu.cn,xuchuanfu@nudt.edu.cn

Journal Article

Pressure in Gas-assisted Injection Molding

Ou Changjin

Journal Article

Research on fuzzy neural network control method for high-frequency vacuum drying of wood

Jiang Bin,Sun Liping,Cao Jun and Zhou Zheng

Journal Article

Simulation Algorithm of Flightdeck Airflow Based on Neural Network

Xun Wensheng,Lin Ming

Journal Article