Search scope:
排序: Display mode:
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
Keywords: 多目标跟踪;深度神经网络;相似度学习
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
Keywords: Deep feedforward neural network Filter layer Passive radar Target tracking Tracking accuracy
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
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
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
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
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
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
Keywords: Neural network Deep learning Deep association neural network (DAN) Recommendation
Robust object tracking with RGBD-based sparse learning Article
Zi-ang MA, Zhi-yu XIANG
Frontiers of Information Technology & Electronic Engineering 2017, Volume 18, Issue 7, Pages 989-1001 doi: 10.1631/FITEE.1601338
Keywords: Object tracking Sparse learning Depth view Occlusion templates Occlusion detection
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
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
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
Research on An On-line Tracking Self-learning Algorithm for Fuzzy Basis Function Neural Network
Xu Feiyun,Zhong Binglin,Huang Ren
Strategic Study of CAE 2007, Volume 9, Issue 11, Pages 48-53
An on-line tracking self-learning algorithm for fuzzy basis function (FBF) neural network classifier is proposed in this paper. Based on the previous possibility distribution of the clusters, which is kept within the sample mean and covariance matrix with forgetting factor, a strategy for constructing the target output of the new training sample set is given. With the new sample set the FBF network can be trained to track the variable clustering boundary. Meanwhile, a recursive algorithm for computing the sample mean and covariance matrix with forgetting factor is also proposed to overcome the difficult of storing the vast old training samples. The proposed method is used for fault recognition of the rotating machinery, and the results show that it is feasible and effective.
Keywords: fuzzy basis function self-learning fault diagnosis
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
An Intelligent System for Navigation Collision Prevention
Hao Yanling,Liu Yuhong,Sun Feng,Sun Yao
Strategic Study of CAE 2000, Volume 2, Issue 3, Pages 48-53
The purpose of this thesis is to developing and exploiting an intelligent system for collision prevention, namely “Intelligent Collision Prevention Expert System for Navigation”(NICPES). The NICPES has a multi-unit and layering Knowledge Base systematic structure and a multi-unit Knowledge Representation (KR) which based on frame KR, production rule KR, procedure KR and neural network KR, to represent and store all kinds of knowledge for navigation collision prevention. The NICPES also builds a multi-inference system, which based on analogy inference, forward illation inference, conversion inference, neural network inference and meta-rule inference, to overcome the shortcoming of unitary inference. For-some problems in collision prevention region, the NICPES builds a set of models to solve them. These models comprise the models of judging collision risk, the model of determining collision prevention time and the model of classifying encounter situation. For multi-ship encounter situation, the NICPES puts forward a tactics to choose optimal collision prevention scheme based on Analytic Hierarchy Process (AHP) and builds a mathematical model that will be used to determine the optimal angle and sailing time during ship's turning for multi and single ship encounter situation. The simulation experiments show that the NICPES can analyze and judge various sailing cases and encounter situation ,and offer a reasonable scheme, which settle the collision problem effectively and ensure the sailing safety.
Keywords: collision prevention expert system neural network fuzzy technique multi-target optimizing
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
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
Chen Aidi,Wang Xinyi
Strategic Study of CAE 2000, Volume 2, Issue 12, Pages 73-77
To research on on-line detecting method and key technologies for part quality, based on the analysis of methods and features of on-line detecting of part dimension and surface roughness, an artificial neural network system for on-line detecting of part dimension and a fuzzy neural network system for on-line detecting of part surface roughness are developed. The Scheme of on-line detecting method for part quality can detect part dimension and surface roughness correctly.
Keywords: on-line detecting neural network fuzzy neural network dimension precision surface roughness
Multi-Objective Optimization Design through Machine Learning for Drop-on-Demand Bioprinting Article
Jia Shi, Jinchun Song, Bin Song, Wen F. Lu
Engineering 2019, Volume 5, Issue 3, Pages 586-593 doi: 10.1016/j.eng.2018.12.009
Drop-on-demand (DOD) bioprinting has been widely used in tissue engineering due to its highthroughput efficiency and cost effectiveness. However, this type of bioprinting involves challenges such as satellite generation, too-large droplet generation, and too-low droplet speed. These challenges reduce the stability and precision of DOD printing, disorder cell arrays, and hence generate further structural errors. In this paper, a multi-objective optimization (MOO) design method for DOD printing parameters through fully connected neural networks (FCNNs) is proposed in order to solve these challenges. The MOO problem comprises two objective functions: to develop the satellite formation model with FCNNs; and to decrease droplet diameter and increase droplet speed. A hybrid multi-subgradient descent bundle method with an adaptive learning rate algorithm (HMSGDBA), which combines the multisubgradient descent bundle (MSGDB) method with Adam algorithm, is introduced in order to search for the Pareto-optimal set for the MOO problem. The superiority of HMSGDBA is demonstrated through comparative studies with the MSGDB method. The experimental results show that a single droplet can be printed stably and the droplet speed can be increased from 0.88 to 2.08 m·s-1 after optimization with the proposed method. The proposed method can improve both printing precision and stability, and is useful in realizing precise cell arrays and complex biological functions. Furthermore, it can be used to obtain guidelines for the setup of cell-printing experimental platforms.
Keywords: Drop-on-demand printing Inkjet printing Gradient descent multi-objective optimization Fully connected neural networks
Title Author Date Type Operation
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
Diffractive Deep Neural Networks at Visible Wavelengths
Hang Chen, Jianan Feng, Minwei Jiang, Yiqun Wang, Jie Lin, Jiubin Tan, Peng Jin
Journal Article
Research on Tracing Evaluation System in Virtual Enterprise Based on Neural Network
Wang Shuo,Tang Xiaowo
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
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
Adversarial Attacks and Defenses in Deep Learning
Kui Ren, Tianhang Zheng, Zhan Qin, Xue Liu
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
Research on An On-line Tracking Self-learning Algorithm for Fuzzy Basis Function Neural Network
Xu Feiyun,Zhong Binglin,Huang Ren
Journal Article
A Survey of Accelerator Architectures for Deep Neural Networks
Yiran Chen, uan Xie, Linghao Song, Fan Chen, Tianqi Tang
Journal Article
An Intelligent System for Navigation Collision Prevention
Hao Yanling,Liu Yuhong,Sun Feng,Sun Yao
Journal Article
Penetration Depth of Projectiles Into Concrete Using Artificial Neural Network
Li Jianguang,Li Yongchi,Wang Yulan
Journal Article
Research on On-line Detecting Method and Key Technologies for Part Quality (Dimension and Surface Roughness)
Chen Aidi,Wang Xinyi
Journal Article