Search | Engineering

Subscribe Submit

Home Journals Focus Achievement Fronts About Us 中文版

Resource Type

Journal Article 82

Year

2023 7

2022 6

2021 10

2020 3

2019 9

2018 6

2017 10

2016 2

2015 1

2014 1

2012 2

2011 2

2010 2

2009 1

2007 1

2006 4

2005 4

2004 6

2002 1

2001 3

open ︾

Keywords

pattern recognition 6

Deep learning 3

Emotion recognition 2

Random forest 2

Speech recognition 2

automatic target recognition 2

performance evaluation 2

21st-Century Maritime Silk Road 1

3D parametric model 1

3D visual knowledge 1

AR model 1

Adverse geology 1

Alteration 1

Amplitude-modulating 1

Anomaly threshold 1

App reviews 1

Appearance feature 1

Arousal 1

Artificial intelligence 1

open ︾

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

Abstract: An artificial intelligence enhanced algorithm is proposed for s in mode. A model based on Vgg16 is used in the artificial intelligence algorithm to classify star images. The training dataset is constructed to achieve the networks’ optimal performance. Simulation results show that the proposed algorithm is highly robust to many kinds of noise, including position noise, magnitude noise, false stars, and the tracker’s angular velocity. With a deep , the identification accuracy is maintained at 96% despite noise and interruptions, which is a significant improvement to traditional pyramid and grid algorithms.

Keywords：星敏感器；姿态失锁；星图识别；卷积神经网络

HTML PDF Collect

Cold War Satellite Imagery Gets New Life

Mitch Leslie

Engineering 2021, Volume 7, Issue 6, Pages 709-711 doi: 10.1016/j.eng.2021.04.004

HTML PDF Collect

Fast uniform content-based satellite image registration using the scale-invariant feature transform descriptor Article

Hamed BOZORGI, Ali JAFARI

Frontiers of Information Technology & Electronic Engineering 2017, Volume 18, Issue 8, Pages 1108-1116 doi: 10.1631/FITEE.1500295

Abstract: Content-based satellite image registration is a difficult issue in the fields of remote sensing and image processing. The difficulty is more significant in the case of matching multisource remote sensing images which suffer from illumination, rotation, and source differences. The scale-invariant feature transform (SIFT) algorithm has been used successfully in satellite image registration problems. Also, many researchers have applied a local SIFT descriptor to improve the image retrieval process. Despite its robustness, this algorithm has some difficulties with the quality and quantity of the extracted local feature points in multisource remote sensing. Furthermore, high dimensionality of the local features extracted by SIFT results in time-consuming computational processes alongside high storage requirements for saving the relevant information, which are important factors in content-based image retrieval (CBIR) applications. In this paper, a novel method is introduced to transform the local SIFT features to global features for multisource remote sensing. The quality and quantity of SIFT local features have been enhanced by applying contrast equalization on images in a pre-processing stage. Considering the local features of each image in the reference database as a separate class, linear discriminant analysis (LDA) is used to transform the local features to global features while reducing dimensionality of the feature space. This will also significantly reduce the computational time and storage required. Applying the trained kernel on verification data and mapping them showed a successful retrieval rate of 91.67% for test feature points.

Keywords： Content-based image retrieval Feature point distribution Image registration Linear discriminant analysis Remote sensing Scale-invariant feature transform

HTML PDF Collect

一种易用的实体识别消歧系统评测框架 Article

辉陈,宝刚魏,一鸣李,Yong-huai LIU,文浩朱

Frontiers of Information Technology & Electronic Engineering 2017, Volume 18, Issue 2, Pages 195-205 doi: 10.1631/FITEE.1500473

Abstract: 实体识别消歧是知识库扩充和信息抽取的重要技术之一。近些年该领域诞生了很多研究成果，提出了许多实体识别消歧系统。但由于缺乏对这些系统的完善评测对比，该领域依然处于良莠淆杂的状态。本文提出一个实体识别消歧系统的统一评测框架，用于公平地比较各个实体识别消歧系统的效果。该框架代码开源，可以采用新的系统、数据集、评测机制扩展。本文分析对比了几个公开的实体识别消歧系统，并总结出了一些有用的结论。

Keywords：实体识别消歧；评测框架；信息抽取

HTML PDF Collect

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

Abstract: has significant potential for remote human identification, but it is easily influenced by identity-unrelated factors such as clothing, carrying conditions, and view angles. Many have been presented that can effectively represent gait features. Each gait template has its advantages and can represent different prominent information. In this paper, gait template fusion is proposed to improve the classical representative gait template (such as a ) which represents incomplete information that is sensitive to changes in contour. We also present a partition method to reflect the different gait habits of different body parts of each pedestrian. The fused template is cropped into three parts (head, trunk, and leg regions) depending on the human body, and the three parts are then sent into the convolutional neural network to learn merged features. We present an extensive empirical evaluation of the CASIA-B dataset and compare the proposed method with existing ones. The results show good accuracy and robustness of the proposed method for .

Keywords：步态识别；分块算法；步态模板；步态分析；步态能量图；深度卷积神经网络；生物特征识别；模式识别

HTML PDF Collect

Surface Ship Target Recognition Research Based on SGA

Jiang Dingding,Xu Zhaolin,Li Kairui

Strategic Study of CAE 2004, Volume 6, Issue 8, Pages 79-81

Abstract:

Surface ship recognition is an important contents of navy's aviation probe. This text discussed the principle, characteristics and calculating step of SGA, and applied this calculating way to surface ship recognition. The experiment results proved the scientificalness and the practical applicability of that methoded.

Keywords： SGA target recognition surface ship

HTML PDF Collect

Application of RFID in the Visual Logistics System

Wang Aiming,Mu Xiaoxi,Li Aihua

Strategic Study of CAE 2006, Volume 8, Issue 8, Pages 65-68

Abstract:

The radio frequency identification (RFID) is a kind of new automatic identification technology. It has many characteristics such as high reliability, privacy , non-contact, convenient and swift. Applying RFID to visual logistics system, can gain actual requirement of guaranteed object and information about the type, amount and way of materials to supply and ensure the supply in the whole time, orientation and course. The paper introduces the RFID system and its principle, and brings about an application of RFID in visual logistics system, which is realized by the radio frequency labels stuck to the containers and equipments.

Keywords： visual logistics radio frequency identification visual system for the carrying materials

HTML PDF Collect

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

Abstract:

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

HTML PDF Collect

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

Abstract:

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

HTML PDF Collect

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

Abstract:

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

HTML PDF Collect

Analysis of Disruptive Technology Identification Methods in Foreign Countries

Wang An,Sun Zongtan,Shen Yanbo and Xu Yuan

Strategic Study of CAE 2017, Volume 19, Issue 5, Pages 79-84 doi: 10.15302/J-SSCAE-2017.05.014

Abstract:

Disruptive technologies, which have groundbreaking effects on existing traditional or mainstream technologies, have great potential applications, and are actively recognized and nurtured by all countries. This article summarizes the standard reports on technology identification research released by foreign government agencies, think tanks, intelligence agencies, consulting firms, universities, and patent analysis institutions. It then analyzes and evaluates the disruptive technology identification methods in order to provide reference for the corresponding disruptive technology identification methods in China.

Keywords： disruptive technologies identification methods

HTML PDF Collect

Safety Risks of Self-driving Vehicle: Identification and Measurement

Dou Wenyue, Hu Ping, Wei Ping, Zheng Nanning

Strategic Study of CAE 2021, Volume 23, Issue 6, Pages 167-177 doi: 10.15302/J-SSCAE-2021.06.016

Abstract:

Self-driving vehicle is a hot application of artificial intelligence, and the identification and measurement of its safety risks has become an urgent research topic in the field of artificial intelligence safety. In this study, we collect qualitative information through case interviews and identify the key elements of safety risks using the qualitative research method and the grounded theory. Further, we propose for the first time a six-element frame for the safety risks of self-driving vehicle. These elements include single vehicle safety, networking safety, technological level, legal policies, public opinion, and industrial risks. Subsequently, we design a questionnaire and conduct two online questionnaires surveys to measure the safety risk elements. To cope with future safety risks of self-driving vehicle, enterprises should strengthen the research and manufacturing of key components, increase investment in information security, participate in the formulation of industry standards and regulations, and maintain a sustainable development. The government should strengthen the supervision over self-driving vehicle tests, improve regulations and standards, and guide talent training. Consumers should keep good driving habits and maintain rational regarding self-driving vehicle.

Keywords： self-driving vehicle safety risk risk identification risk measurement

HTML PDF Collect

High-Temperature Target Recognition Based on Spectral Radiation Information

Fan Xueliang,Cheng Xiaofang,Xu Jun

Strategic Study of CAE 2004, Volume 6, Issue 6, Pages 57-62

Abstract:

Based on the principles of optics and radiometry, the imaging mathematical model is established and the factors of the contrast (signal-noise-ratio) of high-temperature target and the scenery are given. By analyzing not only the differences in spectral properties between objects in the scene, but also the CCD spectral response theoretically, a new method of enhancement of contrast is given. By optimizing the initial image capture stage, using liquid crystal light valve to make a simple modification of the imaging system, the goal of high object recognition is achieved. The experimental results agree with the theoretical predicts.

Keywords： video image object recognition radiation information liquid crystal light valve

HTML PDF Collect

Application of Fuzzy Pattern Recognition in the Measurement of Slurry Concentration

Li Dejun,Lv Runhua,Wang Runtian

Strategic Study of CAE 2007, Volume 9, Issue 5, Pages 81-84

Abstract:

Slurry is widely used in construction projects, and it is important to control the slurry's physical characteristic properly. The acoustic method is used, which can effectively monitor the physical parameters of slurry, such as concentration. Data processing affects directly the precision in the measurement of slurry concentration by the sound attenuation and velocity. Based on the fuzzy pattern recognition, data are sorted and further classified, with cooperative clustering algorithm.

Keywords： fuzzy pattern recognition nearest neighbor(NN) cooperative clustering algorithm(CCA) slurry concentration

HTML PDF Collect

Multi-band Synchronization Model for Speech Recognition Under Noisy Condition

Sun Wei,Wu Zhenyang

Strategic Study of CAE 2006, Volume 8, Issue 3, Pages 31-34

Abstract:

Based on perception characteristic of human ear, this paper proposes synchronization multi-band maximum likelihood linear regression algorithm for robust speech recognition under noisy condition. The algorithm utilizes maximum likelihood as estimation criteria to compensate the effects of noisy condition with multi-band synchronization model and noise corruption assumption. The tests show that the proposed algorithm improves the performance of recognition system effectively.

Keywords： hidden Markov model maximum likelihood multi-band synchronization model speech recognition

HTML PDF Collect

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

Cold War Satellite Imagery Gets New Life

Mitch Leslie

Journal Article

Fast uniform content-based satellite image registration using the scale-invariant feature transform descriptor

Hamed BOZORGI, Ali JAFARI

Journal Article

一种易用的实体识别消歧系统评测框架

辉陈,宝刚魏,一鸣李,Yong-huai LIU,文浩朱

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

Surface Ship Target Recognition Research Based on SGA

Jiang Dingding,Xu Zhaolin,Li Kairui

Journal Article

Application of RFID in the Visual Logistics System

Wang Aiming,Mu Xiaoxi,Li Aihua

Journal Article

Pattern Recognition With Fuzzy Central Clustering Algorithms

Zen Huanglin,Yuan Hui,Liu Xiaofang

Journal Article

Fault Pattern Recognition of Rolling Bearing Based on Radial Basis Function Neural Networks

Lu Shuang,Zhang Zida,Li Meng