Resource Type

Journal Article 502

Year

2024 2

2023 52

2022 44

2021 59

2020 34

2019 41

2018 37

2017 40

2016 24

2015 5

2014 8

2013 3

2012 20

2011 5

2010 4

2009 10

2008 14

2007 26

2006 10

2005 10

open ︾

Keywords

Deep learning 34

Artificial intelligence 11

Machine learning 6

Additive manufacturing 3

Neural network 3

spacecraft 3

5G 2

Accelerator 2

Attention 2

Attention mechanism 2

Autonomous driving 2

Big data 2

Biosensors 2

Blockchain 2

Controller placement 2

Deep neural network 2

Fault-tolerant control 2

IHNI-1 reactor 2

IHNI－1 reactor 2

open ︾

Search scope:

排序： Display mode:

Efficient normalization for quantitative evaluation of the driving behavior using a gated auto-encoder Research Articles

Xin HE, Zhe ZHANG, Li XU, Jiapei YU,xinhe_ee@zju.edu.cn,xupower@zju.edu.cn

Frontiers of Information Technology & Electronic Engineering 2022, Volume 23, Issue 3,   Pages 452-462 doi: 10.1631/FITEE.2000667

Abstract: is important for a fair evaluation of the driving style. The longitudinal control of a vehicle is investigated in this study. The task can be considered as mapping of the in a different environment to the uniform condition. Unlike the model-based approach as in previous work, where a necessary driver model is employed to conduct the driving cycle test, the approach we propose directly normalizes the using an auto-encoder (AE) when following a standard speed profile. To ensure a positive correlation between the vehicle speed and , a gate constraint is imposed in between the encoder and decoder to form a gated AE (gAE). This approach is model-free and efficient. The proposed approach is tested for consistency with the model-based approach and for its applications to of the and fuel consumption analysis. Simulations are conducted to verify the effectiveness of the proposed scheme.

Keywords： Driving behavior     Normalization     Gated auto-encoder     Quantitative evaluation    

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

Representation learning via a semi-supervised stacked distance autoencoder for image classification Research Articles

Liang Hou, Xiao-yi Luo, Zi-yang Wang, Jun Liang,jliang@zju.edu.cn

Frontiers of Information Technology & Electronic Engineering 2020, Volume 21, Issue 7,   Pages 963-1118 doi: 10.1631/FITEE.1900116

Abstract: is an important application of deep learning. In a typical classification task, the classification accuracy is strongly related to the features that are extracted via deep learning methods. An is a special type of , often used for dimensionality reduction and feature extraction. The proposed method is based on the traditional , incorporating the “distance” information between samples from different categories. The model is called a semi-supervised distance . Each layer is first pre-trained in an unsupervised manner. In the subsequent supervised training, the optimized parameters are set as the initial values. To obtain more suitable features, we use a stacked model to replace the basic structure with a single hidden layer. A series of experiments are carried out to test the performance of different models on several datasets, including the MNIST dataset, street view house numbers (SVHN) dataset, German traffic sign recognition benchmark (GTSRB), and CIFAR-10 dataset. The proposed semi-supervised distance method is compared with the traditional , sparse , and supervised . Experimental results verify the effectiveness of the proposed model.

Keywords： 自动编码器；图像分类；半监督学习；神经网络    

HTML PDF Collect

Attention-based efficient robot grasp detection network Research Article

Xiaofei QIN, Wenkai HU, Chen XIAO, Changxiang HE, Songwen PEI, Xuedian ZHANG,xiaofei.qin@usst.edu.cn,obmmd_zxd@163.com

Frontiers of Information Technology & Electronic Engineering 2023, Volume 24, Issue 10,   Pages 1430-1444 doi: 10.1631/FITEE.2200502

Abstract: To balance the inference speed and detection accuracy of a grasp detection algorithm, which are both important for robot grasping tasks, we propose an ; structured pixel-level grasp detection named the attention-based efficient network (AE-GDN). Three spatial attention modules are introduced in the encoder stages to enhance the detailed information, and three channel attention modules are introduced in the stages to extract more semantic information. Several lightweight and efficient DenseBlocks are used to connect the encoder and paths to improve the feature modeling capability of AE-GDN. A high intersection over union (IoU) value between the predicted grasp rectangle and the ground truth does not necessarily mean a high-quality grasp configuration, but might cause a collision. This is because traditional IoU loss calculation methods treat the center part of the predicted rectangle as having the same importance as the area around the grippers. We design a new IoU loss calculation method based on an hourglass box matching mechanism, which will create good correspondence between high IoUs and high-quality grasp configurations. AE-GDN achieves the accuracy of 98.9% and 96.6% on the Cornell and Jacquard datasets, respectively. The inference speed reaches 43.5 frames per second with only about 1.2×10 parameters. The proposed AE-GDN has also been deployed on a practical robotic arm grasping system and performs grasping well. Codes are available at https://github.com/robvincen/robot_gradethttps://github.com/robvincen/robot_gradet.

Keywords： Robot grasp detection     Attention mechanism     Encoder–     decoder     Neural network    

HTML PDF Collect

A new anti-jamming communication technical system：pre-encoded code hopping spread spectrum

Yao Fuqiang,Zhang Yi

Strategic Study of CAE 2011, Volume 13, Issue 10,   Pages 69-75

Abstract:

A kind of pre-encoded code hopping spread spectrum (PCHSS) communication technical system for anti-jamming communication is brought forward and researched after analyzing its necessity based on the deficiency of conventional direct-sequence spread spectrum(DSSS). The main discussions include the basic principle of PCHSS, the differences between PCHSS and self-coded spread spectrum(SCHSS), and some key techniques. The PCHSS basic performance is analyzed finally. The technical system and its basic performance have been proved in practice.

Keywords： anti-jamming communication     direct-sequence spread spectrum     pre-encoded code hopping spread spectrum     self-coded spread spectrum    

HTML PDF Collect

Brain Encoding and Decoding in fMRI with Bidirectional Deep Generative Models Review

Changde Du, Jinpeng Li, Lijie Huang, Huiguang He

Engineering 2019, Volume 5, Issue 5,   Pages 948-953 doi: 10.1016/j.eng.2019.03.010

Abstract:

Brain encoding and decoding via functional magnetic resonance imaging (fMRI) are two important aspects of visual perception neuroscience. Although previous researchers have made significant advances in brain encoding and decoding models, existing methods still require improvement using advanced machine learning techniques. For example, traditional methods usually build the encoding and decoding models separately, and are prone to overfitting on a small dataset. In fact, effectively unifying the encoding and decoding procedures may allow for more accurate predictions. In this paper, we first review the existing encoding and decoding methods and discuss
the potential advantages of a "bidirectional" modeling strategy. Next, we show that there are correspondences between deep neural networks and human visual streams in terms of the architecture and computational rules Furthermore, deep generative models (e.g., variational autoencoders (VAEs) and generative adversarial networks (GANs)) have produced promising results in studies on brain encoding and decoding. Finally, we propose that the dual learning method, which was originally designed for machine translation tasks, could help to improve the performance of encoding and decoding models by leveraging large-scale unpaired data.

Keywords： Brain encoding and decoding     Functional magnetic resonance imaging     Deep neural networks     Deep generative models     Dual learning    

HTML PDF Collect

Displacement measuring grating interferometer: a review Special Feature on Precision Measurement and Inst

Peng-cheng HU, Di CHANG, Jiu-bin TAN, Rui-tao YANG, Hong-xing YANG, Hai-jin FU

Frontiers of Information Technology & Electronic Engineering 2019, Volume 20, Issue 5,   Pages 631-654 doi: 10.1631/FITEE.1800708

Abstract:

A grating interferometer, called the “optical encoder,” is a commonly used tool for precise displacement measurements. In contrast to a laser interferometer, a grating interferometer is insensitive to the air refractive index and can be easily applied to multi-degree-of-freedom measurements, which has made it an extensively researched and widely used device. Classified based on the measuring principle and optical configuration, a grating interferometer experiences three distinct stages of development: homodyne, heterodyne, and spatially separated heterodyne. Compared with the former two, the spatially separated heterodyne grating interferometer could achieve a better resolution with a feature of eliminating periodic nonlinear errors. Meanwhile, numerous structures of grating interferometers with a high optical fold factor, a large measurement range, good usability, and multidegree-of-freedom measurements have been investigated. The development of incremental displacement measuring grating interferometers achieved in recent years is summarized in detail, and studies on error analysis of a grating interferometer are briefly introduced.

Keywords： Grating interferometer     Optical encoder     Displacement measurement     Precision measurement    

HTML PDF Collect

Latent source-specific generative factor learning for monaural speech separation using weighted-factor autoencoder

Jing-jing Chen, Qi-rong Mao, You-cai Qin, Shuang-qing Qian, Zhi-shen Zheng,2221808071@stmail.ujs.edu.cn,mao_qr@ujs.edu.cn,2211908026@stmail.ujs.edu.cn,2211908025@stmail.ujs.edu.cn,3160602062@stmail.ujs.edu.cn

Frontiers of Information Technology & Electronic Engineering 2020, Volume 21, Issue 11,   Pages 1535-1670 doi: 10.1631/FITEE.2000019

Abstract: Much recent progress in monaural (MSS) has been achieved through a series of architectures based on s, which use an encoder to condense the input signal into compressed features and then feed these features into a decoder to construct a specific audio source of interest. However, these approaches can neither learn of the original input for MSS nor construct each audio source in mixed speech. In this study, we propose a novel weighted-factor (WFAE) model for MSS, which introduces a regularization loss in the objective function to isolate one source without containing other sources. By incorporating a latent attention mechanism and a supervised source constructor in the separation layer, WFAE can learn source-specific and a set of discriminative features for each source, leading to MSS performance improvement. Experiments on benchmark datasets show that our approach outperforms the existing methods. In terms of three important metrics, WFAE has great success on a relatively challenging MSS case, i.e., speaker-independent MSS.

Keywords： 语音分离；生成因子；自动编码器；深度学习    

HTML PDF Collect

Deep learning compact binary codes for fingerprint indexing None

Chao-chao BAI, Wei-qiang WANG, Tong ZHAO, Ru-xin WANG, Ming-qiang LI

Frontiers of Information Technology & Electronic Engineering 2018, Volume 19, Issue 9,   Pages 1112-1123 doi: 10.1631/FITEE.1700420

Abstract:

With the rapid growth in fingerprint databases, it has become necessary to develop excellent fingerprint indexing to achieve efficiency and accuracy. Fingerprint indexing has been widely studied with real-valued features, but few studies focus on binary feature representation, which is more suitable to identify fingerprints efficiently in large-scale fingerprint databases. In this study, we propose a deep compact binary minutia cylinder code (DCBMCC) as an effective and discriminative feature representation for fingerprint indexing. Specifically, the minutia cylinder code (MCC), as the state-of-the-art fingerprint representation, is analyzed and its shortcomings are revealed. Accordingly, we propose a novel fingerprint indexing method based on deep neural networks to learn DCBMCC. Our novel network restricts the penultimate layer to directly output binary codes. Moreover, we incorporate independence, balance, quantization-loss-minimum, and similarity-preservation properties in this learning process. Eventually, a multi-index hashing (MIH) based fingerprint indexing scheme further speeds up the exact search in the Hamming space by building multiple hash tables on binary code substrings. Furthermore, numerous experiments on public databases show that the proposed approach is an outstanding fingerprint indexing method since it has an extremely small error rate with a very low penetration rate.

Keywords： Fingerprint indexing     Minutia cylinder code     Deep neural network     Multi-index hashing    

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

On the principles of Parsimony and Self-consistency for the emergence of intelligence Position Paper

Yi MA, Doris TSAO, Heung-Yeung SHUM

Frontiers of Information Technology & Electronic Engineering 2022, Volume 23, Issue 9,   Pages 1298-1323 doi: 10.1631/FITEE.2200297

Abstract: Ten years into the revival of and artificial , we propose a theoretical framework that sheds light on understanding within a bigger picture of in general. We introduce two fundamental principles, and , which address two fundamental questions regarding : what to learn and how to learn, respectively. We believe the two principles serve as the cornerstone for the emergence of , artificial or natural. While they have rich classical roots, we argue that they can be stated anew in entirely measurable and computable ways. More specifically, the two principles lead to an effective and efficient computational framework, compressive , which unifies and explains the evolution of modern and most practices of artificial . While we use mainly visual data modeling as an example, we believe the two principles will unify understanding of broad families of autonomous intelligent systems and provide a framework for understanding the brain.

Keywords： Intelligence     Parsimony     Self-consistency     Rate reduction     Deep networks     Closed-loop transcription    

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

Attention-based encoder-decoder model for answer selection in question answering Article

Yuan-ping NIE, Yi HAN, Jiu-ming HUANG, Bo JIAO, Ai-ping LI

Frontiers of Information Technology & Electronic Engineering 2017, Volume 18, Issue 4,   Pages 535-544 doi: 10.1631/FITEE.1601232

Abstract: One of the key challenges for question answering is to bridge the lexical gap between questions and answers because there may not be any matching word between them. Machine translation models have been shown to boost the performance of solving the lexical gap problem between question-answer pairs. In this paper, we introduce an attention-based deep learning model to address the answer selection task for question answering. The proposed model employs a bidirectional long short-term memory (LSTM) encoder-decoder, which has been demonstrated to be effective on machine translation tasks to bridge the lexical gap between questions and answers. Our model also uses a step attention mechanism which allows the question to focus on a certain part of the candidate answer. Finally, we evaluate our model using a benchmark dataset and the results show that our approach outperforms the existing approaches. Integrating our model significantly improves the performance of our question answering system in the TREC 2015 LiveQA task.

Keywords： Question answering     Answer selection     Attention     Deep learning    

HTML PDF Collect

A New Algorithm of Fractal Image Coding

Wang Xiuni,Jiang Wei,Wang Licun

Strategic Study of CAE 2006, Volume 8, Issue 1,   Pages 54-57

Abstract:

Because it takes too much of time in fractal image coding, the paper analyses the factors that affect the speed of fractal image coding , and proposes a novel idea by using the reformed variance (tentatively) to improve image fractal compression performance . A theorem is proved that the IFS cannot change the image blocks' reformed variance. Moreover , it gives a novel fractal image compression method based on the reformed variance. The simulation results illuminate that the new method can run fast, at the same time it can improve the PSNR when compared with other fast algorithms.

Keywords： fractal coding     image compression     variance    

HTML PDF Collect

Application of Hydraulic Pressure Sensore System on Riverb ed ErosionDepth for Real-time Monitoring

Chen Zhijian,Liu Dawei,Zhang Weiwen

Strategic Study of CAE 2007, Volume 9, Issue 5,   Pages 17-21

Abstract:

The problem of groundsill eroding is general and important for deep-water foundation in tidal reach.  Application,  technical difficulty and its settlement scheme of hydraulic pressure sensors system are introduced based on expounding the essentiality of riverbed erosion for real-time monitoring within group piled foundation. Amendment of fluctuant water level is realized by setting a sensor to monitor the tide. The sensors are fixed on the side of the piles reliably and sensor signal is transmitted smoothly with single point setting method. This method shows the characteristics of real-time,  continuity,  long-term and high precision when applied to the Su-Tong Bridge Project. Based on the results of monitoring, the mechanism of local scour within group piled foundation is analyzed.

Keywords： hydraulic pressure sensor     tidal reach     group piled foundation     local scour     real-time monitoring    

HTML PDF Collect

Title Author Date Type Operation

Efficient normalization for quantitative evaluation of the driving behavior using a gated auto-encoder

Xin HE, Zhe ZHANG, Li XU, Jiapei YU,xinhe_ee@zju.edu.cn,xupower@zju.edu.cn

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

Representation learning via a semi-supervised stacked distance autoencoder for image classification

Liang Hou, Xiao-yi Luo, Zi-yang Wang, Jun Liang,jliang@zju.edu.cn

Journal Article

Attention-based efficient robot grasp detection network

Xiaofei QIN, Wenkai HU, Chen XIAO, Changxiang HE, Songwen PEI, Xuedian ZHANG,xiaofei.qin@usst.edu.cn,obmmd_zxd@163.com

Journal Article

A new anti-jamming communication technical system：pre-encoded code hopping spread spectrum

Yao Fuqiang,Zhang Yi

Journal Article

Brain Encoding and Decoding in fMRI with Bidirectional Deep Generative Models

Changde Du, Jinpeng Li, Lijie Huang, Huiguang He

Journal Article

Displacement measuring grating interferometer: a review

Peng-cheng HU, Di CHANG, Jiu-bin TAN, Rui-tao YANG, Hong-xing YANG, Hai-jin FU

Journal Article

Latent source-specific generative factor learning for monaural speech separation using weighted-factor autoencoder

Jing-jing Chen, Qi-rong Mao, You-cai Qin, Shuang-qing Qian, Zhi-shen Zheng,2221808071@stmail.ujs.edu.cn,mao_qr@ujs.edu.cn,2211908026@stmail.ujs.edu.cn,2211908025@stmail.ujs.edu.cn,3160602062@stmail.ujs.edu.cn

Journal Article

Deep learning compact binary codes for fingerprint indexing

Chao-chao BAI, Wei-qiang WANG, Tong ZHAO, Ru-xin WANG, Ming-qiang LI

Journal Article

A Survey of Accelerator Architectures for Deep Neural Networks

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

Journal Article

On the principles of Parsimony and Self-consistency for the emergence of intelligence

Yi MA, Doris TSAO, Heung-Yeung SHUM

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

Attention-based encoder-decoder model for answer selection in question answering

Yuan-ping NIE, Yi HAN, Jiu-ming HUANG, Bo JIAO, Ai-ping LI

Journal Article

A New Algorithm of Fractal Image Coding

Wang Xiuni,Jiang Wei,Wang Licun

Journal Article

Application of Hydraulic Pressure Sensore System on Riverb ed ErosionDepth for Real-time Monitoring

Chen Zhijian,Liu Dawei,Zhang Weiwen

Journal Article