|
|
|
题名
|
作者
|
年代
|
出处
|
被引量
|
| 1 | Deep forest显示文摘Current deep-learning models are mostly built upon neural networks, i.e. multiple layers of parameterized differentiable non-linear modules that can be trained by backpropagation. In this paper, we explore the possibility of building deep models based on non-differentiable modules such as decision trees. After a discussion about the mystery behind deep neural networks, particularly by contrasting them with shallow neural networks and traditional machine-learning techniques such as decision trees and boosting machines,we conjecture that the success of deep neural networks owes much to three characteristics, i.e.layer-by-layer processing, in-model feature transformation and sufficient model complexity. On one hand,our conjecture may offer inspiration for theoretical understanding of deep learning; on the other hand, to verify the conjecture, we propose an approach that generates deep forest holding these characteristics. This is a decision-tree ensemble approach, with fewer hyper-parameters than deep neural networks, and its model complexity can be automatically determined in a data-dependent way. Experiments show that its performance is quite robust to hyper-parameter settings, such that in most cases, even across different data from different domains, it is able to achieve excellent performance by using the same default setting. This study opens the door to deep learning based on non-differentiable modules without gradient-based adjustment, and exhibits the possibility of constructing deep models without backpropagation. | Zhi-Hua Zhou Ji Feng | 2019 | National Science Review2019，6，1： | 52 |
| 2 | The State of the Art of Data Science and Engineering in Structural Health Monitoring显示文摘Structural health monitoring (SHM) is a multi-discipline field that involves the automatic sensing of structural loads and response by means of a large number of sensors and instruments, followed by a diagnosis of the structural health based on the collected data. Because an SHM system implemented into a structure automatically senses, evaluates, and warns about structural conditions in real time, massive data are a significant feature of SHM. The techniques related to massive data are referred to as data science and engineering, and include acquisition techniques, transition techniques, management techniques, and processing and mining algorithms for massive data. This paper provides a brief review of the state of the art of data science and engineering in SHM as investigated by these authors, and covers the compressive sampling-based data-acquisition algorithm, the anomaly data diagnosis approach using a deep learning algorithm, crack identification approaches using computer vision techniques, and condition assessment approaches for bridges using machine learning algorithms. Future trends are discussed in the conclusion. | Yuequan Bao Zhicheng Chen Shiyin Wei Yang Xu Zhiyi Tang Hui Li | 2019 | Engineering2019，5，2： | 47 |
| 3 | Diagnostic accuracy of a deep learning approach to calculate FFR from coronary CT angiography显示文摘Background The computational fluid dynamics(CFD)approach has been frequently applied to compute the fractional flow reserve(FFR)using computed tomography angiography(CTA).This technique is efficient.We developed the DEEPVESSEL-FFR platform using the emerging deep learning technique to calculate the FFR value out of CTA images in five minutes.This study is to evaluate the DEEPVESSEL-FFR platform using the emerging deep learning technique to calculate the FFR value from CTA images as an efficient method.Methods A single-center,prospective study was conducted and 63 patients were enrolled for the evaluation of the diagnostic performance of DEEPVESSEL-FFR.Automatic quantification method for the three-dimensional coronary arterial geometry and the deep learning based prediction of FFR were developed to assess the ischemic risk of the stenotic coronary arteries.Diagnostic performance of the DEEPVESSEL-FFR was assessed by using wire-based FFR as reference standard.The primary evaluation factor was defined by using the area under receiver-operation characteristics curve(AUC)analysis.Results For per-patient level,taking the cut-off value<0.8 referring to the FFR measurement,DEEPVESSEL-FFR presented higher diagnostic performance in determining ischemia-related lesions with area under the curve of 0.928 compare to CTA stenotic severity 0.664.DEEPVESSEL-FFR correlated with FFR(R=0.686,P<0.001),with a mean di&ference of-0.006士0.0091(P=0.619).The secondary evaluation factors,indicating per vessel accuracy,sensitivity,specificity,positive predictive value,and negative predictive value were 87.3%,97.14%,75%,82.93%,and 95.45%,respectively.Conclusion DEEPVESSEL-FFR is a novel method that allows efficient assessment of the functional significance of coronary stenosis. | Zhi-Qiang WANG Yu-Jie ZHOU Ying-Xin ZHAO Dong-Mei SHI Yu-Yang LIU Wei LIU Xiao-Li LIU Yue-Ping LI | 2019 | Journal of Geriatric Cardiology2019，16，1： | 37 |
| 4 | Deep Learning in Medical Ultrasound Analysis: A Review显示文摘Ultrasound (US) has become one of the most commonly performed imaging modalities in clinical practice. It is a rapidly evolving technology with certain advantages and with unique challenges that include low imaging quality and high variability. From the perspective of image analysis, it is essential to develop advanced automatic US image analysis methods to assist in US diagnosis and/or to make such assessment more objective and accurate. Deep learning has recently emerged as the leading machine learning tool in various research fields, and especially in general imaging analysis and computer vision. Deep learning also shows huge potential for various automatic US image analysis tasks. This review first briefly introduces several popular deep learning architectures, and then summarizes and thoroughly discusses their applications in various specific tasks in US image analysis, such as classification, detection, and segmentation. Finally, the open challenges and potential trends of the future application of deep learning in medical US image analysis are discussed. | Shengfeng Liu Yi Wang Xin Yang Baiying Lei Li Liu Shawn Xiang Li Dong Ni Tianfu Wang | 2019 | Engineering2019，5，2： | 24 |
| 5 | Artificial intelligence in medical imaging of the liver显示文摘Artificial intelligence(AI), particularly deep learning algorithms, is gaining extensive attention for its excellent performance in image-recognition tasks. They can automatically make a quantitative assessment of complex medical image characteristics and achieve an increased accuracy for diagnosis with higher efficiency. AI is widely used and getting increasingly popular in the medical imaging of the liver, including radiology, ultrasound, and nuclear medicine. AI can assist physicians to make more accurate and reproductive imaging diagnosis and also reduce the physicians' workload. This article illustrates basic technical knowledge about AI, including traditional machine learning and deep learning algorithms, especially convolutional neural networks, and their clinical application in the medical imaging of liver diseases, such as detecting and evaluating focal liver lesions, facilitating treatment, and predicting liver treatment response. We conclude that machine-assisted medical services will be a promising solution for future liver medical care. Lastly, we discuss the challenges and future directions of clinical application of deep learning techniques. | Li-Qiang Zhou Jia-Yu Wang Song-Yuan Yu Ge-Ge Wu Qi Wei You-Bin Deng Xing-Long Wu Xin-Wu Cui Christoph F Dietrich | 2019 | World Journal of Gastroenterology2019，25，6： | 21 |
| 6 | Machine learning methods for rockburst prediction-state-of-the-art review显示文摘One of the most serious mining disasters in underground mines is rockburst phenomena.They can lead to injuries and even fatalities as well as damage to underground openings and mining equipment.This has forced many researchers to investigate alternative methods to predict the potential for rockburst occurrence.However,due to the highly complex relation between geological,mechanical and geometric parameters of the mining environment,the traditional mechanics-based prediction methods do not always yield precise results.With the emergence of machine learning methods,a breakthrough in the prediction of rockburst occurrence has become possible in recent years.This paper presents a state-ofthe-art review of various applications of machine learning methods for the prediction of rockburst potential.First,existing rockburst prediction methods are introduced,and the limitations of such methods are highlighted.A brief overview of typical machine learning methods and their main features as predictive tools is then presented.The current applications of machine learning models in rockburst prediction are surveyed,with related mechanisms,technical details and performance analysis. | Yuanyuan Pu Derek B.Apel Victor Liu Hani Mitri | 2019 | International Journal of Mining Science and Technology2019，29，4： | 19 |
| 7 | Photogrammetry and Deep Learning显示文摘Deep learning has become popular and the mainstream technology in many researches related to learning,and has shown its impact on photogrammetry.According to the definition of photogrammetry,that is,a subject that researches shapes,locations,sizes,characteristics and inter-relationships of real objects from optical images,photogrammetry considers two aspects,geometry and semantics.From the two aspects,we review the history of deep learning and discuss its current applications on photogrammetry,and forecast the future development of photogrammetry.In geometry,the deep convolutional neural network(CNN)has been widely applied in stereo matching,SLAM and 3D reconstruction,and has made some effects but needs more improvement.In semantics,conventional methods that have to design empirical and handcrafted features have failed to extract the semantic information accurately and failed to produce types of“semantic thematic map”as 4D productions(DEM,DOM,DLG,DRG)of photogrammetry.This causes the semantic part of photogrammetry be ignored for a long time.The powerful generalization capacity,ability to fit any functions and stability under types of situations of deep leaning is making the automatic production of thematic maps possible.We review the achievements that have been obtained in road network extraction,building detection and crop classification,etc.,and forecast that producing high-accuracy semantic thematic maps directly from optical images will become reality and these maps will become a type of standard products of photogrammetry.At last,we introduce our two current researches related to geometry and semantics respectively.One is stereo matching of aerial images based on deep learning and transfer learning;the other is precise crop classification from satellite spatio-temporal images based on 3D CNN. | Jianya GONG Shunping JI | 2018 | Journal of Geodesy and Geoinformation Science2018，1，1： | 19 |
| 8 | FUSAR-Ship:building a high-resolution SAR-AIS matchup dataset of Gaofen-3 for ship detection and recognition显示文摘Gaofen-3 (GF-3) is China's first civil C-band fully polarimetric spaceborne synthetic aperture radar (SAR) primarily missioned for ocean remote sensing and marine monitoring. This paper proposes an automatic sea segmentation, ship detection, and SAR-AIS matchup procedure and an extensible marine target taxonomy of 15 primary ship categories, 98 sub-categories, and many non-ship targets. The FUSAR-Ship high-resolution GF-3 SAR dataset is constructed by running the procedure on a total of 126 GF-3 scenes covering a large variety of sea, land, coast, river and island scenarios. It includes more than 5000 ship chips with AIS messages as well as samples of strong scatterer, bridge, coastal land, islands, sea and land clutter. FUSAR-Ship is intended as an open benchmark dataset for ship and marine target detection and recognition. A preliminary 8-type ship classification experiment based on convolutional neural networks demonstrated that an average of 79% test accuracy can be achieved. | Xiyue HOU Wei AO Qian SONG Jian LAI Haipeng WANG Feng XU | 2020 | Science China(Information Sciences)2020，63，4： | 19 |
| 9 | A Deep Adaptive Learning Method for Rolling Bearing Fault Diagnosis Using Immunity显示文摘The extraction of rolling bearing fault features using traditional diagnostic methods is not sufficiently comprehensive and the features are often chosen subjectively and depend on human experience. In this paper, an improved deep convolutional process is used to extract a set of features adaptively. The hidden multi-layer feature of deep convolutional neural networks is also exploited to improve the extraction features. A deterministic detection of low-confidence samples is performed to ensure the reliability of the recognition results and to decrease the rate of false positives by evaluating the diagnosis of the deep convolutional neural network. To improve the efficiency of the continuous learning elements of the rolling bearing fault diagnosis, a clone learning strategy based on cloning and mutation operations is proposed. The experimental results show that the proposed deep convolutional neural network model can extract multiple rolling bearing fault features, improve classification and detection accuracy by reducing the false positive rate when diagnosing rolling bearing faults, and accelerate learning efficiency when using low-confidence rolling bearing fault samples. | Yuling Tian Xiangyu Liu | 2019 | Tsinghua Science and Technology2019，24，6： | 18 |
| 10 | A general end-to-end diagnosis framework for manufacturing systems显示文摘The manufacturing sector is envisioned to be heavily influenced by artificial-intelligence-based technologies with the extraordinary increases in computational power and data volumes. A central challenge in the manufacturing sector lies in the requirement of a general framework to ensure satisfied diagnosis and monitoring performances in different manufacturing applications. Here, we propose a general data-driven,end-to-end framework for the monitoring of manufacturing systems. This framework, derived from deep-learning techniques, evaluates fused sensory measurements to detect and even predict faults and wearing conditions. This work exploits the predictive power of deep learning to automatically extract hidden degradation features from noisy, time-course data. We have experimented the proposed framework on 10 representative data sets drawn from a wide variety of manufacturing applications. Results reveal that the framework performs well in examined benchmark applications and can be applied in diverse contexts,indicating its potential use as a critical cornerstone in smart manufacturing. | Ye Yuan Guijun Ma Cheng Cheng Beitong Zhou Huan Zhao Hai-Tao Zhang Han Ding | 2020 | National Science Review2020，7，2： | 18 |
| 11 | Deep Learning Based Single Image Super-resolution:A Survey显示文摘Single image super-resolution has attracted increasing attention and has a wide range of applications in satellite imaging, medical imaging, computer vision, security surveillance imaging, remote sensing, objection detection, and recognition. Recently, deep learning techniques have emerged and blossomed, producing ' the state-of-the-art” in many domains. Due to their capability in feature extraction and mapping, it is very helpful to predict high-frequency details lost in low-resolution images. In this paper, we give an overview of recent advances in deep learning-based models and methods that have been applied to single image super-resolution tasks. We also summarize, compare and discuss various models from the past and present for comprehensive understanding and finally provide open problems and possible directions for future research. | Viet Khanh Ha Jin-Chang Ren Xin-Ying Xu Sophia Zhao Gang Xie Valentin Masero Amir Hussain | 2019 | International Journal of Automation and computing2019，16，4： | 17 |
| 12 | Satellite Image Matching Method Based on Deep Convolutional Neural Network显示文摘This article focuses on the first aspect of the album of deep learning: the deep convolutional method. The traditional matching point extraction algorithm typically uses manually designed feature descriptors and the shortest distance between them to match as the matching criterion. The matching result can easily fall into a local extreme value, which causes missing of the partial matching point. Targeting this problem, we introduce a two-channel deep convolutional neural network based on spatial scale convolution, which performs matching pattern learning between images to realize satellite image matching based on a deep convolutional neural network. The experimental results show that the method can extract the richer matching points in the case of heterogeneous, multi-temporal and multi-resolution satellite images, compared with the traditional matching method. In addition, the accuracy of the final matching results can be maintained at above 90%. | Dazhao FAN Yang DONG Yongsheng ZHANG | 2019 | Journal of Geodesy and Geoinformation Science2019，2，2： | 16 |
| 13 | Deep-learning classifier with ultrawide-field fundus ophthalmoscopy for detecting branch retinal vein occlusion显示文摘AIM: To investigate and compare the efficacy of two machine-learning technologies with deep-learning(DL) and support vector machine(SVM) for the detection of branch retinal vein occlusion(BRVO) using ultrawide-field fundus images. METHODS: This study included 237 images from 236 patients with BRVO with a mean±standard deviation of age 66.3±10.6 y and 229 images from 176 non-BRVO healthy subjects with a mean age of 64.9±9.4 y. Training was conducted using a deep convolutional neural network using ultrawide-field fundus images to construct the DL model. The sensitivity, specificity, positive predictive value(PPV), negative predictive value(NPV) and area under the curve(AUC) were calculated to compare the diagnostic abilities of the DL and SVM models. RESULTS: For the DL model, the sensitivity, specificity, PPV, NPV and AUC for diagnosing BRVO was 94.0%(95%CI: 93.8%-98.8%), 97.0%(95%CI: 89.7%-96.4%), 96.5%(95%CI: 94.3%-98.7%), 93.2%(95%CI: 90.5%-96.0%) and 0.976(95%CI: 0.960-0.993), respectively. In contrast, for the SVM model, these values were 80.5%(95%CI: 77.8%-87.9%), 84.3%(95%CI: 75.8%-86.1%), 83.5%(95%CI: 78.4%-88.6%), 75.2%(95%CI: 72.1%-78.3%) and 0.857(95%CI: 0.811-0.903), respectively. The DL model outperformed the SVM model in all the aforementioned parameters(P<0.001). CONCLUSION: These results indicate that the combination of the DL model and ultrawide-field fundus ophthalmoscopy may distinguish between healthy and BRVO eyes with a high level of accuracy. The proposed combination may be used for automatically diagnosing BRVO in patients residing in remote areas lacking access to an ophthalmic medical center. | Daisuke Nagasato Hitoshi Tabuchi Hideharu Ohsugi Hiroki Masumoto Hiroki Enno Naofumi Ishitobi Tomoaki Sonobe Masahiro Kameoka Masanori Niki Yoshinori Mitamura | 2019 | International Journal of Ophthalmology(English edition)2019，12，1： | 16 |
| 14 | A Deep Learning Based Energy-Efficient Computational Offloading Method in Internet of Vehicles显示文摘With the emergence of advanced vehicular applications, the challenge of satisfying computational and communication demands of vehicles has become increasingly prominent. Fog computing is a potential solution to improve advanced vehicular services by enabling computational offloading at the edge of network. In this paper, we propose a fog-cloud computational offloading algorithm in Internet of Vehicles(IoV) to both minimize the power consumption of vehicles and that of the computational facilities. First, we establish the system model, and then formulate the offloading problem as an optimization problem, which is NP-hard. After that, we propose a heuristic algorithm to solve the offloading problem gradually. Specifically, we design a predictive combination transmission mode for vehicles, and establish a deep learning model for computational facilities to obtain the optimal workload allocation. Simulation results demonstrate the superiority of our algorithm in energy efficiency and network latency. | Xiaojie Wang Xiang Wei Lei Wang | 2019 | China Communications2019，16，3： | 15 |
| 15 | Adversarial Attacks and Defenses in Images, Graphs and Text: A Review显示文摘Deep neural networks(DNN)have achieved unprecedented success in numerous machine learning tasks in various domains.However,the existence of adversarial examples raises our concerns in adopting deep learning to safety-critical applications.As a result,we have witnessed increasing interests in studying attack and defense mechanisms for DNN models on different data types,such as images,graphs and text.Thus,it is necessary to provide a systematic and comprehensive overview of the main threats of attacks and the success of corresponding countermeasures.In this survey,we review the state of the art algorithms for generating adversarial examples and the countermeasures against adversarial examples,for three most popular data types,including images,graphs and text. | Han Xu Yao Ma Hao-Chen Liu Debayan Deb Hui Liu Ji-Liang Tang Anil K.Jain | 2020 | International Journal of Automation and computing2020，17，2： | 15 |
| 16 | Deep Learning Based 2D Human Pose Estimation:A Survey显示文摘Human pose estimation has received significant attention recently due to its various applications in the real world. As the performance of the state-of-the-art human pose estimation methods can be improved by deep learning, this paper presents a comprehensive survey of deep learning based human pose estimation methods and analyzes the methodologies employed. We summarize and discuss recent works with a methodologybased taxonomy. Single-person and multi-person pipelines are first reviewed separately. Then, the deep learning techniques applied in these pipelines are compared and analyzed. The datasets and metrics used in this task are also discussed and compared. The aim of this survey is to make every step in the estimation pipelines interpretable and to provide readers a readily comprehensible explanation. Moreover, the unsolved problems and challenges for future research are discussed. | Qi Dang Jianqin Yin Bin Wang Wenqing Zheng | 2019 | Tsinghua Science and Technology2019，24，6： | 14 |
| 17 | Using deep learning to detect small targets in infrared oversampling images显示文摘According to the oversampling imaging characteristics, an infrared small target detection method based on deep learning is proposed. A 7-layer deep convolutional neural network(CNN) is designed to automatically extract small target features and suppress clutters in an end-to-end manner. The input of CNN is an original oversampling image while the output is a cluttersuppressed feature map. The CNN contains only convolution and non-linear operations, and the resolution of the output feature map is the same as that of the input image. The L1-norm loss function is used, and a mass of training data is generated to train the network effectively. Results show that compared with several baseline methods, the proposed method improves the signal clutter ratio gain and background suppression factor by 3 – 4 orders of magnitude, and has more powerful target detection performance. | LIN Liangkui WANG Shaoyou TANG Zhongxing | 2018 | Journal of Systems Engineering and Electronics2018，29，5： | 14 |
| 18 | Emphasizing Essential Words for Sentiment Classification Based onRecurrent Neural Networks显示文摘With the explosion of online communication and publication, texts become obtainable via forums, chat mes-sages, blogs, book reviews and movie reviews. Usually, these texts are much short and noisy without sufficient statisticalsignals and enough information for a good semantic analysis. Traditional natural language processing methods such asBow-of-Word (BOW) based probabilistic latent semantic models fail to achieve high performance due to the short textenvironment. Recent researches have focused on the correlations between words, i.e., term dependencies, which could behelpful for mining latent semantics hidden in short texts and help people to understand them. Long short-term memory(LSTM) network can capture term dependencies and is able to remember the information for long periods of time. LSTMhas been widely used and has obtained promising results in variants of problems of understanding latent semantics of texts.At the same time, by analyzing the texts, we find that a number of keywords contribute greatly to the semantics of thetexts. In this paper, we establish a keyword vocabulary and propose an LSTM-based model that is sensitive to the wordsin the vocabulary; hence, the keywords leverage the semantics of the full document. The proposed model is evaluated ina short-text sentiment analysis task on two datasets: IMDB and SemEval-2016, respectively. Experimental results demon-strate that our model outperforms the baseline LSTM by 1%-2% in terms of accuracy and is effective with significantperformance enhancement over several non-recurrent neural network latent semantic models (especially in dealing withshort texts). We also incorporate the idea into a variant of LSTM named the gated recurrent unit (GRU) model and achievegood performance, which proves that our method is general enough to improve different deep learning models. | Fei Hu Li Li Zi-Li Zhang Jing-Yuan Wang Xiao-Fei Xu | 2017 | Journal of Computer Science & Technology2017，32，4： | 13 |
| 19 | Identity-aware convolutional neural networks for facial expression recognition显示文摘Facial expression recognition is a hot topic in computer vision, but it remains challenging due to the feature inconsistency caused by person-specific characteristics of facial expressions.To address such a challenge, and inspired by the recent success of deep identity network(Deep ID-Net) for face identification, this paper proposes a novel deep learning based framework for recognising human expressions with facial images. Compared to the existing deep learning methods, our proposed framework, which is based on multi-scale global images and local facial patches,can significantly achieve a better performance on facial expression recognition. Finally, we verify the effectiveness of our proposed framework through experiments on the public benchmarking datasets JAFFE and extended Cohn-Kanade(CK+). | Chongsheng Zhang Pengyou Wang Ke Chen Joni-Kristian Kamarainen | 2017 | Journal of Systems Engineering and Electronics2017，28，4： | 12 |
| 20 | Artificial intelligence in breast ultrasound显示文摘Artificial intelligence(AI) is gaining extensive attention for its excellent performance in image-recognition tasks and increasingly applied in breast ultrasound. AI can conduct a quantitative assessment by recognizing imaging information automatically and make more accurate and reproductive imaging diagnosis. Breast cancer is the most commonly diagnosed cancer in women,severely threatening women's health, the early screening of which is closely related to the prognosis of patients. Therefore, utilization of AI in breast cancer screening and detection is of great significance, which can not only save time for radiologists, but also make up for experience and skill deficiency on some beginners. This article illustrates the basic technical knowledge regarding AI in breast ultrasound, including early machine learning algorithms and deep learning algorithms, and their application in the differential diagnosis of benign and malignant masses. At last, we talk about the future perspectives of AI in breast ultrasound. | Ge-Ge Wu Li-Qiang Zhou Jian-Wei Xu Jia-Yu Wang Qi Wei You-Bin Deng Xin-Wu Cui Christoph F Dietrich | 2019 | World Journal of Radiology2019，11，2： | 12 |
您所在的机构暂未开通此部分的功能，请联系管理员