资源类型

期刊论文 803

年份

2024 2

2023 102

2022 120

2021 68

2020 73

2019 54

2018 50

2017 47

2016 33

2015 43

2014 16

2013 17

2012 16

2011 10

2010 12

2009 11

2008 18

2007 21

2006 21

2005 6

展开 ︾

关键词

机器学习 27

深度学习 15

人工智能 13

多目标优化 9

神经网络 4

COVID-19 3

5G 2

优化 2

可靠性灵敏度 2

并联机构 2

强化学习 2

材料设计 2

稳健设计 2

结构健康监测 2

高层建筑 2

2 Mb/s高速信令 1

2D—3D配准 1

3D打印 1

6G 1

展开 ︾

检索范围：

排序： 展示方式：

View-invariant human action recognition via robust locally adaptive multi-view learning

Jia-geng FENG,Jun XIAO

《信息与电子工程前沿（英文）》 2015年 第16卷 第11期   页码 917-920 doi: 10.1631/FITEE.1500080

摘要： Human action recognition is currently one of the most active research areas in computer vision. It has been widely used in many applications, such as intelligent surveillance, perceptual interface, and content-based video retrieval. However, some extrinsic factors are barriers for the development of action recognition; e.g., human actions may be observed from arbitrary camera viewpoints in realistic scene. Thus, view-invariant analysis becomes important for action recognition algorithms, and a number of researchers have paid much attention to this issue. In this paper, we present a multi-view learning approach to recognize human actions from different views. As most existing multi-view learning algorithms often suffer from the problem of lacking data adaptiveness in the nearest neighborhood graph construction procedure, a robust locally adaptive multi-view learning algorithm based on learning multiple local L1-graphs is proposed. Moreover, an efficient iterative optimization method is proposed to solve the proposed objective function. Experiments on three public view-invariant action recognition datasets, i.e., ViHASi, IXMAS, and WVU, demonstrate data adaptiveness, effectiveness, and efficiency of our algorithm. More importantly, when the feature dimension is correctly selected (i.e.,>60), the proposed algorithm stably outperforms state-of-the-art counterparts and obtains about 6% improvement in recognition accuracy on the three datasets.

关键词： View-invariant     Action recognition     Multi-view learning     L1-norm     Local learning    

HTML PDF 收藏

基于迁移学习与多视角感兴趣点的膝关节运动追踪网络 Article

王聪, 谢帅宁, 李康, 王重阳, 刘旭东, 赵亮, 蔡宗远

《工程（英文）》 2021年 第7卷 第6期   页码 881-888 doi: 10.1016/j.eng.2020.03.016

摘要：

近年来，深度学习为一种基于二维（2D）—三维（3D）配准技术以测量人体膝关节运动的方法，该方法提供了快速完成配准并增加捕捉范围的可能性。但这类方法受限于大量的数据需求，因此，我们提出了一种基于特征的迁移学习法，用于提取荧光透视影像的特征。通过三个受试者以及不到100对荧光透视影像，我们获得了40%的平均配准成功率。本研究提出的基于学习的配准方法，可在荧光透视影像数量有限时使用。

关键词： 2D—3D配准     机器学习     领域自适应     点对应    

HTML PDF 收藏

论文演化图：学术文献多视角结构化检索 None

Dan-ping LIAO, Yun-tao QIAN

《信息与电子工程前沿（英文）》 2019年 第20卷 第2期   页码 187-205 doi: 10.1631/FITEE.1700105

摘要： 学术文献检索关注于选取最可能符合用户信息需求的论文。目前大部分检索系统局限于输出相关文献列表，而这些检出文献相互独立。本文旨在揭示检索结果的相互关系。提出一种为学术文献建立结构化检索结果的方法，称为论文演化图（PEG）。PEG采用多个演化链描述查询输入信息在不同主题方向的演化情况。通过论文作者、参考文献引用、论文内容信息这3个视角，PEG能够发现文献之间各种潜在关系，并多视角展示文献演化过程。该文献检索系统支持关键词、单篇论文、双论文3种查询方式。PEG构造主要有3个步骤：首先，采用元图分解法把文献软聚合为多个群落，获取每篇论文的主题分布；其次，从与查询相关的文献群落中提取主题连贯性演化链。每条演化链反映查询信息的某一视角；最后，提取的演化链组合形成论文演化图，可以覆盖查询涉及的所有主题。基于真实文献数据库的实验结果表明，该方法能够建立对用户有意义的论文演化图。

关键词： 论文演化图；学术文献检索；元图分解；主题连贯性    

HTML PDF 收藏

Development of machine learning multi-city model for municipal solid waste generation prediction

《环境科学与工程前沿（英文）》 2022年 第16卷 第9期 doi: 10.1007/s11783-022-1551-6

摘要：

● A database of municipal solid waste (MSW) generation in China was established.

关键词： Municipal solid waste     Machine learning     Multi-cities     Gradient boost regression tree    

HTML PDF 收藏

Unknown fault detection for EGT multi-temperature signals based on self-supervised feature learning and

《能源前沿（英文）》 2023年 第17卷 第4期   页码 527-544 doi: 10.1007/s11708-023-0880-x

摘要： Intelligent power systems can improve operational efficiency by installing a large number of sensors. Data-based methods of supervised learning have gained popularity because of available Big Data and computing resources. However, the common paradigm of the loss function in supervised learning requires large amounts of labeled data and cannot process unlabeled data. The scarcity of fault data and a large amount of normal data in practical use pose great challenges to fault detection algorithms. Moreover, sensor data faults in power systems are dynamically changing and pose another challenge. Therefore, a fault detection method based on self-supervised feature learning was proposed to address the above two challenges. First, self-supervised learning was employed to extract features under various working conditions only using large amounts of normal data. The self-supervised representation learning uses a sequence-based Triplet Loss. The extracted features of large amounts of normal data are then fed into a unary classifier. The proposed method is validated on exhaust gas temperatures (EGTs) of a real-world 9F gas turbine with sudden, progressive, and hybrid faults. A comprehensive comparison study was also conducted with various feature extractors and unary classifiers. The results show that the proposed method can achieve a relatively high recall for all kinds of typical faults. The model can detect progressive faults very quickly and achieve improved results for comparison without feature extractors in terms of F1 score.

关键词： fault detection     unary classification     self-supervised representation learning     multivariate nonlinear time series    

HTML PDF 收藏

Integrated energy view of wastewater treatment: A potential of electrochemical biodegradation

《环境科学与工程前沿（英文）》 2022年 第16卷 第4期 doi: 10.1007/s11783-021-1486-3

摘要：

• Energy is needed to accelerate the biological wastewater treatment.

关键词： Biological wastewater treatment     Integrated energy view     Electroactive bacteria     Extracellular electron transfer    

HTML PDF 收藏

Multi-color space threshold segmentation and self-learning k-NN algorithm for surge test EUT status

Jian HUANG,Gui-xiong LIU

《机械工程前沿（英文）》 2016年 第11卷 第3期   页码 311-315 doi: 10.1007/s11465-016-0376-z

摘要：

The identification of targets varies in different surge tests. A multi-color space threshold segmentation and self-learning k-nearest neighbor algorithm (k-NN) for equipment under test status identification was proposed after using feature matching to identify equipment status had to train new patterns every time before testing. First, color space (L*a*b*, hue saturation lightness (HSL), hue saturation value (HSV)) to segment was selected according to the high luminance points ratio and white luminance points ratio of the image. Second, the unknown class sample Sr was classified by the k-NN algorithm with training set Tz according to the feature vector, which was formed from number of pixels, eccentricity ratio, compactness ratio, and Euler’s numbers. Last, while the classification confidence coefficient equaled k, made Sr as one sample of pre-training set Tz′. The training set Tz increased to Tz+1 by Tz′ if Tz′ was saturated. In nine series of illuminant, indicator light, screen, and disturbances samples (a total of 21600 frames), the algorithm had a 98.65% identification accuracy, also selected five groups of samples to enlarge the training set from T0 to T5 by itself.

关键词： multi-color space     k-nearest neighbor algorithm (k-NN)     self-learning     surge test    

HTML PDF 收藏

把握生物经济时代精神，实践进步的幸福观

甘自恒

《中国工程科学》 2007年 第9卷 第2期   页码 5-11

摘要：

据预测，2020年，全球将进入以生物技术产业为主导产业的生物经济时代；阐述了生物经济的提出、 分类、特征和定义；主张把握生物经济时代精神，实践进步的幸福观；探讨了为什么要强调谋求人民幸福，什 么是进步的幸福观，应提倡那些进步的幸福观，以及我国科技界应该怎样实践进步的幸福观。

关键词： 生物经济     幸福     进步的幸福观    

HTML PDF 收藏

基于RGBD和稀疏学习的鲁棒目标跟踪 Article

Zi-ang MA, Zhi-yu XIANG

《信息与电子工程前沿（英文）》 2017年 第18卷 第7期   页码 989-1001 doi: 10.1631/FITEE.1601338

摘要： 鲁棒目标跟踪近年来成为计算机视觉领域一项重要的且极具挑战性的研究方向。随着深度传感器的普及，深度信息因其对光照变化与遮挡表现出一定的鲁棒性而被广泛应用于视觉目标跟踪算法中。本文提出了一种基于RGBD和稀疏学习的跟踪算法，从三个方面将深度信息应用到稀疏学习跟踪框架。首先将深度图像特征结合现有的基于彩色图像的视觉特征用于目标外观的鲁棒特征描述。为了适应跟踪过程中的各种遮挡情况，我们设计了一种特殊的遮挡物模板用于增广现有的超完备字典。最后，我们进一步提出了一种基于深度信息的遮挡物检测方法用于有效地指示模板更新。基于KITTI和Princeton数据集的大量实验证明了所提出算法的跟踪效果优于时下最先进的多种跟踪器，包括基于稀疏学习的跟踪以及基于RGBD的跟踪。

关键词： 目标跟踪；稀疏学习；深度视角；遮挡物模板；深度图像特征    

HTML PDF 收藏

Deep convolutional neural network for multi-level non-invasive tunnel lining assessment

《结构与土木工程前沿（英文）》 2022年 第16卷 第2期   页码 214-223 doi: 10.1007/s11709-021-0800-2

摘要： In recent years, great attention has focused on the development of automated procedures for infrastructures control. Many efforts have aimed at greater speed and reliability compared to traditional methods of assessing structural conditions. The paper proposes a multi-level strategy, designed and implemented on the basis of periodic structural monitoring oriented to a cost- and time-efficient tunnel control plan. Such strategy leverages the high capacity of convolutional neural networks to identify and classify potential critical situations. In a supervised learning framework, Ground Penetrating Radar (GPR) profiles and the revealed structural phenomena have been used as input and output to train and test such networks. Image-based analysis and integrative investigations involving video-endoscopy, core drilling, jacking and pull-out testing have been exploited to define the structural conditions linked to GPR profiles and to create the database. The degree of detail and accuracy achieved in identifying a structural condition is high. As a result, this strategy appears of value to infrastructure managers who need to reduce the amount and invasiveness of testing, and thus also to reduce the time and costs associated with inspections made by highly specialized technicians.

关键词： concrete structure     GPR     damage classification     convolutional neural network     transfer learning    

HTML PDF 收藏

基于最大间隔的贝叶斯分类器 Article

Tao-cheng HU,Jin-hui YU

《信息与电子工程前沿（英文）》 2016年 第17卷 第10期   页码 973-981 doi: 10.1631/FITEE.1601078

摘要： 概要：多分类学习中经常需要考虑在泛化性能和计算开销间进行权衡。本文提出一个生成式概率多分类器，综合考虑了泛化性和学习/预测速率。我们首先证明了我们的分类器具有最大间隔性质，这意味着对于未来数据的预测精度几乎和训练阶段一样高。此外，我们消除了目标函数中的大量的局部变元，极大地简化了优化问题。通过凸分析和概率语义分析，我们设计了高效的在线算法，与经典情形的最大不同在于这个算法使用聚集而非平均化处理梯度。实验证明了我们的算法具有很好的泛化性能和收敛速度。

关键词： 多类学习；最大间隔学习；在线算法    

HTML PDF 收藏

Understand the local and regional contributions on air pollution from the view of human health impacts

《环境科学与工程前沿（英文）》 2021年 第15卷 第5期 doi: 10.1007/s11783-020-1382-2

摘要：

• PM2.5-related deaths were estimated to be 227 thousand in BTH & surrounding regions.

关键词： PM2.5     Regional transport     Local emissions     Health impact     Environmental inequality    

HTML PDF 收藏

River restoration challenges with a specific view on hydromorphology

Jianhua LI, Stephan HOERBINGER, Clemens WEISSTEINER, Lingmin PENG, Hans Peter RAUCH

《结构与土木工程前沿（英文）》 2020年 第14卷 第5期   页码 1033-1038 doi: 10.1007/s11709-020-0665-9

HTML PDF 收藏

A hybrid Wavelet-CNN-LSTM deep learning model for short-term urban water demand forecasting

《环境科学与工程前沿（英文）》 2023年 第17卷 第2期 doi: 10.1007/s11783-023-1622-3

摘要：

● A novel deep learning framework for short-term water demand forecasting.

关键词： Short-term water demand forecasting     Long-short term memory neural network     Convolutional Neural Network     Wavelet multi-resolution analysis     Data-driven models    

HTML PDF 收藏

Sliding window games for cooperative building temperature control using a distributed learning method

Zhaohui ZHANG, Ruilong DENG, Tao YUAN, S. Joe QIN

《工程管理前沿（英文）》 2017年 第4卷 第3期   页码 304-314 doi: 10.15302/J-FEM-2017045

摘要： In practice, an energy consumer often consists of a set of residential or commercial buildings, with individual units that are expected to cooperate to achieve overall optimization under modern electricity operations, such as time-of-use price. Global utility is decomposed to the payoff of each player, and each game is played over a prediction horizon through the design of a series of sliding window games by treating each building as a player. During the games, a distributed learning algorithm based on game theory is proposed such that each building learns to play a part of the global optimum through state transition. The proposed scheme is applied to a case study of three buildings to demonstrate its effectiveness.

关键词： game theory     demand response     HVAC control     multi-building system    

HTML PDF 收藏

标题 作者 时间 类型 操作

View-invariant human action recognition via robust locally adaptive multi-view learning

Jia-geng FENG,Jun XIAO

期刊论文

基于迁移学习与多视角感兴趣点的膝关节运动追踪网络

王聪, 谢帅宁, 李康, 王重阳, 刘旭东, 赵亮, 蔡宗远

期刊论文

论文演化图：学术文献多视角结构化检索

Dan-ping LIAO, Yun-tao QIAN

期刊论文

Development of machine learning multi-city model for municipal solid waste generation prediction

期刊论文

Unknown fault detection for EGT multi-temperature signals based on self-supervised feature learning and

期刊论文

Integrated energy view of wastewater treatment: A potential of electrochemical biodegradation

期刊论文

Multi-color space threshold segmentation and self-learning k-NN algorithm for surge test EUT status

Jian HUANG,Gui-xiong LIU

期刊论文

把握生物经济时代精神，实践进步的幸福观

甘自恒

期刊论文

基于RGBD和稀疏学习的鲁棒目标跟踪

Zi-ang MA, Zhi-yu XIANG

期刊论文

Deep convolutional neural network for multi-level non-invasive tunnel lining assessment

期刊论文

基于最大间隔的贝叶斯分类器

Tao-cheng HU,Jin-hui YU

期刊论文

Understand the local and regional contributions on air pollution from the view of human health impacts

期刊论文

River restoration challenges with a specific view on hydromorphology

Jianhua LI, Stephan HOERBINGER, Clemens WEISSTEINER, Lingmin PENG, Hans Peter RAUCH

期刊论文

A hybrid Wavelet-CNN-LSTM deep learning model for short-term urban water demand forecasting

期刊论文

Sliding window games for cooperative building temperature control using a distributed learning method

Zhaohui ZHANG, Ruilong DENG, Tao YUAN, S. Joe QIN

期刊论文