资源类型

期刊论文 16

年份

2024 4

2023 3

2022 4

2020 2

2018 1

2017 1

2015 1

展开 ︾

关键词

语义通信 2

6G 1

PowerShell；抽象语法树；混淆和解混淆；恶意脚本检测 1

交通规则 1

形式化 1

数字化 1

无监督领域自适应；优化步骤；跨域判别表示；语义判别 1

智能反射面 1

智能通信 1

机器翻译；语义角色；句法树；串到树模型 1

查询子主题挖掘；查询意图；分布式表示；语义组合 1

模分多址（MDMA）；语义通信；多址技术 1

第六代（6G）移动通信 1

联邦学习 1

自动驾驶 1

语义信息 1

通信感知计算一体化 1

验证 1

展开 ︾

检索范围：

排序： 展示方式：

Digital twin-enabled smart facility management: A bibliometric review

《工程管理前沿（英文）》 2024年 第11卷 第1期   页码 32-49 doi: 10.1007/s42524-023-0254-4

摘要： In recent years, the architecture, engineering, construction, and facility management (FM) industries have been applying various emerging digital technologies to facilitate the design, construction, and management of infrastructure facilities. Digital twin (DT) has emerged as a solution for enabling real-time data acquisition, transfer, analysis, and utilization for improved decision-making toward smart FM. Substantial research on DT for FM has been undertaken in the past decade. This paper presents a bibliometric analysis of the literature on DT for FM. A total of 248 research articles are obtained from the Scopus and Web of Science databases. VOSviewer is then utilized to conduct bibliometric analysis and visualize keyword co-occurrence, citation, and co-authorship networks; furthermore, the research topics, authors, sources, and countries contributing to the use of DT for FM are identified. The findings show that the current research of DT in FM focuses on building information modeling-based FM, artificial intelligence (AI)-based predictive maintenance, real-time cyber–physical system data integration, and facility lifecycle asset management. Several areas, such as AI-based real-time asset prognostics and health management, virtual-based intelligent infrastructure monitoring, deep learning-aided continuous improvement of the FM systems, semantically rich data interoperability throughout the facility lifecycle, and autonomous control feedback, need to be further studied. This review contributes to the body of knowledge on digital transformation and smart FM by identifying the landscape, state-of-the-art research trends, and future needs with regard to DT in FM.

关键词： digital twin     building information modeling     facility management     semantic interoperability     artificial intelligence     intelligent monitoring     autonomous control feedback    

HTML PDF 收藏

Fast detection algorithm for cracks on tunnel linings based on deep semantic segmentation

《结构与土木工程前沿（英文）》 2023年 第17卷 第5期   页码 732-744 doi: 10.1007/s11709-023-0965-y

摘要： An algorithm based on deep semantic segmentation called LC-DeepLab is proposed for detecting the trends and geometries of cracks on tunnel linings at the pixel level. The proposed method addresses the low accuracy of tunnel crack segmentation and the slow detection speed of conventional models in complex backgrounds. The novel algorithm is based on the DeepLabv3+ network framework. A lighter backbone network was used for feature extraction. Next, an efficient shallow feature fusion module that extracts crack features across pixels is designed to improve the edges of crack segmentation. Finally, an efficient attention module that significantly improves the anti-interference ability of the model in complex backgrounds is validated. Four classic semantic segmentation algorithms (fully convolutional network, pyramid scene parsing network, U-Net, and DeepLabv3+) are selected for comparative analysis to verify the effectiveness of the proposed algorithm. The experimental results show that LC-DeepLab can accurately segment and highlight cracks from tunnel linings in complex backgrounds, and the accuracy (mean intersection over union) is 78.26%. The LC-DeepLab can achieve a real-time segmentation of 416 × 416 × 3 defect images with 46.98 f/s and 21.85 Mb parameters.

关键词： tunnel engineering     crack segmentation     fast detection     DeepLabv3+     feature fusion     attention mechanism    

HTML PDF 收藏

Optimal CNN-based semantic segmentation model of cutting slope images

Mansheng LIN; Shuai TENG; Gongfa CHEN; Jianbing LV; Zhongyu HAO

《结构与土木工程前沿（英文）》 2022年 第16卷 第4期   页码 414-433 doi: 10.1007/s11709-021-0797-6

摘要： This paper utilizes three popular semantic segmentation networks, specifically DeepLab v3+, fully convolutional network (FCN), and U-Net to qualitively analyze and identify the key components of cutting slope images in complex scenes and achieve rapid image-based slope detection. The elements of cutting slope images are divided into 7 categories. In order to determine the best algorithm for pixel level classification of cutting slope images, the networks are compared from three aspects: a) different neural networks, b) different feature extractors, and c) 2 different optimization algorithms. It is found that DeepLab v3+ with Resnet18 and Sgdm performs best, FCN 32s with Sgdm takes the second, and U-Net with Adam ranks third. This paper also analyzes the segmentation strategies of the three networks in terms of feature map visualization. Results show that the contour generated by DeepLab v3+ (combined with Resnet18 and Sgdm) is closest to the ground truth, while the resulting contour of U-Net (combined with Adam) is closest to the input images.

关键词： slope damage     image recognition     semantic segmentation     feature map     visualizations    

HTML PDF 收藏

基于分布式表示语义组合的查询子主题挖掘 None

Wei SONG, Ying LIU, Li-zhen LIU, Han-shi WANG

《信息与电子工程前沿（英文）》 2018年 第19卷 第11期   页码 1409-1419 doi: 10.1631/FITEE.1601476

摘要： 推断查询意图对于信息检索具有重要意义。查询子主题挖掘旨在找到可能的子主题，用于表示给定查询的潜在意图。由于查询较短，子主题挖掘具有挑战性。学习词或句子分布式表示推动和影响了很多领域的发展。然而，没有清晰的结论表明该分布式表示是否有助于应对查询子主题挖掘面临的挑战。提出并比较利用分布式表示的语义组合进行查询子主题挖掘。采用两种分布式表示策略：能学习任意长度文本分布式表示的段落向量（paragraph vector）以及词向量的语义组合。探索了语义组合策略和数据类型对查询表示的影响。在国家信息学研究所信息获取研究试验平台和社区（National Institute of Informatics Testbeds and Community for Information Access Research，NTCIR）提供的公开数据集上的实验结果表明，与传统语义表示相比，分布式语义表示能获得更优查询子主题挖掘性能。文中做了更多深入探讨。

关键词： 查询子主题挖掘；查询意图；分布式表示；语义组合    

HTML PDF 收藏

超图计算 Review

Yue Gao,Shuyi Ji,Xiangmin Han,Qionghai Dai

《工程（英文）》 2024年 第40卷 第9期   页码 188-201 doi: 10.1016/j.eng.2024.04.017

摘要：

Practical real-world scenarios such as the Internet, social networks, and biological networks present the challenges of data scarcity and complex correlations, which limit the applications of artificial intelligence. The graph structure is a typical tool used to formulate such correlations, it is incapable of modeling high-order correlations among different objects in systems; thus, the graph structure cannot fully convey the intricate correlations among objects. Confronted with the aforementioned two challenges, hypergraph computation models high-order correlations among data, knowledge, and rules through hyperedges and leverages these high-order correlations to enhance the data. Additionally, hypergraph computation achieves collaborative computation using data and high-order correlations, thereby offering greater modeling flexibility. In particular, we introduce three types of hypergraph computation methods: ① hypergraph structure modeling, ② hypergraph semantic computing, and ③ efficient hypergraph computing. We then specify how to adopt hypergraph computation in practice by focusing on specific tasks such as three-dimensional (3D) object recognition, revealing that hypergraph computation can reduce the data requirement by 80% while achieving comparable performance or improve the performance by 52% given the same data, compared with a traditional data-based method. A comprehensive overview of the applications of hypergraph computation in diverse domains, such as life sciences and computer vision, is also provided. Finally, we introduce an open-source deep learning library, DeepHypergraph (DHG), which can serve as a tool for the practical usage of hypergraph computation.

关键词： High-order correlation     Hypergraph structure modeling     Hypergraph semantic computing     Efficient hypergraph computing     Hypergraph computation framework    

HTML PDF 收藏

迈向6G智简网络——基于语义通信的网络新范式 Article

张平, 许文俊, 高晖, 牛凯, 许晓东, 秦晓琦, 袁彩霞, 秦志金, 赵海涛, 魏急波, 张钫炜

《工程（英文）》 2022年 第8卷 第1期   页码 60-73 doi: 10.1016/j.eng.2021.11.003

摘要： wisdom-evolutionary and primitive-concise network, WePCN）的新途径——以深入挖掘信息的语义层次内涵为主线，首先提出了全新的语义表征框架模型，即语义基（semanticbase），进而构建了面向“智简”6G的“一面-三层”智能高效语义通信（intelligent and efficient semantic communication

关键词： 第六代（6G）移动通信     语义信息     语义通信     智能通信    

HTML PDF 收藏

融合目标语言端语义角色的串到树翻译模型 Article

Chao SU, Yu-hang GUO, He-yan HUANG, Shu-min SHI, Chong FENG

《信息与电子工程前沿（英文）》 2017年 第18卷 第10期   页码 1534-1542 doi: 10.1631/FITEE.1601349

摘要： 串到树模型是统计机器翻译中最为成功的基于句法的模型之一。它通过对目标语言端句法信息进行建模，使得机器输出的译文更符合语法。然而，它并未利用任何语义信息，产生的译文仍然包含语义角色混淆和语块顺序混乱等错误。提出两种方式，利用语义角色提高串到树模型性能：（1）在句法树上添加语义角色标签；（2）先将语义角色转换成树结构，再引入句法信息。将上述两种新的树结构用于串到树机器翻译模型训练，使得系统能够利用语义信息学习或选择更好的翻译规则。实验表明，在口语和新闻两种语料上，我们的方法都超越了传统串到树翻译系统；在大规模新闻语料上，我们的方法超越了基于短语的机器翻译系统。

关键词： 机器翻译；语义角色；句法树；串到树模型    

HTML PDF 收藏

SPSSNet: a real-time network for image semantic segmentation

Saqib Mamoon, Muhammad Arslan Manzoor, Fa-en Zhang, Zakir Ali, Jian-feng Lu,saqibmamoon@njust.edu.cn,arsalaan@njust.edu.cn,zhangfaen@ainnovation.com,alizakir@njust.edu.cn,lujf@njust.edu.cn

《信息与电子工程前沿（英文）》 2020年 第21卷 第12期   页码 1671-1814 doi: 10.1631/FITEE.1900697

摘要： Although deep neural networks (DNNs) have achieved great success in semantic segmentation tasks, it is still challenging for real-time applications. A large number of feature channels, parameters, and floating-point operations make the network sluggish and computationally heavy, which is not desirable for real-time tasks such as robotics and autonomous driving. Most approaches, however, usually sacrifice spatial resolution to achieve inference speed in real time, resulting in poor performance. In this paper, we propose a light-weight semantic segmentation network (SPSSN), which can efficiently reuse the paramount features from early layers at multiple stages, at different spatial resolutions. SPSSN takes input of full resolution 2048×1024 pixels, uses only 1.42×10 parameters, yields 69.4% mIoU accuracy without pre-training, and obtains an inference speed of 59 frames/s on the Cityscapes dataset. SPSSN can run directly on mobile devices in real time, due to its light-weight architecture. To demonstrate the effectiveness of the proposed network, we compare our results with those of state-of-the-art networks.
HTML PDF 收藏

Pixel-level crack segmentation of tunnel lining segments based on an encoder–decoder network

《结构与土木工程前沿（英文）》 2024年 第18卷 第5期   页码 681-698 doi: 10.1007/s11709-024-1048-4

摘要： Regular detection and repair for lining cracks are necessary to guarantee the safety and stability of tunnels. The development of computer vision has greatly promoted structural health monitoring. This study proposes a novel encoder–decoder structure, CrackRecNet, for semantic segmentation of lining segment cracks by integrating improved VGG-19 into the U-Net architecture. An image acquisition equipment is designed based on a camera, 3-dimensional printing (3DP) bracket and two laser rangefinders. A tunnel concrete structure crack (TCSC) image data set, containing images collected from a double-shield tunnel boring machines (TBM) tunnel in China, was established. Through data preprocessing operations, such as brightness adjustment, pixel resolution adjustment, flipping, splitting and annotation, 2880 image samples with pixel resolution of 448 × 448 were prepared. The model was implemented by Pytorch in PyCharm processed with 4 NVIDIA TITAN V GPUs. In the experiments, the proposed CrackRecNet showed better prediction performance than U-Net, TernausNet, and ResU-Net. This paper also discusses GPU parallel acceleration effect and the crack maximum width quantification.

关键词： tunnel lining segment     crack detection     semantic segmentation     convolutional neural network     encoder–decoder structure    

HTML PDF 收藏

Beyond bag of latent topics: spatial pyramid matching for scene category recognition

Fu-xiang LU,Jun HUANG

《信息与电子工程前沿（英文）》 2015年 第16卷 第10期   页码 817-828 doi: 10.1631/FITEE.1500070

摘要： We propose a heterogeneous, mid-level feature based method for recognizing natural scene categories. The proposed feature introduces spatial information among the latent topics by means of spatial pyramid, while the latent topics are obtained by using probabilistic latent semantic analysis (pLSA) based on the bag-of-words representation. The proposed feature always performs better than standard pLSA because the performance of pLSA is adversely affected in many cases due to the loss of spatial information. By combining various interest point detectors and local region descriptors used in the bag-of-words model, the proposed feature can make further improvement for diverse scene category recognition tasks. We also propose a two-stage framework for multi-class classification. In the first stage, for each of possible detector/descriptor pairs, adaptive boosting classifiers are employed to select the most discriminative topics and further compute posterior probabilities of an unknown image from those selected topics. The second stage uses the prod-max rule to combine information coming from multiple sources and assigns the unknown image to the scene category with the highest ‘final’ posterior probability. Experimental results on three benchmark scene datasets show that the proposed method exceeds most state-of-the-art methods.

关键词： Scene category recognition     Probabilistic latent semantic analysis     Bag-of-words     Adaptive boosting    

HTML PDF 收藏

Implementation and performance evaluation of advance metering infrastructure for Borneo-Wide Power Grid

Mujahid TABASSUM,Manas K. HALDAR,Duaa Fatima S. KHAN

《能源前沿（英文）》 2020年 第14卷 第1期   页码 192-211 doi: 10.1007/s11708-016-0438-2

摘要： In this paper, a supervisory computer network for Borneo-Wide Power Grid system have been proposed and implemented, which includes a renewable power generation and advanced metering infrastructure. An Internet-based communication network running on multiprotocol label switching (MPLS) has been implemented for a smart power grid, with the addition of the renewable energy monitoring system. The centralized supervisory control and data acquisition systems (SCADA) are replaced by a wide area monitoring system(WAMS) comprising of a phasor measurement unit (PMU). The implemented communication network used advanced metering infrastructure that operates on worldwide interoperability for microwave access (WiMAX), wireless fidelity (Wi-Fi) and low power Wi-Fi, which are proposed for the distribution systems of Sarawak Energy. The proposed wide area network (WAN) is simulated using OPNET Modeler and the results are compared with the existing WAN used by Sarawak Energy.

关键词： renewable energy     multiprotocol label switching (MPLS)     power grid     phasor measurement unit (PMU)     supervisory control and data acquisition systems (SCADA)     wide area monitoring system (WAMS)     worldwide interoperability for microwave access (WiMAX)     synchronous digital hierarchy (SDH)    

HTML PDF 收藏

无监督域自适应的动态参数化学习 Research Article

蒋润华1,2,韩亚洪1,2

《信息与电子工程前沿（英文）》 2023年 第24卷 第11期   页码 1616-1632 doi: 10.1631/FITEE.2200631

摘要： 无监督领域自适应通过学习域不变表示实现神经网络从有标签数据组成的源域到无标签数据组成的目标域迁移。近期研究通过直接匹配这两个域的边缘分布实现这一目标。然而，已有研究大多数忽略域对齐和语义判别学习之间的动态平衡，因此容易受负迁移和异常样本影响。为解决这些问题，引入动态参数化学习框架。首先，通过探索领域级语义知识，提出动态对齐参数自适应地调整域对齐和语义判别学习的优化过程。此外，为获得判别能力强和域不变的表示，提出在源域和目标域上对齐优化过程。本文通过综合实验证明了所提出方法的有效性，并在3个视觉任务的7个数据集上进行广泛比较，证明可行性。

关键词： 无监督领域自适应；优化步骤；跨域判别表示；语义判别    

HTML PDF 收藏

面向语义通信的模分多址技术 Research Article

张平1,2,3,许晓东1,2,3,董辰1,牛凯1,2,梁灏泰1,梁子键1,秦晓琦1,孙梦颖1,陈昊2,马楠1,2,许文俊1,王光宇1,陶小峰2,4

《信息与电子工程前沿（英文）》 2023年 第24卷 第6期   页码 801-812 doi: 10.1631/FITEE.2300196

摘要： 在多用户系统中，系统资源应分配给不同用户。在传统通信系统中，系统资源通常包括时间、频率、空间和功率，因此广泛使用诸如时分多址（TDMA）、频分多址（FDMA）、空分多址（SDMA）、码分多址（CDMA）、非正交多址（NOMA）之类多址技术。在被认为是下一代通信系统新范式的语义通信中，我们从语义角度，以基于模型的人工智能方法，从信源中提取高维语义域特征，并针对信源和信道特征联合构建模型信息空间。从模型信息空间中挖掘语义信息的共性化和个性化信息，提出一种新的基于语义域资源的多址技术，称为模分多址（MDMA）。从信息论角度，证明模分多址比传统多址技术获得更多性能提升。仿真结果表明，模分多址比传统多址技术节省更多带宽资源，并且在低信噪比条件下，在加性高斯白噪声（AWGN）信道中，相比非正交多址具有至少5 dB的性能优势。

关键词： 模分多址（MDMA）；语义通信；多址技术    

HTML PDF 收藏

6G中联邦学习的应用、挑战和机遇 Review

杨照辉,陈明哲,黃繼傑,H. Vincent Poor,崔曙光

《工程（英文）》 2022年 第8卷 第1期   页码 33-41 doi: 10.1016/j.eng.2021.12.002

摘要：

标准的机器学习方法需要在数据中心集中训练数据，从而采用集中式机器学习算法来进行数据分析和推理。然而，由于无线网络中的隐私限制以及无线通信资源受限，边缘设备将数据传输到参数服务器通常是不可取和不切实际的。联邦学习可解决这些问题。联邦学习可以使设备能够在没有数据共享和传输的情况下训练机器学习模型。本文全面概述了未来第六代（6G）无线网络的联邦学习应用。特别是，首先描述了将联邦学习应用于无线通信中的基本要求。然后详细介绍了无线通信中潜在的联邦学习新型应用，讨论了与新型应用相关的主要问题和挑战。最后，描述了用于无线通信的联邦学习的详细实现方案，并给出了联邦学习的难点和应用前景。

关键词： 联邦学习     6G     智能反射面     语义通信     通信感知计算一体化    

HTML PDF 收藏

数字交通规则的语义一致性和正确性验证 Article

万蕾, 王长君, 罗达新, 刘航, 马莎, 胡伟超

《工程（英文）》 2024年 第33卷 第2期   页码 48-62 doi: 10.1016/j.eng.2023.04.016

摘要：

“人车同规”(自动驾驶汽车与人类驾驶汽车遵从相同的交通规则)被汽车行业和交通管理部门视为准则。通过形式化和数字化方法，基于自然语言描述的交通规则可以被转换为数字规则，并被自动驾驶汽车使用。本文提出了一种有效的转换流程，利用分层次的信息提取，可以从丰富而复杂的自然语言语义中提取出交通规则中的有效信息，甚至是隐藏的假设。然而，如何确保转换成的数字规则的准确性，并且与原始交通规则保持一致，是个重要且未被探索过的问题。我们将等价性验证与模型检测相结合，得出了一种行之有效的形式化验证方法。利用本文所提出的交通规则数字化流程和验证方法，可以得到合理可靠的数字交通规则。在仿真环境中，我们利用这些数字交通规则对车辆行为进行了交规符合性评估。实验结果表明，通过本文所提流程获得的度量时序逻辑描述的数字交通规则，可以很方便地被用于仿真平台和自动驾驶系统中。

关键词： 自动驾驶     交通规则     数字化     形式化     验证    

HTML PDF 收藏

标题 作者 时间 类型 操作

Digital twin-enabled smart facility management: A bibliometric review

期刊论文

Fast detection algorithm for cracks on tunnel linings based on deep semantic segmentation

期刊论文

Optimal CNN-based semantic segmentation model of cutting slope images

Mansheng LIN; Shuai TENG; Gongfa CHEN; Jianbing LV; Zhongyu HAO

期刊论文

基于分布式表示语义组合的查询子主题挖掘

Wei SONG, Ying LIU, Li-zhen LIU, Han-shi WANG

期刊论文

超图计算

Yue Gao,Shuyi Ji,Xiangmin Han,Qionghai Dai

期刊论文

迈向6G智简网络——基于语义通信的网络新范式

张平, 许文俊, 高晖, 牛凯, 许晓东, 秦晓琦, 袁彩霞, 秦志金, 赵海涛, 魏急波, 张钫炜

期刊论文

融合目标语言端语义角色的串到树翻译模型

Chao SU, Yu-hang GUO, He-yan HUANG, Shu-min SHI, Chong FENG

期刊论文

SPSSNet: a real-time network for image semantic segmentation

Saqib Mamoon, Muhammad Arslan Manzoor, Fa-en Zhang, Zakir Ali, Jian-feng Lu,saqibmamoon@njust.edu.cn,arsalaan@njust.edu.cn,zhangfaen@ainnovation.com,alizakir@njust.edu.cn,lujf@njust.edu.cn

期刊论文

Pixel-level crack segmentation of tunnel lining segments based on an encoder–decoder network

期刊论文

Beyond bag of latent topics: spatial pyramid matching for scene category recognition

Fu-xiang LU,Jun HUANG

期刊论文

Implementation and performance evaluation of advance metering infrastructure for Borneo-Wide Power Grid

Mujahid TABASSUM,Manas K. HALDAR,Duaa Fatima S. KHAN

期刊论文

无监督域自适应的动态参数化学习

蒋润华1,2,韩亚洪1,2

期刊论文

面向语义通信的模分多址技术

张平1,2,3,许晓东1,2,3,董辰1,牛凯1,2,梁灏泰1,梁子键1,秦晓琦1,孙梦颖1,陈昊2,马楠1,2,许文俊1,王光宇1,陶小峰2,4

期刊论文

6G中联邦学习的应用、挑战和机遇

杨照辉,陈明哲,黃繼傑,H. Vincent Poor,崔曙光

期刊论文

数字交通规则的语义一致性和正确性验证

万蕾, 王长君, 罗达新, 刘航, 马莎, 胡伟超

期刊论文