检索结果-内蒙古大学图书馆

T³Planner: Multi-Phase Planning Across Structure-Constrained Optical, IP, and Routing Topologies

IEEE Journal on Selected Areas in Communications 2025年第5期43卷 1823-1839页

作者： Hao, Yijun Yang, Shusen Li, Fang Zhang, Yifan Zhao, Cong Ren, Xuebin Zhao, Peng Xu, Chenren Wang, Shibo Xi’an Jiaotong University National Engineering Laboratory for Big Data Analytics Xi’an710049 China Xi’an Jiaotong University National Engineering Laboratory for Big Data Analytics Ministry of Education Key Laboratory for Intelligent Networks and Network Security Xi’an710049 China Peking University School of Computer Science Beijing100871 China The Chinese University of Hong Kong Department of Computer Science and Engineering Hong Kong National Engineering Laboratory for Big Data Analytics Xi'an Jiaotong University Xi'an710049 China

Network topology planning is an essential multi-phase process to build and jointly optimize the multi-layer network topologies in wide-area networks (WANs). Most existing practices target single-phase/layer planning, and are incapable of satisfying all rigorous topological structure constraints (e.g., dual-homing rings) defined by network standards and operators, especially in large-scale networks. These significantly limit their usability and performance in production networks. We consider a general topology planning problem with typical structure constraints over three essential phases (greenfield, reconfiguration, and site expansion) and topological layers (optical, IP, and routing topologies). We present, T3Planner, a novel practical solver to this problem in production. Specifically, we develop a structure-driven encoder based on graph neural network (GNN) for concise structure encoding, and design a new learning framework with optical-centric layer compression/reconstruction and rule-aided reinforcement learning (RL) for fast convergence and high performance. Extensive experiments on nine real topologies demonstrate that T3Planner scales to large optical networks with hundreds of sites, saves 46.6% cost, and supports 3.12x more demand when compared to related existing approaches. © 1983-2012 IEEE.

关键词： Network topology

来源：评论

学校读者我要写书评

暂无评论

An efficient speech emotion recognition based on a dual-stream CNN-transformer fusion network

引用

International Journal of Speech Technology 2023年第2期26卷 541-557页

作者： Tellai, Mohammed Gao, Lijian Mao, Qirong Department of Computer Science and Communication Engineering Jiangsu University Jiangsu Zhenjiang212013 China Jiangsu Engineering Research Center of Big Data Ubiquitous Perception and Intelligent Agriculture Applications Jiangsu Zhenjiang212013 China

The use of machine learning and artificial intelligence enables us to create intelligent systems. Speech emotion recognition system analyzes the speaker’s speech to determine his/her emotional state. Speech emotion recognition is a challenging pattern recognition task. This paper proposes a new robust and lightweight speech emotion recognition system based on a dual-stream CNN-Transformer fusion network that effectively captures spatial and temporal information disentangled in long-distance raw features by exploring both MFCCs and Mel-spectrograms in a parallel mechanism. Experiments are performed on the widely used emotional benchmark datasets. Our approach has shown to be quite efficient. It outperforms the best-known state-of-the-art models with an accuracy of 97.64%, 99.42%, and 97.53% on RAVDESS, TESS, and EMO-DB datasets respectively. The results demonstrate the significant advantages of the proposed model and the ability of this architecture to learn to recognize emotional data features accurately. © 2023, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Improved Demonstration-Knowledge Utilization in Reinforcement Learning

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第5期5卷 2139-2150页

作者： Liu, Yanyu Zeng, Yifeng Ma, Biyang Pan, Yinghui Gao, Huifan Zhang, Yuting Xiamen University Xiamen Key Laboratory of Big Data Intelligent Analysis and Decision Department of Automation Xiamen361102 China Northumbria University Department of Computer and Information Sciences NewcastleNE1 8ST United Kingdom Minnan Normal University Department of Computer Science Zhangzhou363000 China Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen518060 China

Reinforcement learning (RL) has made great success in recent years. Generally, the learning process requires a huge amount of interaction with the environment before an agent can achieve acceptable performance. This motivates many techniques, such as incorporating prior knowledge which is usually presented as experts' demonstration, and using a probability distribution to represent state-and-action values, to accelerate the learning process. The methods perform well when the prior knowledge is genuinely correct and no much change occurs to the learning environment. However, the requirement is not perfectly realistic in many complex applications. The demonstration knowledge may not reflect the true environment and even be full of noise. In this article, we introduce a dynamic distribution merging method to improve knowledge utilization in a general RL algorithm, namely Q-learning. The new method adapts a normal distribution to represent state-action values and merges the prior and learned knowledge in a discriminative way. We theoretically analyze the new learning method and demonstrate its empirical performance over multiple problem domains. © 2020 IEEE.

关键词： Merging

来源：评论

学校读者我要写书评

暂无评论

CCTG-NET: Contextualized Convolutional Transformer-GRU Network for speech emotion recognition

引用

International Journal of Speech Technology 2023年第4期26卷 1099-1116页

作者： Tellai, Mohammed Mao, Qirong Department of Computer Science and Communication Engineering Jiangsu University Jiangsu Province Zhenjiang212013 China Jiangsu Engineering Research Center of Big Data Ubiquitous Perception and Intelligent Agriculture Applications Jiangsu Province Zhenjiang212013 China

Speech is a crucial aspect of human-to-human interactions and plays a fundamental role in the advancement of human–computer interaction (HCI) systems. Developing an accurate speech emotion recognition (SER) system for human conversations poses a critical yet challenging task. Existing state-of-the-art (SOTA) research in SER primarily focuses on modeling vocal information within individual conversational speech utterances, overlooking the significance of incorporating transactional information from the interaction context. In this paper, we present a novel Contextualized Convolutional Transformer-GRU Network (CCTG-Net) for recognizing speech emotions using Mel-spectrogram features, effectively integrating contextual information for emotion recognition. Our experiments are conducted on the widely-used emotional benchmark dataset, IEMOCAP. Compared to SOTA methods in four-class emotion recognition, our proposed model achieves a weighted accuracy of 88.4% and an unweighted accuracy (UA) of 89.1%. This marks a substantial 3.0% enhancement in UA while maintaining an optimal balance between performance and complexity. © 2023, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

A Review of PM2.5 in China - From the Qualitative and Quantitative Perspectives 3

A Review of PM2.5 in China - From the Qualitative and Quanti...

引用

3rd International Conference on Green Energy, Environment and Sustainable Development, GEESD 2022

作者： Cheng, Haiyan Yang, Ruiqi Di, Guangzhi Department of Big Data and Intelligent Engineering Southwest Forestry University Kunming China

ISBN: (纸本)9781643683126

According to the environmental bulletin in recent years, PM2.5 has been one of the primary pollutants of air pollution in China. And researches about PM2.5 in source analysis, composition, physical and chemical properties, prediction and other aspects have been studied. In order to better figure out the current research status of PM2.5 in China, this paper analyzes these related studies from the qualitative and quantitative aspects. From the qualitative aspect, the paper analyzes the composition and source of PM2.5. From the quantitative aspect, the paper describes the prediction method of PM2.5 concentration from two aspects, one is based on ground observation stations, the other is based on satellite data. Whether from a qualitative or quantitative perspective, the research on PM2.5 is still very necessary. The control of air pollution has a long way to go, and continuous research and practice are still required. © 2022 The authors and IOS Press.

关键词： Chemical analysis

来源：评论

学校读者我要写书评

暂无评论

Road Detection Based on Fusion of LiDAR data and Visual data 1

Road Detection Based on Fusion of LiDAR Data and Visual Data

引用

1st International Conference on intelligent Transportation and Smart Cities, ICITSC 2024

作者： Yang, Chaoju Rong, Jian Chin, Soon Ku School of Big Data and Intelligent Engineering Southwest Forestry University Kunming China Department of Computer Science Universiti Tunku Abdul Rahman Kampar31900 Malaysia

ISBN: (纸本)9781643685205

Smart transportation is a new development model for intelligent traffic based on the combination of the Internet, the Internet of Things, and other networks. Road detection is one of the foundational and core technologies in smart transportation. It provides accurate, reliable, and real-time road information for applications such as autonomous driving, intelligent traffic management, and urban planning. This contributes to the improvement of traffic safety, efficiency, and sustainability. However, relying solely on visual images for road detection still faces numerous challenges, such as changes in lighting conditions, image blurring, and occlusions. To enhance the robustness and accuracy of road detection, leveraging LiDAR (Light Detection and Ranging) data as supplementary information is considered. LiDAR data is not affected by visual noise and can offer more precise depth and height information. Nevertheless, effectively integrating and adapting to different data and feature spaces remain crucial challenges. This paper proposes an improved road detection method based on the PLARD (Progressive LiDAR Adaptation for Road Detection) network. It introduces the U-Net network as an additional branch, collaborating with the image and point cloud branches for feature fusion and road detection. The U-Net network utilizes information from the images for initial segmentation, providing a better prior, and enhances the feature fusion capability of the PLARD network, thereby improving segmentation accuracy and robustness. Experiments conducted on the KITTI Road dataset demonstrate that the proposed method outperforms the PLARD network and other baseline methods in terms of the Dice coefficient. Particularly, it excels in complex urban scenarios and exhibits strong generalization capabilities. The introduced road detection approach, combining LiDAR and visual data, provides an efficient, robust, and versatile solution for smart transportation. It adapts to different scenarios

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Influencing Factors of Healthy Aging Risk Assessed Using Biomarkers:A Life Course Perspective

引用

China CDC weekly 2024年第11期6卷 219-224,I0014-I0017页

作者： Cedric Zhang Bo Lua Yajie Gao Jinming Li Xingqi Cao Xinwei Lyu Yinuo Tu Shuyi Jin Zuyun Liu Center for Clinical Big Data and Analytics of the Second Affiliated Hospital and Department of Big Data in Health Science School of Public Healththe Key Laboratory of Intelligent Preventive Medicine of Zhejiang ProvinceZhejiang University School of MedicineHangzhou CityZhejiang ProvinceChina Institute of Epidemiology and Health Care University College LondonLondonUK College of Chemical and Biological Engineering Zhejiang UniversityHangzhou CityZhejiang ProvinceChina

Assessing individual risks of healthy aging using biomarkers and identifying associated factors have become important areas of *** this study,we conducted a literature review of relevant publications between 2018 and 2023 in both Chinese and English *** studies have predominantly used single biomarkers,such as C-reactive protein,or focused on specific life course stages and factors such as socioeconomic status,mental health,educational levels,and unhealthy *** summarizing the progress in this field,our study provides valuable insights and future directions for promoting healthy aging from a life course perspective.

关键词： such insight directions

来源：评论

学校读者我要写书评

暂无评论

Nonlinearity Estimation and Compensation for Accurate PMSM Modeling and Voltage Prediction

引用

CES Transactions on Electrical Machines and Systems 2024年第4期8卷 394-403页

作者： Beichen Ding Yuting Lu Chunyan Lai Weiwen Peng Kaide Huang Guodong Feng IEEE School of Advanced Manufacturing Sun Yat-sen UniversityShenzhen 510275China School of Intelligent Systems Engineering Sun Yat-sen UniversityShenzhen 510275China Department of Electrical and Computer Engineering Concordia UniversityMontrealCanada School of Mathematics and Big Data Foshan UniversityFoshan 528000China

For permanent magnet synchronous machine(PMSM),the machine model is critical to predict the operating states for motor control,which,however,can be greatly affected by system ***,this paper investigates accurate machine modeling for control and parameter *** the proposed approach,the PMSM model with saturated inductances is used as the base model,and this paper investigates modeling and compensation of the offsets to the base model due to system nonlinearities such as saturation and core loss effects for accurate machine modeling and voltage ***,the offsets to the base model are modeled using nonlinear functions with variable coefficients to compensate saturation and core loss effect,which can achieve better accuracy without changing the model structure.A differential estimation model is derived to estimate the model coefficients from a small amount of measurements with simplified ***,the model offset calculation is both computation and memory efficient with simplified *** contribution is to improve the machine model accuracy and achieve precise voltage prediction for practical ***,comparisons and the application to temperature estimation are conducted on a test interior PMSM to validate the proposed approach.

关键词： Core loss Differential modeling Multiparameter estimation PMSM

来源：评论

学校读者我要写书评

暂无评论

Massive data clustering by multi-scale psychological observations

引用

National Science Review 2022年第2期9卷 43-51页

作者： Shusen Yang Liwen Zhang Chen Xu Hanqiao Yu Jianqing Fan Zongben Xu National Engineering Laboratory of Big Data Analytics Xi'an Jiaotong University Industrial Artificial Intelligent Center Pazhou Laboratory Department of Mathematics and Statistics University of Ottawa Center for Statistics and Machine Learning Princeton University

Clustering is the discovery of latent group structure in data and is a fundamental problem in artificial intelligence,and a vital procedure in data-driven scientific research over all ***,existing methods have various limitations,especially we ak cognitive interpretability and poor computational scalability,when it comes to clustering massive datasets that are increasingly available in all ***,by simulating the multi-scale cognitive observation process of humans,we design a scalable algorithm to detect clusters hierarchically hidden in massive *** observation scale changes,following the Weber-Fechner law to capture the gradually emerging meaningful grouping *** validated our approach in real datasets with up to a billion records and 2000 dimensions,including taxi trajectories,single-cell gene expressions,face images,computer logs and *** approach outperformed popular methods in usability,efficiency,effectiveness and robustness across different domains.

关键词： massive data clustering psychological observation Weber–Fechner law cognitive interpretability computational scalability

来源：评论

学校读者我要写书评

暂无评论

Using analytic hierarchy process to evaluate deep learning for infrared target recognition

引用

Multimedia Tools and Applications 2024年第38期83卷 86229-86245页

作者： Xu, Laixiang Cao, Bingxu Wei, Xinhong Li, Bei Su, Jingfeng Ning, Shiyuan Zhao, Junmin School of Computer and Data Science Henan University of Urban Construction Pingdingshan467036 China School of Information Engineering Luohe Vocational Technology College Henan University of Technology Luohe Institute of Technology Luohe462000 China School of Computer and Data Science Innovation Laboratory of Smart Traffic and Big Data Development of Hainan Province Pingdingshan467036 China School of Computer and Data Science Research Center of Smart City and Big Data Engineering of Henan Province Henan University of Urban Construction Pingdingshan467036 China Department of Software Information China Electronics Technology Group Corporation 36-th Research Institute Jiaxing314033 China School of Computer and Data Science Research Center of Smart City and Big Data Engineering of Henan Province Research Center of Intelligent Campus Application Engineering of Henan Province Innovation Laboratory of Smart Traffic and Big Data Development of Hainan Province Henan University of Urban Construction Pingdingshan467036 China

In order to promote the evaluation performance of deep learning infrared automatic target recognition (ATR) algorithms in the complex environment of air-to-air missile research, we proposed an analytic hierarchy process (AHP) evaluation system consisting of the target recognition ability, the generalization recognition ability, the anti-interference ability, the background suppression ability, and the cost metrics ability. According to detailed quantitative analysis and experimental results, we establish probability evaluation models and get their probability values. Compared with traditional evaluation systems, our proposed method implementation is showing high reliability. Similar superior performances are also achieved, such as quick, comprehensive, and scientific. Through the above research, the key technology of deep learning performance evaluation in automatic target recognition has been broken through, which provides some basis and guidance for the analysis of infrared imaging-guided weapon systems. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Infrared imaging

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：