检索结果-内蒙古大学图书馆

IEEE Conference on Global Communications (GLOBECOM)

作者： Kuiyuan Ding Fangfang Liu Yang Yang Mingzhe Chen Caili Guo Beijing Key Laboratory of Network System Architecture and Convergence School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing China Department of Electrical and Computer Engineering and the Institute for Data Science and Computing University of Miami Coral Gables FL USA Beijing Laboratory of Advanced Information Networks School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing China

ISBN: (数字)9798350351255

ISBN: (纸本)9798350351262

Large scale artificial intelligence (AI) models possess excellent capabilities in semantic representation and understanding, making them particularly well-suited for semantic encoding and decoding. However, the substantial scale of these AI models imposes unacceptable computational resources and communication delays. To address this issue, we propose a semantic communication scheme based on robust knowledge distillation (RKD-SC) for large scale model enabled semantic communications. In the considered system, a transmitter extracts the features of the source image for robust transmission and accurate image classification at the receiver. To effectively utilize the superior capability of large scale model while make the cost affordable, we first transfer knowledge from a large scale model to a smaller scale model to serve as the semantic encoder. Then, to enhance the robustness of the system against channel noise, we propose a channel-aware autoencoder (CAA) based on the Transformer architecture. Experimental results show that the encoder of proposed RKD-SC system can achieve over 93.3% of the performance of a large scale model while compressing 96.67% number of parameters. Code: https://***/echojayne/RKD-SC.

关键词： Transmitters Computational modeling Noise Autoencoders Receivers Semantic communication Transformers Feature extraction Robustness Decoding

来源：评论

学校读者我要写书评

暂无评论

Visual defect detection for historical building preservation

引用

Expert Systems with Applications 2025年 291卷

作者： Cheng, Mengqiu Zhang, Xinting Xia, Leihua Chen, Junming Xie, Jiayuan Ma, Zongfang Li, Qing School of Mechanical and Electrical Engineering Xi'an University of Architecture and Technology Xi'an China School of Information and Control Engineering Xi'an University of Architecture and Technology Xi'an China Department of Computing Hong Kong Polytechnic University Hong Kong SAR China Faculty of Humanities and Arts Macau University of Science and Technology Macau China Department of Mathematics The University of Hong Kong Hong Kong SAR China

Advancements in automated building defect detection technology are essential for preserving historical architecture. Although existing intelligent technologies have made notable progress in detecting defects in modern residential buildings, their application to historical buildings faces significant challenges due to the complexity of structures, material diversity, and long-term natural and human-induced deterioration. This study focuses on historical buildings in Guangzhou, China, and introduces a dedicated task for detecting defects in such buildings. To support this task, a high-quality, customized dataset has been developed as a research foundation. To address challenges such as image blurriness during data collection and the complex structural characteristics of historical buildings, this study proposes a baseline model named Deblur-DetNet. The model employs a two-stage approach that integrates image deblurring and defect detection, significantly enhancing both accuracy and robustness. Experimental results demonstrate that the proposed method performs exceptionally well in the task of historical building defect detection, particularly in identifying fine-grained defects. This research provides robust technical support for the protection and restoration of historical buildings and establishes a solid foundation for further studies in cultural heritage preservation. Our dataset is available at https://***/file/d/1-9NiAw0hzomWHOA9RMEMXOOwIq5HScPx/view?usp=sharing. © 2025

关键词： Computer vision Defect detection Historical building Image deblurring technology

来源：评论

学校读者我要写书评

暂无评论

Design of User Experience Optimization System Based on Media Device Network Modeling

Design of User Experience Optimization System Based on Media...

引用

Chinese Automation Congress (CAC)

作者： Lu Ding Luzhen Huang Guangyuan Zhang Bochen Li Dan Huang Lei Song Center for aerospace systems engineering Shanghai Jiao Tong University Shanghai China Architecture Technical Innovation Dept Huawei Cloud Computing Technologies Co. Ltd Shenzhen China School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai China School of Aeronautics and Astronautics Shanghai Jiao Tong University Shanghai China

ISBN: (数字)9798350368604

ISBN: (纸本)9798350368611

The media network faces challenges in systematically improving user experience due to the computational transmission tasks of massive data and highly coupled technical processes. Therefore, this paper designs a comprehensive user experience optimization system based on media device network modeling for key business scenarios, with user experience as the core, to achieve comprehensive user experience improvement for media device networks. We first use a network model to model the device network and achieve the mapping from physical space to mathematical space. Secondly we design a multi domain user experience model to map network capabilities to experience indicators. Finally, a multi-objective optimization method based on pareto optimality has been proposed for device networks to optimize their capabilities and achieve the goal of improving the overall quality of experience (QoE). We simulate weak network such as latency and packet loss in cloud gaming scenarios. When the user experience is poor, the proposed method is used to optimize the device network. The experimental results show that the user experience is significantly improved after optimization, proving the effectiveness of the proposed method.

关键词： Packet loss Optimization methods Media Cloud gaming User experience Mathematical models Quality of experience Optimization System analysis and design Faces

来源：评论

学校读者我要写书评

暂无评论

An Effective Hybrid Approach Based on Machine Learning Techniques for Auto-Translation: Japanese to English

An Effective Hybrid Approach Based on Machine Learning Techn...

引用

2021 International Conference on Innovation and Intelligence for Informatics, computing, and Technologies, 3ICT 2021

作者： Sharif, Mhd Saeed Romo, Bilyaminu Auwal Maltby, Harry Al-Bayatti, Ali School of Architecture Computing and Engineering ACE UEL University Way London United Kingdom School of Computer Science and Informatics CEM De Montfort University LeicesterLE1 9BH United Kingdom

ISBN: (纸本)9781665440325

In recent years machine learning techniques have been able to perform tasks previously thought impossible or impractical such as image classification and natural language translation, as such this allows for the automation of tasks previously thought only possible by humans. This research work aims to test a naïve post processing grammar correction method using a Long Short Term Memory neural network to rearrange translated sentences from Subject Object Verb to Subject Verb Object. Here machine learning based techniques are used to successfully translate works in an automated fashion rather than manually and post processing translations to increase sentiment and grammar accuracy. The implementation of the proposed methodology uses a bounding box object detection model, optical character recognition model and a natural language processing model to fully translate manga without human intervention. The grammar correction experimentation tries to fix a common problem when machines translate between two natural languages that use different ordering, in this case from Japanese Subject Object Verb to English Subject Verb Object. For this experimentation 2 sequence to sequence Long Short Term Memory neural networks were developed, a character level and a word level model using word embedding to reorder English sentences from Subject Object Verb to Subject Verb Object. The results showed that the methodology works in practice and can automate the translation process successfully. © 2021 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

SYNERGISING CONTINUOUS IMPROVEMENT WITH CIRCULAR ECONOMY FOR ADVANCING INNOVATION IN THE CONSTRUCTION SECTOR: A TEXT MINING APPROACH 39

SYNERGISING CONTINUOUS IMPROVEMENT WITH CIRCULAR ECONOMY FOR...

引用

39th Annual ARCOM Conference, ARCOM 2023

作者： Omotayo, Temitope S. Awuzie, Bankole Lovelin, Obi School of Built Environment Engineering and Computing Leeds Beckett University City Campus West Yorkshire LeedsLS2 8AG United Kingdom School of Construction Economics and Management University of Witwatersrand 10b Yale Rd Braamfontein Johannesburg2000 South Africa Department of Architecture and Built Environment Northumbria University Sutherland Building Northumberland Road Newcastle-upon-TyneNE1 8ST United Kingdom

Integrating continuous improvement and circular economy principles can promote sustainable construction practices (SCPs) and deliver long-term environmental, social and economic benefits. This study demonstrated how text mining could be applied to explicate the linkage between continuous improvement and circular economy principles in enhancing sustainable construction practices. The research applied unsupervised machine learning using text mining analyses through collocations to identify thematic areas where the integration of continuous improvement and circular economy principles would foster sustainable construction. Eighty-nine (89) peer-reviewed publications were extracted from the Scopus database for text mining analysis. The findings from text mining presented seven cogent themes through which continuous improvement and circular economy can be integrated. The optimal integration of the linkages advocated in this research can facilitate improved SCPs such as design for disassembly, modular construction, adaptive reuse, eco-friendly materials, innovative technologies, industrial symbiosis, life cycle assessment, cradle-to-cradle design, and lean construction practices. This investigation elucidated the utility of machine learning text mining in thematising and advancing sustainable construction research. © ARCOM *** rights reserved.

关键词： Circular economy

来源：评论

学校读者我要写书评

暂无评论

Data Availability Optimization for Cyber-Physical Systems 15

Data Availability Optimization for Cyber-Physical Systems

引用

2022 IEEE Congress on Cybermatics: 15th IEEE International Conferences on Internet of Things, iThings 2022, 18th IEEE International Conferences on Green computing and Communications, GreenCom 2022, 2022 IEEE International Conference on Cyber, Physical and Social computing, CPSCom 2022 and 8th IEEE International Conference on Smart Data, SmartData 2022

作者： Li, Liying Cong, Peijin Zhou, Junlong Gu, Zonghua Li, Keqin School of Computer Science and Engineering Nanjing University of Science and Technology China State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences China Department of Applied Physics and Electronics Ume˚a University Sweden Department of Computer Science State University of New York United States

ISBN: (数字)9781665454179

ISBN: (纸本)9781665454179

As the backbone of Industry 4.0, Cyber-Physical Systems (CPSs) have attracted extensive attention from industry, academia, and government. Missing data is a common problem in CPS data processing and may cause incorrect results and eventually serious malfunction. Existing data availability optimization methods either rely on a large amount of complete training data or suffer from poor performance. To solve these problems, this paper proposes an iterative data availability optimization method for CPSs. Specifically, the proposed method first pre-processes the raw dataset by using a Singular Value Decomposition-based feature selection approach to identify crucial features and reduce computation overheads. It then makes an initial guess for missing values via a designed K-Means-based imputation approach. The appropriate initial estimation decreases the probability of the proposed method falling into the local optimum. Finally, the proposed method iteratively estimates missing data based on the Orthogonal Matching Pursuit algorithm. The proposed method optimizes data availability by accurately imputing missing values. Simulation results on two datasets demonstrate that compared to multiple state-of-the-art approaches, the proposed data availability optimization method can reduce imputation error by up to 99.65%. © 2022 IEEE.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

A Novel Effectiveness Assessment Framework for Neoadjuvant Chemoradiotherapy of Locally Advanced Rectal Cancer Based on Multi-modal Intelligence

A Novel Effectiveness Assessment Framework for Neoadjuvant C...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Xiao Tian Dong Sui Weifeng Liu Maozu Guo Gongning Luo Kuanquan Wang Beijing Key Laboratory for Intelligent Processing Methods of Architectural Big Data Beijing China School of Electrical and Information Engineering Beijing University of Civil Engineering and Architecture Beijing China Perceptual Computing Research Center Harbin Institute of Technology Harbin China

ISBN: (数字)9798350337488

ISBN: (纸本)9798350337495

Neoadjuvant chemoradiotherapy (nCRT) is the stan-dard treatment for locally advanced rectal cancer (LARC). With the development of artificial intelligence, an increasing number of studies have begun to explore its application in cancer treatment prediction. However, the prior methods exhibit considerable variability even with slight modifications to the input data, which could potentially undermine the reliability of the results. In this paper, we proposed RP-Net, a novel multi-modal fusion-based framework that combines feature information from magnetic resonance imaging (MRI) and whole slide images (WSI), establishing a relationship to map the therapeutic effectiveness of nCRT for LARC. We investigated the relationship of the tumour region and its periphery tissues, and demonstrated the validity of the proposed framework that involving 11 different combinations of modalities. The experimental results revealed that it has achieved higher prediction accuracy compared to the four intra-categories single-modal combinations and outperformed the two intra-categories multi-modal combinations. When compared to the other four inter-categories multi-modal combinations, the fusion features get accuracy of 2 % ~ 6% improvement respectively.

关键词： Protocols Magnetic resonance imaging Decision making Cancer treatment Reliability Bioinformatics Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Modeling and evaluation design of heterogeneous media networks considering quality of experience

Modeling and evaluation design of heterogeneous media networ...

引用

Chinese Automation Congress (CAC)

作者： Kun Cong Luzhen Huang Ziqi He Lu Ding Dan Huang Lei Song School of Aeronautics and Astronautics Shanghai Jiao Tong University Shanghai China Architecture & Technical Innovation Dept Huawei Cloud Computing Technologies Co. Ltd. Shenzhen China School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai China Center for aerospace systems engineering Shanghai Jiao Tong University Shanghai China

ISBN: (数字)9798350368604

ISBN: (纸本)9798350368611

Aiming at social media platforms with different commercial scenarios, especially for “cloud gaming”, this paper proposes a modeling and analysis framework for heterogeneous media networks considering quality of experience, which addresses the challenges of quantifying human impacts. Through standardized definitions of humans and equipment, man-machine information transmission is classified formally. Then, the evaluation of quality of experience for entities and media networks are defined. Finally, a case study about analysis and optimization for media network in the scenario of “cloud gaming” is derived. Different simulation results and the experiment's comparison imply the applicability and effectiveness of the framework proposed in this paper.

关键词： Social networking (online) Simulation Supervised learning Information processing Complex networks Media Cloud gaming Topology Quality of experience Optimization

来源：评论

学校读者我要写书评

暂无评论

Achieving Indoor Visual Comfort Via Thermal Performance-Centred Glazed Fenestration in the UK Residential Office Environments

SSRN

引用

SSRN 2024年

作者： Gagg, Ryan Torpy, Fraser R. Ekanayake, Biyanka Wilkinson, Sara Yang, Siliang School of Built Environment Engineering and Computing Leeds Beckett University Leeds United Kingdom School of Life Sciences Faculty of Science University of Technology Sydney Sydney Australia School of Built Environment Faculty of Design Architecture and Building University of Technology Sydney Sydney Australia Mott MacDonald Leeds United Kingdom Leeds Beckett University United Kingdom

The COVID-19 pandemic has led to a rise in residential office utilisation. As a result, it has become increasingly important to configure workspaces and design dwellings to ensure adequate indoor environmental quality conditions, so as to mitigate detrimental health impacts caused by inadequate home office spaces. Currently, UK industry best practice focuses on rationalising the window-to-wall ratio (WWR) for dwellings. However, there is an increased regulatory stringency on new build glazing thermal performance, without much regard to achieving adequate daylighting. This paper looks into optimising daylighting sufficiency within newly constructed UK housing to attain the specific daylighting availability requirements set out within the British Standard – BS EN 17037:2018+A1:2021, whilst simultaneously ensuring visual comfort, thermal comfort, and sustainability. A quantitative analytical methodology was adopted through a calibrated daylighting model simulation in association with thermal modelling for a typical semi-detached house in the UK. The performance of five glazing solutions with varying WWR was assessed against BS EN 17037:2018+A1:2021. The WWR of all glazing types was increased from an initial WWR of 15.26% until daylighting sufficiency was realised. Our findings show that the house attained inadequate daylighting with the initial WWR of 15.26%, as 77% of frequently occupied spaces achieved an illuminance of 100 lux for 50% of the daylight hours and 300 lux for 42% of the frequently occupied space for 50% of the daylight hours, which failed to comply with the standard. Thus, a larger WWR of 20% is required for the house to comply with the current daylighting standard. In this study, an optimisation strategy was conceived to review a combination of key parameters for optimising the glazing selection. However, it was found that no compliant daylighting optimisation strategy could be realised without an increase of 3.66°C to the peak operative temperature. T

关键词： Daylighting

来源：评论

学校读者我要写书评

暂无评论

Self and peer evaluations of student performance in skills based design projects 22

Self and peer evaluations of student performance in skills b...

引用

22nd International Conference on engineering and Product Design Education, E and PDE 2020

作者： Covill, Derek Katz, Tim Smith, Steven Hicks, Dan School of Computing Engineering and Mathematics University of Brighton United Kingdom School of Architecture and Design University of Brighton United Kingdom

ISBN: (纸本)9781912254101

Self and peer assessment have been shown to help improve student engagement in assessment tasks, to improve behaviour and maintain interest and attention levels, and ultimately to improve student performance. In this study, we critically evaluated the process, reliability, validity, benefits and drawbacks of self and peer assessment in a first-year product design project with the aim to also establish a recommended resolution for rubric grade boundaries. Students (n = 51) carried out five separate week-long design projects. They then undertook self and peer assessments and were assessed by the module tutors, by additional staff (both technical and academic not linked to the project module) and students on other years of the course. All staff had reasonable agreement with tutor grades, although there were mixed results on whether these were a valid means to accurately assess the project outcome-depending on which statistical analysis was adopted. For all staff, >90% of their assessments were within 10% of the benchmark (agreed) grades, while for student self-Assessments 84.2% were within 10% and for student peer assessments 60.5% of the overall grades were within 10% of the tutors grades. When we analysed the data for individual tutor marks for all assessment criteria, 37.3% of grades were within 5% of each other, 85.8% were within 10% of each other, and the range within which 95% of grades could be bound was 20%, suggesting that the resolution of our rubric grade boundaries should be increased to 20% between grades boundaries for individual criteria in such practical assessment tasks in design. More generally, understanding the reliability and validity of assessment processes can help inform the assessment design to ensure an appropriate resolution is used for criteria. © International Conference on engineering and Product Design Education, E and PDE *** right reserved.

关键词： Students

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：