检索结果-内蒙古大学图书馆

Low-rank matrix recovery with total generalized variation for defending adversarial examples

Frontiers of Information Technology & Electronic engineering 2024年第3期25卷 432-445页

作者： Wen LI Hengyou WANG Lianzhi HUO Qiang HE Linlin CHEN Zhiquan HE Wing W.Y.Ng School of Science Beijing University of Civil Engineering and ArchitectureBeijing 100044China School of Computer Science and Engineering South China University of TechnologyGuangzhou 510006China Aerospace Information Research Institute Chinese Academy of SciencesBeijing 100094China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen 518060China Institute of Big Data Modeling and Technology Beijing University of Civil Engineering and ArchitectureBeijing 100044China

Low-rank matrix decomposition with first-order total variation(TV)regularization exhibits excellent performance in exploration of image *** advantage of its excellent performance in image denoising,we apply it to improve the robustness of deep neural ***,although TV regularization can improve the robustness of the model,it reduces the accuracy of normal samples due to its *** our work,we develop a new low-rank matrix recovery model,called LRTGV,which incorporates total generalized variation(TGV)regularization into the reweighted low-rank matrix recovery *** the proposed model,TGV is used to better reconstruct texture information without *** reweighted nuclear norm and Li-norm can enhance the global structure ***,the proposed LRTGV can destroy the structure of adversarial noise while re-enhancing the global structure and local texture of the *** solve the challenging optimal model issue,we propose an algorithm based on the alternating direction method of *** results show that the proposed algorithm has a certain defense capability against black-box attacks,and outperforms state-of-the-art low-rank matrix recovery methods in image restoration.

关键词： Total generalized variation Low-rank matrix Alternating direction method of multipliers Adversarial example

来源：评论

学校读者我要写书评

暂无评论

Fresh Retail Layout and Forecast Based on Multi-Source Big Data and Machine Learning: A Case Study of Guangzhou

Fresh Retail Layout and Forecast Based on Multi-Source Big D...

引用

2024 International Conference on Construction and Real Estate Management: ESG Development in the Construction Industry, ICCREM 2024

作者： Wu, Kaixin Liu, Ziye Wei, Zongcai Liang, Jing Jiang, Rui Hu, Zilin School of Architecture South China Univ. of Technology Guangzhou China School of Computer Science and Engineering South China Univ. of Technology Guangzhou China State Key Laboratory of Subtropical Building and Urban Science South China Univ. of Technology Guangzhou China

ISBN: (数字)9780784485910

ISBN: (纸本)9780784485910

Fresh retail is an important facility in the community life circle. Exploring its spatial distribution is essential for improving the allocation of life service resources. This paper introduces a method based on supply and demand matching and machine learning, designed to analyze and forecast the current state of supply and demand in offline fresh retail. Specifically, we take the four central districts of Guangzhou as the research object and apply the two-step mobile search method to filter the training set grid. Utilizing machine learning, we obtained the feature matrices of these grids and applied them to the supply prediction of the remaining grids. The results indicate that the Commercial Residential Density, Travel Convenience Index, and Food Service Density are the main factors affecting the location selection of offline fresh retail. The supply and demand in Yuexiu and Haizhu Districts show imbalance, and the construction of offline fresh retail facilities must be fortified. © ASCE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Pioneering Research on a Neurodiverse ADHD Workforce in the Future Construction Industry

Pioneering Research on a Neurodiverse ADHD Workforce in the ...

引用

Construction Research Congress 2024, CRC 2024

作者： Chang, Woei-Chyi Ismael Becerra, Joshua Karalunas, Sarah L. Esmaeili, Behzad Yu, Lap-Fai Hasanzadeh, Sogand Lyles School of Civil Engineering Purdue Univ. West LafayetteIN United States Dept. of Psychological Sciences Purdue Univ. West LafayetteIN United States School of Industrial Engineering and Civil Engineering Purdue Univ. West LafayetteIN United States Dept. of Computer Science George Mason Univ. FairfaxVA United States

ISBN: (数字)9780784485293

ISBN: (纸本)9780784485293

While incorporating novel technologies aims to facilitate the inclusion of the future construction industry, the empirical investigation of diverse workers' performance is necessary to better understand the strategies to broaden their participation. The literature has rarely focused on inclusivity in terms of involving workers with various disabilities in the construction sector. Thus, this study aims to pioneer the discussion on inclusivity in construction by focusing on workers with attention-deficit/hyperactivity disorder (ADHD). A future bricklaying worker-AI collaborative task was developed to examine workers' attentional allocation, situational awareness (SA), and productivity in future works. The results indicated that ADHD workers exhibited a lower SA of dynamic objects by focusing on the primary task with no increase in productivity, leading to lower overall performance. This study provided insights into (1) understanding ADHD workers' performance on human-AI teaming of future jobsites, and (2) proposing strategies to facilitate inclusivity in the future construction industry. © CRC 2024. All rights reserved.

关键词： Construction industry

来源：评论

学校读者我要写书评

暂无评论

Construction of Python programming case library for artificial intelligence under the background of new engineering disciplines 24

Construction of Python programming case library for artifici...

引用

Proceedings of the 2024 2nd International Conference on Information Education and Artificial Intelligence

作者： Cheng Lv Department of Computer Science School of Electrical and Information Engineering Beijing University of Civil Engineering and Architecture Beijing China

ISBN: (纸本)9798400711732

Python language has a powerful artificial intelligence algorithm library. This study adopts a project driven approach and fully utilizes graphical visualization programming tools such as Raptor and Orange3 to assist teaching. At the same time, with the help of large models to assist programming, the cultivation of mathematical thinking, logical thinking, AI thinking, engineering thinking, and programming training are integrated into Python language course teaching in a step-by-step and progressive manner, forming a robust teaching ecosystem. Under the innovative teaching mode, students have gained sufficient practical training through graphic visualization programming, large model assisted programming, Python program writing and debugging, etc., mastering the Python language and gaining intuitive understanding of engineering project development, and enabling them to have preliminary research and development capabilities for artificial intelligence.

关键词： Advanced Case Library

来源：评论

学校读者我要写书评

暂无评论

Influence of Leakage from Buried Drainage Pipes on Shallow Soil Settlement and Urban Road Collapse

引用

Natural Hazards Review 2025年第3期26卷

作者： Li, Xinyue Cao, Liting Li, Zhongying Li, Jiacheng Lv, Xiangfeng School of Civil and Resource Engineering Univ. of Science and Technology Beijing Beijing100083 China

Frequent road collapses caused by water leakages from pipelines pose a severe threat to urban safety and the wellbeing of city residents. Limited research has been conducted on the relationship between pipeline leakage and soil settlement, thus resulting in a lack of mathematical models that accurately describe the soil settlement process resulting from water erosion. In this study, we developed an equation for pipeline leakage, conducted physical model experiments on road collapses induced by drainage pipeline leakage, investigated the functional relationship between drainage pipeline leakage and soil settlement, and validated this relationship through physical experiments with pipelines of various sizes. The results indicated that drainage pipeline leakage triggered internal erosion and damaged the soil layers in four stages: soil particle detachment, seepage channel formation, void development, and road collapse. When the pipeline size was increased by a factor of 1.14, the total duration of road collapse induced by pipeline leakage increased by 20.78%, and the total leakage water volume increased by 33.5%. The Pearson correlation coefficient between the theoretical and actual settlement exceeded 0.9, thus demonstrating the reasonableness and effectiveness of the proposed settlement calculation method. The findings of this study serve as a basis for monitoring soil settlement and issuing early road collapse warnings. © 2025 American Society of civil Engineers.

关键词： Drainage

来源：评论

学校读者我要写书评

暂无评论

Supply and Demand Relationship of Fresh Retail Based on Accessibility: A Case Study of Guangzhou

Supply and Demand Relationship of Fresh Retail Based on Acce...

引用

2024 International Conference on Construction and Real Estate Management: ESG Development in the Construction Industry, ICCREM 2024

作者： Jiang, Rui Hu, Zilin Wei, Zongcai Wu, Kaixin Liang, Jing Liu, Ziye School of Architecture South China Univ. of Technology Guangzhou China State Key Laboratory of Subtropical Building and Urban Science South China Univ.of Technology Guangzhou China School of Computer Science and Engineering South China Univ. of Technology Guangzhou China

ISBN: (数字)9780784485910

ISBN: (纸本)9780784485910

Whether the supply-demand relationship of fresh food retail services matches is of great significance to urban planning and construction and residents' lives. This work takes four central districts in Guangzhou as an example to calculate the accessibility of fresh retail in different types of residential areas. In addition, this work explores the spatial clustering distribution relationship of fresh retail supply and demand. Results show that the frequency of purchasing fresh food in central areas is typically higher than that in border areas. However, the supply-demand matching is poor due to the large population size. The online accessibility of newly built urban areas, such as Tianhe District, is better, but offline fresh food retailing dominates. Offline fresh food retail supply and demand matching is better than online in the marginal area. The analysis of the accessibility of fresh food in residential areas is beneficial for providing a reference for urban spatial layout and planning and construction. © ASCE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An IoT-Based System for Lifecycle-Wide Carbon Emissions Assessment in Prefabricated Construction

An IoT-Based System for Lifecycle-Wide Carbon Emissions Asse...

引用

2024 International Conference on Construction and Real Estate Management: ESG Development in the Construction Industry, ICCREM 2024

作者： Zhang, Boyu Shen, Geoffrey Qiping Wu, Hengqin China Academy of Building Research Beijing China Dept. of Building and Real Estate Hong Kong Polytechnic Univ. Hong Kong School of Civil Engineering and Architecture Zhejiang Sci-Tech Univ. Hangzhou China

ISBN: (数字)9780784485910

ISBN: (纸本)9780784485910

Given the recognized capacity of prefabricated construction (PC) to minimize carbon emissions (CEs), there is a growing imperative for the establishment of comprehensive monitoring systems. Traditional monitoring methodologies have been limited to assessing CEs in discrete segments of prefabricated construction, often neglecting the intricacies of prefabricated and recyclable processes, which is a barrier to the deployment of effective CE mitigation strategies. Addressing this deficiency, the current investigation introduces an IoT-enabled system designed to quantify CEs throughout the entire lifecycle of prefabricated construction. The focus of this system is on the lifecycle stages with significant CE implications, thereby enabling thorough tracking of emissions particularly within prefabricated and recyclable operations. A bespoke CE quantification model, pertinent to the lifecycle of prefabrication, has been formulated, laying the analytical groundwork for the monitoring system. The utility of IoT technology in this context is scrutinized via case study analyses, which serve to substantiate the system's practicality and impact. The findings illustrate an enhanced precision in monitoring efforts, with a successful integration of a wide array of CE-related activities within the prefabricated construction domain into the IoT-based system. © ASCE.

关键词： Carbon cycle

来源：评论

学校读者我要写书评

暂无评论

Revisiting the Efficacy of Signal Decomposition in AI-based Time Series Prediction

Revisiting the Efficacy of Signal Decomposition in AI-based ...

引用

2024 International Conference Optoelectronic Information and Optical engineering, OIOE 2024

作者： Zhang, Dan Jiang, Kexin Wu, Chuhan Peng, Yan Han, Zhaolong Chen, Yaoran Institute of Artificial Intelligence Shanghai University Shanghai200444 China Department of Computer Engineering and Science Shanghai University Shanghai200444 China Department of Electronic Engineering Tsinghua University Beijing100084 China School of Naval Architecture Ocean & Civil Engineering Shanghai Jiao Tong University Shanghai200240 China

ISBN: (数字)9781510688209

ISBN: (纸本)9781510688193

Time series prediction is a fundamental problem in scientific exploration and artificial intelligence (AI) technologies have substantially bolstered its efficiency and accuracy. A well-established paradigm in AI-driven time series prediction is injecting physical knowledge into neural networks through signal decomposition methods, and sustaining progress in numerous scenarios has been reported. However, we uncover non-negligible evidence that challenges the effectiveness of signal decomposition in AI-based time series prediction. We confirm that improper dataset processing with subtle future label leakage is unfortunately widely adopted, possibly yielding abnormally superior but misleading results. By processing data in a strictly causal way without any future information, the effectiveness of additional decomposed signals diminishes. Our work probably identifies an ingrained and univ.rsal error in time series modeling, and the de facto progress in relevant areas is expected to be revisited and calibrated to prevent future scientific detours and minimize practical losses. © 2025 SPIE.

关键词： Information leakage

来源：评论

学校读者我要写书评

暂无评论

Mechanism and Key Parameters of Coal Fragmentation by Supersonic Gas Jet Impact: Numerical and Physical Simulation Research

引用

Journal of Energy engineering 2025年第4期151卷

作者： Wang, Gongda Zhou, Zhenxing Tian, Fan Wang, Haiyan Liu, Yikang Wang, Yuanyuan Research Institute of Macro-Safety Science Univ. of Science and Technology Beijing Beijing100083 China School of Civil and Resource Engineering Univ. of Science and Technology Beijing Beijing100083 China

To address the challenges of hole collapse and plugging in soft coal seams resulting from water jet-enhanced extraction technology, this paper investigates the continuous process mechanisms, jet characteristics, and comprehensive relationships among key parameters of enhanced gas extraction induced by gas jet impacts. The analysis employs theoretical evaluation, numerical simulations, and physical testing methods. Examination of the gas jet's development through various stages reveals that the coal fragmentation process consists primarily of three stages: the free jet stage, the impact jet stage, and the wall jet stage. The key parameters affecting coal-breaking capacity include jet pressure, target distance, and nozzle size. The findings indicate that coal-breaking capacity increases with higher jet pressure, while the optimal target distance for effective jet impact cracking is typically around 7-8 times the nozzle diameter. Although nozzle size has a limited effect on erosion and fragmentation, an increase in nozzle size results in a gradual enhancement of fragmentation, stabilizing at approximately 2.75 MPa. These insights significantly advance on-site enhanced gas extraction technology from coal seams through the impact of supersonic gas jets. Furthermore, the research findings offer a novel approach and theoretical foundation for local pressure relief and enhanced gas drainage in coal seams. © 2025 American Society of civil Engineers.

关键词： Coal breakage

来源：评论

学校读者我要写书评

暂无评论

FusTP-FL: Enhancing Differential Federated Learning through Personalized Layers and Data Transformation

FusTP-FL: Enhancing Differential Federated Learning through ...

引用

IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom)

作者： Xiong Yan Kedong Yan Chanying Huang Dan Yin Shan Xiao School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China School of Comp. Science & Engineering Nanjing Univ. of Science & Technology Nanjing China School of Elec. & Inf. Engineering Beijing Univ. of Civil Engineering & Architecture Beijing China Fiberhome Comm. Tech. Co. Wuhan China

ISBN: (数字)9798331506209

ISBN: (纸本)9798331506216

Federated Learning enables multiple clients to collaboratively train a model without sharing their individual data, thereby protecting local data privacy. However, attackers, such as untrusted servers, can still compromise the privacy of clients’ local training data through various inference attacks. One feasible approach to protect client privacy during training is the incorporation of differential privacy. Nevertheless, achieving an ideal level of privacy protection with differential privacy often degrades the model’s performance, significantly reducing its accuracy. To enhance model accuracy while minimizing the additional client heterogeneity introduced by differential privacy, this paper proposes a method that integrates personalized layers and data transformations, FusTP-FL. The core of our FusTP-FL is the incorporation of personalized layers and personalized data transformations within the client’s local training model, which further reduces client heterogeneity and improves model accuracy. We evaluated the model’s accuracy on six common datasets; experimental results demonstrate that the proposed FusTP-FL effectively enhances model accuracy across two different differential privacy modes (CDP and LDP), increasing it by up to 45%. Furthermore, we show that compared to PRIVATEFL, our method achieves lower client heterogeneity.

关键词： Training Differential privacy Privacy Accuracy Federated learning Computational modeling Training data Data models Servers Security

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：