检索结果-内蒙古大学图书馆

SSRN 2023年

作者： He, Yulin Zhang, Manjing Liu, Guangwu Fournier-Viger, Philippe Dai, Shan Huang, Joshua Zhexue Shenzhen518107 China Department of Management Sciences City University of Hong Kong 518057 Hong Kong College of Computer Science & Software Engineering Shenzhen University Shenzhen518060 China Shenzhen Research Institute of Big Data Shenzhen518172 China

The thresholding bandit (TB) problem is a popular sequential decision-making problem, which aims at identifying the systems whose means are greater than a threshold. The TB problem is a variant of the multi-armed bandit (MAB) problem, which seeks to maximize the total reward by balancing the trade-off between exploration and exploitation. This paper presents a parameter-free policy for the TB problem based on the large-deviation theory, and proposes a large-deviation (LD) algorithm to solve the TB problem using an optimal allocation rule. We theoretically show that the LD algorithm is asymptotically optimal, and its probability of incorrect identification converges more quickly than the existing algorithms as the sample size approaches to infinity. Furthermore, to improve the robustness of the LD algorithm for optimization problems with small sample sizes, a decay rate-based approximate large-deviation (ALD) algorithm is proposed that takes the sample means and sample variances into account in a direct and simple way. Extensive experiments are conducted to validate the effectiveness of the LD and ALD algorithms. Simulation results indicate that both LD and ALD are viable solutions to handle the TB problem. © 2023, The Authors. All rights reserved.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

False data Injection Attack Detection of Cyber-Physical Charging Systems Based on Time-Frequency Analysis

False Data Injection Attack Detection of Cyber-Physical Char...

引用

Smart Electrical Grid and Renewable Energy (SEGRE), International Conference on

作者： Chao Hu Peishun Fan Yuxin Li I-Ju Chiu Yibin Wang Yiquan Zhou Yi Li Heng Li Big Data Institute Central South University Changsha China School of Computer Science and Engineering Central South University Changsha China Department of Information Studies University College London London UK Hunan Post and Telecommunication College Changsha China

Distributed charging systems play a critical role in the operation of supercapacitor electric vehicles. During the charging process, multiple charging modules rely on a communication network to achieve information sharing and interaction. If an external attack occurs on the network, the system will be in danger. To solve this problem, this paper proposes an anomaly detection mechanism based on real-time feature extraction to process measurement data. By analyzing the delayed effect of communication signal propagation, a method for identifying component faults and false data injection attacks (FDIA) is proposed. Moreover, the effectiveness and feasibility of the proposed distributed detection method are verified through experiments. Multiple experiments have consistently demonstrated that the proposed method outperforms existing methods FDIA detection.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Study of PSO Optimized BP Neural Network and Smith Predictor for MOCVD Temperature Control in 7nm 5G Chip Process 6th

Study of PSO Optimized BP Neural Network and Smith Predictor...

引用

6th International Conference on Advanced Intelligent Systems and Informatics, AISI 2020

作者： Chang, Kuo-Chi Zhou, Yu-Wen Wang, Hsiao-Chuan Lin, Yuh-Chung Chu, Kai-Chun Hsu, Tsui-Lien Pan, Jeng-Shyang School of Information Science and Engineering Fujian University of Technology Fuzhou China Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology Fuzhou China Institute of Environmental Engineering National Taiwan University Taipei Taiwan Department of Business Management Fujian University of Technology Fuzhou China Institute of Construction Engineering and Management National Central University Taoyuan Taiwan College of Computer Science and Engineering Shandong University of Science and Technology Shandong China College of Mechanical and Electrical Engineering National Taipei University of Technology Taipei Taiwan

ISBN: (纸本)9783030586683

The key industries of information technology in the semiconductor integrated circuit industry will have an important role after 2020, In the third generation of advanced semiconductor of 7nm 5G chips GaN is be used, MOCVD is a key technology for preparing high-quality communication semiconductor crystals. This study proposes PID controller of PSO and BP neural network algorithm to improve the control ability of MOCVD temperature. From the research results, it is found that the method proposed in this study adopts the PSO and BP neural network intelligent PID algorithm controller with Smith predictor, which has better dynamic performance, and the value from 150 to 500s is stable from 0 to 1 no vibration, any overshoot and short adjustment time, ideal control. © 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Controllers

来源：评论

学校读者我要写书评

暂无评论

Cutting Force Similarity Calculation in Milling Process Using Siamese LSTM Structure

Cutting Force Similarity Calculation in Milling Process Usin...

引用

Mechatronics and Electrical engineering (MEEE), International Conference on

作者： Juheon Kwak Wonkeun Jo Soomin Lee Hyein Kim Jeongin Koo Dongil Kim Division of Artificial Intelligence and Software Ewha Womans University Seoul South Korea Computer Science and Engineering Chungnam National University Daejeon South Korea Manufacturing System R&BD Group Korea Institute of Industrial Technology Cheonan South Korea Department of Data Science Ewha Womans University Seoul South Korea

Cutting force is a key factor in machining processes. Cutting force similarity is required for several important issues, namely: stability evaluation, process control, and process parameter setting. This study employed a long short-term memory (LSTM) with Siamese architecture to measure the similarity of the cutting forces in a milling process. The Siamese LSTM was trained with time series data of the vertical cutting force collected from a cutting tool during the milling process to calculate the similarity. For evaluation, dynamic time warping (DTW), a common approach used to calculate the similarity of time series data, was employed for comparison with the Siamese LSTM. Experimental results showed that the proposed Siamese LSTM outperformed the conventional DTW-based similarity calculation.

关键词： Training Electrical engineering Mechatronics Force measurement Force Time series analysis Process control

来源：评论

学校读者我要写书评

暂无评论

Generative AI for Advanced UAV Networking

引用

IEEE Network 2024年

作者： Sun, Geng Xie, Wenwen Niyato, Dusit Du, Hongyang Kang, Jiawen Wu, Jing Sun, Sumei Zhang, Ping Jilin University College of Computer Science and Technology Changchun130012 China Jilin University Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education Changchun130012 China Nanyang Technological University College of Computing and Data Science Singapore639798 Singapore The University of Hong Kong Department of Electrical and Electronic Engineering Hong Kong999077 Hong Kong Guangdong University of Technology School of Automation Guangzhou510006 China Agency for Science Technology and Research Institute for Infocomm Research Singapore639798 Singapore Beijing University of Posts and Telecommunications State Key Laboratory of Networking and Switching Technology Beijing100876 China

With the impressive achievements of chatGPT and Sora, generative artificial intelligence (GAI) has received increasing attention. Not limited to the field of content generation, GAI is also widely used to solve the problems in wireless communication scenarios due to its powerful learning and generalization capabilities. Therefore, we discuss key applications of GAI in improving unmanned aerial vehicle (UAV) communication and networking performance in this article. Specifically, we first review the key technologies of GAI and the important roles of UAV networking. Then, we show how GAI can improve the communication, networking, and security performances of UAV systems. Subsequently, we propose a novel framework of GAI for advanced UAV networking, and then present a case study of UAV-enabled spectrum map estimation and transmission rate optimization based on the proposed framework to verify the effectiveness of GAI-enabled UAV systems. Finally, we discuss some important open directions. © 2024 IEEE.

关键词： Aircraft communication

来源：评论

学校读者我要写书评

暂无评论

CrossDiff: Exploring Self-Supervised Representation of Pansharpening via Cross-Predictive Diffusion Model

arXiv

引用

arXiv 2024年

作者： Xing, Yinghui Qu, Litao Zhang, Shizhou Zhang, Kai Zhang, Yanning Ran, Lingyan Zhang, Xiuwei Yin, Hanlin The Shaanxi Provincial Key Laboratory of Speech and Image Information Processing The National Engineering Laboratory for Integrated Aerospace-GroundOcean Big Data Application Technology School of Computer Science Northwestern Polytechnical University Xi’an710072 China The Research Development Institute Northwestern Polytechnical University in Shenzhen Shenzhen518057 China

Fusion of a panchromatic (PAN) image and corresponding multispectral (MS) image is also known as pansharpening, which aims to combine abundant spatial details of PAN and spectral information of MS. Due to the absence of high-resolution MS images, available deep-learning-based methods usually follow the paradigm of training at reduced resolution and testing at both reduced and full resolution. When taking original MS and PAN images as inputs, they always obtain sub-optimal results due to the scale variation. In this paper, we propose to explore the self-supervised representation of pansharpening by designing a cross-predictive diffusion model, named CrossDiff. It has two-stage training. In the first stage, we introduce a cross-predictive pretext task to pre-train the UNet structure based on conditional DDPM, while in the second stage, the encoders of the UNets are frozen to directly extract spatial and spectral features from PAN and MS, and only the fusion head is trained to adapt for pansharpening task. Extensive experiments show the effectiveness and superiority of the proposed model compared with state-of-the-art supervised and unsupervised methods. Besides, the cross-sensor experiments also verify the generalization ability of proposed self-supervised representation learners for other satellite’s datasets. We will release our code for reproducibility. © 2024, CC BY.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

DP2-Pub: Differentially Private High-Dimensional data Publication with Invariant Post Randomization

arXiv

引用

arXiv 2022年

作者： Jiang, Honglu Yu, Haotian Cheng, Xiuzhen Pei, Jian Pless, Robert Yu, Jiguo The Department of Computer Science and Software Engineering Miami University OxfordOH45056 United States The Department of Computer Science The George Washington University WashingtonDC20052 United States The Department of Data Analytics The George Washington University WashingtonDC20052 United States The School of Computer Science and Technology Shandong University Qingdao266510 China The Departments of Computer Science Biostatistics and Bioinformatics Electrical and Computer Engineering Duke University DurhamNC27708 United States Big Data Institute Qilu University of Technology Jinan250353 China Shandong Fundamental Research Center for Computer Science Qilu University of Technology Shandong Jinan250353 China

A large amount of high-dimensional and heterogeneous data appear in practical applications, which are often published to third parties for data analysis, recommendations, targeted advertising, and reliable predictions. However, publishing these data may disclose personal sensitive information, resulting in an increasing concern on privacy violations. Privacy-preserving data publishing has received considerable attention in recent years. Unfortunately, the differentially private publication of high dimensional data remains a challenging problem. In this paper, we propose a differentially private high-dimensional data publication mechanism (DP2-Pub) that runs in two phases: a Markov-blanket-based attribute clustering phase and an invariant post randomization (PRAM) phase. Specifically, splitting attributes into several low-dimensional clusters with high intra-cluster cohesion and low inter-cluster coupling helps obtain a reasonable allocation of privacy budget, while a double-perturbation mechanism satisfying local differential privacy facilitates an invariant PRAM to ensure no loss of statistical information and thus significantly preserves data utility. We also extend our DP2-Pub mechanism to the scenario with a semi-honest server which satisfies local differential privacy. We conduct extensive experiments on four real-world datasets and the experimental results demonstrate that our mechanism can significantly improve the data utility of the published data while satisfying differential privacy. Copyright © 2022, The Authors. All rights reserved.

关键词： Bayesian networks

来源：评论

学校读者我要写书评

暂无评论

Multi-Objective Coordinated Ev Charging Strategy in Distribution Networks Using an Improved Augmented Epsilon-Constrained Method

SSRN

引用

SSRN 2024年

作者： Wang, Yunqi Wang, Hao Razzaghi, Reza Jalili, Mahdi Liebman, Ariel Department of Data Science and AI Monash University ClaytonVIC3800 Australia Monash Energy Institute Monash University ClaytonVIC3800 Australia Department of Electrical and Computer Systems Engineering Monash University ClaytonVIC3800 Australia MelbourneVIC3000 Australia The University of Sydney Australia

The surging adoption of electric vehicles (EVs) poses significant challenges for distribution networks (DNs) due to EV charging impact. This paper presents a multi-objective optimization (MOO) model that coordinates EV charging in DNs, aiming to address the interests of different stakeholders, such as the distribution network operator (DNO) and EV owners and achieve a balanced outcome. Specifically, our model’s objectives include minimizing the operation costs for distribution network operators (DNO), power loss in the DN, and EV owners’ charging expenses, emphasizing the delicate trade-off between these objectives. An innovative improved-augmented epsilon-constrained (IAUGMENCON)method is proposed to tackle the complex trade-offs by solving the MOO effectively and efficiently. A case study on an modified IEEE 33-bus DN attests to the strategy’s efficacy, showcasing a range of solutions that coordinate DNO’s costs, DN power loss, and EV charging costs. Furthermore, our I-AUGMENCON outperforms other prevalent MOO solution methods, such as the weighted-sum and NSGA-II, in determining non-dominated solutions and obtaining a Pareto-efficient solution set for the MOO to characterize an effective trade-off between three key objectives. © 2024, The Authors. All rights reserved.

关键词： Electric power distribution

来源：评论

学校读者我要写书评

暂无评论

Exploring the Tangible Impact of Artificial Intelligence and Machine Learning: Bridging the Gap between Hype and Reality

Exploring the Tangible Impact of Artificial Intelligence and...

引用

Advanced Computing and Emerging Technologies (ACET), International Conference on

作者： Rahul Dattangire Ruchika Vaidya Divya Biradar Ashish Joon Data Engineering Publicis Sapient Houston Texas USA Department of Artificial Intelligence and Machine Learning Datta Meghe Institute of Higher Education and Research (DU) Wardha Maharashtra India Computer Science University of Texas at Arlington Arlington Texas USA Software Developer Andhus Technologies Inc Pensacola FL

ISBN: (数字)9798350367720

ISBN: (纸本)9798350367737

Beyond being merely trendy terms in technology, machine learning (ML) and artificial intelligence (AI) have directly influenced every industry. This article thus demystifies the true meaning of these technologies by sifting through the sultry descriptions. Here, we explore how AI and ML enhance efficiency, decision-making, and problem-solving in various sectors including health, Agriculture, finance, and production as we discover real-world applications. Continuing with the discussion of implementation challenges, the aspects of bias, ethical pitfalls, and report cards are examined. In addition, the article also covered how the integration of AI as well as ML remains a way of improving processes, creating better user experiences, and spurring innovation. This paper, which is also based on case studies, discusses the relationship between social welfare and AI and the importance of AI’s development and use being done responsibly. Considering all the discussed aspects, this volume provides a rather nuanced perspective on AI and ML, unmasking the myths around these concepts to reveal the fact that they have a highly significant impact on the current reality and its projected evolutions.

关键词： Technological innovation Ethics Decision making Finance Machine learning Production Pressing Medical services Writing Problem-solving

来源：评论

学校读者我要写书评

暂无评论

Fair Machine Learning in Healthcare: A Review

arXiv

引用

arXiv 2022年

作者： Feng, Qizhang Du, Mengnan Zou, Na Hu, Xia The Department of Computer Science & Engineering Texas A&M University TX77843 United States The Department of Data Science New Jersey Institute of Technology NJ07102 United States The Department of Engineering Technology & Industrial Distribution Texas A&M University TX77843 United States The Department of Computer Science Rice University TX77251 United States

The digitization of healthcare data coupled with advances in computational capabilities has propelled the adoption of machine learning (ML) in healthcare. However, these methods can perpetuate or even exacerbate existing disparities, leading to fairness concerns such as the unequal distribution of resources and diagnostic inaccuracies among different demographic groups. Addressing these fairness problem is paramount to prevent further entrenchment of social injustices. In this survey, we analyze the intersection of fairness in machine learning and healthcare disparities. We adopt a framework based on the principles of distributive justice to categorize fairness concerns into two distinct classes: equal allocation and equal performance. We provide a critical review of the associated fairness metrics from a machine learning standpoint and examine biases and mitigation strategies across the stages of the ML lifecycle, discussing the relationship between biases and their countermeasures. The paper concludes with a discussion on the pressing challenges that remain unaddressed in ensuring fairness in healthcare ML, and proposes several new research directions that hold promise for developing ethical and equitable ML applications in healthcare. © 2022, CC BY.

关键词： Machine learning

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：