检索结果-内蒙古大学图书馆

China Semiconductor Technology International Conference (CSTIC)

作者： Tianhao Huang Pan Liu Zeyang Chen Jianming Wu Dawei Gao Guodong Zhou College of Integrated Circuits Zhejiang University Hangzhou China Zhejiang ICsprout Semiconductor Co. Ltd Hangzhou China ZJU-Hangzhou Global Scientific and Technological Innovation Center Zhejiang University Hangzhou China

ISBN: (数字)9798331513351

ISBN: (纸本)9798331513368

In semiconductor manufacturing, handling missing values in measurement data is a crucial step to ensure accurate data analysis or feature extraction. Traditional interpolation algorithms, such as K-nearest neighbor (KNN), have been widely used to estimate missing die locations on wafer maps. However, when applied to CD-SEM measured wafer maps in lithography, such interpolation methods may not accurately approximate the true data due to the lack of consideration for lithography process characteristics. This paper proposes a modified direction-weighted KNN interpolation algorithm with considerations of scanner exposure direction. Comparative analysis demonstrates that the modified algorithm more effectively represents the feature data after interpolation, leading to better alignment with the original wafer map.

关键词： Integrated circuits Interpolation Semiconductor device measurement Data analysis Accuracy Lithography Nearest neighbor methods Semiconductor device manufacture approximation algorithms Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Bi-Criteria Optimization for Combinatorial Bandits: Sublinear Regret and Constraint Violation under Bandit Feedback

arXiv

引用

arXiv 2025年

作者： Aggarwal, Vaneet Jain, Shweta Pokhriyal, Subham Quinn, Christopher John Purdue University United States IIT Ropar India Iowa State University United States

In this paper, we study bi-criteria optimization for combinatorial multi-armed bandits (CMAB) with bandit feedback. We propose a general framework that transforms discrete bi-criteria offline approximation algorithms into online algorithms with sublinear regret and cumulative constraint violation (CCV) guarantees. Our framework requires the offline algorithm to provide an (α, β)-bi-criteria approximation ratio with δresilience and utilize N oracle calls to evaluate the objective and constraint functions. We prove that the proposed framework achieves sublinear regret and CCV, with both bounds scaling as O (δ2/3N1/3T 2/3 log1/3(T) ) . Crucially, the framework treats the offline algorithm with δresilience as a black box, enabling flexible integration of existing approximation algorithms into the CMAB setting. To demonstrate its versatility, we apply our framework to several combinatorial problems, including submodular cover, submodular cost covering, and fair submodular maximization. These applications highlight the framework’s broad utility in adapting offline guarantees to online bi-criteria optimization under bandit feedback. Copyright © 2025, The Authors. All rights reserved.

关键词： approximation algorithms

来源：评论

学校读者我要写书评

暂无评论

Research on the Application System of Multi-Objective Optimization Algorithm in the Allocation of Educational Resources in Colleges and Universities

Research on the Application System of Multi-Objective Optimi...

引用

Cybersecurity, Internet of Things and Soft Computing (CITSC), Asia-Europe Conference on

作者： Feng Qian Lei Zhang School of Mathematics and Computer Science Tongling University Tongling China

ISBN: (数字)9798331504205

ISBN: (纸本)9798331504212

This article examines the application system of multi-objective optimization algorithm in resource allocation, to enhance the fairness and efficiency of resource allocation. Resource allocation encompasses multiple objectives, such as maximizing resource utilization, minimizing costs and guaranteeing fairness, thus it is extremely crucial to construct a rational optimization model. This paper first designs a resource allocation algorithm based on multi-objective optimization, combining the weight allocation method and the Pareto optimal solution to adapt to the diversified needs of resources. Then a simulation platform is constructed to simulate the actual resource allocation scenario through the operation of the algorithm, and the allocation results are accurately analyzed. The experimental outcomes demonstrate that the algorithm can effectively enhance the efficiency and fairness of resource allocation within different resource limitations. In comparison with the traditional allocation approach, the resource utilization ratio is raised by over 15%, the cost is decreased by approximately 10%, and the fairness index is notably optimized. This system not only provides a reference for the reasonable allocation of resources, but also lays the foundation for the dynamic optimization of resource allocation.

关键词： Costs Supply and demand Heuristic algorithms Optimization models Pareto optimization approximation algorithms Dynamic scheduling Resource management Internet of Things Optimization

来源：评论

学校读者我要写书评

暂无评论

Energy-Efficient Beamforming Based on Statistical CSI for Multicast LEO Satellite Communications

Energy-Efficient Beamforming Based on Statistical CSI for Mu...

引用

IEEE Conference on Wireless Communications and Networking

作者： Shiang-Yu Kung Hung-Yun Hsieh Graduate Institute of Communication Engineering National Taiwan University Taipei Taiwan Department of Electrical Engineering National Taiwan University Taipei Taiwan

ISBN: (数字)9798350368369

ISBN: (纸本)9798350368376

Low Earth Orbit (LEO) satellites have recently attracted attention as solutions for enabling global connectivity because of the low propagation latency and low path loss compared to other satellite systems. In the meantime, however, the high orbital speed as well as the low production cost have rendered power consumption minimization as one of the most critical issues for performance optimization in LEO satellite communications. In this paper, we investigate energy-efficient beamforming design for LEO satellites that support multigroup multicast downlink communications. Different from related work that assumes availability of instantaneous channel state information (CSI), our design relies only on the slow-varying statistical CSI (sCSI). The formulated problem aims to maximize energy efficiency while meeting the target data rate requirements. To solve the problem, we first approximate the average rate function by applying a closed-form tight upper bound. We then use the Dinkelbach's algorithm to transform the fractional function for energy efficiency into a concave function. We finally adopt the Convex-Concave Procedure (CCCP) to solve the problem. Numerical results show that the proposed algorithm is able to achieve higher energy efficiency than existing approaches for multicast LEO satellite communications.

关键词： Satellites Multicast algorithms Upper bound Array signal processing Low earth orbit satellites Transforms Production approximation algorithms Propagation losses Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Discovering Options That Minimize Average Planning Time 39

Discovering Options That Minimize Average Planning Time

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Ivanov, Alexander Bagaria, Akhil Konidaris, George Brown University ProvidenceRI United States Amazon New YorkNY United States

ISBN: (纸本)157735897X

We present an option discovery algorithm that accelerates planning by minimizing the shortest distance between any two states in the MDP. The proposed algorithm produces options that approximately minimize planning time in the multi-goal setting: it is shown to be a worst-case (4α, 2)-approximation of the optimal option set, where α is the approximation ratio of the k-medians with penalties subroutine. We then present a variation, Fast Average Options, with improved run-time and describe a general means of producing similar algorithms based on the selection of a k-medians subroutine. We empirically evaluate our method on four discrete and two continuous control planning domains where it outperforms other leading option discovery algorithms. Copyright © 2025, Association for the Advancement of Artificial Intelligence.

关键词： approximation algorithms

来源：评论

学校读者我要写书评

暂无评论

A Non Local Feature-Preserving Strategy for Image Denoising

引用

Chinese Journal of Electronics 2023年第4期21卷 651-656页

作者： Ning HE Ke LU School of Information Beijing Union University Beijing China College of Computing and Communication Engineering Graduate University of Chinese Academy of Sciences Beijing China

In this paper, we propose a variational image denoising model by exploiting an adaptive feature-preserving strategy which is derived from the Non-local means (NL-means) denoising approach. The commonly used NL-means filter is not optimal for noisy images containing small features of interest since image noise always makes it difficult to estimate the correct coefficients for averaging, leading to over-smoothing and other artifacts. We address this problem by a non-local detail preserving constraint, which is performed by adding two terms in the Total variation (TV) model. One is a non local patch based regularization term that controls the amount of denoising to preserve textures, small details, or global information, the other is a new data fidelity term, which forces the gradients of desired image being close to the smoothed normal. The Euler-Lagrange equation is used to solve the problem. Experimental results show that the proposed method can alleviate the over-smoothing effect and other artifacts, while preserving the fine details.

关键词： TV Image edge detection Noise reduction Force Information security approximation algorithms Mathematical models

来源：评论

学校读者我要写书评

暂无评论

AIAS: Experimental Evaluation of Spectrum Utilization Over Cognitive Radio Networks Using Artificial Intelligence (AI) Assisted Adaptive Searching Algorithm

AIAS: Experimental Evaluation of Spectrum Utilization Over C...

引用

Advances in Electrical, Computing, Communication and Sustainable Technologies (ICAECT), International Conference on

作者： P. Shyamala Bharathi A Shankar Department of Electronics and Communication Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai

ISBN: (数字)9798350356236

ISBN: (纸本)9798350356243

The AI-Assisted Adaptive Searching Algorithm (AIAS) enhances spectrum utilization in Cognitive Radio Networks (CRNs) by predicting and dynamically allocating available frequency bands to secondary users. Using the Kaggle Spectrum Dataset, AIAS employs supervised learning to forecast spectrum availability with a 91.3% average accuracy, outperforming traditional searching methods by approximately 13%. Additionally, reinforcement learning enables real-time decision-making for optimal frequency allocation, achieving an average spectrum utilization efficiency of 92.5% and interference-free allocations up to 95.1%. Compared to conventional algorithms, AIAS reduces latency by an average of 50%, achieving allocation times of approximately 15.2 milliseconds. These improvements demonstrate AIAS's capability to adapt in spectrum-dense environments, ensuring minimal interference with primary users and higher spectrum utilization efficiency. This study highlights the potential of AIAS to address the limitations of static allocation in CRNs and underscores the advantages of machine learning in dynamic spectrum management. Future research could focus on integrating advanced AI models, such as deep learning, to further optimize prediction accuracy and enhance the robustness of adaptive spectrum utilization in increasingly complex network environments.

关键词： Adaptive systems Accuracy Supervised learning Reinforcement learning Prediction algorithms approximation algorithms Robustness Resource management Cognitive radio Radio spectrum management

来源：评论

学校读者我要写书评

暂无评论

A Simulation Model of Air Levitation for Reinforcement Learning Applications

A Simulation Model of Air Levitation for Reinforcement Learn...

引用

Cybernetics & Informatics (K&I)

作者： Michal Hlavatý Alena Kozáková Gabriel Gálik Štefan Kozák Slovak University of Technology in Bratislava FEI Bratislava Slovakia Faculty of Informatics Pan-European University Bratislava Slovakia

ISBN: (数字)9798331541811

ISBN: (纸本)9798331541828

In automatic control, Artificial Neual Networks (ANN) can be used to replace any term of the control loop. Mostly, they are used to model highly nonlinear plants with complex dynamics or are designed to mimic standard controllers and further trained for improved performance. Reinforcement Learning (RL) algorithms can also be used as controllers and do not need to be trained on the real plant. Due to the length of the training process and other aspects, it is difficult to select the optimal algorithm and tune its hyperparameters on a real device. Instead, simulation environments are used. The paper presents development of the air levitation simulation environment in the OpenAI Gymnasium framework that supports RL applications. The environment models the challenging complex nonlinear dynamics exhibited by air levitation plants. Using this safe and effective RL algorithm training platform, multiple agents can train in parallel without a threat of damaging physical equipment. The Soft Actor-Critic (SAC) algorithm from the StableBaselines3 library is used to demonstrate efficiency of the developed environment.

关键词： Training Heuristic algorithms Atmospheric modeling Laboratories Reinforcement learning Artificial neural networks Levitation approximation algorithms Libraries Standards

来源：评论

学校读者我要写书评

暂无评论

A Sequential Fusion Localization Algorithm Based on AUKF for UWB/IMU/ODOM Systems

A Sequential Fusion Localization Algorithm Based on AUKF for...

引用

Sensors and Information Technology (ICSI), International Conference on

作者： Qingxi Zeng Yuxin Song Rongchen Wang Xia You College of Automation Engineering Nanjing University of Aeronautics and Astronautics Nanjing China

ISBN: (数字)9798331542887

ISBN: (纸本)9798331542894

To address the positioning problem of Ultra-Wideband (UWB) in complex dynamic environments, this paper proposes a UWB/ Inertial Measurement Units (IMU)/Odometry (ODOM) fusion algorithm based on the Adaptive Unscented Kalman Filter (AUKF). By designing an independent measurement update module, centralized sequential fusion of UWB and trajectory estimation is achieved. This approach handles time-asynchronous data flexibly and introduces an adaptive noise adjustment mechanism and Mahalanobis distance-based outlier removal strategy, enhancing the system's dynamic adaptability and state estimation accuracy. Experimental results show that the proposed algorithm reduces the root mean square error by approximately 22.1% and 24.1% compared to UWB and trajectory estimation, respectively, and can perform continuous localization even when UWB data is interfered with or fails.

关键词： Meters Location awareness Accuracy Adaptive systems Heuristic algorithms Noise approximation algorithms Trajectory Odometry State estimation

来源：评论

学校读者我要写书评

暂无评论

Comparison of Crop Image Classification Model Performance According to Image Augmentation Techniques

Comparison of Crop Image Classification Model Performance Ac...

引用

International Conference on Big Data and Smart Computing (BIGCOMP)

作者： Dong Kyu Yun Seong Ju Joe Ki Tae Park Seok Kee Lee Sang Hyun Choi dept. of Bigdata Chungbuk National University Cheongju Republic of Korea dept. of Computer Engineering Hansung University Seoul Republic of Korea dept. of MIS/Bigdata Chungbuk National University Cheongju Republic of Korea

ISBN: (数字)9798331529024

ISBN: (纸本)9798331529031

Currently, the agricultural population is rapidly decreasing in Korea, and the aging population is getting worse. Therefore, the development of smart farm-related technologies is more necessary, and image processing technologies using big data and AI are very important. In this study, after collecting crop images directly from farms, three datasets were constructed according to the preprocessing method, and images between crops were classified using a CNN-based image classification model. As a result of the analysis, it was confirmed that the method using dataset B and NASNetLarge with five data augmentation was the best with an average classification accuracy of $\mathbf{9 6 . 7 1 \%}$.

关键词： Smart agriculture YOLO Accuracy Crops Big Data approximation algorithms Image augmentation Classification algorithms Convolutional neural networks Image classification

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：