检索结果-内蒙古大学图书馆

International Conference on Advanced Communication Technologies and Networking (CommNet)

作者： Widad Belaoura Saud Althunibat Mazen Hasna Khalid Qaraqe Electrical Systems Engineering Department University of M’Hamed Bougara Boumerdes Boumerdes Algeria Department of Electrical and Computer Engineering Texas A&M University at Qatar Doha Qatar Department of Electrical Engineering Qatar University Doha Qatar College of Science and Engineering Hamad Bin Khalifa University Doha Qatar

ISBN: (数字)9798350367027

ISBN: (纸本)9798350367034

Index modulation-aided orthogonal frequency division multiple access (IM-OFDMA) is envisioned as an advanced solution for the upcoming wireless communication systems. This paper proposes a highly efficient scheme by combining multiple-input multiple-output (MIMO) and IM-OFDMA to leverage both techniques collectively, offering a new possibility to boost spectrum efficiency compared with the IM-OFDMA and MIMO-OFDMA schemes. The basic principle of the resulting MIMO-IM-OFDMA scheme is to independently perform the IMOFDMA process on each transmit antenna, thereby achieving higher diversity. Considering different system configurations, Monte Carlo simulations demonstrate that the MIMO-IMOFDMA scheme not only enhances the communication error’s performance but also improves the spectral efficiency compared to the conventional IM-OFDMA and MIMO-OFDMA schemes.

关键词： Monte Carlo methods Spectral efficiency OFDM Spatial diversity Transmitting antennas Diversity reception Symbols Indexes MIMO communication Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Optimizing Bidding Curves for Renewable Energy in Two-Settlement Electricity Markets

arXiv

引用

arXiv 2025年

作者： Zhao, Dongwei Delikaraoglou, Stefanos Dvorkin, Vladimir Lamadrid, Alberto J.L. Botterud, Audun Argonne National Laboratory LemontIL United States Laboratory for Information and Decision Systems Massachusetts Institute of Technology CambridgeMA United States Department of Electrical Engineering and Computer Science University of Michigan Ann ArborMI United States Department of Economics Department of Industrial and Systems Engineering Lehigh University BethlehemPA United States

Coordination of day-ahead and real-time electricity markets is imperative for cost-effective electricity supply and also to provide efficient incentives for the energy transition. Although stochastic market designs feature the least-cost coordination, they are incompatible with current deterministic markets. This paper proposes a new approach for compatible coordination in two-settlement markets based on benchmark bidding curves for variable renewable energy. These curves are optimized based on a bilevel optimization problem, anticipating per-scenario responses of deterministic market-clearing problems and ultimately minimizing the expected cost across day-ahead and real-time markets. Although the general bilevel model is challenging to solve, we theoretically prove that a single-segment bidding curve with a zero bidding price is sufficient to achieve system optimality if the marginal cost of variable renewable energy is zero, thus addressing the computational challenge. In practice, variable renewable energy producers can be allowed to bid multi-segment curves with non-zero prices. We test the bilevel framework for both single- and multiple-segment bidding curves under the assumption of fixed bidding prices. We leverage duality theory and McCormick envelopes to derive the linear programming approximation of the bilevel problem, which scales to practical systems such as a 1576-bus NYISO system. We benchmark the proposed coordination and find absolute dominance over the baseline solution, which assumes that renewables agnostically bid their expected forecasts. We also demonstrate that our proposed scheme provides a good approximation of the least-cost, yet unattainable in practice, stochastic market outcome. © 2025, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Explicit Formula for Partial Information Decomposition

arXiv

引用

arXiv 2024年

作者： Lyu, Aobo Clark, Andrew Raviv, Netanel Department of Electrical and Systems Engineering Washington University in St. Louis St. LouisMO United States Department of Computer Science and Engineering Washington University in St. Louis St. LouisMO United States

Mutual information between two random variables is a well-studied notion, whose understanding is fairly complete. Mutual information between one random variable and a pair of other random variables, however, is a far more involved notion. Specifically, Shannon’s mutual information does not capture fine-grained interactions between those three variables, resulting in limited insights in complex systems. To capture these fine-grained interactions, in 2010 Williams and Beer proposed to decompose this mutual information to information atoms, called unique, redundant, and synergistic, and proposed several operational axioms that these atoms must satisfy. In spite of numerous efforts, a general formula which satisfies these axioms has yet to be found. Inspired by Judea Pearl’s do-calculus, we resolve this open problem by introducing the do-operation, an operation over the variable system which sets a certain marginal to a desired value, which is distinct from any existing approaches. Using this operation, we provide the first explicit formula for calculating the information atoms so that Williams and Beer’s axioms are satisfied, as well as additional properties from subsequent studies in the field. Copyright © 2024, The Authors. All rights reserved.

关键词： Random variables

来源：评论

学校读者我要写书评

暂无评论

Multilayer perceptron ensembles in a truly sparse training context

引用

Neural Computing and Applications 2025年

作者： van der Wal, Peter R. D. Strisciuglio, Nicola Azzopardi, George Mocanu, Decebal Constatin Information Systems Group Bernoulli Institute for Mathematics Computer Science and Artificial Intelligence University of Groningen Nijenborgh 9 Groningen9747 AG Netherlands Data Management and Biometrics Group Faculty of Electrical Engineering Mathematics and Computer Science University of Twente Hallenweg 19 Enschede7522 NH Netherlands Department of Computer Science Faculty of Science Technology and Medicine University of Luxembourg Maison du Nombre 6 avenue de la Fonte Esch4364 Luxembourg

Ensemble learning for artificial neural networks (ANNs) is an effective method to enhance predictive performance. However, ANNs are computationally and memory intensive, and naively training multiple networks can lead to excessive training times and costs. An effective tool for improving ensemble efficiency is introducing topological sparsity. Even though several implementations of efficient ensembles have been proposed, none of them can provide actual benefits in terms of computational overhead as the sparsity is simulated using binary masks. In this paper, we address this issue by introducing a Truly Sparse Ensemble without binary masks and directly incorporate native sparsity. We also propose two algorithms for initializing new subnetworks within the ensemble, leveraging this native topological sparsity to enhance subnetwork diversity. We demonstrate the performance of the resulting models at high levels of sparsity on several datasets in terms of classification accuracy, floating point operations (FLOPs), and actual running time. The proposed methods outperform all baseline dense and truly sparse models on tabular data, successfully diversify the training trajectory of the subnetworks, and increase the topological distance between subnetworks after re-initialization. © The Author(s) 2025.

关键词： Digital arithmetic

来源：评论

学校读者我要写书评

暂无评论

Domain Adaptation for Semantic Segmentation of Cataract Surgical Images Based on Masked Image Consistency 2nd

Domain Adaptation for Semantic Segmentation of Cataract Surg...

引用

2nd International Conference on Applied Intelligence, ICAI 2024

作者： Zhang, Yuzhu Pan, Yijie Ou, Mingyang Gong, Guanghui Zhang, Qinhu Li, Haojin Li, Heng Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology Shenzhen China Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China Ningbo China Eastern Institute for Advanced Study Eastern Institute of Technology Ningbo China

ISBN: (纸本)9789819619061

Cataract surgery is a complex procedure requiring precise execution of multiple steps. To improve the accuracy and efficiency of cataract surgeries, we present a semantic segmentation model for cataract surgery scenes. Our model leverages Unsupervised Domain Adaptation (UDA) techniques to enhance segmentation performance in clinical surgical environments, addressing challenges such as domain shift, occlusions between surgical tools and tissues, and long tail problem. The model utilizes a Teacher-Student model, where a student model is trained in the target domain with pseudo-labels generated by an Exponential Moving Average (EMA) teacher model, ensuring robust learning across domains. Additionally, we utilize a Masked Image Consistency (MIC) module to improve the model’s understanding of occluded regions by enforcing consistency between masked and unmasked predictions. To mitigate class imbalance between anatomical structures and surgical tools, we employ a maximum squares loss, enabling the model to achieve balanced learning. Our results demonstrate that the proposed model improves segmentation accuracy and robustness in cataract surgery scenarios. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Distributed Optimization with Finite Bit Adaptive Quantization for Efficient Communication and Precision Enhancement

Distributed Optimization with Finite Bit Adaptive Quantizati...

引用

IEEE Conference on Decision and Control

作者： Apostolos I. Rikos Wei Jiang Themistoklis Charalambous Karl H. Johansson Artificial Intelligence Thrust of the Information Hub The Hong Kong University of Science and Technology (Guangzhou) Guangzhou China Department of Computer Science and Engineering The Hong Kong University of Science and Technology Clear Water Bay Hong Kong China Department of Electrical Engineering and Automation School of Electrical Engineering Aalto University Espoo Finland Department of Electrical and Computer Engineering School of Engineering University of Cyprus Nicosia Cyprus Division of Decision and Control Systems KTH Royal Institute of Technology SE-100 44 Stockholm Sweden

ISBN: (数字)9798350316339

ISBN: (纸本)9798350316346

In realistic distributed optimization scenarios, individual nodes possess only partial information and communicate over bandwidth constrained channels. For this reason, the development of efficient distributed algorithms is essential. In our paper we addresses the challenge of unconstrained distributed optimization. In our scenario each node’s local function exhibits strong convexity with Lipschitz continuous gradients. The exchange of information between nodes occurs through 3-bit bandwidth-limited channels (i.e., nodes exchange messages represented by a only 3 -bits). Our proposed algorithm respects the network’s bandwidth constraints by leveraging zoom-in and zoom-out operations to adjust quantizer parameters dynamically. We show that during our algorithm’s operation nodes are able to converge to the exact optimal solution. Furthermore, we show that our algorithm achieves a linear convergence rate to the optimal solution. We conclude the paper with simulations that highlight our algorithm’s unique characteristics.

关键词： Adaptation models Quantization (signal) Heuristic algorithms Bandwidth Distributed algorithms Optimization Convergence

来源：评论

学校读者我要写书评

暂无评论

Cross-Cultural Insights in Health: Integrating Machine Learning and Deep Learning for Early Predictive Diabetes Detection

Cross-Cultural Insights in Health: Integrating Machine Learn...

引用

International Conference on computer and Information Technology (ICCIT)

作者： Tonmoy Roy H.M. Nahid Kawsar Iffat Rimi Md. Zehan Alam Department of Data Analytics and Information Systems Utah State University Logan Utah USA Department of Applied Mathematics Noakhali Science and Technology University Bangladesh Department of Computer Science and Engineering Daffodil International University Dhaka Bangladesh Department of Mathematics University of Dhaka Dhaka Bangladesh

ISBN: (数字)9798331519094

ISBN: (纸本)9798331519100

Diabetes, a potentially life-threatening condition if undetected, necessitates an early and accurate diagnosis. This study evaluates traditional machine learning (ML) models and deep neural networks (DNNs) for diabetes prediction, utilizing the Pima Indians Diabetes Dataset (PIDD) and the Sylhet Diabetes Hospital dataset (SDHD). We optimized six ML models—Logistic Regression, Decision Trees, Random Forests, Gradient Boosting, Support Vector Machines, and K-Nearest Neighbors—using GridSearchCV and ensemble learning, and deployed DNNs with varied train-test splits (90-10%, 80-20%, and 70-30%). Evaluations on accuracy, precision, recall, F1-score, and AUC-ROC highlighted RF’s outstanding performance after GridSearchCV on the SDHD with Accuracy: 98%, Precision: 100%, Recall: 96%, F1 Score: 98%, AUC: 100% and on PIDD with Accuracy: 76%, Precision: 63%, Recall: 80%, F1 Score:70%, AUC:81%. This underscores advanced ML’s effectiveness in handling complex datasets and enhancing early diabetes detection strategies.

关键词： Support vector machines Accuracy Hospitals Artificial neural networks Predictive models Prediction algorithms Diabetes Ensemble learning Regression tree analysis Random forests

来源：评论

学校读者我要写书评

暂无评论

Shoulder Surfing Resistant Graphical Password Schema: Randomized Pass Points (RPP) 14

Shoulder Surfing Resistant Graphical Password Schema: Random...

引用

14th International Conference on Information Security and Cryptology, ISCTURKEY 2021

作者： Bostan, Hakan Bostan, Atila Middle East Technical University Computer Engineering Department Ankara Turkey Ankara Science University Management Information Systems Ankara Turkey

ISBN: (纸本)9781665407762

In this study, a pass-graph methodology that benefits from randomity and alternative pass-graphs derivation is proposed with the name of Randomized Pass Points. The proposed authentication methodology is scrutinized for its resistance against brute force and shoulder-surfing attacks. Evaluations prove that the proposed alternative is stronger than that of 8-digit 71-character-set password methodology against brute force attacks and it necessitates at least 5 valid log-ins be captured by the attacker to derive the pass-graph under given assumptions in shoulder-surfing attack. © 2021 IEEE.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Optimized Energy-Efficient Hybrid LW-AES and LW-ECC Security Framework for VLC and RF Networks

Optimized Energy-Efficient Hybrid LW-AES and LW-ECC Security...

引用

Communication, Computing and Energy Efficient Technologies (I3CEET), International Conference on

作者： Venkatesan C Thamaraimanalan T Sathiya T Ranjithkumar M Radha K Shanmuga Priya K Department of Electronics and Communication Engineering HKBK College of Engineering Bengaluru Karnataka India Department of Electronics and Communication Engineering Sri Eshwar College of Engineering Coimbatore Tamilnadu India Department of Computer Science and Engineering Sona College of Technology Salem Tamilnadu India Department of Computer Science and Business Systems Knowledge Institute of Technology Salem Tamilnadu India Department of AI & DS Vivekananda College of Technology for Women Thiruchengode Tamilnadu India Department of Cyber Scurity K.S.R College of Engineering Thiruchengode Tamilnadu India

ISBN: (数字)9798331541583

ISBN: (纸本)9798331541590

In hybrid Visible Light Communication (VLC) and Radio Frequency (RF) networks, optimizing energy efficiency and ensuring secure resource allocation are key challenges. This paper addresses these issues by introducing a Hybrid Lightweight Advanced Encryption Standard (LW-AES) and Lightweight Elliptic Curve Cryptography (LW-ECC) secure resource algorithm. This innovative approach aims to enhance the sustainability and reliability of communication systems across diverse environments. Our analysis reveals substantial performance improvements compared to existing methods, including higher throughput (100 Mbps) and packet delivery ratio (98%), with reduced latency (10 ms) and extended network lifetime (500 hours). The algorithm also features lower memory usage (100 KB) and enhanced energy efficiency, showing a 20% decrease in energy consumption (800 mW) and an energy efficiency of 0.8 mJ/bit. Security is bolstered with a 25% reduction in interception probability (3.75%) and a 50% increase in secure communication range (150 meters). Moreover, the approach aligns with green communication objectives, reducing CO2 emissions by 20% (800 kg/year) and achieving an energy efficiency metric of 10 nJ/bit. Communication safety is markedly improved, with an 80% decrease in outage probability (1%) and a 40% boost in reliability (84%). By integrating LW-AES and LW-ECC in a hybrid configuration, this research offers a robust framework for advancing sustainable and resilient hybrid VLC-RF networks, effectively meeting the evolving needs of modern communication systems.

关键词： Radio frequency Communication systems Memory management Throughput Energy efficiency Safety Security Resource management Reliability Visible light communication

来源：评论

学校读者我要写书评

暂无评论

Dual-pronged deep learning preprocessing on heterogeneous platforms with CPU, GPU and CSD

arXiv

引用

arXiv 2024年

作者： Wei, Jia Zhang, Xingjun Pedrycz, Witold Wang, Longxiang Zhao, Jie The School of Computer Science and Technology Xi'an Jiaotong University Xi'An710049 China The Department of Electrical and Computer Engineering University of Alberta EdmontonABT6G 2G6 Canada The Department of Electrical and Computer Engineering King Abdulaziz University Jeddah21589 Saudi Arabia The Systems Research Institute PAS Warsaw01-447 Poland The College of Computer Science and Electronic Engineering Hunan University Changsha410082 China

As accelerator computation speeds increase and the number of single compute node accelerators increases, data reading and preprocessing gradually become a bottleneck for deep learning. Most existing data preprocessing is done at the CPU. Although some studies use techniques such as multiprocessing and double buffering to accelerate CPU preprocessing, CPU computational speed and storage bandwidth still limit the processing speed. Other studies try to use intelligent data storage devices, such as computational storage devices (CSD), to complete data preprocessing instead of CPUs. The current studies use only one device to complete data preprocessing operations, which cannot fully overlap data preprocessing and accelerator computation time. To fully exploit the independence and high bandwidth of the novel CSD, this paper proposes an advanced, highly parallel dual-pronged data preprocessing algorithm (DDLP) that significantly improves the execution efficiency and computational overlap between heterogeneous devices. DDLP enables the CPU and CSD to start data preprocessing operations from both ends of the dataset separately. Meanwhile, we propose two adaptive dynamic selection strategies to make DDLP control the GPU to automatically read data from different sources. We achieve sufficient computational overlap between CSD data preprocessing and CPU preprocessing, GPU computation, and GPU data reading. In addition, DDLP leverages GPU Direct Storage (GDS) technology to enable efficient SSD-to-GPU data transfer. DDLP reduces the usage of expensive CPU and DRAM resources, reduces the number of SSD-to-GPU data transfers, and improves the energy efficiency of preprocessing while reducing the overall preprocessing and training time. Extensive experimental results show that DDLP can improve learning speed by up to 23.5% on ImageNet Dataset while reducing energy consumption by 19.7% and CPU and DRAM usage by 37.6%. DDLP also improve learning speed by up to 27.6% on Cifar-10 Dataset

关键词： Dynamic random access storage

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：