检索结果-内蒙古大学图书馆

Reducing idleness in financial cloud services via multi-objective evolutionary reinforcement learning based load balancer

引用

Science China(Information Sciences) 2024年第2期67卷 20-40页

作者： Peng YANG Laoming ZHANG Haifeng LIU Guiying LI Department of Statistics and Data Science Southern University of Science and Technology Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation Department of Computer Science and EngineeringSouthern University of Science and Technology Academy for Advanced Interdisciplinary Studies Southern University of Science and Technology Guangdong OPPO Mobile Telecommunications Corp. Ltd Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology

In recent years, various companies have started to shift their data services from traditional data centers to the cloud. One of the major motivations is to save on operational costs with the aid of cloud elasticity. This paper discusses an emerging need from financial services to reduce the incidence of idle servers retaining very few user connections, without disconnecting them from the server side. This paper considers this need as a bi-objective online load balancing problem. A neural network based scalable policy is designed to route user requests to varied numbers of servers for the required elasticity. An evolutionary multi-objective training framework is proposed to optimize the weights of the policy. Not only is the new objective of idleness reduced by over 130% more than traditional industrial solutions, but the original load balancing objective itself is also slightly improved. Extensive simulations with both synthetic and real-world data help reveal the detailed applicability of the proposed method to the emergent problem of reducing idleness in financial services.

关键词： evolutionary reinforcement learning evolutionary multi-objective optimization load balance cloud computing

来源：评论

学校读者我要写书评

暂无评论

Unlocking the Renewable Energy Potential: A Comprehensive Study of Saudi Arabia's Eastern Region

Unlocking the Renewable Energy Potential: A Comprehensive St...

引用

Annual Conference of Industrial Electronics Society

作者： Abdullah Baraean Shehab Al-Sakkaf Mahmoud Kassas Muhammad Khalid Electrical Engineering Department King Fahd University of Petroleum and Minerals (KFUPM) Dhahran Saudi Arabia Al-Awn Foundation for Development Mukalla Yemen Interdisciplinary Research Center for Sustainable Energy Systems KFUPM Dhahran Saudi Arabia

ISBN: (数字)9781665464543

ISBN: (纸本)9781665464550

This paper presents a study on a small-scale hybrid renewable energy system (HRES) in the eastern region of Saudi Arabia. The purpose is to model and analyze the system's energy performance under different weather conditions. Real environmental data collected in 2016 at Dhahran city is used to determine the annual average energy generated by the renewable sources in the system. In addition, the paper conducts a detailed energy analysis of the HRES for three specific days, representing different seasons. The energy generated by the HRES, which includes solar photovoltaic (PV) and wind turbines (WTs), is compared with the actual load demand data recorded from a residential house in the same location and year. To determine the optimal size of the battery energy storage system (BESS) for the HRES, a battery sizing algorithm (BSA) is employed. The results demonstrate the feasibility and recommendation of installing small-scale renewable energy systems in residential houses in the eastern region of Saudi Arabia. Sufficient energy can be harvested from renewable resources during the winter, spring, and autumn seasons to meet the load demand, with backup systems available for use during the summer season. The study emphasizes that variations in solar irradiation, ambient temperature, and wind speed throughout the year significantly affect the generation of renewable energy.

关键词： Photovoltaic systems Renewable energy sources Radiation effects Temperature distribution Battery energy storage system Wind speed Urban areas Wind turbines Batteries Springs

来源：评论

学校读者我要写书评

暂无评论

LINEAR AND NON-LINEAR MODELS FOR MASTER SCHEDULING OF DYNAMIC RESOURCES PRODUCT MIX

arXiv

引用

arXiv 2024年

作者： Mohammed, Ayman R. Abu Sleem, Ahmad Abdel-Aal, Mohammad A.M. Industrial & Systems Engineering Department King Fahd University of Petroleum and Minerals Dhahran31261 Saudi Arabia Interdisciplinary Research Center of Smart Mobility & Logistics King Fahd University of Petroleum and Minerals Dhahran31261 Saudi Arabia

The literature on master production scheduling for product mix problems under the Theory of Constraints (TOC) was considered by many previous studies. Most studies assume a static resources availability. In this study, the raw materials supplied to the manufacturer is considered as dynamic depending on the results of the problem. Thus, an integer linear heuristic, an integer non-linear optimization model, and a basic non-linear model are developed to find a good solution of the problem. The results of the three models were compared to each other in terms of profit, raw materials costs, inventory costs and raw materials utilization. Recent studies in the field are reviewed and conclusions are drawn. Copyright © 2024, The Authors. All rights reserved.

关键词： Nonlinear programming

来源：评论

学校读者我要写书评

暂无评论

A Strategic Approach for Nanostructured Zn/Zno Based Electrocatalyst for Highly Selective Electrochemical Conversion of Co2 to Co

SSRN

引用

SSRN 2024年

作者： Kanase, Rohini Subhash Arunachalam, Maheswari Badiger, Jyoti Sayed, Suzan Abdelfattah Choi, Jonghoon Ha, Jun-Seok Kang, Soon Hyung Department of Interdisciplinary Program for Photonic Engineering Chonnam National University Gwangju61186 Korea Republic of Department of Chemistry Education Chonnam National University Gwangju61186 Korea Republic of Department of Advanced Chemicals and Engineering Chonnam National University Gwangju61186 Korea Republic of Department of Chemistry Education and Optoelectronic Convergence Research Center Chonnam National University Gwangju61186 Korea Republic of

Electroreduction of carbon dioxide (CO2) directly facilitates the conversion of intermittent recycling into value-added chemicals and fuel, presenting a favorable strategy to resolve the energy and environmental crises caused by CO2 emissions. Therefore, there is a necessity to develop highly active and selective emerging electrocatalysts to perform electrochemical CO2 reduction (ECR) to carbon monoxide (CO). This work identifies a low-cost, earth-abundant, and non-toxic Zinc Oxide (ZnO-based) electrocatalyst as a promising electrocatalyst for CO selectivity. Initially, two different nanostructured Zinc (Zn) electrocatalysts, namely Nanosheet (NS) and Nanodendrites (ND), were synthesized by a facile electrodeposition (ED) method in ex situ mode using a standard cell and in situ mode using a gas diffusion electrode (GDE) based on the flow cell, and their ECR performances were compared. Here, the ND-Zn electrocatalysts, grown by the in situ ED method, showed a large electroactive surface area, demonstrating more efficient ECR activity toward CO production with a Faradaic efficiency (FECO) of 88.4% at –0.87 V versus reversible hydrogen electrode (VRHE). However, the NS-Zn electrocatalyst, grown by the ex situ ED method, exhibited a FECO of 65.6% at –0.98 VRHE at an applied current density of 100 mA cm–2. Accordingly, the enhanced electrochemical activity of the ND-Zn electrocatalyst can be attributed to the large surface area, which provides great adsorption capacity, and the Zn2+ sites. Moreover, the ND-Zn electrocatalyst stabilizes the intermediate step (CO*) during ECR, enhancing the reaction rate by reducing the activation energy. © 2024, The Authors. All rights reserved.

关键词： Electrocatalysts

来源：评论

学校读者我要写书评

暂无评论

D-SRGAN: DEM Super-Resolution with Generative Adversarial Networks

引用

SN Computer Science 2021年第1期2卷 1-11页

作者： Demiray, Bekir Z. Sit, Muhammed Demir, Ibrahim Department of Computer Science University of Iowa Iowa City United States Interdisciplinary Graduate Program in Informatics University of Iowa Iowa City United States Department of Civil and Environmental Engineering University of Iowa Iowa City United States Department of Electrical and Computer Engineering University of Iowa Iowa City United States

Digital elevation model (DEM) is a critical data source for variety of applications such as road extraction, hydrological modeling, flood mapping, and many geospatial studies. The usage of high-resolution DEMs as inputs in many application areas improves the overall reliability and accuracy of the raw dataset. The goal of this study is to develop a machine learning model that increases the spatial resolution of DEM without additional information. In this paper, a GAN based model (D-SRGAN), inspired by single image super-resolution methods, is developed and evaluated to increase the resolution of DEMs. The experiment results show that D-SRGAN produces promising results while constructing 3 feet high-resolution DEMs from 50 feet low-resolution DEMs. It outperforms common statistical interpolation methods and neural network *** study shows that it is possible to use the power of artificial neural networks to increase the resolution of the DEMs. The study also demonstrates that approaches from single image super-resolution can be applied for DEM super-resolution. © 2021, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. part of Springer Nature.

关键词： Deep learning DEM DEM reconstruction Generative adversarial networks (GANs) Super-resolution

来源：评论

学校读者我要写书评

暂无评论

AVTENet: A Human-Cognition-Inspired Audio-Visual Transformer-Based Ensemble Network for Video Deepfake Detection

引用

IEEE Transactions on Cognitive and Developmental systems 2025年

作者： Hashmi, Ammarah Shahzad, Sahibzada Adil Lin, Chia-Wen Tsao, Yu Wang, Hsin-Min Taiwan International Graduate Program Academia Sinica Social Networks and Human-Centered Computing Program Taipei11529 Taiwan National Tsing Hua University Institute of Information Systems and Applications Hsinchu30013 Taiwan National Chengchi University Department of Computer Science Taipei11605 Taiwan National Tsing Hua University Department of Electrical Engineering Institute of Communications Engineering Hsinchu300044 Taiwan Academia Sinica Research Center for Information Technology Innovation Taipei11529 Taiwan

The recent proliferation of hyper-realistic deepfake videos has drawn attention to the threat of audio and visual forgeries. Most previous studies on detecting artificial intelligence-generated fake videos only utilize visual modality or audio modality. While some methods exploit audio and visual modalities to detect forged videos, they have not been comprehensively evaluated on multimodal datasets of deepfake videos involving acoustic and visual manipulations, and are mostly based on convolutional neural networks with low detection accuracy. Considering that human cognition instinctively integrates multisensory information including audio and visual cues to perceive and interpret content and the success of transformer in various fields, this study introduces the audio-visual transformer-based ensemble network (AVTENet). This innovative framework tackles the complexities of deepfake technology by integrating both acoustic and visual manipulations to enhance the accuracy of video forgery detection. Specifically, the proposed model integrates several purely transformer-based variants that capture video, audio, and audio-visual salient cues to reach a consensus in prediction. For evaluation, we use the recently released benchmark multimodal audio-video FakeAVCeleb dataset. For a detailed analysis, we evaluate AVTENet, its variants, and several existing methods on multiple test sets of the FakeAVCeleb dataset. Experimental results show that the proposed model outperforms all existing methods and achieves state-of-the-art performance on Testset-I and Testset-II of the FakeAVCeleb dataset. We also compare AVTENet against humans in detecting video forgery. The results show that AVTENet significantly outperforms humans. © 2016 IEEE.

关键词： audio-visual AVTENet Deepfake detection

来源：评论

学校读者我要写书评

暂无评论

FedClassAvg: Local Representation Learning for Personalized Federated Learning on Heterogeneous Neural Networks

arXiv

引用

arXiv 2022年

作者： Jang, Jaehee Ha, Heonseok Jung, Dahuin Yoon, Sungroh Department of Electrical and Computer Engineering Seoul National University Seoul Korea Republic of Department of Electrical and Computer Engineering Interdisciplinary Program in Artificial Intelligence Seoul National University Seoul Korea Republic of

Personalized federated learning is aimed at allowing numerous clients to train personalized models while participating in collaborative training in a communication-efficient manner without exchanging private data. However, many personalized federated learning algorithms assume that clients have the same neural network architecture, and those for heterogeneous models remain understudied. In this study, we propose a novel personalized federated learning method called federated classifier averaging (FedClassAvg). Deep neural networks for supervised learning tasks consist of feature extractor and classifier layers. FedClassAvg aggregates classifier weights as an agreement on decision boundaries on feature spaces so that clients with not independently and identically distributed (non-iid) data can learn about scarce labels. In addition, local feature representation learning is applied to stabilize the decision boundaries and improve the local feature extraction capabilities for clients. While the existing methods require the collection of auxiliary data or model weights to generate a counterpart, FedClassAvg only requires clients to communicate with a couple of fully connected layers, which is highly communication-efficient. Moreover, FedClassAvg does not require extra optimization problems such as knowledge transfer, which requires intensive computation overhead. We evaluated FedClassAvg through extensive experiments and demonstrated it outperforms the current state-of-the-art algorithms on heterogeneous personalized federated learning tasks. © 2022, CC BY.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Evaluating a Hospital Smart Notification System in a Simulated Environment: The Method 25th

Evaluating a Hospital Smart Notification System in a Simulat...

引用

25th International Conference on Human-Computer Interaction, HCII 2023

作者： Ali, Haneen Fatemi, Yasin Batchelor, Miranda Capodiferro, Cordelia Marler, Logan Hamasha, Sa’d Department of Industrial and Systems Engineering Auburn University AuburnAL United States Health Services Administration Program Auburn University AuburnAL United States

ISBN: (纸本)9783031359910

The call light system is a central communication technology linking care providers and patients. Call light systems in hospital settings help reduce the likelihood and severity of adverse events and ambulatory conditions by allowing nurses to quickly respond to patient needs. However, the call light system was found to be associated with major challenges and usability issues that negatively impacted patients’ safety and quality of care. This study aims at evaluating the effectiveness of a high-fidelity prototype of a previously designed smart communication system in a simulated environment. College students were invited to mimic the role of patients, and nursing students were invited to perform routine tasks using a traditional call light system and the smart system. Participants were instructed to perform routine tasks using pre-designed scenarios in a simulated environment using the traditional call light system and the smart system. Results show that the smart system reduced the overall response time by more than 50%. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Hospitals

来源：评论

学校读者我要写书评

暂无评论

PUCA: Patch-Unshuffle and Channel Attention for Enhanced Self-Supervised Image Denoising

arXiv

引用

arXiv 2023年

作者： Jang, Hyemi Park, Junsung Jung, Dahuin Lew, Jaihyun Bae, Ho Yoon, Sungroh Department of Electrical and Computer Engineering Seoul National University Korea Republic of Interdisciplinary Program in Artificial Intelligence Seoul National University Korea Republic of Department of Cyber Security Ewha Womans University Korea Republic of

Although supervised image denoising networks have shown remarkable performance on synthesized noisy images, they often fail in practice due to the difference between real and synthesized noise. Since clean-noisy image pairs from the real world are extremely costly to gather, self-supervised learning, which utilizes noisy input itself as a target, has been studied. To prevent a self-supervised denoising model from learning identical mapping, each output pixel should not be influenced by its corresponding input pixel;This requirement is known as J -invariance. Blind-spot networks (BSNs) have been a prevalent choice to ensure J -invariance in self-supervised image denoising. However, constructing variations of BSNs by injecting additional operations such as downsampling can expose blinded information, thereby violating J -invariance. Consequently, convolutions designed specifically for BSNs have been allowed only, limiting architectural flexibility. To overcome this limitation, we propose PUCA, a novel J -invariant U-Net architecture, for self-supervised denoising. PUCA leverages patch-unshuffle/shuffle to dramatically expand receptive fields while maintaining J -invariance and dilated attention blocks (DABs) for global context incorporation. Experimental results demonstrate that PUCA achieves state-of-the-art performance, outperforming existing methods in self-supervised image denoising. Copyright © 2023, The Authors. All rights reserved.

关键词： Image denoising

来源：评论

学校读者我要写书评

暂无评论

Testing the Inference Accuracy of Accelerator-Friendly Approximate Phylogeny Tracking

Testing the Inference Accuracy of Accelerator-Friendly Appro...

引用

2025 IEEE Symposium on Computational Intelligence in Artificial Life and Cooperative Intelligent systems, ALIFE-CIS 2025

作者： Moreno, Matthew Andres Ranjan, Anika Dolson, Emily Zaman, Luis University of Michigan Department of Ecology and Evolutionary Biology Ann Arbor United States Center for the Study of Complex Systems University of Michigan Ann Arbor United States Michigan Institute for Data and Ai in Society University of Michigan Ann Arbor United States Undergraduate Research Opportunities Program University of Michigan Ann Arbor United States Michigan State University Department of Computer Science and Engineering East Lansing United States Program in Ecology Evolution and Behavior Michigan State University East Lansing United States

ISBN: (纸本)9798331508371

Computer simulations are an important tool for studying the mechanics of biological evolution. In particular, agent-based approaches provide an opportunity to collect high-quality records of ancestry relationships. Such phylogenies can provide insight into evolutionary dynamics within these simulations. Previous work generally tracks lineages directly, yielding an exact phylogenetic record of evolutionary history. However, challenges exist in scaling direct ancestrytracking approaches to highly-distributed, many-processor evolution in silico. An alternative approach is to estimate phylogenetic history via noncoding annotations on digital genomes, akin to how bioinformaticians build phylogenies by assessing genetic similarities between organisms. Recent work has extended this 'hereditary stratigraphy' approach to support powerful hardware accelerator platforms, such as the Cerebras Wafer-Scale Engine. Although these second-generation 'surface'-based hereditary stratigraphy algorithms have demonstrated order-ofmagnitude speedups over first-generation 'column'-based algorithms, it remains unknown how they impact the accuracy of reconstructed phylogenies. To address this question, we assessed reconstruction accuracy under alternative configurations across a matrix of evolutionary conditions varying in selection pressure, spatial structure, and ecological dynamics. Encouragingly, we find that the second-generation approaches provide higher reconstruction quality across most surveyed conditions. © 2025 IEEE.

关键词： Biostratigraphy

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：