检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Alawadi, Sadi Ait-Mlouk, Addi Toor, Salman Hellander, Andreas Department of Computer Science Blekinge Institute of Technology Karlskrona Sweden School of Informatics University of Skövde Skövde Sweden Department of Information Technology Division of Scientific Computing Uppsala University Sweden Scaleout Systems Sweden

Federated learning (FL) enables edge nodes to collaboratively contribute to constructing a global model without sharing their data. This is accomplished by devices computing local, private model updates that are then aggregated by a server. However, computational resource constraints and network communication can become a severe bottleneck for larger model sizes typical for deep learning (DL) applications. Edge nodes tend to have limited hardware resources (RAM, CPU), and the network bandwidth and reliability at the edge is a concern for scaling federated fleet applications. In this paper, we propose and evaluate a FL strategy inspired by transfer learning in order to reduce resource utilization on devices, as well as the load on the server and network in each global training round. For each local model update, we randomly select layers to train, freezing the remaining part of the model. In doing so, we can reduce both server load and communication costs per round by excluding all untrained layer weights from being transferred to the server. The goal of this study is to empirically explore the potential trade-off between resource utilization on devices and global model convergence under the proposed strategy. We implement the approach using the FL framework FEDn. A number of experiments were carried out over different datasets (CIFAR-10, CASA, and IMDB), performing different tasks using different DL model architectures. Our results show that training the model partially can accelerate the training process, efficiently utilizes resources on-device, and reduce the data transmission by around 75% and 53% when we train 25%, and 50% of the model layers, respectively, without harming the resulting global model accuracy. Furthermore, our results demonstrate a negative correlation between the number of participating clients in the training process and the number of layers that need to be trained on each client’s side. As the number of clients increases, there is a decrease

关键词： Data privacy

来源：评论

学校读者我要写书评

暂无评论

Characterization of Systematic Bias in ALOS-2 Multilooked Interferograms

Characterization of Systematic Bias in ALOS-2 Multilooked In...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Ryu Sugimoto Yu Morishita Masanobu Shimada Ryo Natsuaki Chiaki Tsutsumi Ryosuke Nakamura Toru Kouyama Digital Architecture Research Center National Institute of Advanced Industrial Science and Technology Japan Division of Architectural Civil and Environmental Engineering School of Science and Engineering Tokyo Denki University Japan Department of Electrical Engineering and Information Systems The University of Tokyo Japan

ISBN: (数字)9798350360325

ISBN: (纸本)9798350360332

Interferometric SAR time series analysis using multilooked interferograms has measured ground deformation with high accuracy over large areas, but is known to be contaminated by a systematic bias when using only short-term interferograms. This bias, also referred to as a "fading signal", has been investigated using the abundant time series data from Sentinel-1 C-band SAR, and soil moisture and biomass changes have been suggested as two possible causes for the observed bias. Several correction methods have been proposed to mitigate the phase bias, assuming a periodic observation strategy. The phase bias is supposed to increase with the wavelength, but the bias in ALOS-2 L-band SAR has not been investigated in detail because the data distribution policy restricts its users. In addition, these correction methods are not suitable for the infrequently observed data such as ALOS-2. In this paper, we investigated the systematic bias in ALOS-2 multilooked interferograms with respect to various interferometric pairs. We also corrected the phase bias using the noise-filtering technique. The bias in ALOS-2 multilooked interferograms showed >3 mm/year with an average temporal baseline of 144 days, which is equivalent to that of Sentinel-1 with the temporal baseline of 78 days. That is, the bias effect toward the temporal baseline was larger in ALOS-2 than in Sentinel-1. The noise-filtering technique could mitigate the bias with less pairs regardless of land-use.

关键词： Fading channels Systematics Soil measurements Time series analysis Soil moisture Sentinel-1 Geoscience and remote sensing

来源：评论

学校读者我要写书评

暂无评论

POSSIBILITIES AND LIMITS OF DIAGNOSTIC METHODS FOR POWER TRANSFORMERS IN SERVICE 23

POSSIBILITIES AND LIMITS OF DIAGNOSTIC METHODS FOR POWER TRA...

引用

23rd International Symposium on High Voltage Engineering, ISH 2023

作者： Schreiter, Sebastian Lohmeyer, Holger Werle, Peter HTWK Leipzig Leipzig University of Applied Science Faculty of Electrical Engineering and Information Technology Department of Electric Power Systems Germany FTZ Leipzig e. V. Research and Transfer Centre The HTWK Leipzig Germany Hitachi Energy Transformer Service Centre Halle Oil Lab. Halle Germany Leibniz University Hannover Institute of Electric Power Systems Division of High Voltage Engineering and Asset Management Schering-Institute Hannover Germany

ISBN: (纸本)9781839539954

The detection of possible faults in an early state is of elementary interest to operators of transformers in order to avoid unplanned outages. Such unplanned failures lead to the interruption of energy supply or even loss of production. Therefore, a large number of diagnostic methods are available such as oil analysis and electrical measurements up to high-voltage tests on site. For this reason, it is necessary for operators to select the meaningful diagnostic procedures in each case. In this contribution investigation are discussed concerning the question which diagnostic procedures or which combination of procedures can be used to detect faults reliable. This was done based on a large population of transformers in service. © The Institution of Engineering & technology 2023.

关键词： Distribution transformers

来源：评论

学校读者我要写书评

暂无评论

Risk-Averse Learning with Non-Stationary Distributions

arXiv

引用

arXiv 2024年

作者： Wang, Siyi Wang, Zifan Yi, Xinlei Zavlanos, Michael M. Johansson, Karl H. Hirche, Sandra Department of Electrical and Computer Engineering Technical University of Munich Munich80333 Germany Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm10044 Sweden Lab for Information & Decision Systems Massachusetts Institute of Technology CambridgeMA02139 United States Mechanical Engineering and Material Science Duke University DurhamNC27708 United States

Considering non-stationary environments in online optimization enables decision-maker to effectively adapt to changes and improve its performance over time. In such cases, it is favorable to adopt a strategy that minimizes the negative impact of change to avoid potentially risky situations. In this paper, we investigate risk-averse online optimization where the distribution of the random cost changes over time. We minimize risk-averse objective function using the Conditional Value at Risk (CVaR) as risk measure. Due to the difficulty in obtaining the exact CVaR gradient, we employ a zeroth-order optimization approach that queries the cost function values multiple times at each iteration and estimates the CVaR gradient using the sampled values. To facilitate the regret analysis, we use a variation metric based on Wasserstein distance to capture time-varying distributions. Given that the distribution variation is sub-linear in the total number of episodes, we show that our designed learning algorithm achieves sub-linear dynamic regret with high probability for both convex and strongly convex functions. Moreover, theoretical results suggest that increasing the number of samples leads to a reduction in the dynamic regret bounds until the sampling number reaches a specific limit. Finally, we provide numerical experiments of dynamic pricing in a parking lot to illustrate the efficacy of the designed algorithm. Copyright © 2024, The Authors. All rights reserved.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Asymmetric Feedback Learning in Online Convex Games

arXiv

引用

arXiv 2023年

作者： Wang, Zifan Yi, Xinlei Shen, Yi Zavlanos, Michael M. Johansson, Karl H. Division of Decision and Control Systems School of Electrical Enginnering and Computer Science Kth Royal Institute of Technology Sweden Digital Futures StockholmSE-10044 Sweden The Lab for Information & Decision Systems Massachusetts Institute of Technology United States The Department of Mechanical Engineering and Materials Science Duke University DurhamNC United States

This paper considers online convex games involving multiple agents that aim to minimize their own cost functions using locally available feedback. A common assumption in the study of such games is that the agents are symmetric, meaning that they have access to the same type of information or feedback. Here we lift this assumption, which is often violated in practice, and instead consider asymmetric agents;specifically, we assume some agents have access to first-order gradient feedback and others have access to the zeroth-order oracles (cost function evaluations). We propose an asymmetric feedback learning algorithm that combines the agent feedback mechanisms. We analyze the regret and Nash equilibrium convergence of this algorithm for convex games and strongly monotone games, respectively. Specifically, we show that our algorithm always performs between pure first-order and zeroth-order methods, and can match the performance of these two extremes by adjusting the number of agents with access to zeroth-order oracles. Therefore, our algorithm incorporates the pure first-order and zeroth-order methods as special cases. We provide numerical experiments on an online market problem for both deterministic and risk-averse games to demonstrate the performance of the proposed algorithm. Copyright © 2023, The Authors. All rights reserved.

关键词： Cost functions

来源：评论

学校读者我要写书评

暂无评论

Green Routing Game: Strategic Logistical Planning using Mixed Fleets of ICEVs and EVs

Green Routing Game: Strategic Logistical Planning using Mixe...

引用

IEEE Conference on Decision and Control

作者： Hampei Sasahara György Dán Saurabh Amin Henrik Sandberg Department of Systems and Control Engineering School of Engineering Tokyo Institute of Technology Tokyo Japan Division of Network and Systems Engineering School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm Sweden Laboratory for Information and Decision Systems Massachusetts Institute of Technology Cambridge MA USA Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm Sweden

ISBN: (数字)9781665467612

ISBN: (纸本)9781665467629

This paper introduces a “green” routing game between multiple logistic operators (players), each owning a mixed fleet of internal combustion engine vehicle (ICEV) and electric vehicle (EV) trucks. Each player faces the cost of delayed delivery (due to charging requirements of EVs) and a pollution cost levied on the ICEVs. This cost structure models: 1) limited battery capacity of EVs and their charging requirement; 2) shared nature of charging facilities; 3) pollution cost levied by regulatory agency on the use of ICEVs. We characterize Nash equilibria of this game and derive a condition for its uniqueness. We also use the gradient projection method to compute this equilibrium in a distributed manner. Our equilibrium analysis is useful to analyze the trade-off faced by players in incurring higher delay due to congestion at charging locations when the share of EVs increases versus a higher pollution cost when the share of ICEVs increases. A numerical example suggests that to increase marginal pollution cost can reduce inefficiency of equilibria.

关键词： Costs Pollution Green products Internal combustion engines Games Routing Planning

来源：评论

学校读者我要写书评

暂无评论

Deep multiple instance learning on heterogeneous graph for drug–disease association prediction

引用

Computers in Biology and Medicine 2025年 184卷 109403-109403页

作者： Gu, Yaowen Zheng, Si Zhang, Bowen Kang, Hongyu Jiang, Rui Li, Jiao Beijing100020 China Department of Chemistry New York University NY10027 United States Institute for Artificial Intelligence Department of Computer Science and Technology BNRist Tsinghua University Beijing100084 China Beijing StoneWise Technology Co Ltd. Beijing100080 China Ministry of Education Key Laboratory of Bioinformatics Bioinformatics Division at the Beijing National Research Center for Information Science and Technology Center for Synthetic and Systems Biology Department of Automation Tsinghua University Beijing100084 China

Drug repositioning offers promising prospects for accelerating drug discovery by identifying potential drug–disease associations (DDAs) for existing drugs and diseases. Previous methods have generated meta-path-augmented node or graph embeddings for DDA prediction in drug–disease heterogeneous networks. However, these approaches rarely develop end-to-end frameworks for path instance-level representation learning as well as the further feature selection and aggregation. By leveraging the abundant topological information in path instances, more fine-grained and interpretable predictions can be achieved. To this end, we introduce deep multiple instance learning into drug repositioning by proposing a novel method called MilGNet. MilGNet employs a heterogeneous graph neural network (HGNN)-based encoder to learn drug and disease node embeddings. Treating each drug–disease pair as a bag, we designed a special quadruplet meta-path form and implemented a pseudo meta-path generator in MilGNet to obtain multiple meta-path instances based on network topology. Additionally, a bidirectional instance encoder enhances the representation of meta-path instances. Finally, MilGNet utilizes a multi-scale interpretable predictor to aggregate bag embeddings with an attention mechanism, providing predictions at both the bag and instance levels for accurate and explainable predictions. Comprehensive experiments on five benchmarks demonstrate that MilGNet significantly outperforms ten advanced methods. Notably, three case studies on one drug (Methotrexate) and two diseases (Renal Failure and Mismatch Repair Cancer Syndrome) highlight MilGNet's potential for discovering new indications, therapies, and generating rational meta-path instances to investigate possible treatment mechanisms. The source code is available at https://***/gu-yaowen/MilGNet. © 2024 Elsevier Ltd

关键词： Graph embeddings

来源：评论

学校读者我要写书评

暂无评论

Automatic Concrete Surface Crack Recognition Using EfficientNetV2 Variants

Automatic Concrete Surface Crack Recognition Using Efficient...

引用

2023 International Conference on System, Computation, Automation and Networking, ICSCAN 2023

作者： Rama, A. Damasevicius, Robertas Arunmozhi, S. Mohammed, Mazin Abed Hussam, Ragheed Rajinikanth, V. Saveetha School of Engineering Simats Department of CSE TN Chennai602105 India Kaunas University of Technology Centre of Real Time Computer Systems Kaunas51423 Lithuania Manakula Vinayagar Institute of Technology Department of Electronics and Communication Engineering TN Puducherry605 107 India College of Computer Science and Information Technology University of Anbar Department of Artificial Intelligence Anbar31001 Iraq Al-farahidi University Medical Instruments Engineering Techniques Baghdad10021 Iraq Saveetha School of Engineering Simats Division of Research and Innovation Department of Computer Science and Engineering TN Chennai602105 India

ISBN: (纸本)9798350315127

Building health and structural integrity are important to ensure occupant safety and long-term durability. Monitoring and assessing building condition regularly ensures that potential problems are identified early. This research aims to develop and implement a deep-learning (DL) supported tool to examine the concrete surface images collected using digital camera. The data gathering forms the first stage and the chosen DL algorithm is used for feature extraction followed by the feature selection and then fusion is done and finally a fivefold cross verification schema is applied for a binary classification. This work considered the EfficientNetV2 (ENV2) model with variants like small, medium and large for the examination. The investigation is implemented using individual and fused deep-features and the performance of the developed tool is confirmed using the achieved accuracy. The outcome of this research confirms that the proposed tool produces a betterment of >96% accuracy with individual-features and 100% accuracy with fused-features. These results confirm that the proposed scheme provides significant result during the crack detection. © 2023 IEEE.

关键词： Crack detection

来源：评论

学校读者我要写书评

暂无评论

Monkeypox Detection with Deep-Learning and Ensemble of Features: A Study

Monkeypox Detection with Deep-Learning and Ensemble of Featu...

引用

Technological Advancements in Computational sciences (ICTACS), International Conference on

作者： Venkatesan Rajinikanth David Taniar Robertas Damaševičius Department of Computer Science and Engineering Division of Research and Innovation Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai TN India Faculty of Information Technology Monash University Melbourne VIC Australia Centre of Real Time Computer Systems Kaunas University of Technology Kaunas Lithuania

ISBN: (数字)9798350387490

ISBN: (纸本)9798350387506

There is a growing global prevalence of infectious diseases in the human population and it is imperative to have precise diagnosis and therapy in order to effectively cure these diseases. Monkeypox (Mpox) is an infectious disease that can cause varying degrees of skin infection, ranging from minor to severe. The recent spread of Mpox has been confirmed as Public Health Emergency of International Concern (PHEIC) due to its large infection rate. This study aims to develop a deep-learning (DL) scheme for Mpox identification. To enhance the detection accuracy, this study considered preprocessed skin images for the analysis and employed the binary classification with Ensemble of Deep-Features (EDF) using 5-fold cross validation. The outcome of this investigation validate that the suggested deep learning tool enables the attainment of a detection accuracy of 100% on the augmented images from the Monkeypox Skin Images Dataset (MSID). Compared to the existing results in the literature, this research provides a significant result on the chosen MSID database.

关键词： Training Deep learning Accuracy Infectious diseases Databases Medical treatment Feature extraction Skin Distance measurement Public healthcare

来源：评论

学校读者我要写书评

暂无评论

Distributed Event-Triggered Bandit Convex Optimization with Time-Varying Constraints

arXiv

引用

arXiv 2024年

作者： Zhang, Kunpeng Yi, Xinlei Wen, Guanghui Cao, Ming Johansson, Karl H. Chai, Tianyou Yang, Tao The State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang110819 China The Laboratory for Information and Decision Systems Massachusetts Institute of Technology CambridgeMA02139 United States The Department of Mathematics Southeast University Nanjing210096 China The Engineering and Technology Institute Groningen Faculty of Science and Engineering University of Groningen GroningenAG 9747 Netherlands Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Sweden Digital Futures Stockholm10044 Sweden

This paper considers the distributed bandit convex optimization problem with time-varying inequality constraints over a network of agents, where the goal is to minimize network regret and cumulative constraint violation. Existing distributed online algorithms require that each agent broadcasts its decision to its neighbors at each iteration. To better utilize the limited communication resources, we propose a distributed event-triggered online primal-dual algorithm with two-point bandit feedback. Under several classes of appropriately chosen decreasing parameter sequences and non-increasing event-triggered threshold sequences, we establish dynamic network regret and network cumulative constraint violation bounds. These bounds are comparable to the results achieved by distributed event-triggered online algorithms with full-information feedback. Finally, a numerical example is provided to verify the theoretical results. Copyright © 2024, The Authors. All rights reserved.

关键词： Convex optimization

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：