检索结果-内蒙古大学图书馆

Multiband Patch Antenna Design Using Nature-Inspired Optimization Method

学校读者我要写书评

暂无评论

IEEE Open Journal of Antennas and Propagation

IEEE Open Journal of Antennas and Propagation 2021年 2卷 151-162页

作者： Boursianis, Achilles D. Papadopoulou, Maria S. Pierezan, Juliano Mariani, Viviana C. Coelho, Leandro S. Sarigiannidis, Panagiotis Koulouridis, Stavros Goudos, Sotirios K. ELEDIA@AUTH Research Group School of Physics Aristotle University of Thessaloniki Thessaloniki54124 Greece Department of Electrical Engineering Federal University of Parana Curitiba80060-000 Brazil Industrial and Systems Engineering Graduate Program and Mechanical Engineering Graduate Program Pontifical Catholic University of Parana Curitiba80215-901 Brazil Department of Electrical and Computer Engineering University of Western Macedonia Kozani501 00 Greece Electrical and Computer Engineering Department University of Patras Patras26504 Greece

Radio frequency energy harvesting has attracted considerable interest as a technique of enabling self-powered wireless networks. This technique faces several challenges, such as the receiving and the rectifying modules of a rectenna system. Multiband antennas provide several comparative advantages against the goal of maximizing the amount of energy harvesting. In this work, we present a multiband microstrip patch antenna with three slits operating in the LoRaWAN (Long Range Wide Area Network) and the cellular (GSM-1800 and UMTS) communication frequency bands. A feasible solution of the antenna is obtained by the application of a recently introduced nature-inspired optimization technique, namely the Coyote Optimization Algorithm. The proposed antenna operates satisfactorily in the LoRaWAN (Long Range Wide Area Network) and the cellular (GSM-1800 and UMTS) communication frequency bands. Measured results of the proposed antenna exhibit an acceptable performance (multiband frequency operation, maximum gain of 3.94 dBi, broadside operation) and demonstrate features of operation, which make it a strong candidate for various RF energy harvesting applications. © 2020 IEEE.

关键词： Microstrip antennas

Towards last-layer retraining for group robustness with fewer annotations 23

学校读者我要写书评

暂无评论

Towards last-layer retraining for group robustness with fewe...

Proceedings of the 37th International Conference on Neural Information Processing systems

作者： Tyler LaBonte Vidya Muthukumar Abhishek Kumar H. Milton Stewart School of Industrial and Systems Engineering Georgia Institute of Technology School of Electrical and Computer Engineering Georgia Institute of Technology and H. Milton Stewart School of Industrial and Systems Engineering Georgia Institute of Technology Google DeepMind

Empirical risk minimization (ERM) of neural networks is prone to over-reliance on spurious correlations and poor generalization on minority groups. The recent deep feature reweighting (DFR) technique [33] achieves state-of-the-art group robustness via simple last-layer retraining, but it requires held-out group and class annotations to construct a group-balanced reweighting dataset. In this work, we examine this impractical requirement and find that last-layer retraining can be surprisingly effective with no group annotations (other than for model selection) and only a handful of class annotations. We first show that last-layer retraining can greatly improve worst-group accuracy even when the reweighting dataset has only a small proportion of worst-group data. This implies a "free lunch" where holding out a subset of training data to retrain the last layer can substantially outperform ERM on the entire dataset with no additional data or annotations. To further improve group robustness, we introduce a lightweight method called selective last-layer fine-tuning (SELF), which constructs the reweighting dataset using misclassifications or disagreements. Our empirical and theoretical results present the first evidence that model disagreement upsamples worst-group data, enabling SELF to nearly match DFR on four well-established benchmarks across vision and language tasks with no group annotations and less than 3% of the held-out class annotations. Our code is available at https://***/tmlabonte/last-layer-retraining.

关键词：

DT4I4-Secure: Digital Twin Framework for Industry 4.0 systems Security

学校读者我要写书评

暂无评论

DT4I4-Secure: Digital Twin Framework for Industry 4.0 System...

IEEE Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON)

作者： Yu-Zheng Lin Sicong Shao Md Habibor Rahman Mohammed Shafae Pratik Satam Department of Electrical and Computer Engineering University of Arizona Tucson AZ USA School of Electrical Engineering and Computer Science University of North Dakota Grand Forks ND USA Department of Systems and Industrial Engineering University of Arizona Tucson AZ USA

The rapid adoption of automation in the Cyber-Physical systems (CPS) is triggering Industry 4.0 (I4.0), integrating cloud computing, machine learning (ML), artificial intelligence (AI), and universal network connectivity into traditionally isolated systems. These I4.0 changes are optimizing the performance of Smart Manufacturing (SM) systems at the cost of increased complexity, exposing I4.0 systems to more cyberattacks than ever before. To address these challenges, this work presents DT4I4-Secure: A Digital Twin Framework for Industry 4.0 Security. The DT4I4-Secure presents a framework to create Digital Twins (DT) for I4.0 systems using a combination of models (including physics and data-based models). This paper showcases the use of the DT framework to detect attacks on I4.0 systems by comparing observations with future predictions from the DT. This paper evaluates the performance of the DT4I4-Secure for a computer Numerical Control (CNC) turning process manufacturing a metallic spool, wherein the experimental results show the model can predict normal operations with a mean absolute error (MAE) of 0.005081. This work also explores using an Exponentially Weighted Moving Average (EWMA) based dynamic threshold instead of a traditional static threshold for attack detection when the CNC turning process is under three separate attack scenarios. The DT4I4-Secure combined with the dynamic threshold shows a 3.46 times improvement in F 1 -Scores over all three attack scenarios for instantaneous attack detection while having 100% accuracy during the manufacturing cycle.

关键词：

Real-Time Data-Driven Maintenance Logistics: A Public-Private Collaboration

学校读者我要写书评

暂无评论

Real-Time Data-Driven Maintenance Logistics: A Public-Privat...

2024 Commit2Data, C2D 2024

作者： van Jaarsveld, Willem Bliek, Laurens de Weerdt, Mathijs Kapodistria, Stella Pronk, Verus Verleijsdonk, Peter Voorberg, Simon Akçay, Alp da Costa, Paulo Eshuis, Rik Kaymak, Uzay van Houtum, Geert-Jan Verwer, Sicco Zhang, Yingqian Department of Industrial Engineering and Innovation Sciences Eindhoven University of Technology Netherlands Faculty of Electrical Engineering Mathematics and Computer Science Delft University of Technology Netherlands Department of Mathematics and Computer Science Eindhoven University of Technology Netherlands Philips Research Laboratories Eindhoven Netherlands Department of Information Systems Supply Chain Management and Decision Analysis NEOMA Business School Rouen France Etsy Inc. Dublin Ireland Jheronimus Academy of Data Science Eindhoven University of Technology Netherlands

ISBN: (纸本)9783959773515

The project "Real-time data-driven maintenance logistics" was initiated with the purpose of bringing innovations in data-driven decision making to maintenance logistics, by bringing problem owners in the form of three innovative companies together with researchers at two leading knowledge institutions. This paper reviews innovations in three related areas: How the innovations were inspired by practice, how they materialized, and how the results impact practice. © Willem van Jaarsveld, Alp Akçay, Laurens Bliek, Paulo da Costa, Mathijs de Weerdt, Rik Eshuis, Stella Kapodistria, Uzay Kaymak, Verus Pronk, Geert-Jan van Houtum, Peter Verleijsdonk, Sicco Verwer, Simon Voorberg, and Yingqian Zhang.

关键词： Scheduled maintenance

ELA: Exploited Level Augmentation for Offline Learning in Zero-Sum Games

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Lei, Shiqi Lee, Kanghoon Li, Linjing Park, Jinkyoo Li, Jiachen Institute of Automation Chinese Academy of Sciences Beijing China Department of Industrial & Systems Engineering KAIST Daejeon Korea Republic of Department of Electrical and Computer Engineering University of California RiversideCA United States

Offline learning has become widely used due to its ability to derive effective policies from offline datasets gathered by expert demonstrators without interacting with the environment directly. Recent research has explored various ways to enhance offline learning efficiency by considering the characteristics (e.g., expertise level or multiple demonstrators) of the dataset. However, a different approach is necessary in the context of zero-sum games, where outcomes vary significantly based on the strategy of the opponent. In this study, we introduce a novel approach that uses unsupervised learning techniques to estimate the exploited level of each trajectory from the offline dataset of zero-sum games made by diverse demonstrators. Subsequently, we incorporate the estimated exploited level into the offline learning to maximize the influence of the dominant strategy. Our method enables interpretable exploited level estimation in multiple zero-sum games and effectively identifies dominant strategy data. Also, our exploited level augmented offline learning significantly enhances the original offline learning algorithms including imitation learning and offline reinforcement learning for zero-sum games. Copyright © 2024, The Authors. All rights reserved.

关键词： Reinforcement learning

Design of ANN Based Non-Linear Network Using Interconnection of Parallel Processor

学校读者我要写书评

暂无评论

computer systems Science & engineering 2023年第9期46卷 3491-3508页

作者： Anjani Kumar Singha Swaleha Zubair Areej Malibari Nitish Pathak Shabana Urooj Neelam Sharma Department of Computer Science Aligarh Muslim UniversityAligarh202002India Department of Industrial and Systems Engineering College of EngineeringPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Information Technology Bhagwan Parshuram Institute of Technology(BPIT)GGSIPUNew Delhi110078India Department of Electrical Engineering College of EngineeringPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Artificial Intelligence&Machine Learning Maharaja Agrasen Institute of Technology(MAIT)GGSIPUNew Delhi110086India

Suspicious mass traffic constantly evolves,making network behaviour tracing and structure more *** networks yield promising results by considering a sufficient number of processing elements with strong interconnections between *** offer efficient computational Hopfield neural networks models and optimization constraints used by undergoing a good amount of parallelism to yield optimal *** neural network(ANN)offers optimal solutions in classifying and clustering the various reels of data,and the results obtained purely depend on identifying a *** this research work,the design of optimized applications is presented in an organized *** addition,this research work examines theoretical approaches to achieving optimized results using *** mainly focuses on designing *** optimizing design approach of neural networks analyzes the internal process of the neural *** in developing the network are based on the interconnections among the hidden nodes and their learning *** methodology is proven best for nonlinear resource allocation problems with a suitable design and complex *** ANN proposed here considers more or less 46k nodes hidden inside 49 million connections employed on full-fledged parallel *** proposed ANN offered optimal results in real-world application problems,and the results were obtained using MATLAB.

关键词： Artificial neural network(ANN) multiprocessor hidden node nonlinear optimization parallel processing

Projection-Free Methods for Stochastic Simple Bilevel Optimization with Convex Lower-level Problem

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Cao, Jincheng Jiang, Ruichen Abolfazli, Nazanin Hamedani, Erfan Yazdandoost Mokhtari, Aryan Department of Electrical and Computer Engineering The University of Texas AustinTX United States Department of Systems and Industrial Engineering The University of Arizona TucsonAZ United States

In this paper, we study a class of stochastic bilevel optimization problems, also known as stochastic simple bilevel optimization, where we minimize a smooth stochastic objective function over the optimal solution set of another stochastic convex optimization problem. We introduce novel stochastic bilevel optimization methods that locally approximate the solution set of the lower-level problem via a stochastic cutting plane, and then run a conditional gradient update with variance reduction techniques to control the error induced by using stochastic gradients. For the case that the upper-level function is convex, our method requires Õ(max{1/Ε2f, 1/Ε2g}) stochastic oracle queries to obtain a solution that is Εf-optimal for the upper-level and Εgoptimal for the lower-level. This guarantee improves the previous best-known complexity of O(max{1/Ε4f, 1/Ε4g}). Moreover, for the case that the upper-level function is non-convex, our method requires at most Õ(max{1/Ε3f, 1/Ε3g}) stochastic oracle queries to find an (Εf, Εg)stationary point. In the finite-sum setting, we show that the number of stochastic oracle calls required by our method are Õ(√n/Ε) and Õ(√n/Ε2) for the convex and non-convex settings, respectively, where Ε = min{Εf, Εg}. Copyright © 2023, The Authors. All rights reserved.

关键词： Stochastic systems

When Demonstrations Meet Generative World Models: A Maximum Likelihood Framework for Offline Inverse Reinforcement Learning

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zeng, Siliang Li, Chenliang Garcia, Alfredo Hong, Mingyi Department of Electrical and Computer Engineering University of Minnesota MN United States Department of Industrial and Systems Engineering Texas A&M University TX United States

Offline inverse reinforcement learning (Offline IRL) aims to recover the structure of rewards and environment dynamics that underlie observed actions in a fixed, finite set of demonstrations from an expert agent. Accurate models of expertise in executing a task has applications in safety-sensitive applications such as clinical decision making and autonomous driving. However, the structure of an expert's preferences implicit in observed actions is closely linked to the expert's model of the environment dynamics (i.e. the "world" model). Thus, inaccurate models of the world obtained from finite data with limited coverage could compound inaccuracy in estimated rewards. To address this issue, we propose a bi-level optimization formulation of the estimation task wherein the upper level is likelihood maximization based upon a conservative model of the expert's policy (lower level). The policy model is conservative in that it maximizes reward subject to a penalty that is increasing in the uncertainty of the estimated model of the world. We propose a new algorithmic framework to solve the bi-level optimization problem formulation and provide statistical and computational guarantees of performance for the associated optimal reward estimator. Finally, we demonstrate that the proposed algorithm outperforms the state-of-the-art offline IRL and imitation learning benchmarks by a large margin, over the continuous control tasks in MuJoCo and different datasets in the D4RL benchmark. Copyright © 2023, The Authors. All rights reserved.

关键词： Reinforcement learning

An Inexact Conditional Gradient Method for Constrained Bilevel Optimization

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Abolfazli, Nazanin Jiang, Ruichen Mokhtari, Aryan Hamedani, Erfan Yazdandoost Department of Systems and Industrial Engineering The University of Arizona TucsonAZ United States Department of Electrical and Computer Engineering The University of Texas AustinTX United States

Bilevel optimization is an important class of optimization problems where one optimization problem is nested within another. While various methods have emerged to address unconstrained general bilevel optimization problems, there has been a noticeable gap in research when it comes to methods tailored for the constrained scenario. The few methods that do accommodate constrained problems, often exhibit slow convergence rates or demand a high computational cost per iteration. To tackle this issue, our paper introduces a novel single-loop projection-free method employing a nested approximation technique. This innovative approach not only boasts an improved per-iteration complexity compared to existing methods but also achieves optimal convergence rate guarantees that match the best-known complexity of projection-free algorithms for solving convex constrained single-level optimization problems. In particular, when the hyper-objective function corresponding to the bilevel problem is convex, our method requires Õ(ϵ−1) iterations to find an ϵ-optimal solution. Moreover, when the hyper-objective function is non-convex, our method’s complexity for finding an ϵ-stationary point is O(ϵ−2). To showcase the effectiveness of our approach, we present a series of numerical experiments that highlight its superior performance relative to state-of-the-art methods. Copyright © 2023, The Authors. All rights reserved.

关键词： Gradient methods