检索结果-内蒙古大学图书馆

DEEP MEMORY SEARCH: A METAHEURISTIC APPROACH FOR OPTIMIZING HEURISTIC SEARCH

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Hedar, Abdel-Rahman Abdel-Hakim, Alaa E. Deabes, Wael Alotaibi, Youseef Bouazza, Kheir Eddine Department of Computer Science Faculty of Computers & Information Assiut University Assiut71526 Egypt Computer Science Department in Jamoum Umm Al-Qura University Electrical Engineering Department Assiut University Assiut71516 Egypt Texas A&M University-San Antonio One University Way Hall 334 San AntonioTX78224 United States Department of Computer Science College of Computer and Information Systems Umm Al-Qura University Makkah24381 Saudi Arabia Computer and Information Science Division Higher Colleges of Technology Abu Dhabi United Arab Emirates

Metaheuristic search methods have proven to be essential tools for tackling complex optimization challenges, but their full potential is often constrained by conventional algorithmic frameworks. In this paper, we introduce a novel approach called Deep Heuristic Search (DHS), which models metaheuristic search as a memory-driven process. DHS employs multiple search layers and memory-based exploration-exploitation mechanisms to navigate large, dynamic search spaces. By utilizing model-free memory representations, DHS enhances the ability to traverse temporal trajectories without relying on probabilistic transition models. The proposed method demonstrates significant improvements in search efficiency and performance across a range of heuristic optimization *** Codes I.2.6 © 2024, CC BY-NC-ND.

关键词： Constrained optimization

Monotonically Convergent Regularization by Denoising

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Hu, Yuyang Liu, Jiaming Xu, Xiaojian Kamilov, Ulugbek S. Department of Electrical and Systems Engineering Washington University in St. Louis MO63130 United States Department of Computer Science and Engineering Washington University in St. Louis MO63130 United States

Regularization by denoising (RED) is a widely-used framework for solving inverse problems by leveraging image denoisers as image priors. Recent work has reported the state-of-the-art performance of RED in a number of imaging applications using pre-trained deep neural nets as denoisers. Despite the recent progress, the stable convergence of RED algorithms remains an open problem. The existing RED theory only guarantees stability for convex data-fidelity terms and nonexpansive denoisers. This work addresses this issue by developing a new monotone RED (MRED) algorithm, whose convergence does not require nonexpansiveness of the deep denoising prior. Simulations on image deblurring and compressive sensing recovery from random matrices show the stability of MRED even when the traditional RED algorithm diverges. Copyright © 2022, The Authors. All rights reserved.

关键词： Deep neural networks

The Role of Time Delay in Sim2real Transfer of Reinforcement Learning for Cyber-Physical systems

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Chehadeh, Mohamad Boiko, Igor Zweiri, Yahya Center for Autonomous Robotic Systems Khalifa University Abu Dhabi United Arab Emirates Department of Electrical Engineering and Computer Science Department of Aerospace Engineering Khalifa University Abu Dhabi United Arab Emirates

his paper analyzes the simulation to reality gap in reinforcement learning (RL) cyber-physical systems with fractional delays (i.e. delays that are non-integer multiple of the sampling period). The consideration of fractional delay has important implications on the nature of the cyber-physical system considered. systems with delays are non-Markovian, and the system state vector needs to be extended to make the system Markovian. We show that this is not possible when the delay is in the output, and the problem would always be non-Markovian. Based on this analysis, a sampling scheme is proposed that results in efficient RL training and agents that perform well in realistic multirotor unmanned aerial vehicle simulations. We demonstrate that the resultant agents do not produce excessive oscillations, which is not the case with RL agents that do not consider time delay in the model. © 2022, CC BY-NC-SA.

关键词： Reinforcement learning

Optimal and instance-dependent guarantees for Markovian linear stochastic approximation

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Mou, Wenlong Pananjady, Ashwin Wainwright, Martin J. Bartlett, Peter L. Department of Electrical Engineering and Computer Sciences United States Department of Statistics UC Berkeley United States Schools of Industrial & Systems Engineering and Electrical & Computer Engineering Georgia Tech United States

We study stochastic approximation procedures for approximately solving a d-dimensional linear fixed point equation based on observing a trajectory of length n from an ergodic Markov chain. We first exhibit a non-asymptotic bound of the order tmix nd on the squared error of the last iterate of a standard scheme, where tmix is a mixing time. We then prove a non-asymptotic instance-dependent bound on a suitably averaged sequence of iterates, with a leading term that matches the local asymptotic minimax limit, including sharp dependence on the parameters (d, tmix) in the higher order terms. We complement these upper bounds with a non-asymptotic minimax lower bound that establishes the instance-optimality of the averaged SA estimator. We derive corollaries of these results for policy evaluation with Markov noise—covering the TD(λ) family of algorithms for all λ ∈ [0, 1)—and linear autoregressive models. Our instance-dependent characterizations open the door to the design of fine-grained model selection procedures for hyperparameter tuning (e.g., choosing the value of λ when running the TD(λ) algorithm). Copyright © 2021, The Authors. All rights reserved.

关键词： Stochastic systems

Deep Model-Based Architectures for Inverse Problems under Mismatched Priors

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Shoushtari, Shirin Liu, Jiaming Hu, Yuyang Kamilov, Ulugbek S. Department of Electrical & Systems Engineering Washington University St. LouisMO63130 United States Department of Computer Science & Engineering Washington University St. LouisMO63130 United States

There is a growing interest in deep model-based architectures (DMBAs) for solving imaging inverse problems by combining physical measurement models and learned image priors specified using convolutional neural nets (CNNs). For example, well-known frameworks for systematically designing DMBAs include plug-and-play priors (PnP), deep unfolding (DU), and deep equilibrium models (DEQ). While the empirical performance and theoretical properties of DMBAs have been widely investigated, the existing work in the area has primarily focused on their performance when the desired image prior is known exactly. This work addresses the gap in the prior work by providing new theoretical and numerical insights into DMBAs under mismatched CNN priors. Mismatched priors arise naturally when there is a distribution shift between training and testing data, for example, due to test images being from a different distribution than images used for training the CNN prior. They also arise when the CNN prior used for inference is an approximation of some desired statistical estimator (MAP or MMSE). Our theoretical analysis provides explicit error bounds on the solution due to the mismatched CNN priors under a set of clearly specified assumptions. Our numerical results compare the empirical performance of DMBAs under realistic distribution shifts and approximate statistical estimators. Copyright © 2022, The Authors. All rights reserved.

关键词： Inverse problems

The Future of Smart Grids: Revolutionizing Energy Distribution with Advanced IoT, and Renewable Integration

学校读者我要写书评

暂无评论

The Future of Smart Grids: Revolutionizing Energy Distributi...

Global Conference for Advancement in Technology (GCAT)

作者： S. Avinash J.C. Vinitha S. Sree Dharinya V. Samuthira Pandi Lakshmi Priya J Jaishika S Department of MBA St. Joseph's College of Engineering Chennai Department of Electrical and Electronics Engineering Rajalakshmi Engineering College Chennai Tamil Nadu India School of Computer Science Engineering and Information Systems VIT University Vellore Centre for Advanced Wireless Integrated Technology Chennai Institute of Technology Chennai Tamil Nadu India Department of ECE Saveetha Engineering College Chennai Department of Electronics and Communication Engineering Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Chennai

ISBN: (数字)9798350376685

ISBN: (纸本)9798350376692

Smart grids, which integrate modern Internet of Things (IoT) technology and renewable energy sources to boost efficiency, sustainability, and dependability, are poised to bring about a dramatic shift in the future of energy distribution. Intelligent grids are expected to bring about this shift. Focusing on the role of the Internet of Things (IoT) in enabling real-time monitoring and control, as well as the incorporation of renewable energy to support a low-carbon future, this research investigates the potential for smart grids to change the energy sector. This study gives insights into how smart grids can be efficiently deployed to satisfy the growing energy needs of society by studying the technological breakthroughs, obstacles, and benefits of smart grids. Specifically, the study's focus is on smart grids. The research highlights the essential role that smart grids play in aiding the shift towards a more sustainable and resilient energy infrastructure by conducting an in-depth analysis of case studies, pilot projects, and industry trends all around the world. Providing recommendations for policymakers, industry stakeholders, and utilities to exploit the full potential of smart grids in determining the future of energy distribution, the findings contribute to the continuing discourse on the strategic development and implementation of smart grid technologies. Both of these topics are currently being discussed.

关键词： Industries Renewable energy sources Protocols Real-time systems Smart grids Internet of Things Stakeholders Standards Resilience Investment

Tracking and Calculating Speed of Mixing Vehicles Using YOLOv4 and DeepSORT 9

学校读者我要写书评

暂无评论

Tracking and Calculating Speed of Mixing Vehicles Using YOLO...

9th NAFOSTED Conference on Information and computer Science, NICS 2022

作者： Huu, Phat Nguyen Anh, Bang Nguyen Nam, Vu Tran Ngoc Hoang, Tran Manh Nguyen, Tien Dzung Minh, Quang Tran School of Electrical and Electronic Engineering Hanoi University of Science and Technology Hanoi Viet Nam Specialized Math Class HUS High School for Gifted Students Hanoi Viet Nam Ho Chi Minh City University of Technology Faculty of Computer Science and Engineering Department of Information Systems Hochiminh Viet Nam Vietnam National University HoChiMinh City Hochiminh Viet Nam

ISBN: (纸本)9781665454223

Today, strong development of socio-economic has promoted participation in traffic. As a result, traffic management is becoming more and more difficult. To effectively solve the problem, artificial intelligence (AI) applications are applied for the improvement of urban traffic management and administration. Therefore, we propose an intelligent algorithm for monitoring and detecting vehicles. We use data collected from cameras and apply deep learning technology to track objects in the paper. The proposed algorithm uses YOLOv4 combined with DeepSORT for tracking and calculating the speed of detected vehicles. Results show that the proposed algorithm improves accuracy up to 95% which is suitable to apply for real applications. © 2022 IEEE.

关键词： Object detection

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

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Sasahara, Hampei Dán, György Amin, Saurabh Sandberg, Henrik The Department of Systems and Control Engineering School of Engineering Tokyo Institute of Technology Tokyo152-8552 Japan The Division of Network and Systems Engineering School of Electrical Engineering and Computer Science Kth Royal Institute of Technology StockholmSE-100 44 Sweden The Laboratory for Information and Decision Systems Massachusetts Institute of Technology CambridgeMA02139 United States The Division of Decision and Control Systems School of Electrical Engineering and Computer Science Kth Royal Institute of Technology StockholmSE-100 44 Sweden

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 dramatically reduce inefficiency of equilibria. © 2022, CC BY-NC-ND.

关键词： Economic and social effects

Predicting of Uncertainty Facial Expressions in Children with Autism Spectrum Disorder Based on an Improved Fuzzy Convolutional Neural Network Model

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Abd-Alhalem, Samia M. Ali, Hesham A. El-Shafai, Walid Soliman, Naglaa F. Algarni, Abeer D. El-Samie, Fathi E. Takieldeen, Ali E. Faculty of Artificial Intelligence Delta University for Science and Technology Gamasa35712 Egypt Computers and Control Systems Engineering Department Faculty of Engineering Mansoura University Mansoura35516 Egypt Security Engineering Lab Computer Science Department Prince Sultan University Riyadh11586 Saudi Arabia Department Electronics and Electrical Communications Engineering Faculty of Electronic Engineering Menoufia University Menouf32952 Egypt Department of Information Technology College of Computer and Information Sciences Princess Nourah bint Abdulrahman University P.O. Box 84428 Riyadh11671 Saudi Arabia Zagazig University Egypt Menoufia University Egypt

Facial expression recognition plays a pivotal role in comprehending emotions and social interactions, particularly in individuals grappling with autism spectrum disorder (ASD), who often encounter challenges in non-verbal communication. For some with ASD, even subtle shifts in their facial expressions can prove elusive, rendering it arduous to categorize their emotional states accurately. Consequently, the analysis and processing of facial expression data hold the potential to facilitate early autism diagnosis, thereby enabling timely therapeutic interventions and alleviating the economic and psychological burdens experienced by patients. In this study, we introduce an enhanced approach that leverages a fuzzy convolutional neural network (CNN) and an Improved Binary Genetic Algorithm (IBGA) for autism diagnosis based on facial expression data. Our model confronts the intricate task of recognizing facial images by selecting salient features employing the IBGA method. Moreover, it employs fuzzy weights to ascertain the probability of similarity within the classifier layer. Our proposed model has yielded impressive outcomes, boasting an average accuracy of 0.9405 for ASD detection and 0.9365 for the recognition of six distinct facial expressions. These results hold profound implications for the enhancement of emotion recognition systems and the refinement of interventions aimed at bolstering social interactions for individuals grappling with ASD. © 2024, The Authors. All rights reserved.

关键词： Emotion Recognition