检索结果-内蒙古大学图书馆

Intelligent Technologies (ACOIT), Asian Conference on

作者： Ramakrishnan Raman Vikram Kumar Biju G. Pillai Apurv Verma Shailesh Rastogi R. Meenakshi Symbiosis International (Deemed University SRV Media Pvt. Ltd BIIB & Dean – Faculty of Management IT & Business Analytics Sri Balaji University Pune Computer science & Eng. Faculty of Engineering and Technology Parul institute of Technology Parul University Symbiosis Institute of Business Management Nagpur Symbiosis International (Deemed University) Pune Computer Science and Engineering Chennai Institute of technology

ISBN: (数字)9798350374957

ISBN: (纸本)9798350374964

In the dynamic field of Reinforcement Learning (RL), optimizing multiple objectives simultaneously poses a significant challenge, addressed by Decomposition-Based multi-objective Reinforcement Learning (DB-MORL). This paper introduces a comprehensive taxonomy and analytical framework for DB-MORL, emphasizing a novel algorithmDynamic Hybrid DB-MORL (DH-DB-MORL)-that innovatively adapts between scalarization and Pareto-front methods based on real-time assessments. This approach enhances the efficiency and quality of solutions by dynamically exploring the trade-offs between conflicting objectives, thereby improving both solution diversity on the Pareto front and computational efficiency. Through extensive empirical testing across various synthetic and real-world scenarios, the DH-DBMORL algorithm demonstrated notable enhancements in computational time, solution quality, and scalability compared to baseline models such as NSGA-II, MOEA/D, and SPEA2. Our findings reveal that the DH-DB-MORL algorithm significantly reduces computational time, produces a higher number of Pareto-optimal solutions, and achieves superior solution quality as evidenced by higher hypervolume scores. Additionally, the algorithm’s adaptability enables it to maintain high performance even as the complexity of the problem space increases. This study not only refines our understanding of DBMORL strategies but also sets a new benchmark for future research and applications in fields requiring nuanced multi-objective optimization, such as autonomous systems and resource management. The dynamic adaptability and comprehensive taxonomy provided by DH-DB-MORL offer a more effective approach to handling the complexities of high-dimensional, multi-objective problems, advancing both theoretical and practical aspects of multi-objective optimization in RL.

关键词： Heuristic algorithms Scalability Taxonomy Reinforcement learning Switches Benchmark testing Real-time systems Complexity theory Resource management optimization

来源：评论

学校读者我要写书评

暂无评论

multi-Session multi-objective Budget optimization for Auction-based Federated Learning

Multi-Session Multi-Objective Budget Optimization for Auctio...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Xiaoli Tang Han Yu College of Computing and Data Science Nanyang Technological University Singapore

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Auction-based Federated Learning (AFL) has become a significant focus in recent years. Existing approaches for model users (MUs) in FL generally operate under the assumption that the entire set of essential data owners (DOs) must be gathered before the training process initiates. However, in practical scenarios, the MU can initiate the FL training process multiple times, gradually recruiting DOs across multiple FL training sessions. Current AFL methods are not equipped to handle such situations. The challenge of optimizing the AFL budget across multiple sessions and objectives remains unresolved. To address this gap, we propose the Efficient and Utility Return-Optimizing budget management strategy for MUs in Auction-based Federated Learning (EURO-AFL). By incorporating the hierarchical reinforcement learning framework, EURO-AFL concurrently optimizes inter-session budget pacing and intra-session budget allocation, with the dual objective of maximizing total utility while minimizing waiting time. Extensive experiments conducted on four real-world datasets illustrate the substantial advantages of EURO-AFL compared to five state-of-the-art baselines. It outperforms the best-performing baseline by 6.26%, 47.9% and 17.6% in terms of model accuracy, number of training sessions sustained, and training efficiency, respectively. To our best knowledge, EURO-AFL is the first multi-session multi-objective budget optimization approach designed for AFL MUs.

关键词： Training Knowledge engineering Accuracy Federated learning Neural networks Reinforcement learning Data models

来源：评论

学校读者我要写书评

暂无评论

Evaluating two multi-model simulation-optimization approaches for managing groundwater contaminant plumes

引用

JOURNAL OF HYDROLOGY 2020年 590卷 125427-125427页

作者： Elshall, Ahmed S. Ye, Ming Finkel, Michael Florida State Univ Dept Earth Ocean & Atmospher Sci Tallahassee FL 32306 USA Univ Tubingen Ctr Appl Geosci Tubingen Germany

Addressing conceptual model uncertainty using multi-model approaches has become an important topic in groundwater hydrology. Model uncertainty is of practical importance when designing a pump-and-treat system for groundwater remediation, as inappropriate consideration of model uncertainty may ultimately lead to ineffective system designs. This study introduces two multi-model approaches for addressing model uncertainty at a site contaminated by chlorinated hydrocarbons and BTEX compounds. We use a multi-objective simulation-optimization method to design a multiple-well pump-and-treat system to contain contaminant plumes within the site perimeter, while minimizing the pumping rate. The design parameters include the coordinates of the pumping well locations and pumping rates. We consider four groundwater models to address uncertainty in conceptualizing site geology, boundary condition, and recharge. Using two multi-model approaches, we evaluate different design concepts. The first approach is a model selection approach that identifies the critical models, which particularly govern the design process, within the multi-model ensemble. The second approach is a model aggregation approach that identifies system designs that meet the remediation objectives for all models of the ensemble. Results show that the model aggregation approach is a more conservative option, which results in reliable designs at the expense of higher pumping rates. This study evaluates these two approaches within the context of multi-model simulation-optimization, providing insights on multi-model simulation-optimization in groundwater management.

关键词： Groundwater remediation Contaminant plume containment Water quality control multi-objective optimization Conceptual model uncertainty

来源：评论

学校读者我要写书评

暂无评论

A novel combined forecasting system based on advanced optimization algorithm-A study on optimal interval prediction of wind speed

引用

ENERGY 2023年 264卷

作者： Li, Jingrui Wang, Jiyang Li, Zhiwu Macau Univ Sci & Technol Inst Syst Engn Macau 999078 Peoples R China

Wind speed forecasting is becoming increasingly crucial for an environmentally friendly and sustainable economy because of the renewability and benefits of wind energy. Currently, many scholars have proposed various approaches to forecasting wind speed;however, due to the limitations of point prediction and drawbacks of traditional individual methods, it is challenging to acquire satisfactory results. Compared with the previous articles, this paper combines a data preprocessing strategy by fuzzification, interval estimation, and advanced optimization methods to enhance the accuracy of wind speed forecasting. Moreover, the weight coefficient allocated by a multi-objective algorithm is proved to reach Pareto optimal solution in theory. Based on the comparative experiments and discussion of the performance of the developed combined forecasting system and other control groups, it is revealed that the combined system not only outperforms for predicting wind speed with higher accuracy and stability but also enables a valid assessment of uncertainty than the former studies. It can be convinced that the developed predicting system is an appropriate and efficient tool for further practical applications in energy systems.

关键词： Wind speed forecasting Data preprocessing technique Combined system Whale optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

TOWARDS EFFICIENT multi-objective OPTIMISATION FOR REAL-WORLD POWER GRID TOPOLOGY CONTROL

arXiv

引用

arXiv 2025年

作者： Manyari, Yassine El Fuxjäger, Anton R. Zahlner, Stefan Van Dijk, Joost Castagna, Alberto Barbieri, Davide Viebahn, Jan Wasserer, Marcel enliteAI Vienna Austria TenneT TSO Arnhem Netherlands

Power grid operators face increasing difficulties in the control room as the increase in energy demand and the shift to renewable energy introduce new complexities in managing congestion and maintaining a stable supply. Effective grid topology control requires advanced tools capable of handling multi-objective trade-offs. While Reinforcement Learning (RL) offers a promising framework for tackling such challenges, existing multi-objective Reinforcement Learning (MORL) approaches fail to scale to the large state and action spaces inherent in real-world grid operations. Here we present a two-phase, efficient and scalable multi-objective Optimisation (MOO) method designed for grid topology control, combining an efficient RL learning phase with a rapid planning phase to generate day-ahead plans for unseen scenarios. We validate our approach using historical data from TenneT, a European Transmission System Operator (TSO), demonstrating minimal deployment time, generating day-ahead plans within 4–7 minutes with strong performance. These results underline the potential of our scalable method to support real-world power grid management, offering a practical, computationally efficient, and time-effective tool for operational planning. Based on current congestion costs and inefficiencies in grid operations, adopting our approach by TSOs could potentially save millions of euros annually, providing a compelling economic incentive for its integration in the control room. Copyright © 2025, The Authors. All rights reserved.

关键词： multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Advanced Computational approaches in HR: Utilizing Neural Networks and Genetic Algorithms for Talent Acquisition 4

Advanced Computational Approaches in HR: Utilizing Neural Ne...

引用

4th IEEE Asian Conference on Innovation in Technology, ASIANCON 2024

作者： Sharma, Rishabh Reddy, B. Chitkara University Centre for Research Impact & Outcome Punjab Rajpura140401 India Chitkara University Chitkara Centre for Research and Development Himachal Pradesh 174103 India

ISBN: (纸本)9798350354218

Despite the constant changes within today's Human Resources (HR) field, talent acquisition stands out as one of the most important strategic processes determining the performance of a company. The conventional recruiting approach is mostly performed and oftentimes proves to be time-consuming and non-inclusive. To address these challenges, this research focuses on the combination of intelligent technologies, namely neural networks and genetic algorithms in the context of talent acquisition. As a result, it was decided to use neural networks that have the best function for processing and analyzing massive unstructured information, such as resumes and job descriptions, to determine candidate suitability. Hypothesis 3 posited that since GAs are about optimization, multi-objective and were used to consider various factors at one time in the context of candidate job matching. As data sources, resumes of the IT employees, job descriptions of the positions, and employee performance analytics of this leading global technology company were used for the study. The CNN model needs to be further trained using other candidate sets of questions and achieve a screening accuracy of 85%, and an AUC-ROC score of 0.88 to properly screen candidates. The genetic algorithm model was also quite good with a classification accuracy of 82% and by using AUC-ROC it scored well 0.85. The best results employing both NNs and GAs indicated the highest performance measures;accuracy equal to 87%, precision equal to 85%, recall equal to 86%, and an AUC-ROC of 0.90. Such findings support the effectiveness of using both neural networks and genetic algorithms in redefining talent management by automating the process and reducing errors and prejudice in choosing talents. The implications for practical application for HR professionals and organizations are immense and identify that the use of these more complex computational methodologies can indeed provide a step up in recruiting performance. The study al

关键词： Ethical technology

来源：评论

学校读者我要写书评

暂无评论

optimization Techniques in Electronics: Advances, Challenges, and Future Directions

Optimization Techniques in Electronics: Advances, Challenges...

引用

International Conference on ent Computing and Control Systems (ICICCS)

作者： Gaurav Mishra Khushi Kumari Chethan Sharma Dept of CSE M.S. Ramaiah Institute of Technology Bangalore Dept of CSE(AI & ML) M.S. Ramaiah Institute of Technology Bangalore Dept of CSE(AI & ML) and Dept of CSE (Cyber Security) M.S. Ramaiah Institute of Technology Bangalore

ISBN: (数字)9798331512088

ISBN: (纸本)9798331512095

optimization techniques support the solutions of contemporary electronic challenges by managing resources while improving energy conservation and boosting performance together with scalability capabilities. The rapid technological progress of Very Large-Scale Integration (VLSI) together with Internet of Things (IoT) and computer networks and signal processing and communication systems requires improved optimization techniques. Research focuses on few selected studies from 2023 to 2025 to conduct an extensive review of optimization methods used in these technological fields. The review groups selected studies according to their application sectors and their methodologies as well as their findings while noting important advantages and constraints along with practical results. The objective of this work is to provide a comprehensive analysis of existing optimization strategies, identifying their strengths and limitations to guide future advancements. The review discusses future optimization directions based on the study of emerging trends which include AI optimization principles and quantum computing capabilities and multi-objective optimization approaches. Research has identified major gaps in scalability and computational complexity along with the need for real-world testing and energy efficiency studies for electronic system optimization. Future work recommendations target these gaps to improve electronic system optimization.

关键词： Quantum computing Reviews Scalability Very large scale integration Signal processing Energy efficiency Computer networks Internet of Things Computational complexity optimization

来源：评论

学校读者我要写书评

暂无评论

CARDINALITY-CONSTRAINED multi-objective optimization: NOVEL OPTIMALITY CONDITIONS AND ALGORITHMS

arXiv

引用

arXiv 2023年

作者： Lapucci, Matteo Mansueto, Pierluigi Department of Information Engineering University of Florence Via di Santa Marta 3 Florence50139 Italy

In this paper, we consider multi-objective optimization problems with a sparsity constraint on the vector of variables. For this class of problems, inspired by the homonymous necessary optimality condition for sparse single-objective optimization, we define the concept of L-stationarity and we analyze its relationships with other existing conditions and Pareto optimality concepts. We then propose two novel algorithmic approaches: the first one is an Iterative Hard Thresholding method aiming to find a single L-stationary solution, while the second one is a two-stage algorithm designed to construct an approximation of the whole Pareto front. Both methods are characterized by theoretical properties of convergence to points satisfying necessary conditions for Pareto optimality. Moreover, we report numerical results establishing the practical effectiveness of the proposed *** Codes 90C26, 90C29, 90C46 Copyright © 2023, The Authors. All rights reserved.

关键词： Numerical methods

来源：评论

学校读者我要写书评

暂无评论

Design and control of electrotechnological systems A multi-objective optimization approach

引用

COMPEL-THE INTERNATIONAL JOURNAL FOR COMPUTATION AND MATHEMATICS IN ELECTRICAL AND ELECTRONIC ENGINEERING 2020年第1期39卷 239-247页

作者： Pleshivtseva, Yuliya Rapoport, Edgar Nacke, Bernard Nikanorov, Alexander Di Barba, Paolo Forzan, Michele Sieni, Elisabetta Lupi, Sergio Samara State Tech Univ Fac Heat & Power Engn Samara Russia Samara State Tech Univ Inst Automat & Informat Technol Samara Russia Leibniz Univ Hannover Inst Electrotechnol Hannover Germany St Petersburg Electrotech Univ Dept Electrotechnol & Converter Engn St Petersburg Russia Univ Pavia Dept Elect Engn Pavia Italy Univ Padua Dept Ind Engn Padua Italy Insubria Univ Dept Theoret & Appl Sci Varese Italy

Purpose This paper aims to investigate different multi-objective optimization (MOO) approaches for design and control of electromagnetic devices. The main goal of MOO is to find the set of design variables or control parameters which will provide the best possible values of typical conflicting objective functions. Design/methodology/approach In the research studies, standard genetic algorithm (GA), non-dominated sorting GA (NSGA-II), migration NSGA algorithm and alternance method of optimal control theory are discussed and compared. Findings The test practical problems of multi-criteria optimization of induction heating processes with respect to chosen quality criteria confirm the effectiveness of application of considered MOO approaches both for the problems of design and control. Originality/value This paper represents and investigates different MOO approaches for design and control of electrotechnological systems.

关键词： Induction heating Optimal control Optimal design multi-objective optimization

来源：评论

学校读者我要写书评

暂无评论

Enhancing Robotics Online 3D Bin Packing: A Comparative Study of Conventional Heuristic and Deep Reinforcement Learning approaches

Enhancing Robotics Online 3D Bin Packing: A Comparative Stud...

引用

IEEE International Conference on Automation Science and Engineering (CASE)

作者： Heng Xiong Kai Ding Wan Ding Xuchong Qiu Klaus Janschek Jianfeng Xu State Key Laboratory of Intelligent Manufacturing Equipment and Technology School of Mechanical Science and Engineering Huazhong University of Science and Technology Wuhan China BOSCH Corporate Research Technische Universität Dresden Germany

ISBN: (数字)9798350358513

ISBN: (纸本)9798350358520

Robotic object packing holds a wide array of practical applications across logistics and manufacturing sectors. The online 3D Bin Packing Problem (BPP) is a challenging task that involves online packing of three-dimensional boxes into a container while considering constraints and objectives. Unlike the offline version, where all boxes are known in advance, the online variant requires decisions about how to pack each box as it arrives, without prior knowledge of upcoming *** maximize space utilization, our study explores two distinct strategies: conventional heuristics-based algorithms and a deep reinforcement learning (DRL)-based approach. For the heuristic strategy, we propose four heuristic criteria alongside two variants of multi-objective optimization (MOO) algorithms. Quantitative experiments reveal that MOO outperforms single-objective approaches for online bin packing. In our DRL-based approach, we introduce a framework that leverages a candidate map that indicates the potentially feasible placements, ensuring a balanced exploration and exploitation in the considerable discrete action space. Experiments demonstrate the superior performance of our DRL-based approach compared to both DRL-based baseline methods and conventional approaches. Additionally, we discuss the limitations of DRL-based methods and offer practical recommendations for real-world applications.

关键词： Three-dimensional displays Computer aided software engineering Heuristic algorithms Containers Deep reinforcement learning Explosions Manufacturing Robots optimization Logistics

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：