检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Liu, Shengcai Lu, Ning Hong, Wenjing Qian, Chao Tang, Ke Southern University of Science and Technology China Nanjing University China

The field of adversarial textual attack has significantly grown over the last few years, where the commonly considered objective is to craft adversarial examples (AEs) that can successfully fool the target model. However, the imperceptibility of attacks, which is also essential for practical attackers, is often left out by previous studies. In consequence, the crafted AEs tend to have obvious structural and semantic differences from the original human-written text, making them easily perceptible. In this work, we advocate leveraging multi-objectivization to address such issue. Specifically, we reformulate the problem of crafting AEs as a multi-objective optimization problem, where the attack imperceptibility is considered as an auxiliary objective. Then, we propose a simple yet effective evolutionary algorithm, dubbed HydraText, to solve this problem. To the best of our knowledge, HydraText is currently the only approach that can be effectively applied to both score-based and decision-based attack settings. Exhaustive experiments involving 44237 instances demonstrate that HydraText consistently achieves competitive attack success rates and better attack imperceptibility than the recently proposed attack approaches. A human evaluation study also shows that the AEs crafted by HydraText are more indistinguishable from human-written text. Finally, these AEs exhibit good transferability and can bring notable robustness improvement to the target model by adversarial training. Copyright © 2021, 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

Enhanced multi-objective Evolutionary Mating Algorithm with improved crowding distance and Levy flight for optimizing comfort index and energy consumption in smart buildings

Franklin Open

引用

Franklin Open 2025年 11卷

作者： Nordin, Muhammad Naim Bin Sulaiman, Mohd Herwan Zakaria, Nor Farizan Mustaffa, Zuriani Faculty of Electrical & Electronics Engineering Technology Universiti Malaysia Pahang Al-Sultan Abdullah Pahang Pekan 26600 Malaysia Centre for Research in Advanced Fluid & Processes (Fluid Centre) Universiti Malaysia Pahang Al-Sultan Abdullah Gambang Campus Pahang Kuantan 26300 Malaysia Faculty of Computing Universiti Malaysia Pahang Al-Sultan Abdullah Pahang Pekan 26600 Malaysia

This paper introduces a novel multi-objective Evolutionary Mating Algorithm (MOEMA) designed to address the inherent challenges of optimizing comfort index and energy consumption in smart building systems. While current Evolutionary Mating Algorithms (EMA) primarily focus on single-objective optimization and rely on weighted functions for handling multiple objectives, such approaches prove impractical for the complex trade-offs between comfort index and energy efficiency. The proposed MOEMA enhances the original EMA framework through two key innovations: an improved crowding distance function inspired by the Non-dominated Sorting Genetic Algorithm (NSGA) to enhance solution diversity and selection pressure, and the integration of Levy flight mechanics to improve exploration efficiency by balancing local and global searches. These enhancements enable MOEMA to effectively navigate complex multi-objective landscapes, leading to more diverse and well-converged Pareto-optimal solutions. The algorithm's performance is thoroughly assessed using the chosen benchmark functions and validated through practical applications in smart building environments. It simultaneously optimizes various comfort parameters, including temperature, illuminance, and air quality, while minimizing energy consumption and maximizing the comfort index. Comparative analysis against established algorithms, like NSGA-II demonstrates MOEMA's effectiveness in achieving superior solution diversity and convergence characteristics. The results indicate that MOEMA offers a robust framework for handling the complex balance between the smart building's comfort index and energy usage where it achieves 0.03 % better at comfort index and with 10.65 % lower energy consumption than NSGA-II. It contributing to the broader fields of building automation and sustainable development while aligning with Industry 4.0 initiatives. © 2025 The Author(s)

关键词： Comfort index optimization Crowding distance Energy efficiency Evolutionary Mating Algorithm Levy flight multi-objective optimization Pareto optimization Smart buildings

来源：评论

学校读者我要写书评

暂无评论

Distribution systems techno-economic performance optimization through renewable energy resources integration

引用

ARRAY 2021年 9卷

作者： Hassan, Ahmed S. Othman, ElSaeed A. Bendary, Fahmy M. Ebrahim, Mohamed A. Minist Elect & Renewable Energy MOERE Cairo Egypt Al Azhar Univ Fac Engn Dept Elect Engn Cairo Egypt Benha Univ Fac Engn Shoubra Dept Elect Engn Cairo Egypt

This article presents three new multi-objective optimization methodologies as a solution for enhancing the traditional EDN techno-economic performance through integrating Distributed Generation (DG) of different categories. A combination of four types of DG resources is presented for identifying the optimal mix sizing and positioning through applying the Whale optimization Algorithm, Sine Cosine Algorithm and multi-Verse optimization Algorithm. The proposed approaches are constructed and subjected to a multi-objective function to minimize the active power losses, improve the voltage Stability and decrease overall additional costs. While taking into consideration the allowable margin of DG units' penetration level and their operating power factor in addition to the systems' voltage profile boundaries. The methodologies have been applied to two IEEE benchmark test systems (33-bus and 118-bus) besides a realistic part of the distribution grid of the Egyptian distribution network which is added as a practical case study. However, the proposed base cases have failed in keeping the voltage magnitudes boundaries at all busbars especially the realistic case, but the proposed algorithms have attained almost the same significant results regarding both of voltage stability and power loss for the mediumsized network IEEE 33-bus system. Furthermore, for both of the two large scale systems (IEEE 118-bus system and the realistic network), the MVO has proved its superiority compared to the proposed algorithms in addressing the optimization problem with higher results' accuracy. Meanwhile, the MVO has reached the optimal solutions for all cases in less time and iterations number.

关键词： Distributed generation optimization algorithm Voltage stability index Distribution network Distribution networks

来源：评论

学校读者我要写书评

暂无评论

Evolutionary Computation in Scheduling 1.

引用

2020年

作者： Amir H. Gandomi Ali Emrouznejad Mo M. Jamshidi Kalyanmoy Deb Iman Rahimi

ISBN: (数字)9781119574293

ISBN: (纸本)9781119573845

Presents current developments in the field of evolutionary scheduling and demonstrates the applicability of evolutionary computational techniques to solving scheduling problems This book provides insight into the use of evolutionary computations (EC) in real-world scheduling, showing readers how to choose a specific evolutionary computation and how to validate the results using metrics and statistics. It offers a spectrum of real-world optimization problems, including applications of EC in industry and service organizations such as healthcare scheduling, aircraft industry, school timetabling, manufacturing systems, and transportation scheduling in the supply chain. It also features problems with different degrees of complexity, practical requirements, user constraints, and MOEC solution approaches. Evolutionary Computation in Scheduling starts with a chapter on scientometric analysis to analyze scientific literature in evolutionary computation in scheduling. It then examines the role and impacts of ant colony optimization (ACO) in job shop scheduling problems, before presenting the application of the ACO algorithm in healthcare scheduling. Other chapters explore task scheduling in heterogeneous computing systems and truck scheduling using swarm intelligence, application of sub-population scheduling algorithm in multi-population evolutionary dynamic optimization, task scheduling in cloud environments, scheduling of robotic disassembly in remanufacturing using the bees algorithm, and more. This book: Provides a representative sampling of real-world problems currently being tackled by practitioners Examines a variety of single-, multi-, and many-objective problems that have been solved using evolutionary computations, including evolutionary algorithms and swarm intelligence Consists of four main parts: Introduction to Scheduling Problems, Computational Issues in Scheduling Problems, Evolutionary Computation, and Evolutionary Computations for Scheduling Problems Evoluti

关键词： evolutionary computation evolutionary scheduling decision science decision analytics evolutionary algorithms computational numerical methods numerical analysis mathematics statistics analytics computer engineering EC MOEC optimization

来源：评论

学校读者我要写书评

暂无评论

multi-objective fixed-charge solid transportation problem with product blending under intuitionistic fuzzy environment

引用

APPLIED INTELLIGENCE 2019年第10期49卷 3524-3538页

作者： Roy, Sankar Kumar Midya, Sudipta Vidyasagar Univ Dept Appl Math Oceanol & Comp Programming Midnapore 721102 W Bengal India

This paper analyzes multi-objective fixed-charge solid transportation problem with product blending in intuitionistic fuzzy environment. The parameters of multi-objective fixed-charge solid transportation problem may not be defined precisely because of globalization of the market and other unmanageable factors. So, we often hesitate in prediction of market demand and other parameters connected with transporting systems in a period. Based on these facts, the parameters of the formulated model are chosen as triangular intuitionistic fuzzy number. New ranking method is used to convert intuitionistic fuzzy multi-objective fixed-charge solid transportation problem with product blending to a deterministic form. New intuitionistic fuzzy technique for order preference by similarity to ideal solution (TOPSIS) is initiated to derive Pareto-optimal solution from the proposed model. Furthermore, we solve the formulated model using intuitionistic fuzzy programming;and a comparison is drawn between the obtained solutions extracted from the approaches. Finally, a practical (industrial) problem is incorporated to illustrate the applicability and feasibility of the proposed study. Conclusions with future research based on the paper are described at last.

关键词： Fixed-charge solid transportation problem Product blending multi-objective optimization Intuitionistic fuzzy programming Ranking method Intuitionistic fuzzy TOPSIS

来源：评论

学校读者我要写书评

暂无评论

Pareto frontier for multi-objective wind farm layout optimization balancing power production and turbine fatigue life

引用

RENEWABLE ENERGY 2025年 252卷

作者： Yang, Kun Zhang, Mingming Yang, Shanghui Song, Yuwei Dong, Xinhui Deng, Yanfei Deng, Xiaowei Univ Hong Kong Dept Civil Engn Hong Kong Peoples R China Harbin Inst Technol Shenzhen Inst Green Low Carbon Energy Innovat Technol Shenzhen Peoples R China

Layout optimization is a promising design process that will enhance the power efficiency of wind farms in the design stage. Single optimization targeting maximizing power production for wind farms has been studied for decades. Recently, multiple-objective layout optimization, considering more practical factors, has become urgently required with the rapid growth of wind energy. In this paper, we established a multiple-objective layout optimization framework that considers power performance and turbine fatigue life. Efficient power and fatigue life assessment approaches are adopted. Different scales of wind farms and typical wind roses are investigated. Pareto frontiers are drawn for each case to show the optimal solutions for multiple-objective optimizations. Notably, the deduction of wind speed and increase of turbulence intensity in the wake region have contrasting influences on the fatigue life. The turbines of optimal layouts are distant for higher overall power output but prefer to be closer for longer fatigue lives. Characteristic spacing describing the turbine density and the utilized area is suggested to be larger than 3.65D for any case and no less than 4.85D if the wind farm cannot afford the 85% power performance of the theoretical upper limit without wake loss.

关键词： Wind farm layout optimization multiple-objective optimization Fatigue life assessment Energy efficiency Pareto frontier

来源：评论

学校读者我要写书评

暂无评论

Boosting static timing analysis with programming and algorithmic approaches

Boosting static timing analysis with programming and algorit...

引用

作者： Guo, Guannan University of Illinois Urbana-Champaign

学位级别：硕士

The increasing complexity in digital design has spurred demand for faster design closure. As a primary timing measurement tool frequently used in design stage and optimization stage, static timing analysis has become one of the major performance bottlenecks in digital design. We study a novel parallel programming model and algorithm to boost timing analysis. As multi-core systems have become common in modern electronics, how to fit timing analysis into the multithreading environment is a trending research topic. We explore this direction with a new task-based multithreading framework and demonstrate its superior efficiency over existing tools. Critical path generation is a major objective timing analysis. optimization tools always need to report on critical paths under several path constraints. We propose a general path search algorithm which can fulfill all practical path constraints and outperforms an industrial timing analysis tool. Combining the tasks proposed above, we aim to improve the efficiency of static timing analysis with both a new programming framework and new algorithm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

multi-source data-driven intelligent analysis and decision optimization for high-density pedestrian flows in urban public spaces

引用

Automation in Construction 2025年 177卷

作者： Shiqi Zeng Xiangsheng Chen Dong Su Haofeng Gong State Key Laboratory of Intelligent Geotechnics and Tunnelling (Shenzhen University) Shenzhen China College of Civil and Transportation Engineering Shenzhen University Shenzhen China Key Laboratory of Coastal Urban Resilient Infrastructures (Shenzhen University) Ministry of Education Shenzhen China National Engineering Research Center of Deep Shaft Construction Shenzhen China

Managing high-density pedestrian flows in urban public spaces via Information Technologies (IT) is crucial for safety and efficiency. Despite advancements in sensing, AI-driven prediction, and control, a critical gap persists: lacking the systematic integration needed for robust automated crowd management systems, an issue intensified by AI/IoT growth. To address this challenge, a comprehensive review of the literature from 2014 to 2024 has been conducted, analyzing and synthesizing IT-driven decision support approaches for automated crowd management. The field is organized around three core technological pillars: (1) multi-source data fusion architectures for comprehensive real-time monitoring; (2) intelligent prediction systems using deep learning for accurate forecasting and anomaly detection; and (3) advanced decision optimization platforms enabling dynamic, multi-objective control strategies. In addition, the review explores key emerging trends such as edge computing, digital twins, and human-machine collaboration. The findings offer theoretical insights, practical guidelines, an overview of persistent challenges, and strategic directions for future research in intelligent crowd management within the broader context of smart cities and resilient infrastructure.

关键词：

来源：评论

学校读者我要写书评

暂无评论

multi-objectiveoptimization of solid oxide fuel cell/gas turbine combined heat and power system: A comparison between particle swarm and genetic algorithms

引用

INTERNATIONAL JOURNAL OF ENERGY RESEARCH 2020年第11期44卷 9001-9020页

作者： Safari, Sadegh Hajilounezhad, Taher Ehyaei, Mehdi Ali Islamic Azad Univ Fac Nat Resources & Environm Sci & Res Branch Dept Energy Engn Tehran Iran Univ Missouri Dept Mech & Aerosp Engn Columbia MO 65211 USA Islamic Azad Univ Pardis Branch Dept Mech Engn Pardis Iran

Many studies have attempted to optimize integrated Solid Oxide Fuel Cell-Gas Turbine (SOFC-GT), although different and somehow conflicting results are reported employing various algorithms. In this study, multi-objective optimization (MOO) is employed to approach the optimal design of SOFC-GT considering all prevailing factors. The emphasis is placed on the evaluation of the Particle Swarm optimization (PSO) and Genetic Algorithm (GA) performance as two effective approaches for solving the multi-objective and non-linear optimization problems. multi- objective optimization is carried out on two vital objectives;the electrical efficiency and the overall output power of the system. The considerable achievements are the set of optimal points that aim to identify the system optimal performance which provides a practical basis for the decision-makers to choose the appropriate target functions. For the studied conditions, the two algorithms nearly exhibit similar performance, while the PSO is faster and more efficient in terms of computational effort. The PSO appears to achieve its ultimate parameter values in fewer generations compared to the GA algorithm under the examined circumstances. It is found that the maximum power of 410 kW is accomplished employing the GA optimization method with an efficiency of 64%, while PSO method yields the maximum power of 419.19 kW at the efficiency of 58.9%. The results stress that PSO offers more satisfactory convergence and fidelity of the solution for the SOFC-GT MOO problems.

关键词： gas turbine heat recovery steam generation modeling multi-objective optimization solid oxide fuel cell

来源：评论

学校读者我要写书评

暂无评论

Wind Speed Forecasting Using a Two-Stage Forecasting System With an Error Correcting and Nonlinear Ensemble Strategy

引用

IEEE ACCESS 2019年 7卷 176000-176023页

作者： Zhang, Lifang Dong, Yao Wang, Jianzhou Dongbei Univ Finance & Econ Sch Stat Dalian 116025 Peoples R China Jiangxi Univ Finance & Econ Sch Stat Nanchang 330013 Jiangxi Peoples R China Jiangxi Univ Finance & Econ Appl Stat Res Ctr Nanchang 330013 Jiangxi Peoples R China

Precise wind speed prediction is increasingly practical for sustained and stable wind energy utilization considering the growing portion of wind energy in the global electric grid. Although plenty of wind speed forecasting approaches have been devoted to improving forecasting performance, the majority have neglected the utilization of error information, integrated the forecasting value of every component with simple ensemble approaches, and ignored forecasting stability, which may make the forecasting results poor. Considering the above drawbacks, a two-stage forecasting system is performed in our study based on the data preprocessing approach, improved multi-objective optimization algorithm, error correction and nonlinear ensemble strategy. The developed system effectively overcomes the shortcomings of previous models and observably prompts wind speed forecasting capacity. For investigating the prediction capacity of the developed system, six wind speed series obtained from China and Spain are applied as case sites. The forecasting consequences indicate that the developed system is more conducive to enhancing forecasting precision and stability than other involved models, which can provide beneficial assistance for wind speed forecasting.

关键词： Wind speed forecasting multi-objective optimization algorithm ensemble strategy forecasting accuracy

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：