检索结果-内蒙古大学图书馆

Bi-objective optimization for customers' satisfaction improvement in a Public Bicycle Sharing System

COMPUTERS & INDUSTRIAL ENGINEERING 2021年 161卷

作者： Vishkaei, Behzad Maleki Fathi, Mahdi Khakifirooz, Marzieh De Giovanni, Pietro LUISS Univ Dept Business & Management Rome Italy Univ North Texas Dept Informat Technol Decis Sci G Brint Ryan Coll Business Denton TX USA Tecnol Monterrey Dept Ind Engn Monterrey Mexico

In recent years, the popularity of the Public Bicycle Sharing System (PBSS) for urban transportation is increasing. The fleet size of the system and the capacity of its stations are some key factors in establishing successful sharing system. These factors affect the number of rejected demands and the lack of free docks for returning bicycles because of demand variation at stations. This paper presents a bi-objective optimization solution for PBSS in which the first objective function minimizes the mean number of rejected requests for renting bikes and free docks for returning bikes per each satisfied demand. In other words, this function tries to minimize the mean number of dissatisfied users per each replied demand for renting. The second objective function minimizes the total number of bicycles and docks of the system. The goal is to minimize users' dissatisfaction with the least possible fleet size considering capacity constraints. The model is discussed under Jackson Network and the Mean Value Analysis (MVA). non-dominated sorting genetic algorithm (NSGA-II) is used to solve and examine the efficiency of the proposed model via different numerical examples.

关键词： Public Bicycle Sharing System (PBSS) Fleet size non-dominated sorting genetic algorithm (NSGA-II) Mean Value Analysis (MVA) Customer satisfaction

来源：评论

学校读者我要写书评

暂无评论

Automatic detection of non-apneic sleep arousal regions from polysomnographic recordings

引用

BIOMEDICAL SIGNAL PROCESSING AND CONTROL 2021年第0期66卷 102394-102394页

作者： Karimi, Jamileh Asl, Babak Mohammadzadeh Tarbiat Modares Univ Dept Biomed Engn Tehran Iran

A signal processing/machine learning (ML), data-driven approach for classifying targeted sleep arousal regions of polysomnography (PSG) signals is presented focusing on feature subset selection and consensus methods, deploying ensemble techniques. The targeted regions are the regions where RERA and non-RERA-non-Apnea events are present. The sensor independent and sensor-based features in time and frequency domain were derived from the PSG signals. To reduce the feature space dimension, a combination of feature selection strategies and a method of rank aggregation was applied to rank the features. Aiming to find a feature set, which conveys the most discriminative information of detection in designated learning models, the non-dominated sorting genetic algorithm was used as the optimization algorithm. In order to capture the relation between feature vectors across time, a composition of feature vectors was formed. To tackle the unbalanced data problem, several techniques were used and a data fusion strategy stood out. Also, considering a more robust classifier, a metaclassifier was generated using different features, datasets, and classifiers. Finally, the predictions of models generated by bagging techniques and boosting methods were compared. The presented method was developed, validated and tested on the PhysioNet Challenge 2018 training dataset consisting of 994 subjects. The highest performance on 192 test subjects based on the area under precision-recall curve (AUPRC) and the area under receiver operating characteristic (AUROC) curve were 0.465 and 0.927, respectively. This study suggests that automatic detection of RERA and non-RERA-non-Apnea sleep arousal regions from biosignals is possible and can be a suitable substitution for PSG.

关键词： non-apneic sleep arousals Multi objective genetic algorithms non-dominated sorting genetic algorithm Respiratory effort-related arousal Polysomnographic recordings

来源：评论

学校读者我要写书评

暂无评论

A new swift algorithm for bi-objective optimum design of steel moment frames

引用

JOURNAL OF BUILDING ENGINEERING 2021年 39卷

作者： Ghasemof, Ali Mirtaheri, Masoud Mohammadi, Reza Karami KN Toosi Univ Technol Dept Civil Engn Tehran Iran

In this paper, a new algorithm is proposed to multi-objective optimum seismic design of steel moment frames. This algorithm is based on the uniform damage (also known as uniform deformation) theory and so-called multiobjective uniform damage optimization (MUDO). MUDO is a swift algorithm formulated according to a bi-objective approach. Structural weight and maximum interstory drift ratio (IDR) are treated as two conflicting objectives representing economy and safety measures, respectively, and they are minimized simultaneously subject to a set of design constraints. To achieve the optimal Pareto front, MUDO tries to create a uniform distribution of story drifts in the structure and bring it to a target value that gradually varies from the low (minimum damage) to high (maximum damage). In this way, the algorithm obtains a set of optimal solutions in terms of structural weight at different damage levels, which is the Pareto front. To demonstrate the efficiency and robustness of the proposed algorithm, its results for 3-, 6- and 9-story steel moment frames are compared with those of two well-known multi-objective optimization algorithms, NSGA-II and MOPSO. Results indicate that MUDO can achieve better optimal solutions set in a much less computational time than the other two methods.

关键词： Multi-objective optimization Uniform damage optimization Uniform deformation theory Steel moment frame non-dominated sorting genetic algorithm Multi-objective particle swarm optimization

来源：评论

学校读者我要写书评

暂无评论

A Simulation-Based Multi-Objective Optimization Framework for the Production Planning in Energy Supply Chains

引用

ENERGIES 2021年第9期14卷 2684页

作者： Chen, Shiyu Wang, Wei Zio, Enrico Politecn Milan Energy Dept Via La Masa 34 I-20156 Milan Italy City Univ Hong Kong Dept Mech Engn Kowloon Hong Kong 999077 Peoples R China Aramis Srl Via Pergolesi 5 I-20121 Milan Italy PSL Res Univ CRC MINES ParisTech F-06904 Sophia Antipolis France

The work presents a simulation-based Multi-Objective Optimization (MOO) framework for efficient production planning in Energy Supply Chains (ESCs). An Agent-based Model (ABM) that is more comprehensive than others adopted in the literature is developed to simulate the agent's uncertain behaviors and the transaction processes stochastically occurring in dynamically changing ESC structures. These are important realistic characteristics that are rarely considered. The simulation is embedded into a non-dominated sorting genetic algorithm (NSGA-II)-based optimization scheme to identify the Pareto solutions for which the ESC total profit is maximized and the disequilibrium among its agent's profits is minimized, while uncertainty is accounted for by Monte Carlo (MC) sampling. An oil and gas ESC model with five layers is considered to show the proposed framework and its capability of enabling efficient management of the ESC sustained production while considering the agent's uncertain interactions and the dynamically changing structure.

关键词： energy supply chain oil and gas supply chain multi-objective optimization agent-based modeling uncertainty structure dynamics Monte Carlo simulation non-dominated sorting genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

Development of a Hybrid Simulation Technology to Optimize Parameters of Multiple Power System Stabilizers 5

Development of a Hybrid Simulation Technology to Optimize Pa...

引用

5th Asia Conference on Power and Electrical Engineering (ACPEE)

作者： Zheng, Xiujie Wu, Ning Yi, Jianbo Univ Elect Sci & Technol China Chengdu Coll Chengdu Peoples R China Lanzhou Inst Technol Coll Comp & Artificial Intelligence Lanzhou Peoples R China Univ Elect Sci & Technol China Chengdu Peoples R China

ISBN: (纸本)9781728152813

Traditional power system simulation and analysis software cannot easily extend additional application technologies to combine data-intensive and multi-purpose advanced artificial intelligence computing methods. This paper studies the coordinated control of multiple Power System Stabilizers (PSSs) in the stability of complex power systems based on massive Power System Analysis Software Package (PSASP) simulation data. First, this paper proposes a multi-objective comprehensive objective function that considers the robustness and stability of multi-machine PSSs. Second, there employs PSASP transient simulation data to expand the multi-objective optimization algorithm with additional non-dominated sorting genetic algorithm (NSGA-II). Third, this paper develops a PSASP-MATLAB hybrid simulation technology to realize the global parameters optimization of multi-machine PSSs under the system transient simulation data of multi-operating modes.

关键词： hybrid simulation technology parameters optimization power system stabilizer power system analysis software package non-dominated sorting genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

Optimization on kinematic characteristics and lightweight of a camellia fruit picking machine based on the Kriging surrogate model

引用

MECHANICS & INDUSTRY 2021年第1期22卷

作者： Kang, Di Chen, Ze Jun Fan, You Hua Li, Cheng Mi, Chengji Tang, Ying Hong Hunan Acad Forestry Sci Changsha 410004 Peoples R China Hunan Univ Technol Dept Mech Engn Zhuzhou 412007 Peoples R China

In order to achieve fully automated picking of camellia fruit and overcome the technical difficulties of current picking machinery such as inefficient service and manual auxiliary picking, a novel multi-links-based picking machine was proposed in this paper. The working principle and process of this device was analyzed. The mechanism kinematics equation was given, and the velocity executive body was obtained, as well as the acceleration. The acceleration at pivotal positions was tested in the camellia fruit forest, and the simulated results agreed well with the experimental ones. Then, the maximum acceleration of executive body and weight was considered as the optimization objective, and the rotating speed of crank, the radius and thickness of crank and the length and radius of link rod were regarded as the design variable. Based on the Kriging surrogate model, the relationship between variables and optimization objectives was built, and their interrelations were analyzed. Finally, the optimal solution was acquired by the non-dominated sorting genetic algorithm II, which resulted in the reduction of the maximum acceleration of executive body by 31.30%, as well as decrease of weight by 27.51%.

关键词： Multi-links kinematic characteristics optimization design surrogate model non-dominated sorting genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

A Novel Grid-based Crowding Distance for Multimodal Multi-objective Optimization

A Novel Grid-based Crowding Distance for Multimodal Multi-ob...

引用

IEEE Congress on Evolutionary Computation (CEC) as part of the IEEE World Congress on Computational Intelligence (IEEE WCCI)

作者： Javadi, Mahrokh Ramirez-Atencia, Cristian Mostaghim, Sanaz Otto von Guericke Univ Fac Comp Sci Univ Pl 2 D-39106 Magdeburg Germany

ISBN: (纸本)9781728169293

Preserving diversity in decision space plays an important role in Multimodal Multi-objective Optimization problems (MMOPs). Due to the lack of mechanisms to keep different solutions with the same fitness value, most of the available Multi-objective Evolutionary algorithms (MOEAs) perform poorly when applied to MMOPs. To deal with these problems, this paper proposes a novel method for diversity preserving in the decision space. To this end, the concept of grid-based crowding distance for decision space is introduced. Furthermore, to keep a good diversity of solutions in both decision and objective spaces, we propose different frameworks by combining this method with crowding distance in decision space, crowding distance in objective space, and the weighted sum of both crowding distances. In order to evaluate the performance of these frameworks, we integrate them into the diversity preserving part of the NSGA-II algorithm, and compare them with the NSGA-II (as the baseline algorithm) and the state-of-the-art multimodal multi-objective optimization algorithms on ten different MMOPs with different levels of complexity.

关键词： Grid-based Crowding distance Multi modality Evolutionary algorithms non-dominated sorting genetic algorithm Multi-objective Optimization

来源：评论

学校读者我要写书评

暂无评论

Multi-Objective Optimisation of Multi-Output Neural Trees

Multi-Objective Optimisation of Multi-Output Neural Trees

引用

IEEE Congress on Evolutionary Computation (CEC) as part of the IEEE World Congress on Computational Intelligence (IEEE WCCI)

作者： Ojha, Varun Nicosia, Giuseppe Univ Reading Reading Berks England Univ Cambridge Cambridge England

ISBN: (纸本)9781728169293

We propose an algorithm and a new method to tackle the classification problems. We propose a multi-output neural tree (MONT) algorithm, which is an evolutionary learning algorithm trained by the non-dominated sorting genetic algorithm (NSGA)-III. Since evolutionary learning is stochastic, a hypothesis found in the form of MONT is unique for each run of evolutionary learning, i.e., each hypothesis (tree) generated bears distinct properties compared to any other hypothesis both in topological space and parameter-space. This leads to a challenging optimisation problem where the aim is to minimise the tree-size and maximise the classification accuracy. Therefore, the Pareto-optimality concerns were met by hypervolume indicator analysis. We used nine benchmark classification learning problems to evaluate the performance of the MONT. As a result of our experiments, we obtained MONTs which are able to tackle the classification problems with high accuracy. The performance of MONT emerged better over a set of problems tackled in this study compared with a set of well-known classifiers: multilayer perceptron, reduced-error pruning tree, naive Bayes classifier, decision tree, and support vector machine. Moreover, the performances of three versions of MONT's training using genetic programming, NSGA-II, and NSGA-III suggests that the NSGA-III gives the best Pareto-optimal solution.

关键词： Neural tree Multi-class classification multi-objective optimisation non-dominated sorting genetic algorithm NSGA-III

来源：评论

学校读者我要写书评

暂无评论

A Multiobjective Approach Applied to the Power System Reconfiguration Problem

A Multiobjective Approach Applied to the Power System Reconf...

引用

IEEE International Conference on Systems, Man, and Cybernetics (SMC)

作者： Viana, Enio Rodrigues Sousa, Aldir Silva Lira Rabelo, Ricardo de Andrade Fed Univ Piaui UFPI Dept Comp Sci Teresina Piaui Brazil State Univ Piaui UESPI Dept Comp Sci Teresina Piaui Brazil

ISBN: (纸本)9781728185262

This paper presents an efficient methodology based on Graph Theory for imposing the radial topology constraint in unfeasible solutions that appear in Evolutionary algorithms during the evolution of the optimal solution in Distribution Network Reconfiguration. To reach a better computational time, this paper also presents an effective Backward-Forward method to solve power flow in radial DS (RDS). The algorithm developed was tested in distribution systems With the well-known switch reduction problem to achieve a lower number of active power losses.

关键词： genetic algorithms multiobjective optimization non-dominated sorting genetic algorithm Power Distribution System Reconfiguration

来源：评论

学校读者我要写书评

暂无评论

Modeling the competing demands of carriers, building managers, and urban planners to identify balanced solutions for allocating building and parking resources

引用

TRANSPORTATION RESEARCH INTERDISCIPLINARY PERSPECTIVES 2022年 15卷

作者： Kim, Haena Goodchild, Anne Boyle, Linda Ng Univ Washington Dept Civil & Environm Engn Seattle WA 98195 USA Univ Washington Dept Ind & Syst Engn Seattle WA 98195 USA

While the number of deliveries has been increasing rapidly, infrastructure such as parking and building configurations has changed less quickly, given limited space and funds. This may lead to an imbalance between supply and demand, preventing the current resources from meeting the future needs of urban freight activities. The aim of this study was to discover the future delivery rates that would overflow the current delivery systems and find the optimal numbers of resources. To achieve this objective, we introduced a multi-objective, simulation-based optimization model to define the complex freight delivery cost relationships among delivery workers, building managers, and city planners, based on the real-world observations of the final 50 ft of urban freight activities at an office building in downtown Seattle, Washington, U.S.A. Our discrete-event simulation model with increasing delivery arrival rates showed an inverse relationship in costs between delivery workers and building managers, while the cost of city planners decreased up to ten deliveries/h and then increased until 18 deliveries/h, at which point costs increased for all three parties and overflew the current building and parking resources. The optimal numbers of resources that would minimize the costs for all three parties were then explored by a non-dominated sorting genetic algorithm (NSGA-2) and a multi-objective, evolutionary algorithm based on decomposition (MOEA/D). Our study sheds new light on a data-driven approach for determining the best combination of resources that would help the three entities work as a team to better prepare for the future demand for urban goods deliveries.

关键词： Urban freight Urban goods delivery Parking resource allocation Building infrastructure Urban freight simulation Multi-objective simulation-based optimization non-dominated sorting genetic algorithm

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：