检索结果-内蒙古大学图书馆

An evacuation model based on co-evolutionary multi-particle swarms optimization for pedestrian-vehicle mixed traffic flow

引用

INTERNATIONAL JOURNAL OF MODERN PHYSICS C 2017年第12期28卷 1750142-1750142页

作者： Zong, Xinlu Wang, Chunzhi Chen, Hongwei Hubei Univ Technol Sch Comp Sci & Technol Wuhan 430068 Hubei Peoples R China

In a large common place, a huge number of pedestrians may flood into the surrounding region and mix with the vehicles which originally existed on the roads when emergent events occur. The mutual restriction between pedestrians and vehicles as well as the mutual effect between evacuation individuals and the environment which evacuees are situated in, will have an important impact on evacuation effects. This paper presents a pedestrian-vehicle mixed evacuation model to produce optimal evacuation plans considering both evacuation time and density degree. A co-evolutionary multi-particle swarms optimization approach is proposed to simulate the evacuation process of pedestrians and vehicles separately and the interaction between these two kinds of traffc modes. The proposed model and algorithm are effective for mixed evacuation problems. An illustrating example of a study region around a large stadium has been presented. The experimental results indicate the effective performances for evacuation problems which involve complex environments and various types of traffic modes.

关键词： Mixed evacuation pedestrian particle swarm optimization algorithm co-evolution pheromone

来源：评论

学校读者我要写书评

暂无评论

A greedy algorithm versus metaheuristic solutions to deadlock detection in Graph Transformation Systems

引用

JOURNAL OF INTELLIGENT & FUZZY SYSTEMS 2016年第1期31卷 137-149页

作者： Yousefian, Rosa Aboutorabi, Shahryar Rafe, Vahid Islamic Azad Univ Khomeinishahr Branch Sama Tech & Vocatinal Training Coll Esfahan Iran Arak Univ Dept Comp Engn Fac Engn Arak *** Iran

Nowadays, using model checking techniques is one of the best solutions for software (and hardware) verification. The problem while using model checking techniques is state space explosion in which all the available memory is consumed by the model checker to generate all the reachable states. Among different approaches to cope with the state space explosion problem, using heuristic and meta-heuristic algorithms seems a proper solution. Although in all of these approaches it is not possible to solve the problem totally, however, it is possible to use them as refutation techniques. In the meta-heuristic techniques it is tried to generate only a portion of the state space with the highest probability to reach a faulty state. In this paper, we propose two new algorithms to deadlock detection in complex software systems specified through graph transformation systems. The first approach is a hybrid algorithm using PSO and BAT (BAPSO) and the second one is a greedy algorithm to find deadlocks. The experimental results show that the hybrid approach (BAPSO) is more accurate than PSO, BAT and other existing approaches like Genetic algorithm (GA). In addition, in most of the case studies, the proposed greedy algorithm can compete with the meta-heuristic algorithms in terms of speed and accuracy.

关键词： State space explosion model checking Graph Transformation Systems genetic algorithm BAT algorithm particle swarm optimization algorithm greedy algorithm

来源：评论

学校读者我要写书评

暂无评论

Measurement, evaluation and minimization of CO₂, NO_x, and CO emissions in the open time dependent vehicle routing problem

引用

MEASUREMENT 2016年 90卷 443-452页

作者： Naderipour, Mansoureh Alinaghian, Mahdi Isfahan Univ Technol Dept Ind & Syst Engn Esfahan *** Iran

In this paper, a new comprehensive model has been presented for the measurement, evaluation and minimization of CO2, NOx and CO as three important emissions (emitted from vehicles) in the open time dependent vehicle routing problem (OTDVRP). In the OTDVRP, traffic properties of congested regions like city centers are considered. Travel time between two points depends on the time of departure, and the vehicles do not come back to the depot. In some distribution companies, vehicles are rental;therefore, they do not come back to the depot from the last customer. To solve the proposed problem, an improved particle swarm optimization algorithm is developed. The results show good performance in computation experiments compared to original PSO algorithm. The results of the experiments show that considering minimization, the pollutants can reduce emissions by 16% on the average compared to the classical open TDVRP. Factors causing the variation in emissions are also identified and discussed in this study. (C) 2016 Elsevier Ltd. All rights reserved.

关键词： Air pollution Transportation Environmental emissions Green open time dependent vehicle routing problem particle swarm optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

A novel classification method: A hybrid approach based on extension of the UTADIS with polynomial and PSO-GA algorithm

引用

APPLIED SOFT COMPUTING 2016年 49卷 56-70页

作者： Esmaelian, Majid Shahmoradi, Hadi Vali, Masoumeh Univ Isfahan Dept Management Hezarjerib StAzadi Sq Esfahan Iran Persian Gulf Univ Dept Management Bushehr 75168 Iran

In this study, a new multi-criteria classification technique for nominal and ordinal groups is developed by expanding the UTilites Additives DIScriminantes (UTADIS) method with a polynomial of degree T which is used as the utility function rather than using a piecewise linear function as an approximation of the utility function of each attribute. We called this method as PUTADIS. The objective is calculating the coefficients of the polynomial and the threshold limit of classes and weight of attributes such that it minimizes the number of misclassification error. Estimation of unknown parameters of the problem is calculated by using a hybrid algorithm which is a combination of particle swarm optimization algorithm (PSO) and Genetic algorithm (GA). The results obtained by implementing the model on different datasets and comparing its performance with other previous methods show the high efficiency of the proposed method. (C) 2016 Elsevier B.V. All rights reserved.

关键词： Classification Utility function UTADIS method Genetic algorithm particle swarm optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

On the Localization algorithm of Wireless Sensor Network and Its Application

引用

INTERNATIONAL JOURNAL OF ONLINE ENGINEERING 2017年第3期13卷 40-51页

作者： Jia, Honglei Zheng, Jiaxin Wang, Gang Chen, Yulong Huang, Dongyan Yuan, Hongfang Jilin Univ Coll Biol & Agr Engn Changchun 130022 Peoples R China Jilin Univ Minist Educ Key Lab Bion Engn Changchun 130022 Peoples R China

This paper carries out in-depth and meticulous analysis of the DV-Hop localization algorithm for wireless sensor network. It improves the DV-Hop algorithm into a node localization algorithm based on one-hop range, and proposes the centroid particle swarm optimization localization algorithm based on RSSI by adding the RSSI and particle swarm optimization algorithm to the traditional centroid localization algorithm. Simulation experiment proves that the two algorithms have excellent effect.

关键词： DV-Hoplocalization algorithm WSN localization one-hop RSSI particle swarm optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

A simple and quick control strategy for a class of first-order nonholonomic manipulator

引用

NONLINEAR DYNAMICS 2016年第4期85卷 2261-2276页

作者： Lai, Xu-Zhi Wang, Ya-Wu Cao, Jun-Qing Wu, Min China Univ Geosci Sch Automat Wuhan 430074 Hubei Peoples R China Cent S Univ Sch Informat Sci & Engn Changsha 410083 Hunan Peoples R China

This paper presents a simple and quick control strategy for a class of first-order nonholonomic manipulator: planar n-link manipulator with a passive first joint (no gravity). The control target is driving its endpoint from any initial position to any target position. First, we reduce the planar n-link manipulator to a planar three-link one by maintaining the states (angles and angular velocities) of n-3 active links in the initial value all the time. That is, we only adjust the states of the remaining two active links in the whole control process, and these two adjusted active links are chosen to guarantee that the target position is in the reachable region of the planar n-link manipulator by using the enumeration method. Then, we divide the whole control process into two stages for the reduced planar three-link manipulator. In each stage, the manipulator becomes a planar two-link one by maintaining the states of one adjusted active link to be the constant value. The state constraint existing between the passive first link and the adjusted active link is obtained by using the integral characteristics of a planar two-link manipulator. Meantime, the geometric constraint between the position of the endpoint and angles of all joints is obtained based on the homogeneous coordinate transformation method. According to the above two kinds of constraint, the target angles of the two adjusted active links are calculated by employing the particle swarm optimization algorithm. When the two adjusted active links are controlled to their target angles in turn, the control target of the planar n-link manipulator is completed. Finally, simulation results demonstrate that the proposed control strategy is valid and rapid.

关键词： Underactuated manipulator Nonholonomic constraint Enumeration method particle swarm optimization algorithm Lyapunov function

来源：评论

学校读者我要写书评

暂无评论

Prediction of the temperature in a Chinese solar greenhouse based on LSSVM optimized by improved PSO

引用

COMPUTERS AND ELECTRONICS IN AGRICULTURE 2016年 122卷 94-102页

作者： Yu, Huihui Chen, Yingyi Hassan, Shahbaz Gul Li, Daoliang China Agr Univ Coll Informat & Elect Engn Beijing 100083 Peoples R China Minist Agr Key Lab Agr Informat Acquisit Technol Beijing 100083 Peoples R China Beijing Engn & Technol Res Ctr Internet Things Ag Beijing 100083 Peoples R China

Predictions of the Chinese solar greenhouse temperatures are important because they play a vital role in greenhouse cultivation, with solar greenhouse crops susceptible to potential losses because of cold and hot temperatures. Therefore, it is important to set up a precise predictive model of temperature that can predict the occurrence of temperatures several hours before head to reduce financial losses. This paper presents a novel temperature prediction model based on a least squares support vector machine (LSSVM) model with parameters optimized by improved particle swarm optimization (IPSO). The IPSO with probability of mutation was employed to optimize the required hyper parameters of the LSSVM model. The performance of the IPSO-LSSVM model was compared with traditional modeling approaches by applying it to, predict solar greenhouse temperatures, and the results showed that its predictions of the maximum and minimum temperature were more accurate than those of the standard support vector machine (SVM) and Back propagation neural network (BPNN). Therefore, it is a suitable and effective method for predicting the Chinese solar greenhouse temperatures. (C) 2016 Elsevier B.V. All rights reserved.

关键词： Greenhouse Temperature Predictions Least squares support vector machine particle swarm optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Application of improved support vector regression model for prediction of deformation modulus of a rock mass

引用

ENGINEERING WITH COMPUTERS 2016年第4期32卷 567-580页

作者： Fattahi, Hadi Arak Univ Technol Dept Min Engn Arak Iran

Deformation modulus of a rock mass is one of the crucial parameters used in the design of surface and underground rock engineering structures. Determination of this parameter by testing cylindrical core samples is almost impossible due to the presence of discontinuities. Due to the problems in determining the deformability of jointed rock masses at the laboratory-scale, various in situ test methods such as plate loading tests, dilatometer etc. have been developed. Although these methods are currently the best techniques, they are expensive and time-consuming, and present operational problems. To overcome this difficulty, in this paper, presents the results of the application of hybrid support vector regression (SVR) with harmony search algorithm , differential evolution algorithm and particle swarm optimization algorithm (PSO). The optimized models were applied to available data given in open source literature and the performance of optimization algorithm was assessed by virtue of statistical criteria. In these models, rock mass rating (RMR), depth, uniaxial compressive strength of intact rock (UCS) and elastic modulus of intact rock (E (i)) were utilized as the input parameters, while the deformation modulus of a rock mass was the output parameter. The comparative results revealed that hybrid of PSO and SVR yield robust model which outperform other models in term of higher squared correlation coefficient (R (2)) and variance account for (VAF) and lower mean square error (MSE), root mean squared error (RMSE) and mean absolute percentage error (MAPE).

关键词： Deformation modulus Support vector regression Harmony search algorithm Differential evolution algorithm particle swarm optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

MULTI-OBJECTIVE optimization OF INTEGRATED LOT-SIZING AND SCHEDULING PROBLEM IN FLEXIBLE JOB SHOPS

引用

RAIRO-OPERATIONS RESEARCH 2016年第3期50卷 587-609页

作者： Rohaninejad, Mohammad Sahraeian, Rashed Nouri, Behdin Vahedi Shahed Univ Dept Ind Engn Fac Engn Tehran Iran Bu Ali Sina Univ Dept Ind Engn Fac Engn Hamadan Iran

This paper investigates a particular integrated lotsizing and scheduling problem in a multilevel multi-product, multi-machine and flexible routes environment that is called flexible job shop problem (FJSP). The considered problem involves making simultaneous decision in sequencing operations, sizing lots and assigning machines to operations in order to optimize a multi-objective function including minimizing sum of the system costs, total machines workload and makespan, while a given demand is fulfilled without backlogging. Due to the complexity of the problem, a hybrid meta-heuristic based on a combination of Genetic algorithm and particle swarm optimization algorithm is developed to solve it. Additionally, the Taguchi method is employed to calibrate the influential parameters of the meta-heuristic and boost its capabilities. Finally, the performance of the proposed algorithm is compared with some well-known multi-objective algorithms such as NSGAII, SPEA2 and VEGA. Regarding to the computational results, the hybrid algorithm surpasses the other algorithms in the closeness of solutions to pareto optimal front and diversity criteria.

关键词： Lot-sizing scheduling flexible job shop genetic algorithm particle swarm optimization algorithm TOPSIS

来源：评论

学校读者我要写书评

暂无评论

Multi-objective opportunistic maintenance optimization of a wind farm considering limited number of maintenance groups

引用

RENEWABLE ENERGY 2016年 88卷 247-261页

作者： Abdollahzadeh, Hadi Atashgar, Karim Abbasi, Morteza Malek Ashtar Univ Technol Dept Ind Engn Tehran 158751774 Iran

Several different models provided by researchers to maintain a wind turbine, but most of these models only focused on the case involved a single objective optimization problem. In practice, real cases of wind farms lead to multi-objective approach to optimize maintenance efforts. In this paper, based on an opportunistic approach, a multi-objective based model is proposed to optimize the maintenance of a farm involved several different types of wind turbines. The assumptions of stochastic behavior of wind velocity as well as the existence of a limited number for maintenance groups are also considered in this new approach. The proposed model considering imperfect maintenance, attempts (1) maximizing the expected rate of energy and (2) minimizing the total expected costs related to maintenance efforts. The opportunistic approach is also provided by the component's reliability threshold values. The comparative analysis addresses that the capability of the proposed model is more efficient compared to models addressed in literature. (C) 2015 Elsevier Ltd. All rights reserved.

关键词： Opportunistic maintenance Wind farm Three-phase simulation Imperfect maintenance Multi-objective particle swarm optimization 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：