检索结果-内蒙古大学图书馆

Churn Prediction Using Mathematical Programming via a Linear Classification algorithm

Mathematical Models and Computer Simulations 2024年第3期16卷 504-519页

作者： Barhdadi, Mohamed Benyacoub, Badreddine Ouzineb, Mohamed National Institute for Statistics and Applied Economics Rabat Morocco

Abstract: The initial idea in developing customer churn prediction was to use statistical analysis of a sample of previous customers to help operators predict which existing customers were likely migrate to other operators. In this paper, a nonstatistical approach to this problem can also be envisaged by formulating the problem as a linear program. The main concept of our proposed algorithm is to hybridize the Jackknife resampling technique with an efficient heuristic based on a variable neighborhood search algorithm to construct a new approach that can present an alternative to black-box machine learning methods. The goal is to find possible solutions (or weights) to minimize error distances and the number of misclassified points. We tested the suggested algorithm with an imbalanced instance and the comparisons show that the proposed model outperforms the most existing machine learning classifiers, both in terms of the solution quality and the execution time. The numerical results indicate that the best solution is achieved in 85% over G-mean of all instances tested. The average gap between our solution and the best solution is still quite small (1.15%). © Pleiades Publishing, Ltd. 2024. ISSN 2070-0482, Mathematical Models and Computer Simulations, 2024, Vol. 16, No. 3, pp. 504–519. Pleiades Publishing, Ltd., 2024.

关键词： customer churn prediction linear classification mathematical modeling resampling technique variable neighborhood search algorithm

来源：评论

学校读者我要写书评

暂无评论

Routing Design and Departure Time Determination of Customized Buses Based on Reserved Trip Request 7

Routing Design and Departure Time Determination of Customize...

引用

IEEE 7th International Conference on Intelligent Transportation Engineering (ICITE)

作者： Cheng, Zhuxuan Xiong, Jie Li, Tongfei Chen, Yanyan Minist Transport Key Lab Technol Intelligent Transportat Syst Beijing Peoples R China Beijing Univ Technol Beijing Key Lab Traff Engn Beijing 100124 Peoples R China

ISBN: (纸本)9781665460071

This paper investigates an integrated optimization problem of routing design and departure time determination of customized buses based on demand-responsive service. The problem aims to optimize both a set of customized routes and the departure time of each route based on a set of reserved trip requests. A mixed integer programming model is formulated to address the problem. The model aims to minimize the sum of the operator cost of the bus company and the total travel cost of passengers so that the buses can be efficiently used to provide high-quality services to passengers. To solve the model, a departure time determination method based on a time window backpropagation process is first proposed to optimize the bus departure time for a given route. Then a variable neighborhood search (VNS) algorithm with customized operators is designed to generate the optimized routes. Finally, different numerical tests are conducted to verify the effectiveness of the proposed model and the algorithm, then the sensitivity analysis on key parameters follows.

关键词： customized bus routing design departure time determination variable neighborhood search algorithm

来源：评论

学校读者我要写书评

暂无评论

A Memetic algorithm for Constrainted Weapon Target Assignment Problems 2

A Memetic Algorithm for Constrainted Weapon Target Assignmen...

引用

2nd IEEE International Conference on Computational Intelligence and Applications (ICCIA)

作者： Wang, Jun Luo, Pengcheng Zhou, Jinglun Natl Univ Def Technol Coll Informat Syst & Management Changsha Hunan Peoples R China

ISBN: (纸本)9781538620304

The goal of weapon target assignment (WTA), which is one of the classic military operational problems, is to determine the best assignment scheme in order to gain the most benefit while satisfying a number of constraints deriving from the capability of available platforms and munitions (or weapons), as well as target characteristics. In order to overcome the drawbacks of premature convergence of exiting heuristic algorithms, this paper proposes a memetic algorithm (MA) which combines an adaptive genetic algorithm (AGA) with a variable neighborhood search algorithm (VNSA) to balance the exploitation ability and exploration ability. In the framework of MA, AGA is used for wide scope search while VNSA for local search. The simulation result proves the effectiveness and feasibility of the proposed MA, and through a comparison analysis, advantages of the algorithm over the adaptive genetic algorithm, the immune genetic algorithm and the standard genetic algorithm are revealed.

关键词： weapon target assignment memetic algorithm adaptive genetic algorithm variable neighborhood search algorithm

来源：评论

学校读者我要写书评

暂无评论

A two-phase algorithm for the Sequential Vehicle Routing Problem with Cross Docking (SVRPCD)

A two-phase algorithm for the Sequential Vehicle Routing Pro...

引用

作者：馬荷心元智大學

学位级别：碩士

Today’s customer-driven economic environment shifts from “supply chain” to “demand chain”. To successfully compete, companies are faced with the challenge of minimizing inventory and reducing warehouse costs whenever possible while keeping retailers’ shelves full. Cross Docking is a strategy whose ability to reduce lead times, control inventory carrying costs and deliver just-in-time service with a minimal investment makes it an attractive option for many companies responding to economic pressures. In a cross docking strategy, warehouses and distribution centers serve as transfer points for inventory, but no inventory is held at these transfer points. One of the keys to keeping a Cross Docking facility synchronized is to design a system and schedule that are obtainable, taking into account travel times and expectations for how much freight will actually fit on a truck; therefore, Vehicle Routing should be *** research examines a Vehicle Routing Problem with Cross Docking (VRPCD) considering cross docking operational characteristics such as assignment restrictions, deadlines and door environment. A sequential operational VRPCD model is presented. Its objective is to determine the best route that minimizes operational costs of shipment, and the minimum operational cost within the cross docking facility.A two-phase algorithm using variable neighborhood search (VNS) has been proposed. The experimental results show that the VNS algorithm is capable of finding good solutions in a much shorter computation time when compared with Gurobi Optimizer solutions. Good quality of solutions is obtained in all the experiments developed.

关键词： Cross Docking Vehicle Routing Problem variable neighborhood search algorithm

来源：评论

学校读者我要写书评

暂无评论

Integrated optimization of truck appointment quotas and container relocations for multiple blocks considering transshipment containers handling

引用

ADVANCED ENGINEERING INFORMATICS 2024年 62卷

作者： Duan, Shuang Zheng, Hong-Xing Wang, Zhao-Yang Dalian Maritime Univ Coll Transportat Engn Dalian 116026 Peoples R China

The container terminal is a crucial transshipment node in the sea and land cargo transport supply chain, and the efficiency of container collection and distribution has always been a research hotspot. In this paper, we consider the impact of transshipment containers resulting from various uncertainties and integrate the operations of external truck pickups with the handling of transshipment containers in the import yard of the container terminal. In light of the varying number of transshipment containers and transit times for different blocks, coupled with the unpredictable arrival order of external trucks leading to the unknown number of relocations, it is proposed to dynamically adjust the upper limit of the appointed quota for each block. We establish a two stage mixed integer programming model for the truck appointment quota and the block relocation problem. The objective functions aim to minimize the number of relocations and minimize the number of yard crane moves under the maximal appointment quota, respectively. This model is utilized for dynamically regulating the upper limit of the appointed quota for each block and determining the time intervals for picking up the appointed and transshipment containers, along with the yard crane scheduling scheme. The problem is solved using CPLEX and the improved variable neighborhood search algorithm (IVNS). The IVNS incorporates the correction strategy, decoding strategy, and scheduling rules designed to align closely with the characteristics of the problem. Through scheme comparison and sensitivity analysis, five management insights are proposed for terminals. Experimental results demonstrate that the approach presented in this paper effectively enhances the utilization efficiency of yard cranes, reduces yard congestion, and yields benefits for both terminals and trucking companies.

关键词： Truck appointment quota Transshipment container Yard crane Scheduling Block relocation variable neighborhood search algorithm

来源：评论

学校读者我要写书评

暂无评论

A MULTI-OBJECTIVE APPROACH TO HOME HEALTH CARE ROUTING PROBLEM WITH TEAM FORMATION

引用

INTERNATIONAL JOURNAL OF INDUSTRIAL ENGINEERING-THEORY APPLICATIONS AND PRACTICE 2023年第5期30卷 1150-1168页

作者： Bektur, Gulcin Nenbhard, David Univ Iowa Dept Ind & Syst Engn Iowa City IA 52242 USA Iskenderun Tech Univ Dept Ind Engn Hatay Turkiye Harvey Mudd Coll Dept Engn Claremont CA 91711 USA

Home health care (HHC) services provide the elderly, disabled, and those with chronic diseases health services in their homes. The demand for HHC services has increased due to the growth of the elderly population, the increase in hospital occupancy rates during the pandemic, and developments in medical device technologies. In this study, team formation is taken into consideration in a multi-period and multi-objective HHC assignment, scheduling and routing problem. The team and the assigned patients to this team must be compatible with skill levels and operational requirements. The objective functions are minimization of total completion time and maximum working time overall caregivers. To evaluate our approach, an HHC service unit in a state hospital is adopted as the operational scenario, and we propose a multi-objective mathematical model to solve the problem. In this model, HHC teams are formed, the patients are assigned to the teams, and the route of each team is determined in an integrated manner. The variable neighborhood search algorithm is modified to solve the multi-objective optimization model and is improved with a local search algorithm. The proposed algorithm has been compared with the stateof-the-art multi-objective algorithms in the literature over test problems. Current results show that the model to be an effective means of estimating and predicting system behavior in this complex environment.

关键词： home health care routing problem team formation multi-period multi-objective mathematical model variable neighborhood search algorithm

来源：评论

学校读者我要写书评

暂无评论

Solution approaches for the integrated production and outbound distribution scheduling problem with multiple plants and perishable items

引用

EXPERT SYSTEMS WITH APPLICATIONS 2024年第PartC期237卷

作者： Atasagun, Gozde Can Karaoglan, Ismail Konya Tech Univ Fac Engn & Nat Sci Dept Ind Engn TR-42250 Konya Turkiye

In this manuscript, we consider the integrated production and outbound distribution system in which there are several geographically dispersed facilities. These facilities are responsible for producing and delivering timesensitive customer demands. We propose a mixed integer programming (MIP) formulation, MIP with an initial solution using Clarke and Wright (MIPCW) and a metaheuristic algorithm (variable neighborhood search-VNS) for the problem whose objective is to minimize the maximum delivery time whereby satisfying all customer demands. We conduct a two-stage experimental study to determine the effectiveness of the proposed metaheuristic algorithm. We compare the VNS algorithm with the best-known solutions for the single plant version of the problem, in the first stage. These results indicate that the VNS algorithm yields promising results. The second stage includes the results for the MIP formulation and the VNS algorithm on a set of newly generated test instances. The average percentage gap between the VNS algorithm and the MIPCW formulation is about 5% which means that the VNS algorithm gives better results in average about 70 s computation time. These results show how effective the suggested VNS algorithm is at solving the test instances.

关键词： Time -sensitive products Machine scheduling Vehicle routing problem Mixed integer programming formulation variable neighborhood search algorithm

来源：评论

学校读者我要写书评

暂无评论

A novel robust model for location-allocation of healthcare facilities considering pre-disaster and post-disaster characteristics

引用

SCIENTIA IRANICA 2023年第2期30卷 619-641页

作者： Alinaghian, M. Hejazi, S. R. Bajoul, N. Velni, K. Sadeghi Isfahan Univ Technol Dept Ind & Syst Engn Esfahan *** Iran Univ Tehran Fouman Fac Engn Dept Ind Engn Fouman Iran

Healthcare centers are one of the most important municipal facilities that are responsible for providing personal and social health. Locating medical centers is an important strategy to improve the performance of these facilities and reduce any delay in the relief process. During disasters, these centers play a critical role in reducing the risk of human casualties. In this regard, the current study aims to establish a new robust mathematical model to simultaneously locate and allocate healthcare facilities, including different levels of medical care services, considering the characteristics in normal and disaster situations. Further, to help victims and prevent overcrowding at medical centers during disasters, establishment of temporary and outpatient centers was suggested for emergency provision of basic services. In addition, the possibility of delivering the needed equipment and medical teams to these centers was incorporated in the proposed modeling. To solve the problem, two metaheuristic algorithms, harmony search algorithm and hybrid tabu search combined with variable neighborhood search algorithm, and a lower bound based on Lagrangian relaxation method were employed. To assess the performance of the proposed algorithms, sample problems were randomly generated. The results obtained from the exact solutions and lower bound from the Lagrangian relaxation method were compared with those from the meta-heuristic algorithms, confirming the good performance of the proposed algorithms. (c) 2023 Sharif University of Technology. All rights reserved.

关键词： Health management system Network reliability Hierarchical healthcare facility Location problem Robust optimization variable neighborhood search algorithm Harmony search algorithm

来源：评论

学校读者我要写书评

暂无评论

A simulation-based metro train scheduling optimization incorporating multimodal coordination and flexible routing plans

引用

TRANSPORTATION REsearch PART C-EMERGING TECHNOLOGIES 2023年 146卷

作者： Wang, Xingrong Lv, Ying Sun, Huijun Xu, Guangtong Qu, Yunchao Wu, Jianjun Beijing Jiaotong Univ Inst Transportat Syst Sci & Engn Key Lab Transport Ind Big Data Applicat Technol Co Minist Transport Beijing 100044 Peoples R China Beijing Jiaotong Univ State Key Lab Rail Traff Control & Safety Beijing 100044 Peoples R China

The promotion of multimodal coordination is of great significance to the joint development of diversified urban transportation systems. Focusing on an urban comprehensive passenger trans-port hub (UCPTH) that converges both inter-city modes and multiple inner-city modes, this study aims to customize a bridging metro train operation plan with the utilization of multimodal passenger simulation. A bi-objective integer nonlinear programming model (INLP) incorporating train schedule and flexible routing plan is proposed to minimize passenger waiting time and operating costs simultaneously. Notably, a real-time flow prediction method based on Monte Carlo simulation and queuing network system is proposed and embedded in the optimization model framework to reflect the difference of individual passengers' transfer walking time and thereby provide detailed passenger distribution on the platform for metro hub stations connecting UCPTH. Compared with the estimation using historical data, this method can particularly support the scheduling coordination of metro and other modes during an abrupt change of arrival flows. Moreover, to solve the collaborative optimization model tractably, the epsilon-constraint method based on a tailored variable neighborhood search algorithm is developed to generate approximate Pareto optimal solutions, including the number of effective trains, demand-sensitive headway, the route pattern of each effective train, and train dwell time. Finally, two sets of numerical exper-iments, including a small-scale case and a real-world hub-metro network instance are conducted to demonstrate the effectiveness of the proposed approaches. The study associated with the findings can benefit both metro providers and users especially those who need to transfer to the metro system at hubs by achieving the best match between passenger and train flows in temporal and spatial domains.

关键词： Metro train schedule Multimodal coordination Flexible routing plans Passenger simulation variable neighborhood search algorithm

来源：评论

学校读者我要写书评

暂无评论

A decision model on human-robot collaborative routing for automatic logistics

引用

ADVANCED ENGINEERING INFORMATICS 2022年 53卷

作者： Zhu, Shengyan Wang, Huiwen Zhang, Xiaoqin He, Xueting Tan, Zheyi Yibin Univ Sanjiang Res Inst Artificial Intelligence & Robot Yibin Sichuan Peoples R China Shanghai Univ Sch Management Shanghai Peoples R China

This paper studies an integrated human-robot routing problem arising in collaborative order picking systems. Travelling routes of pickers and robots interact with each other and simultaneously determine the start time of tasks. A mixed-integer programming model is proposed which aims to minimize the total task completion time by optimizing both pickers' and robots' routes. Moreover, a variable neighborhood search and dynamic programming -based heuristic algorithm is developed for solving the problem in large-scale environments. Numerical experiments are conducted to prove the necessity of the proposed model and also validate the efficiency of the proposed heuristic algorithm. The results indicate the methodology can yields solutions with smaller optimality gap within a reasonable period of time, in comparison with an intuitive but common decision rule. A sensitivity analysis is also conducted to derive a number of managerial implications regarding the configuration of pickers and robots and robots' speed setting.

关键词： Order picking system Human -robot collaborative environment Autonomous mobile robots Vehicle routing problem variable neighborhood search algorithm Dynamic programming

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：