检索结果-内蒙古大学图书馆

Improving the efficiency of microseismic source locating using a heuristic algorithm-based virtual field optimization method

引用

GEOMECHANICS AND GEOPHYSICS FOR GEO-ENERGY AND GEO-RESOURCES 2021年第3期7卷 1-18页

作者： Zhou, Jian Shen, Xiaojie Qiu, Yingui Li, Enming Rao, Dijun Shi, Xiuzhi Cent South Univ Sch Resources & Safety Engn Changsha 410083 Peoples R China Univ Politecn Madrid ETSI Minas & Energia Rios Rosas 21 Madrid 28003 Spain

Fast and accurate microseismic locating methods, such as the virtual field optimization method (VFOM), are increasingly used by researchers and mine management personnel. The VFOM can accurately locate a microseismic source under a large picking error. However, due to the complexity of the objective function of the VFOM, especially when a large number of sensors are involved, this method may require substantial time for the locating process. To overcome this problem, heuristic algorithms were used to increase the locating speed of the VFOM, and the performances of two heuristic algorithms (particle swarm optimization algorithm (PSO) and genetic algorithm (GA)) for the VFOM were evaluated. In general, the performances of these algorithms are affected by many factors, such as the Number of generations (NG) and Number of populations (NP). To enhance the performance of heuristic algorithms, a parameter tuning method was used to determine the relevant parameters for these algorithms. In contrast to the traditional gradient-based algorithm, heuristic algorithms can greatly improve the location efficiency of the VFOM with almost no loss of accuracy and can avoid falling into the local optimal value. The results showed that the PSO can provide better location accuracy and computational efficiency for the VFOM than those obtained with the GA. Furthermore, the VFOM and traditional methods were compared to discuss the influence of the number of sensors and positioning of the source on the location identification and the superiority of the VFOM-based location identification was verified.

关键词： Virtual field optimization method (VFOM) heuristic algorithm Microseism Geophysics Source location

来源：评论

学校读者我要写书评

暂无评论

Cost-location aware heuristic algorithm for hybrid SDN deployment

引用

ANNALS OF MATHEMATICS AND ARTIFICIAL INTELLIGENCE 2021年第8-9期89卷 875-897页

作者： Wei, Siew Hong Chin, Tan Saw Kwang, Lee Ching Multimedia Univ Fac Comp & Informat Cyberjaya Malaysia Multimedia Univ Fac Engn Cyberjaya Malaysia

Software-Defined Networking (SDN) has gained tremendous attention in the past few years for its advantages over network controllability. Nonetheless, the deployment of SDN in legacy network is likely to span multi-periods over months or years for budget consideration. Network operators, especially for a network consists of thousand or more nodes, are eager to understand how legacy networks can be deploying gradually towards SDN with variety of constraints. The reliability of network should be the utmost concern during SDN deployment in legacy network. Primarily, node exclusion is essential in SDN deployment process as the exclusion of critical node during the process greatly improves network stability and reliability. Therefore, we propose a heuristic algorithm for multi-periods SDN node migration in legacy network with respect to node exclusion and budget. We first formulate the aforementioned problem in Integer Linear Programming (ILP) model, and we evaluate the proposed ILP model and our proposed heuristic algorithm with regard to solution quality and processing time. The results show that our proposed algorithm maintains its overall correctness with O(N-2) polynomial time complexity. In addition to migration sequence computation, the results of our proposed algorithm reveal the impact of each node in SDN deployment as Key Node, Critical Node and Diminishing Return Analysis. These information offers better decision for network operator during hybrid SDN deployment. Ultimately, the results of our proposed algorithm offers valuable insight in which significantly reduce up to 83% of investment while reaping the most performance gain out of SDN deployment in legacy network.

关键词： Software-defined networking heuristic algorithm Hybrid SDN deployment Integer linear programming

来源：评论

学校读者我要写书评

暂无评论

A bi-level nested heuristic algorithm for divisional seru order acceptance and scheduling problems

引用

APPLIED SOFT COMPUTING 2023年 143卷

作者： Wang, Lili Zhang, Zhe Yin, Yong Nanjing Univ Sci & Technol Sch Econ & Management Nanjing 210094 Peoples R China Doshisha Univ Grad Sch Business Karasuma ImadegawaKamigyo Ku Kyoto 6028580 Japan

This paper focuses on the order acceptance and scheduling problem with worker-operation assignment considering the precedence constraint in the divisional seru production system, which is a new production type derived from Japan and can achieve responsiveness, flexibility, and efficiency simultaneously. With limited production capacity and workers with different skill sets and skill levels, the problem considered in this paper includes three sub-problems: (i) assigning workers to each seru, (ii) making the order acceptance and scheduling plan, and (iii) allocating workers to operations for each order. Subsequently, a nonlinear integer programming model is established for improving the total net revenue, and a bi-level nested heuristic algorithm is designed due to its intractable computation. Computational experiments are made finally, and results show that the objective value obtained by the bi-level nested heuristic algorithm is 3% better than the bi-level genetic algorithm, and the running time is shortened by 99.23%. That is, the proposed bi-level nested heuristic algorithm can achieve better results and higher efficiency for divisional seru order acceptance and scheduling problems. (c) 2023 Elsevier B.V. All rights reserved.

关键词： Divisional seru Order acceptance and scheduling Worker-operation assignment heuristic algorithm

来源：评论

学校读者我要写书评

暂无评论

Sequential data-driven carbon peaking path simulation research of the Yangtze River Delta urban agglomeration based on semantic mining and heuristic algorithm optimization

引用

ENERGY 2023年 285卷

作者： Zeng, Qingshun Shi, Changfeng Zhu, Wenjun Zhi, Jiaqi Na, Xiaohong Hohai Univ Sch Econ & Finance Changzhou 213200 Jiangsu Peoples R China Hohai Univ Business Sch Changzhou 213200 Peoples R China

In this paper, 41 prefecture level cities in the Yangtze River Delta (YRD) are selected as the research objects. Based on the semantic mining model, the policy data information from three dimensions namely national, provincial and municipal levels is integrated to build data-driven multiple scenarios. Then the long short-term memory neural network optimized by particle swarm optimization (PSO-LSTM) is further used to predict the peaking time of the YRD urban agglomeration under multiple scenarios. The results show that the YRD urban agglomeration as a whole can achieve carbon peaking on time under all three simulation paths, but the peaking situation of specific cities within the region will be significantly different due to differentiated policy orienta-tions. Under the business as usual scenario, some cities in the north of the region cannot achieve carbon peaking by 2030. Under the stable growth scenario, more cities cannot achieve carbon peaking on time. However, under the low carbon scenario, all cities within the region can achieve carbon peaking by 2030. Therefore, when exploring effective carbon peaking paths, adopting more stringent policies and measures to limit carbon emis-sions can help achieve the regional carbon peaking goal earlier, ensure that all cities within the region can achieve carbon peaking on time, and can also narrow the gap between cities within the region in terms of peaking time. This paper explores a new scenario analysis parameter setting and carbon emission prediction method, which overcomes the subjectivity of current scenario analysis research in parameter setting to a certain extent, and also provides a scientific reference for predicting the diversified development trend of carbon emission.

关键词： Semantic mining heuristic algorithm LSTM model Scenario analysis Carbon peaking prediction

来源：评论

学校读者我要写书评

暂无评论

A heuristic algorithm optimizing emergency resource storage and location in the South China Sea

引用

OCEAN ENGINEERING 2023年第1期268卷

作者： Wang, Yajie Fan, Jianchun Wu, Shengnan Yang, Yunpeng China Univ Petr Coll Safety Ocean Engn Fuxue Rd 18 Beijing 102249 Peoples R China Minist Emergency Management Key Lab Oil & Gas Safety & Emergency Technol Beijing Peoples R China CNPC Res Inst Safety & Environm Protect Technol Beijing 102206 Peoples R China

With the rapid growth of oil and gas field exploration projects in the South China Sea, there is an increase in operational incidents. It is of the utmost importance to optimize the allocation of limited emergency resources and establish a feasible humanitarian logistics rescue network for on-site operators. This paper proposes a multi -objective optimization model for the storage and location of logistical emergency assistance and rescue resources in the South China Sea. Three components comprise the proposed model: geographical environment impact, emergency rescue response time, and emergency resource allocation cost. In the first step, the Fuzzy Compre-hensive Evaluation Method (FCEM) is used to introduce and calculate the comprehensive impact index of the interference factors on the South China Sea storage candidate spots, which indicates the uncertainty ratio of the target sea influenced by the geographical environment. Consequently, we improve the expected reproduction rate (the possibility of generating storage points) in the Immune algorithm (IA), overcome the general optimi-zation process, suppress the concentration of emergency resource storage scheme, and form a new heuristic algorithm, the Improved Immune algorithm (IIA). Lastly, using a dataset of fire and explosion occurrences during oil and gas development in the South China Sea as an illustration, the effectiveness of the target model and the suggested method are estimated and confirmed. The IIA results indicate that, when different working environments and multi-level accidents are considered, the emergency response time is reduced by 83.71 percent compared to the current emergency resource supply system, and the emergency resource allocation cost is reduced by 1.2%-8.02% compared to the IA. It exhibits the feasibility and rationale of this method's site se-lection results in the specified special zone.

关键词： Location Multi -objective optimization heuristic algorithm Maritime rescue Logistic service

来源：评论

学校读者我要写书评

暂无评论

Numbering teeth in panoramic images: A novel method based on deep learning and heuristic algorithm

引用

ENGINEERING SCIENCE AND TECHNOLOGY-AN INTERNATIONAL JOURNAL-JESTECH 2023年 37卷

作者： Karaoglu, Ahmet Ozcan, Caner Pekince, Adem Yasa, Yasin Sinop Univ Dept Comp Technol Sinop Turkey Karabuk Univ Dept Software Engn Karabuk Turkey Karabuk Univ Dept Oral & Maxillofacial Radiol Karabuk Turkey Ordu Univ Dept Oral & Maxillofacial Radiol Ordu Turkey

Dental problems are one of the most common health problems for people. To detect and analyze these problems, dentists often use panoramic radiographs that show the entire mouth and have low radiation exposure and exposure time. Analyzing these radiographs is a lengthy and tedious process. Recent studies have ensured dental radiologists can perform the analyses faster with various artificial intelligence sup-ports. In this study, the numbering performance of Mask R-CNN and our heuristic algorithm-based method was verified on panoramic dental radiographs according to the Federation Dentaire Internationale (FDI) system. Ground-truth labelling of images required for training the deep learning algorithm was performed by two dental radiologists using the web-based labelling software DentiAssist created by the first author. The dataset was created from 2702 anonymized panoramic radio-graphs. The dataset is divided into 1747, 484, and 471 images, which serve as training, validation, and test sets. The dataset was validated using the k-fold cross-validation method (k = 5). A three-step heuristic algorithm was developed to improve the Mask R-CNN segmentation and numbering results. As far as we know, our study is the first in the literature to use a heuristic method in addition to traditional deep learning algorithms in detection, segmentation and numbering studies in panoramic radiography. The experimental results show that the mAp (@IOU = 0.5), precision, recall and f1 scores are 92.49%, 96.08%, 95.65% and 95.87%, respectively. The results of the learning-based algorithm were improved by more than 4%. In our research, we discovered that heuristic algorithms could improve the accuracy of deep learning-based algorithms. Our research will significantly reduce dental radiologists' workload, speed up diagnostic processes, and improve the accuracy of deep learning systems.(c) 2022 Karabuk University. Publishing services by Elsevier B.V. This is an open access article under the CC

关键词： Deep learning heuristic algorithm Mask R-CNN Panoramic radiographs Segmentation Numbering

来源：评论

学校读者我要写书评

暂无评论

Efficient heuristic algorithm for Precedence-Constrained Multi-Robot Task Assignment

Efficient Heuristic Algorithm for Precedence-Constrained Mul...

引用

第43届中国控制会议

作者： Xiaoshan Bai Baode Li Fuqiang Liu Li Qiu Guangzhong Cao College of Mechanical and Control Engineering Shenzhen University Guangdong Key Laboratory of Electromagnetic Control and Intelligent Robots Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen University College of Mechanical and Vehicle Engineering Chongqing University

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

Due to the widespread application of multi-robot systems, the efficient task assignment for a team of robots has become particularly critical for performing complex tasks. This paper studies the task assignment problem for multiple robots to visit a group of target locations with precedence constraints, which determine the order/sequence in which certain target locations need to be visited before others. A marginal-cost-based heuristic algorithm is developed to minimize the time for the robots to visit the last target location. The algorithm first uses a timestamp strategy to update the anticipated visiting time of each assigned target and the corresponding earliest time that each successor target can be visited under the precedence constraints. Then, it utilizes the topological sorting technique and the marginal-cost-based mechanism to insert the feasible target that induces the minimum marginal cost into the robots' current routes. Numerical simulations demonstrate the effectiveness of the proposed algorithm compared with the popular greedy algorithm and the existing simple iterative auction algorithm.

关键词： Multi-robot task assignment Precedence constraints heuristic algorithm Marginal cost

来源：评论

学校读者我要写书评

暂无评论

A heuristic algorithm for Robust Adaptive Beamforming Design With Nonconvex Uncertainty Sets

A Heuristic Algorithm for Robust Adaptive Beamforming Design...

引用

第43届中国控制会议

作者： Wenjing Xu Jinming Liu Jiao Mou Tingting Wang Enbin Song College of Mathematics Sichuan University Sichuan Aerospace Research Institute of Electronic Equipment China Aerospace Science and Technology Corporation

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

This paper considers a robust adaptive beamforming(RAB) design problem based on the worst-case signal-tointerference-plus-noise ratio(SINR) maximization,where the steering vector has a nonconvex uncertainty set consisting of a similarity constraint and a double-sided ball *** problem can be turned into a quadratic matrix inequality problem,and a linear matrix inequality relaxation is *** sufficient conditions are given to ensure the validity of strong duality and existence of a rank-one solution to the relaxation problem,*** with the perturbation method,we propose a heuristic algorithm to find an optimal/suboptimal solution to the original RAB ***,simulations demonstrate that the proposed method can improve the array output SINR.

关键词： Worst-case SINR maximization robust adaptive beamforming heuristic algorithm

来源：评论

学校读者我要写书评

暂无评论

Recursive heuristic algorithm for Balancing Mixed-Model Assembly Line Type-II in Stochastic Environment 7th

Recursive Heuristic Algorithm for Balancing Mixed-Model Asse...

引用

7th International Conference on Logistics and Supply Chain Management (LSCM)

作者： Aufy, Samah A. Kassam, AllaEldin H. Univ Technol Baghdad Prod Engn & Met Dept Baghdad Iraq

ISBN: (纸本)9783030897437;9783030897420

Straight assembly line and U-shaped assembly line usually required to be extended and updated in order to solve line balancing problems in the real-world based on computational intelligence. In the literature, most models are presented for solving assembly line balancing (ALBP) assume deterministic processing time. This paper is extended solving ALBP with the stochastic environment using fuzzy theory as one of the main pillars of computational intelligent, it's called "Worker-Task Stochastic Assigned toWorkstationheuristic" (W-TSAWH) is adopted. The framework can be structured by creating stochastic work environment (SWE) and assigning process. Firstly, SWEis adopted, with three fuzzy logic models as fuzzy skill level, fuzzy work stability and dynamic fuzzy processing time models. These models are used in order to represent uncertainty associated with task processing time in real assembly system. Secondly, a heuristic algorithm is developed to obtain best solution. The algorithm organized by sequence vector, and a mathematical model that assigns task and worker that subjected to some constraints into constant number of workstations to minimize cycle time. Finally, the performance validation of the methodology is proved using a numerical example.

关键词： Fuzzy logic Mixed-model assembly line heuristic algorithm Cycle time

来源：评论

学校读者我要写书评

暂无评论

A heuristic algorithm for Time-dependent Bus Scheduling Problem

A Heuristic Algorithm for Time-dependent Bus Scheduling Prob...

引用

IEEE International Conference on Industrial Engineering and Engineering Management (IEEM)

作者： Zhang, Yi Wang, Jiguang Liu, Xinglu Chan, Wai Kin (Victor) Li, Feng Li, Zhide Tsinghua Berkeley Shenzhen Inst Intelligent Transportat & Logist Syst Lab Shenzhen Peoples R China Shenzhen Intelligent Publ Transportat Technol Co Shenzhen Peoples R China Tsinghua Shenzhen Int Grad Sch Shenzhen Peoples R China

ISBN: (纸本)9781665437714

The travel time of buses is highly relevant to traffic conditions in real-world schemes. Typically, departing at different times will generally bring travel time changes for a given road segment, i.e., so-called time-dependent. Furthermore, over-flexible schedules are likely to be less satisfying for passengers. Thus, time-dependent-aware bus schedules are essential for bus operators to enhance practicability, resist uncertainty of traffic conditions. In this paper, a heuristic algorithm is developed to create a time-dependent bus schedule (i.e., timetables and fleet schedules). Based on a real dataset from the Shenzhen Eastern Bus company, we first generate initial timetables operating between two terminals, Base station, and Vice station, with respect to minimum trip counts requirements by the government. Assign operational tasks (i.e., timetable) to buses under consideration of time-dependent and fleet size, and then bus schedules are obtained. Results of numerical experiments reveal that our proposed algorithm can handle this problem efficiently.

关键词： Bus schedule Time-dependence heuristic algorithm Time table generation Bus operation

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：