检索结果-内蒙古大学图书馆

Modelling built-up expansion and densification with multinomial logistic regression, cellular automata and genetic algorithm

引用

COMPUTERS ENVIRONMENT AND URBAN SYSTEMS 2018年第Jan.期67卷 147-156页

作者： Mustafa, Ahmed Heppenstall, Alison Omrani, Hichem Saadi, Ismail Cools, Mario Teller, Jacques Univ Liege Urban & Environm Engn Dept LEMA Liege Belgium Purdue Univ Dept Comp Sci 305 N Univ St W Lafayette IN 47907 USA Univ Leeds Sch Geog Leeds W Yorkshire England LISER Urban Dev & Mobil Dept Luxembourg Luxembourg Univ Liege Allee Decouverte 9Quartier Polytech 1 B-4000 Liege Belgium

This paper presents a model to simulate built-up expansion and densification based on a combination of a non ordered multinomial logistic regression (MLR) and cellular automata (CA). 'The probability for built-up development is assessed based on (i) a set of built-up development causative factors and (ii) the land-use of neighboring cells. The model considers four built-up classes: non built-up, low-density, medium-density and high density built-up. Unlike the most commonly used built-up/urban models which simulate built-up expansion, our approach considers expansion and the potential for densification within already built-up areas when their present density allows it. The model is built, calibrated, and validated for Wallonia region (Belgium) using cadastral data. Three 100 x 100 m raster-based built-up maps for 1990, 2000, and 2010 are developed to define one calibration interval (1990-2000) and one validation interval (2000 2010). The causative factors are calibrated using MLR whereas the CA neighboring effects are calibrated based on a multi-objective genetic algoritlun. The calibrated model is applied to simulate the built-up pattern in 2010. The simulated map in 2010 is used to evaluate the model's performance against the actual 2010 map by means of fuzzy set theory. According to the findings, land-use policy, slope, and distance to roads are the most important determinants of the expansion process. The densification process is mainly driven by zoning, slope, distance to different roads and richness index. The results also show that the densification generally occurs where there are dense neighbors whereas areas with lower densities retain their densities over time.

关键词： Built-up density Cellular automata multinomial logistic regression multi-objective genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

Novel adaptive cyberattack prediction model using an enhanced genetic algorithm and deep learning (AdacDeep)

引用

INFORMATION SECURITY JOURNAL 2022年第1期31卷 105-124页

作者： Ibor, Ayei E. Oladeji, Florence A. Okunoye, Olusoji B. Uwadia, Charles O. Univ Calabar Dept Comp Sci Calabar Nigeria Univ Lagos Dept Comp Sci Lagos Nigeria

Some of the problems of extant cyberattack prediction approaches are low prediction accuracy, high false positive rate, very long training time, and the choice of hyperparameters to overcome overfitting or under fitting the model on the training data. These problems have culminated in the escalation of cyberattacks in recent times and as such significant improvement to the performance of extant models is crucial. Some deep learning architectures such as Recurrent Neural Networks (RNN) have been applied to cyberattack prediction. However, Recurrent Neural Networks (RNN) suffer from the vanishing and exploding gradient problem, and are difficult to train. Also, determining the different states and hyperparameters of the network for optimal prediction performance is difficult. Therefore, this paper proposes a novel approach called AdacDeep that uses an Enhanced genetic algorithm (EGA), Deep Autoencoder and a Deep Feedforward Neural Network (DFFNN) with backpropagation learning to accurately predict different attack types. The performance of AdacDeep is evaluated using two well-known datasets, namely, the CICIDS2017 and UNSW_NB15 datasets as the benchmark. The experimental results show that AdacDeep outperforms other state-of-the-art comparative models in terms of prediction accuracy with 0.22-35% improvement, F-Score with 0.1-34.7% improvement and very low false positive rate.

关键词： Deep learning multi-objective genetic algorithm cyberattack prediction information security network traffic

来源：评论

学校读者我要写书评

暂无评论

Designing a fuzzy sliding mode controller for a three-phase inverter via genetic algorithm

引用

INTERNATIONAL JOURNAL OF DYNAMICS AND CONTROL 2023年第5期11卷 2452-2465页

作者： Taran, Babak Mohajeri, Hamed Tarbiat Modares Univ Dept Mech Engn Jalal AleAhmad Highway POB 14115-111 Tehran Iran Univ Zanjan Dept Elect Zanjan Iran

In a three-phase inverter, if the electricity consumers' loads are not equal, balance will be disturbed and switching will be challenged. To overcome this problem, herein, a fuzzy sliding mode control is proposed to control the output voltages of a three-phase inverter. Control methods for commanding IGBTs have advantages over methods such as PWM and SVM as the effect of errors and uncertainties is neutralized by measuring the output error. Sliding mode control has long been used to control systems with uncertainty in modeling. This controller is robust because they provide sliding conditions by generating discontinuous control signals around the sliding surface. Despite these advantages, sliding mode control has its drawbacks. A popular method to solve these problems is fuzzy control, which promotes controller performance. In addition to paying attention to reducing the output error in inverters, changes in the state of switches should also be considered. In practice, the power loss increases and the inverter efficiency decreases, with increasing the disconnection and reconnection of IGBTs. In the present study, a multi-objective genetic algorithm is used so as to select the optimal control coefficients, in such a way that a compromise is made between the error and the number of times the keys are connected and disconnected.

关键词： Three-phase inverter Sliding mode control Fuzzy control multi-objective genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

Optimizing the Geometrical Dimensions of the Seat Suspension Equipped with a Negative Stiffness Structure Based on a genetic algorithm

引用

SAE INTERNATIONAL JOURNAL OF VEHICLE DYNAMICS STABILITY AND NVH 2022年第2期6卷 147-158页

作者： Zha, Jili Nguyen, Vanliem Ni, Dengke Su, Beibei Hubei Polytech Univ Sch Mech & Elect Engn Huangshi Hubei Peoples R China Hubei Polytech Univ Hubei Key Lab Intelligent Conveying Technol & Dev Huangshi Hubei Peoples R China

Based on the negative stiffness structure (NSS) designed on the seat suspension and the effect of the geometrical parameters of the designed NSS on improving the driver's ride comfort, a new optimal method of the multi-objective genetic algorithm (MOGA) is then researched and applied for optimizing the stiffness ratio beta of the seat suspension and the geometrical parameters alpha(1) and alpha(2) of the NSS to further improve the driver's ride comfort and health. The reduction of the root-mean-square (RMS) displacement of the driver's seat (X-RMSs), the weighted RMS acceleration of the driver's seat (a(RMSs)), and the seat effective amplitude transmissibility (SEAT) of the seat suspension are chosen as the objective functions. The study results show that with the optimal parameters of alpha(1) = 1.355, alpha(2) = 1.001, and beta = 0.511, the seat suspension using the optimized NSS has a good effect on isolating low-frequency vibration under various excitation sources of the random, harmonic, and bumpy functions. Particularly, the results of X-RMSs, a(RMSs), and SEAT with the optimized NSS are remarkably reduced by 13.35%, 22.51%, and 22.47%, respectively, compared to the designed NSS, and by 44.65%, 69.45%, and 69.44% in comparison without the NSS under a random excitation of the floor of the cab or vehicle. Therefore, this research results not only contribute to the existing body of knowledge on the seat suspensions equipped with the NSS but also can provide an important reference for optimal design or control of the seat suspension to further improve its isolating efficiency.

关键词： Seat dynamic model Negative stiffness structure Ride comfort multi-objective genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

A non-dominated sorting genetic algorithm for a bi-objective pick-up and delivery problem

引用

ENGINEERING OPTIMIZATION 2012年第3期44卷 305-325页

作者： Velasco, N. Dejax, P. Gueret, C. Prins, C. Univ Los Andes Dept Ingn Ind Bogota Colombia Ecole Mines Nantes UMR 6597 IRCCyN F-44307 Nantes 3 France Univ Technol Troyes FRE 2848 ICD F-10010 Troyes France

Some companies must transport their personnel within facilities. This is especially the case for oil companies that use helicopters to transport engineers, technicians and assistant personnel from platform to platform. This operation has the potential to become expensive if the transportation routes are not correctly planned and provide a bad quality of service. Here this issue is modelled as a pick-up and delivery problem where a set of transportation requests should be scheduled in routes, minimizing the total transportation cost while the most urgent requests are satisfied by priority. To solve the problem, a method based on a Non-dominated Sorting genetic algorithm (NSGA-II) is proposed. This algorithm is tested on both randomly generated and real instances provided by a petroleum company. The results show that the proposed algorithm improves the best-known solutions.

关键词： routing pick-up and delivery personnel transportation non-dominated sorting algorithm multi-objective genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

Redesigning a Supply Chain Distribution Network: Formulation and genetic algorithm-Based Solution Procedure

引用

INTERNATIONAL JOURNAL OF INFORMATION TECHNOLOGY & DECISION MAKING 2015年第4期14卷 847-876页

作者： Zhou, Lina Xu, Xiaofei Deng, Shengchun Liu, Xudong Harbin Inst Technol Sch Software Harbin 150006 Heilongjiang Peoples R China Harbin Inst Technol Sch Comp Sci & Technol Harbin 150006 Heilongjiang Peoples R China

Distribution affects company cost and customer satisfaction. Distribution network design is a strategic concern for nearly all companies, and must be periodically reviewed to ensure fitness to today's rapidly changing business environment. Unlike most of previous research, this paper investigates a highly complicated and realistic distribution network, and develops a multi-objective model to achieve an effective redesign solution. Reconfiguring cost, service differentiation, multiple products, and optional capacity levels are simultaneously considered. A determinant code-based encoding structure is designed to represent the complicated multi-objective optimization problem, and a genetic algorithm (GA)-based procedure is developed as a solution. The paper provides an application example using actual data. Finally, a comparison between the empirical results and those of the Prufer-based GA demonstrate the efficiency of the proposed GA.

关键词： Distribution network customer service level multi-objective genetic algorithm determinant code

来源：评论

学校读者我要写书评

暂无评论

genetic algorithm INTEGRATED SLIDING MODE CONTROL OF A VEHICLE 11

GENETIC ALGORITHM INTEGRATED SLIDING MODE CONTROL OF A VEHIC...

引用

11th World Congress on Computational Mechanics (WCCM) / 5th European Conference on Computational Mechanics (ECCM) / 6th European Conference on Computational Fluid Dynamics (ECFD)

作者： Ozer, Hasan O. Sayin, Alaattin Korkmaz, Nuray Yagiz, Nurkan Istanbul Univ Vocat Sch Tech Sci Programme Air Conditioning & Refrigerat Technol TR-34320 Istanbul Turkey Istanbul Univ Vocat Sch Tech Sci Programme Biomed Equipment Tech TR-34320 Istanbul Turkey Istanbul Univ Fac Engn Dept Mech Engn TR-34320 Istanbul Turkey

ISBN: (纸本)9788494284472

The main propose of suspension systems is to isolate car body motion from the road excitations and improve the ride comfort. Hence, to control of suspension system is important both comfort and road holding. The aim of this study is to design Sliding Mode Controller tuned by genetic algorithm (GA) for providing smooth vertical motion of car body. Sliding mode control (SMC) has been used in many mechanical and structural systems due to its robustness, simplicity and high control performance. However, tuning optimum controller parameters for systems is still an important research area. The proposed SMC parameters have been tuned by GA with several fitness functions to get better dynamic performance. The vehicle model is excited by random road data. Then, simulation results of uncontrolled and GA integrated sliding mode controllers models are compared. The results show that vehicle model with SMC tuned by GA is effective to decrease the effects of road induced vibrations.

关键词： Sliding Mode Controller genetic algorithm multi-objective genetic algorithm Vehicle Model Simulation of Vehicle Vibrations

来源：评论

学校读者我要写书评

暂无评论

Proactive Project Scheduling in an R&D Department A Bi-objective genetic algorithm 5

Proactive Project Scheduling in an R&D Department A Bi-Objec...

引用

2015 International Conference on Industrial Engineering and Operations Management (IEOM)

作者： Capa, Canan Ulusoy, Gunduz Concordia Univ Mech & Ind Engn Montreal PQ Canada Sabanci Univ Mfg Syst Engn Istanbul Turkey

ISBN: (纸本)9781479960651

In this paper, we present part of a study on stochastic, dynamic project scheduling in an R&D Department of a leading home appliances company in Turkey. The problem under consideration is the preemptive resource constrained multi-project scheduling problem with generalized precedence relations in a stochastic and dynamic environment. The model consists of three phases. Phase I of the model provides a systematic approach to assess uncertainty resulting in activity deviation distributions. In Phase II, proactive project scheduling is accomplished through two different scheduling approaches, which employ a bi-objective genetic algorithm. Phase III is the reactive project scheduling phase aiming at rescheduling the disrupted project activities. Here, we will limit our presentation to Phase II-the proactive project scheduling phase. The procedure is demonstrated through an implementation with real data covering 37 R&D projects. Computational study is performed to compare the two different scheduling approaches called single and multi-project scheduling approaches, as well as two different chromosome evaluation heuristics. Results are presented and discussed.

关键词： Proactive project scheduling multi-objective genetic algorithm R&D

来源：评论

学校读者我要写书评

暂无评论

Hybrid genetic-Fuzzy algorithm for Variable Selection in Spectroscopy

Hybrid Genetic-Fuzzy Algorithm for Variable Selection in Spe...

引用

12th International Conference on Artificial Intelligence and Soft Computing, ICAISC 2013

作者： de Lima, Telma Woerle Soares, Anderson da Silva Coelho, Clarimar Jose Salvini, Rogerio Lopes Laureano, Gustavo Teodoro Univ Fed Goias Inst Informat Goiania Go Brazil Pontifical University Catholic Goias Dept Comp Sci Goiania Go Brazil

ISBN: (纸本)9783642386091

This paper presents a hybrid multi-objective genetic fuzzy algorithm for the variable-selection problem in spectroscopy. The problem formulation considers three fitness functions related to linear equations system stability. These fitness functions are models with fuzzy sets that evaluate the fitness solution for pick out the best to crossover. The population diversity is obtained applying the crowding distance method. The study shows that the selection by a fuzzy decision has better results than the selection by non-domination in problems where the fitness weighing is more proper than no-domination solutions.

关键词： multi-objective genetic algorithm Fuzzy logic Variable Selection

来源：评论

学校读者我要写书评

暂无评论

An Efficient genetic algorithm for Subgraph Isomorphism 12

An Efficient Genetic Algorithm for Subgraph Isomorphism

引用

14th International Conference on genetic and Evolutionary Computation Conference (GECCO)

作者： Choi, Jaeun Yoon, Yourim Moon, Byung-Ro Seoul Natl Univ Sch Comp Sci & Engn Seoul 151744 South Korea

ISBN: (纸本)9781450311779

In this paper we propose a multi-objective genetic algorithm for the subgraph isomorphism problem. Usually, the number of different edges between two graphs has been used as a fitness function. This approach has limitations in that it only considers directly-visible characteristics of current solutions, not considering the potential for being an optimal solution. We designed a fitness function in which solutions with higher potential can be rated high. This new fitness function has good properties such as transforming the solution space globally convex and improving the performance of local heuristics and genetic algorithms. Experimental results show that the suggested approach brings a considerable improvement in performance and efficiency.

关键词： genetic algorithm subgraph isomorphism fitness function multi-objective 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：