检索结果-内蒙古大学图书馆

62nd IEEE Conference on Decision and Control (CDC)

作者： Luo, Naifu Wang, Hongjian Huang, Shuang Gao, Wei Zhong, Bo Huang, Yutong Li, Benyin Harbin Engn Univ Coll Intelligent Syst Sci & Engn Harbin Heilongjiang Peoples R China Wuhan Second Ship Design & Res Inst Wuhan Hubei Peoples R China

ISBN: (纸本)9798350301243

Aiming at the problems of scattered distribution, irregular shape, short underwater warning distance, limited carrying capacity of offshore islands and the inability for long term garrison, unmanned underwater vehicle (UUV) is used to search and explore the unknown underwater area near those islands. With the constraints on number of available UUVs, detection ability and energy consumption, a task planning framework of cooperative search and exploration mission of multi-UUV is urgently required. Meanwhile, in each round of task assignment, the most current algorithm could not dynamically assign the different task to corresponding UUV. For instance, the location and state of each UUV could be different during the searching and exploration process. In this paper, regarding the off-shore islands and reefs as the defense base, the models of UUV and its forward looking sonar are constructed, and a multi-UUV cooperative regional search and exploration algorithm is proposed based on multiobjective genetic algorithm (MGA). Aiming at the irregular distribution of targets in the search area and the different proportion of targets found by each UUV in their allocated search areas, we designed a multi-UUV dynamic cooperative (MDC) task planning method based on MGA to accomplish the multi-UUV dynamic scheduling. Finally, the underwater simulation environment is designed to simulate the distribution of offshore islands and reefs. The effectiveness of proposed MGA regional search and exploration algorithm and MDCMGA task planning method is verified from the aspects of platform scale, time consumption and total distance of roadmap on regional search and exploration.

关键词： Multi-UUV evolutionary computing Optimization algorithm Task planning

来源：评论

学校读者我要写书评

暂无评论

Traffic Optimization by Local Bacterial Memetic Algorithm 15th

Traffic Optimization by Local Bacterial Memetic Algorithm

引用

15th International Conference on Computational Collective Intelligence (ICCCI)

作者： Kovacs, Szilard Barta, Zoltan Botzheim, Janos Eotvos Lorand Univ Pazmany P Setany 1-A H-1117 Budapest Hungary

ISBN: (纸本)9783031414558;9783031414565

Transport is an essential part of our lives. Optimizing transport provides significant economic and life quality improvements. Real-time traffic optimization is possible with the help of a fast communication network and decentralized sensing in smart cities. There are several analytical and simulation-based methods for traffic optimization. Analytical solutions usually look at more straightforward cases, while simulations can also consider the behavior of individual drivers. This article focuses on optimization methods and provides efficient traffic control based on simulations. The optimization goal is to find the proper sequence and timings of traffic light signals to ensure maximum throughput. In the article only the waiting time is selected as optimization criterion, but with knowledge of the vehicle stock (fuel type, fuel consumption, startstop settings, number of passengers, etc.) it can be easily expanded to multi-objective optimization. In the literature, there are many optimization solutions, but all have some disadvantages mainly the scalability and the connectivity. Bacterial evolutionary algorithm and hill climbing algorithm are proposed in this paper with special area operators for the traffic optimization task. The developed memetic optimization algorithm can be efficiently scaled to optimize the traffic of even large cities. The method is efficient and well parallelized for real-time optimization use. For this study, a part of the city is examined in a SUMO simulation environment. The simulation result shows that our scalable memetic algorithm outperforms the currently applied methods by 35-45%.

关键词： traffic control memetic algorithm scalable optimization smart city evolutionary computing

来源：评论

学校读者我要写书评

暂无评论

A novel threshold score based multiclass segmentation technique for brain magnetic resonance images using adaptive opposition slime mold algorithm

引用

INTERNATIONAL JOURNAL OF IMAGING SYSTEMS AND TECHNOLOGY 2022年第4期32卷 1397-1413页

作者： Naik, Manoj Kumar Panda, Rutuparna Samantaray, Leena Abraham, Ajith Siksha O Anusandhan Fac Engn & Technol Bhubaneswar Odisha India Veer Surendra Sai Univ Technol Dept Elect & Telecommun Engn Burla 768018 Odisha India Ajay Binay Inst Technol Dept Elect & Commun Engn Cuttack Odisha India Sci Network Innovat & Res Excellence Machine Intelligence Res Labs Auburn WA USA Innopolis Univ Ctr Artificial Intelligence Innopolis Russia

Clinicians can detect diseases early, thanks to the digital image processing methodologies, which improve health together with the treatment experience. The technology of magnetic resonance imaging (MRI) is frequently employed in the brain, research for any kind of related illness. The brain MR image requires precise automated thresholding for a meaningful representation to aid doctors, because of its different modalities and complexity. The majority of the threshold selection strategies are based on entropy. However, these strategies are limited by their reliance on the spatial distribution of gray values. There is also a pressing need to develop a thresholding technique that is independent of the spatial distribution, making it more suitable for a variety of modalities and complexity, such as the brain MR images. A novel non-entropic maximizing objective function for the multilevel thresholding approach using a threshold score (TS) is presented in this paper, to address these concerns. An evolutionary TS-AOSMA approach, using the optimizer called adaptive opposition slime mold algorithm (AOSMA), is suggested to lower the computational cost of TS-based multiclass segmentation, which is a novel idea. The proposed approach is evaluated on T2-weighted brain MR imaging slices from Harvard Medical School's whole brain atlas dataset. When compared to the state-of-the-art Kapur's, Tsallis, and Masi entropy-based technologies, the proposed scheme offered better quantitative and qualitative outcomes. The recommended strategies may be useful in medical image analysis.

关键词： brain MR image evolutionary computing multilevel thresholding slime mold algorithm

来源：评论

学校读者我要写书评

暂无评论

GPU implementation of evolving spiking neural P systems

引用

NEUROcomputing 2022年 503卷 140-161页

作者： V. Gungon, Rogelio Hernandez, Katreen Kyle M. Cabarle, Francis George C. De la Cruz, Ren Tristan A. Adorna, Henry N. Martinez-del-Amor, Miguel A. Orellana-Martin, David Perez-Hurtado, Ignacio Univ Philippines Diliman Dept Comp Sci Quezon City 1101 Philippines Univ Seville Dept Comp Sci & Artificial Intelligence Seville 41012 Spain Univ Seville Res Inst Comp Engn I3US Smart Comp Syst Res & Engn Lab SCORE Seville 41012 Spain ETS Ingn Informat Dept Ciencias Comp & Inteligencia Artificial Avda Reina Mercedes S-N Seville 41012 Spain

Methods for optimizing and evolving spiking neural P systems (in short, SN P systems) have been previously developed with the use of a genetic algorithm framework. So far, these computations, both evolving and simulating, were done only sequentially. Due to the non-deterministic and parallel nature of SN P systems, it is natural to harness parallel processors in implementing its evolution and simulation. In this work, a parallel framework for the evolution of SN P Systems is presented. This is the result of extending our previous work by implementing it on a CUDA-enabled graphics processing unit and adapting CuSNP design in simulations. Using binary addition and binary subtraction with 3 different categories each as initial SN P systems, the GPU-based evolution runs up to 9x faster with respect to its CPU-based evolution counterparts. Overall, when considering the whole process, the GPU framework is up to 3 times faster than the CPU version.(c) 2022 The Author(s). Published by Elsevier B.V. This is an open access article under the CC BY license (http://***/licenses/by/4.0/).

关键词： Membrane computing Spiking neural P systems Genetic algorithm evolutionary computing GPU computing CUDA

来源：评论

学校读者我要写书评

暂无评论

Building Information Modeling Steered by evolutionary computing

引用

JOURNAL OF computing IN CIVIL ENGINEERING 2014年第4期28卷 05014003-05014003页

作者： Rafiq, M. Y. Rustell, M. J. Univ Plymouth Sch Marine Sci & Engn Reynolds Bldg Plymouth PL4 8AA Devon England Univ Surrey Ctr Environm Strategy Guildford GU2 7XH Surrey England

In recent years, there has been a surge in the use of building information modeling (BIM) within construction. Much of the previous published research focuses on the impact of BIM during the detailed design, construction, and postconstruction stages. This paper combines the search and exploration powers of evolutionary computing with BIM during the conceptual stage of design. The main contribution of this paper is a methodology to integrate solutions generated by the interactive and visual clustering genetic algorithm (IVCGA) into a BIM environment to enhance the design information and allow the solutions to be viewed in greater detail as building information models. These models can then be utilized or modified by individual members of the design team to aid in the selection of concept designs that appropriately meet client/design requirements. An Autodesk Revit plug-in application has been developed that enables the IVCGA solution to be transformed into a building information model in a common repository. Using this approach during the conceptual design stage can potentially enhance multidisciplinary decision-making capacity by allowing a wide range of concept designs to be assessed in high detail with more accurate costing prior to committing a large sum of funding to the project (C) 2014 American Society of Civil Engineers.

关键词： Building information modeling evolutionary computing Genetic algorithm Interactive visualization Multidisciplinary optimization

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Adaptive Genetic Algorithm Based T-S Fuzzy Controller For Non-linear Automotive Applications

引用

INTERNATIONAL JOURNAL OF FUZZY SYSTEMS 2022年第1期24卷 607-621页

作者： Abdelrahim, Elsaid Md Tanta Univ Fac Sci Tanta Egypt Northern Border Univ Fac Sci Ar Ar Saudi Arabia

In this paper, a robust and enhanced evolutionary computing assisted Takagi Sugeno (T-S) fuzzy controller was developed for automotive fuel injection control. To augment the rule generation and fuzzy parameter estimation, we propose an enhanced evolutionary computing algorithm named Hierarchical Adaptive Genetic Algorithm (HAGA). The proposed HAGA model was applied to augment T-S fuzzy controller that in conjunction with Fuzzy Clustering Mean (FCM) has enabled optimal rule generation and control parameter estimation. The proposed HAGA model exploits Hierarchical concept-based AGA implementation that itself embodies novelties like adaptive crossover and mutation probability, to enable accurate, swift, and efficient control function by T-S Fuzzy controller. These novelties strengthen the proposed HAGA-TS fuzzy controller to exhibit time efficient and accurate control function that could be of utmost significance for non-linear process control. The proposed controller design is examined for its efficacy over automotive or vehicle data containing fuel injection rate, throttle angle, emission products etc., where considering current emission and/or torque requirements, the throttle angle is varied to achieve environmentally friendly and cost-efficient vehicle design. The simulation results revealed that the proposed HAGA TS-fuzzy controller outperforms other state of art evolutionary computing-based approaches such as GA, PSO based T-S fuzzy controller.

关键词： Takagi-Sugeno fuzzy system Non-linear control Vehicle fuel injection control Torque control evolutionary computing Adaptive Genetic Algorithm

来源：评论

学校读者我要写书评

暂无评论

Improved Levenberg-Marquardt backpropagation neural network by particle swarm and whale optimization algorithms to predict the deflection of RC beams

引用

ENGINEERING WITH COMPUTERS 2022年第SUPPL 5期38卷 3847-3869页

作者： Zhao, Jue Hoang Nguyen Trung Nguyen-Thoi Asteris, Panagiotis G. Zhou, Jian Hunan Univ Technol & Business Inst Big Data & Internet Innovat Changsha 410205 Peoples R China Hunan Univ Technol & Business Coll Comp & Informat Engn Changsha 410205 Peoples R China Duy Tan Univ Inst Res & Dev Da Nang 550000 Vietnam Ton Duc Thang Univ Inst Computat Sci Div Computat Math & Engn Ho Chi Minh City Vietnam Ton Duc Thang Univ Fac Civil Engn Ho Chi Minh City Vietnam Sch Pedag & Technol Educ Computat Mech Lab Athens 14121 Greece Cent South Univ Sch Resources & Safety Engn Changsha 410083 Hunan Peoples R China

The aim of this study is to develop a novel computer-aided method for the prediction of the deflection of reinforced concrete beams (DRCB) under concentrated loads. To this end, in the present work, a Levenberg-Marquardt-based backpropagation novel neural network model, optimized by the whale optimization algorithm (WOA), called WOA-LMBPNN, has been developed. Specifically, a neural network, using the Levenberg-Marquardt backpropagation training algorithm with multiple hidden layers, was optimized by the WOA, aiming to obtain higher accuracy in predicting DRCB. For the training of the models, 120 experiments with the geometrical and mechanical properties of concrete beams were compiled using were used as the input parameters. Seven datasets with different number of input variables were investigated to evaluate the effect of the input variables on DRCB. For comparison purposes, another swarm optimization algorithm (i.e., particle swarm optimization-PSO) was also used to optimize the LMBPNN model (i.e., PSO-LMBPNN model). The results obtained by the PSO-LMBPNN and WOA-LMBPNN models are then compared based on the different datasets. Finally, the results revealed the effective role of the WOA, as well as the efficiency and robustness of the new hybrid WOA-LMBPNN model in predicting DRCB.

关键词： Reinforced concrete beam evolutionary computing Artificial intelligence Smart structures Neural network computing Computer-aided method

来源：评论

学校读者我要写书评

暂无评论

Proof of Swarm Based Ensemble Learning for Federated Learning Applications 23

Proof of Swarm Based Ensemble Learning for Federated Learnin...

引用

38th Annual ACM Symposium on Applied computing (ACM SAC)

作者： Raza, Ali Kim Phuc Tran Koehl, Ludovic Li, Shujun Univ Lille ENSAIT GEMTEX Genie & Mat Text ULR 2461 Lille France Univ Kent Inst Cyber Secur Soc iCSS Canterbury Kent England Univ Kent Sch Comp Canterbury Kent England

ISBN: (纸本)9781450395175

Ensemble learning combines results from multiple machine learning models in order to provide a better and optimised predictive model with reduced bias, variance and improved predictions. However, in federated learning it is not feasible to apply centralised ensemble learning directly due to privacy concerns. Hence, a mechanism is required to combine results of local models to produce a global model. Most distributed consensus algorithms, such as Byzantine fault tolerance (BFT), do not normally perform well in such applications. This is because, in such methods predictions of some of the peers are disregarded, so a majority of peers can win without even considering other peers' decisions. Additionally, the confidence score of the result of each peer is not normally taken into account, although it is an important feature to consider for ensemble learning. Moreover, the problem of a tie event is often left un-addressed by methods such as BFT. To fill these research gaps, we propose PoSw (Proof of Swarm), a novel distributed consensus algorithm for ensemble learning in a federated setting, which was inspired by particle swarm based algorithms for solving optimisation problems. The proposed algorithm is theoretically proved to always converge in a relatively small number of steps and has mechanisms to resolve tie events while trying to achieve sub-optimum solutions. We experimentally validated the performance of the proposed algorithm using ECG classification as an example application in healthcare, showing that the ensemble learning model outperformed all local models and even the FL-based global model.

关键词： Privacy federated learning ensemble consensus protocol evolutionary computing swarm algorithms healthcare

来源：评论

学校读者我要写书评

暂无评论

Local scour depth at piles group exposed to regular waves: On the assessment of expressions based on classification concepts and evolutionary algorithms

引用

RESULTS IN ENGINEERING 2024年 21卷

作者： Najafzadeh, Mohammad Sheikhpour, Razieh Grad Univ Adv Technol Dept Water Engn POB 76315117 Kerman Iran Ardakan Univ Fac Engn Dept Comp Engn POB 184 Ardakan Iran

An accurate estimation of local scour depth around piles group is inevitably essential to provide stability of marine structures. Over the past decades, many investigations have been made to understand the scouring process at piles group exposed to waves for field and experimental scales. This study aims to predict the wave-induced local scour depth by various robust Data Driven Models (DDMs) and Machine Learning Models (MLMs) developed by classification and evolutionary concepts: Model Tree (MT), evolutionary Polynomial Regression (EPR), Multivariate Adaptive Regression Spline (MARS), and Gene-Expression Programming (GEP). From relevant literature, 125 data series were employed to provide empirical relationships for scour depth predictions. The raw variables were related to bed sediment, pile configuration, pile geometry, approaching flow, and wave characteristics. Non-dimensional parameters have been obtained through the Buckingham theorem in order to control local scour depth. In this way, the ratio of spacing between piles to pile diameter (G/D), sediment number (N-s), pile arrangement number (ratio of the number of piles parallel to the flow;m;to the number of piles normal to the flow;n), Shields parameter (theta), and Keulegan-Carpenter (KC) were considered. From the training and testing stages of Artificial Intelligence Models (AIMs), it was found that regression equation given by MARS model provided better performance (e.g., Correlation Coefficient [R] = 0.9297, Root Mean Square Error [RMSE] = 0.3489, and Scatter Index [SI] = 0.2765) than other AI models' efficiency. Additionally, the performance of AI models was assessed for various ranges of dimensionless parameters (i.e., G/D, N-s, and theta) versus KC variation. MARS model had the best performance for G/D = 0-1 and KC < 10 (R = 0.9917 and RMSE = 0.2198) and 0.4 <=theta < 0.5 and 15 < KC < 25 whereas EPR model had promising efficiency in the its highest level for N-s = 1-3 and 10 < KC <= 15 (R = 0.9941 an

关键词： evolutionary computing Classification Keulegan-carpenter number Piles group Scouring assessment Piles arrangement

来源：评论

学校读者我要写书评

暂无评论

A Search for Nonlinear Balanced Boolean Functions by Leveraging Phenotypic Properties

A Search for Nonlinear Balanced Boolean Functions by Leverag...

引用

Genetic and evolutionary Computation Conference (GECCO)

作者： Gasperov, Bruno Durasevic, Marko Jakobovic, Domagoj Univ Zagreb Fac Elect Engn & Comp Zagreb Croatia

ISBN: (纸本)9798400701207

In this paper, we consider the problem of finding perfectly balanced Boolean functions with high non-linearity values. Such functions have extensive applications in domains such as cryptography and error-correcting coding theory. We provide an approach for finding such functions by a local search method that exploits the structure of the underlying problem. Previous attempts in this vein typically focused on using the properties of the fitness landscape to guide the search. We opt for a different path in which we leverage the phenotype landscape (the mapping from genotypes to phenotypes) instead. In the context of the underlying problem, the phenotypes are represented byWalsh-Hadamard spectra of the candidate solutions (Boolean functions). We propose a novel selection criterion, under which the phenotypes are compared directly, and test whether its use increases the convergence speed (measured by the number of required spectra calculations) when compared to a competitive fitness function used in the literature. The results reveal promising convergence speed improvements for Boolean functions of sizes N = 6 to N = 9.

关键词： Boolean functions local search phenotype landscape Walsh-Hadamard Transform evolutionary computing mutation

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：