Proceedings of the Genetic and Evolutionary Computation Conference Companion最新文献

筛选
英文 中文
Exploration of unknown environments via evolution of behavioral and morphological properties of miniaturized sensory agents 探索未知的环境,通过进化的行为和形态特性的小型化感官
Proceedings of the Genetic and Evolutionary Computation Conference Companion Pub Date : 2022-07-09 DOI: 10.1145/3520304.3528991
Cagatay Sariman, Ahmed Hallawa, Erdi Sayar, A. Peine, Lukas Martin, A. Schmeink
{"title":"Exploration of unknown environments via evolution of behavioral and morphological properties of miniaturized sensory agents","authors":"Cagatay Sariman, Ahmed Hallawa, Erdi Sayar, A. Peine, Lukas Martin, A. Schmeink","doi":"10.1145/3520304.3528991","DOIUrl":"https://doi.org/10.1145/3520304.3528991","url":null,"abstract":"In this work, we propose a framework to evolve morphology and behavior of resource-constrained miniaturized sensory agents. One key application of this framework is the exploration of unknown environments. Consequently, we demonstrate its ability to solve multi-objective optimization problem by applying it to an environment exploration task. The goal is to find the position of a pollution source in a U-shaped fluid pipe with unknown fluid dynamics properties. Firstly, morphological evolution is set to find the optimal physical shape for an agent so that it passes through six target points inside the pipe, i.e. it follows a certain trajectory. Based on that, behavioral evolution optimizes then the sensor controller of an agent and tries to solve a Pareto-optimization problem where the objectives are (1) to measure accurately chemical particle concentrations, (2) to measure depth of the agent while in the environment and (3) to minimize power consumption while using the sensors by altering their operation frequencies. We executed 24000 simulations and the best agent hit the target points with accuracy 91% and reached the maximum performance possible in first and second objectives while reducing the power usage by 86.6%, compared to fixed frequency rate.","PeriodicalId":216331,"journal":{"name":"Proceedings of the Genetic and Evolutionary Computation Conference Companion","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114105562","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Comparison of evolutionary multi-objective optimization algorithms using imitation game 基于模仿博弈的进化多目标优化算法比较
Proceedings of the Genetic and Evolutionary Computation Conference Companion Pub Date : 2022-07-09 DOI: 10.1145/3520304.3528768
Yuji Sato, Yoshihisa Murakawa
{"title":"Comparison of evolutionary multi-objective optimization algorithms using imitation game","authors":"Yuji Sato, Yoshihisa Murakawa","doi":"10.1145/3520304.3528768","DOIUrl":"https://doi.org/10.1145/3520304.3528768","url":null,"abstract":"In this paper, we consider the artificial bird song imitation game as dynamic two objective optimization problem and propose it as the benchmark problem that includes a wide variety of transitions. We have evaluated the speed of evolution towards the edge of chaos using NSGA-II and SPEA2 which are representative evolutionary multi-objective optimization algorithms based on Pareto dominance. As a result, we show that our proposed method is effective, and NSGA-II is better than SPEA2 in convergence speed. We also show that the solution tends to converge around the median of the edge of chaos and the chaos region, as compared with the conventional imitation game using the single objective evolutionary algorithm.","PeriodicalId":216331,"journal":{"name":"Proceedings of the Genetic and Evolutionary Computation Conference Companion","volume":"109 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122816393","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Efficient configuration of optimization algorithms 高效配置优化算法
Proceedings of the Genetic and Evolutionary Computation Conference Companion Pub Date : 2022-07-09 DOI: 10.1145/3520304.3534078
M. D. Souza, M. Ritt, Manuel López-Ibáñez
{"title":"Efficient configuration of optimization algorithms","authors":"M. D. Souza, M. Ritt, Manuel López-Ibáñez","doi":"10.1145/3520304.3534078","DOIUrl":"https://doi.org/10.1145/3520304.3534078","url":null,"abstract":"We propose a set of capping methods to speed-up the automatic configuration of optimization algorithms. First, we build a performance envelope based on previous executions of known configurations, which defines the minimum required performance for new configurations. Then, we use the performance envelope to evaluate new configurations, stopping poor performers early. We propose different methods to aggregate previous executions into a performance envelope, and evaluate them on several configuration scenarios. The proposed methods produce solutions of the same or better quality as configuring without capping, but reduce the effort required to configure optimization algorithms. This manuscript for the Hot-Off-the-Press track at GECCO 2022 is based on the article \"Capping methods for the automatic configuration of optimization algorithms\", published in Computers & Operations Research [2].","PeriodicalId":216331,"journal":{"name":"Proceedings of the Genetic and Evolutionary Computation Conference Companion","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121655159","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
A safety checking algorithm with multi-swarm particle swarm optimization 基于多群粒子群优化的安全检测算法
Proceedings of the Genetic and Evolutionary Computation Conference Companion Pub Date : 2022-07-09 DOI: 10.1145/3520304.3528918
Tsutomu Kumazawa, M. Takimoto, Y. Kambayashi
{"title":"A safety checking algorithm with multi-swarm particle swarm optimization","authors":"Tsutomu Kumazawa, M. Takimoto, Y. Kambayashi","doi":"10.1145/3520304.3528918","DOIUrl":"https://doi.org/10.1145/3520304.3528918","url":null,"abstract":"Model checking is a formal verification technique that automatically decides whether a software system conforms to its specification or not. One of the important features of model checking is to output a counterexample, if a violative execution is detected. Traditional exhaustive techniques fail to complete the verification in large-scale systems because of the shortage of computational resources. This is an efficiency problem called State Explosion Problem. On the other hand, the user of model checking hopes to obtain comprehensible and short outputs. However, balancing efficiency and comprehensibility is not easy, since the exhaustive investigation of the system executions is necessary to find a short counterexample. In this paper, we tackle the balancing problem with an approach of Search-Based Software Engineering. We propose a novel verification algorithm using multi-swarm Particle Swarm Optimization. Our technical breakthrough is to use the specification to decompose the verification problem into the small-sized subproblems dynamically. Each swarm solves one of the subproblems efficiently and the aggregation of the partial solutions found by the swarms provides us with sufficiently short counterexamples. Our numerical experiments show that the proposed algorithm outperforms traditional exhaustive techniques and state-of-the-art non-exhaustive techniques in terms of both efficiency and comprehensibility.","PeriodicalId":216331,"journal":{"name":"Proceedings of the Genetic and Evolutionary Computation Conference Companion","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122608479","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
A single neural cellular automaton for body-brain co-evolution 身体-大脑协同进化的单一神经细胞自动机
Proceedings of the Genetic and Evolutionary Computation Conference Companion Pub Date : 2022-07-09 DOI: 10.1145/3520304.3529002
S. Pontes-Filho, Kathryn Walker, Elias Najarro, S. Nichele, S. Risi
{"title":"A single neural cellular automaton for body-brain co-evolution","authors":"S. Pontes-Filho, Kathryn Walker, Elias Najarro, S. Nichele, S. Risi","doi":"10.1145/3520304.3529002","DOIUrl":"https://doi.org/10.1145/3520304.3529002","url":null,"abstract":"A successful development of a complex multicellular organism took millions of years of evolution. The genome of such a multicellular organism guides the development of its body from a single cell, including its control system. Our goal is to imitate this natural process using a single neural cellular automaton (NCA) as a genome for modular robotic agents. In the introduced approach, called Neural Cellular Robot Substrate (NCRS), a single NCA guides the growth of a robot and the cellular activity which controls the robot during deployment. We also introduce three benchmark environments, which test the ability of the approach to grow different robot morphologies. We evolve the NCRS with covariance matrix adaptation evolution strategy (CMA-ES), and covariance matrix adaptation MAP-Elites (CMA-ME). While the NCRS is able to solve the easier tasks in the benchmark, the success rate reduces when the difficulty of the task increases. We discuss directions for future work that may facilitate the use of the NCRS approach for more complex domains.","PeriodicalId":216331,"journal":{"name":"Proceedings of the Genetic and Evolutionary Computation Conference Companion","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121130223","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 3
Multi-objective path planning for environmental monitoring using an autonomous surface vehicle 基于自主地面车辆的环境监测多目标路径规划
Proceedings of the Genetic and Evolutionary Computation Conference Companion Pub Date : 2022-07-09 DOI: 10.1145/3520304.3528978
Federico Peralta, Michael Pearce, Matthias Poloczek, Daniel Gutiérrez-Reina, S. Toral, Juergen Branke
{"title":"Multi-objective path planning for environmental monitoring using an autonomous surface vehicle","authors":"Federico Peralta, Michael Pearce, Matthias Poloczek, Daniel Gutiérrez-Reina, S. Toral, Juergen Branke","doi":"10.1145/3520304.3528978","DOIUrl":"https://doi.org/10.1145/3520304.3528978","url":null,"abstract":"Intelligent environmental monitoring is an exciting and impactful use case of autonomous vehicles. In this work, we explore measuring water quality parameters via a battery-powered Autonomous Surface Vehicle to obtain an accurate spatial model of the quality of a water resource while minimizing the distance traveled (alternatively, time, or battery consumption). We develop an objective function for this class of problems and propose an evolutionary multi-objective optimization algorithm that selects the measurement locations while using a quick novel construction heuristic for determining the path. Our method leverages new crossover and mutation operators that seem to be of independent interest. We demonstrate the efficacy of the proposed approach in obtaining results for two different waterbodies: Lake Ypacarai in Paraguay, and Mar Menor in Spain.","PeriodicalId":216331,"journal":{"name":"Proceedings of the Genetic and Evolutionary Computation Conference Companion","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127664356","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
An effective metaheuristic-based pruning method for convolutional neural network 一种有效的基于元启发式的卷积神经网络修剪方法
Proceedings of the Genetic and Evolutionary Computation Conference Companion Pub Date : 2022-07-09 DOI: 10.1145/3520304.3528935
Kai-Hsun Tsai, Chun-Wei Tsai, Ming-Chao Chiang
{"title":"An effective metaheuristic-based pruning method for convolutional neural network","authors":"Kai-Hsun Tsai, Chun-Wei Tsai, Ming-Chao Chiang","doi":"10.1145/3520304.3528935","DOIUrl":"https://doi.org/10.1145/3520304.3528935","url":null,"abstract":"Selecting filters to be pruned and determining the pruning ratio are two important research issues of model compression because both of them will strongly impact the accuracy, size, and computation time of a neural network. In this study, an effective algorithm---based on a promising metaheuristic algorithm, search economics, to find the pruning ratio and the filter importance of each convolutional layer to remove unimportant filters---is proposed. Experimental results show that the proposed algorithm can find a better solution than other pruning methods compared in this study.","PeriodicalId":216331,"journal":{"name":"Proceedings of the Genetic and Evolutionary Computation Conference Companion","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126444212","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
Opportunities for genetic improvement of cryptographic code 密码遗传改进的机会
Proceedings of the Genetic and Evolutionary Computation Conference Companion Pub Date : 2022-07-09 DOI: 10.1145/3520304.3534049
C. Chuengsatiansup, Markus Wagner, Y. Yarom
{"title":"Opportunities for genetic improvement of cryptographic code","authors":"C. Chuengsatiansup, Markus Wagner, Y. Yarom","doi":"10.1145/3520304.3534049","DOIUrl":"https://doi.org/10.1145/3520304.3534049","url":null,"abstract":"Cryptography is one of the main tools underlying the security of our connected world. Cryptographic code must achieve both high security requirements and high performance. Automatic generation and genetic improvement of such code are underexplored, making cryptographic code a prime target for future research. With the proliferation of computers into all aspects of human life, the amount of sensitive data being processed keeps increasing. As cryptography is one of the main tools underlying the security of our modern and connected world, cryptographic software must meet not only high security requirements, but also exhibit excellent nonfunctional properties, such as high performance and low energy consumption. Hence, we see cryptography as a prime target domain for single- and multi-objective code optimization.","PeriodicalId":216331,"journal":{"name":"Proceedings of the Genetic and Evolutionary Computation Conference Companion","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129059020","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Public transport timetable and charge optimization using multiple electric buses types 公共交通时间表和充电优化使用多种电动公交车类型
Proceedings of the Genetic and Evolutionary Computation Conference Companion Pub Date : 2022-07-09 DOI: 10.1145/3520304.3528959
D. Peña, B. Dorronsoro, Andrei Tchernykh, Patricia Ruiz
{"title":"Public transport timetable and charge optimization using multiple electric buses types","authors":"D. Peña, B. Dorronsoro, Andrei Tchernykh, Patricia Ruiz","doi":"10.1145/3520304.3528959","DOIUrl":"https://doi.org/10.1145/3520304.3528959","url":null,"abstract":"Electrification of transportation brings novel opportunities and challenges in designing new sustainable public transport systems. The adoption of electric buses implies the need for new models that consider the autonomy of batteries, charging opportunities, users' demand, and the capacity of vehicles, among others. We model the problem of a bus lane in Los Angeles as a combinatorial optimization problem and use the available information to obtain the optimal timetable and fleet of buses. For that, an accurate mathematical model to calculate the consumption of each type of bus is defined, and the problem is solved with a genetic algorithm. Thanks to the strategic schedules found by the proposed approach, the buses culminate the day with 26.5% of energy on average. Just 6.5% over the minimum safety threshold required to preserve the battery state of health (20%). Our approach optimizes the number of buses needed and their battery utilization based on the energy consumption per trip, the regenerative braking, and overnight recharging.","PeriodicalId":216331,"journal":{"name":"Proceedings of the Genetic and Evolutionary Computation Conference Companion","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121186248","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
Designing a novel and high performance algorithmic trading model using evolutionary AutoML and technical analysis 设计一个新颖的和高性能的算法交易模型,使用进化自动化和技术分析
Proceedings of the Genetic and Evolutionary Computation Conference Companion Pub Date : 2022-07-09 DOI: 10.1145/3520304.3529038
Abhiram Tirumala, R. Bhatnager, Sriram Mudireddy, P. Manjunath, Jason Zutty
{"title":"Designing a novel and high performance algorithmic trading model using evolutionary AutoML and technical analysis","authors":"Abhiram Tirumala, R. Bhatnager, Sriram Mudireddy, P. Manjunath, Jason Zutty","doi":"10.1145/3520304.3529038","DOIUrl":"https://doi.org/10.1145/3520304.3529038","url":null,"abstract":"Trading point prediction is the action of identifying ideal buy and sell points for stocks to maximize profit. It is a widely studied application of Machine Learning on time series data due to the abundance of available historical data and the challenges presented by stocks' noisy nature. However, we have found that this is not an application that has drawn significant attention from the automated machine learning (AutoML) community despite its ideal nature, due to the large number of available models and algorithms that can address this problem. In this research, we employ the Evolutionary Multi-objective Algorithm Design Engine (EMADE). This search framework uses genetic programming to automate model creation and hyperparameter optimization. Traditionally, EMADE produced novel algorithms for tabular, time-series, and image-based problems. This research extends EMADE's capabilities for trading algorithms by adding technical indicator (TI) primitives and novel objective functions. We present analyses on objective sets, learners, TI primitives, and their hyperparameters for this problem. To measure the effectiveness of the evolved models, we evaluate profit percentage on historical US stock data. We have found that the models discovered through EMADE AutoML search techniques produce returns up to 36.38% on average, more than two-fold that of state-of-the-art.","PeriodicalId":216331,"journal":{"name":"Proceedings of the Genetic and Evolutionary Computation Conference Companion","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115981046","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 2
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信
小红书