检索结果-内蒙古大学图书馆

Multi-Tree genetic programming with Elite Recombination for dynamic task scheduling of satellite edge computing

FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE 2025年 166卷

作者： Zhang, Changzhen Yang, Jun Beihang Univ Sch Reliabil & Syst Engn Beijing 100191 Peoples R China

Satellite Edge Computing (SEC) can provide task computation services to terrestrial users, particularly in areas lacking terrestrial network coverage. With the increasing frequency of computational demands from Internet of Things (IoT) devices and the limited and dynamic nature of computational resources in Low Earth Orbit (LEO) satellites, making effective real-time scheduling decisions in dynamic environments to ensure high task success rate is a critical challenge. In this work, we investigate the dynamic task scheduling of SEC based on genetic programming Hyper-Heuristic (GPHH). Firstly, anew problem model for the dynamic task scheduling of SEC is proposed with the objective of improving the task success rate, where the real-world situations (limited and dynamic nature of satellite resources, randomness and difference of tasks) are taken into account. Secondly, to make efficient real-time routing decision and queuing decision during the dynamic scheduling process, a novel scheduling heuristic with routing rule and queuing rule is developed, considering dynamic features of the SEC system such as real-time load, energy consumption, and remaining deadlines. Thirdly, to automatically learn both routing rule and queuing rule, and improve the performance of the algorithm, a Multi-Tree genetic programming with Elite Recombination (MTGPER) is proposed, which exploits the recombination of the excellent rules to obtain the better scheduling heuristics. The experimental results show that the proposed MTGPER significantly outperforms existing state-of-the-art methods. The scheduling heuristic evolved by MTGPER has quite good interpretability, which facilitates scheduling management in engineering practice.

关键词： Satellite edge computing Dynamic task scheduling genetic programming Task success rate Elite recombination

来源：评论

学校读者我要写书评

暂无评论

Semantics-guided multi-task genetic programming for multi-output regression

引用

PATTERN RECOGNITION 2025年 161卷

作者： Wang, Chunyu Chen, Qi Xue, Bing Zhang, Mengjie Victoria Univ Wellington Ctr Data Sci & Artificial Intelligence Wellington 6140 New Zealand Victoria Univ Wellington Sch Engn & Comp Sci Wellington 6140 New Zealand

Multi-output regression entails the simultaneous prediction of two or more output variables, presenting greater complexities than single-output regression due to the frequent interdependent relationships of these variables. Such dependencies mean that accurately predicting one variable typically requires careful analysis of its relationships with others. In this paper, multi-output regression problems are treated as multi-task problems, with a prediction of one output variable as a distinct task. A new multi-task multi-population genetic programming method is proposed to solve the problem. The method incorporates a semantics based crossover operator to identify the most informative subtree from a similar task that facilitates positive knowledge transfer. Empirical results indicate that our method significantly improves the training and testing performances of other multi-task GP methods, surpassing standard GP and GP with regressor chain on most examined regression datasets. Further analysis reveals that our proposed method can generate high-quality solutions by knowledge transfer and efficiently evolves similar GP models for analogous output variables, significantly enhancing positive knowledge transfer.

关键词： Multi-output regression genetic programming Evolutionary multi-task optimization

来源：评论

学校读者我要写书评

暂无评论

Multi-gene genetic programming of critical boron concentration and power peak factor for nuclear reactor fuel reload calculations

引用

PROGRESS IN NUCLEAR ENERGY 2025年 180卷

作者： Filho, Marcos A. G. S. Lima, Alan M. M. Pinheiro, Victor H. C. Univ Fed Rio De Janeiro UFRJ COPPE Ilha FundaoCtr TecnolPEN BR-21941901 Rio De Janeiro Brazil Univ Tartu Inst Comp Sci Fac Sci & Technol EE-50090 Tartu Estonia

Nuclear fuel reload aims to search for a core configuration of partially burned and fresh nuclear fuel, optimizing the operational cycle length while assuring safety limits. For each configuration, operational cycle length and safety limits are evaluated in terms of boron concentration and power peak factor, respectively. Other safety parameters are not currently predicted with MGGP. In practice, a licensed numerical model is provided by the reactor manufacturer to estimate these physical parameters, and each configuration is simulated in approximately 300 s. Considering all possible core combinations, this approach becomes computationally unfeasible. This work introduces the Multi-Gene genetic programming (MGGP) to generate an explicit closed form mathematical function to estimate the nuclear reload physical parameters more efficiently. Results for a study of a single cycle of the Angra-I reactor show that the algorithmically generated mathematical function calculates boron concentration and power peak factor with a coefficient of determination of 0.997 and 0.95, respectively. For each configuration, the time of assessment is approximately 8E-4 s, which is several orders of magnitude faster than common licensed numerical tools, potentially enabling expensive optimization studies. Also, MGGP performance is compared with an implemented Artificial Neural Network (ANN), and model results are compared.

关键词： genetic programming Artificial Intelligence Power peak factor Nuclear reload problem

来源：评论

学校读者我要写书评

暂无评论

A novel strongly-typed genetic programming algorithm for combining sentiment and technical analysis for algorithmic trading

引用

KNOWLEDGE-BASED SYSTEMS 2025年 311卷

作者： Christodoulaki, Eva Kampouridis, Michael Kyropoulou, Maria Univ Bristol Sch Engn Math & Technol Ada Lovelace Bldg Bristol BS8 1TW England Univ Essex Sch Comp Sci & Elect Engn Wivenhoe Pk Colchester CO4 3SQ Essex England

The use of algorithms in finance and trading has become an increasingly thriving research area, with researchers creating automated and pre programmed trading instructions utilising indicators from technical and sentiment analysis. The indicators of the two analyses have been used mostly individually, despite evidence that their combination can be profitable and financially advantageous. In this paper, we examine the advantages of combining indicators from both technical and sentiment analysis through a novel genetic programming algorithm, named STGP-SATA. Our algorithm introduces technical and sentiment analysis types, through a strongly-typed architecture, whereby the associated tree contains one branch with only technical indicators and another branch with only sentiment analysis indicators. This approach allows for better exploration and exploitation of the search space of the indicators. To evaluate the performance of STGP-SATA we compare it with three other GP variants on three financial metrics, namely Sharpe ratio, rate of return and risk. We furthermore compare STGP-SATA against two financial and four algorithmic benchmarks, namely, multilayer perceptron, support vector machine, extreme gradient boosting, and long short term memory network. Our study shows that the combination of technical and sentiment analysis indicators through STGP-SATA improves the financial performance of the trading strategies and statistically and significantly outperforms the other benchmarks across the three financial metrics.

关键词： Sentiment analysis Technical analysis genetic programming Algorithmic trading

来源：评论

学校读者我要写书评

暂无评论

A novel hyper-heuristic based on surrogate genetic programming for the three-dimensional spatial resource-constrained project scheduling problem under uncertain environments

引用

COMPUTERS & OPERATIONS RESEARCH 2025年 179卷

作者： Li, Lubo Zhang, Jingwen Zhang, Haohua Leus, Roel Northwestern Polytech Univ Sch Management Xian 710072 Shaanxi Peoples R China Katholieke Univ Leuven Fac Econ & Business B-3000 Leuven Belgium

Fora class of large and complex engineering projects with limited construction sites, three-dimensional (3D) spatial resources usually become a bottleneck that hinders their smooth implementation. A project schedule easily disturbed by space conflicts and uncertain environments if these factors are not considered in advance. Firstly, we extend the traditional resource-constrained project scheduling problem (RCPSP) by considering 3D spatial resource constraints under uncertain environments, and propose anew three-dimensional spatial resource-constrained project scheduling problem with stochastic activity durations (3D-sRCPSPSAD). The activity schedule and the space allocation need to be decided simultaneously, so we design the first-fit and the best-fit strategies, and integrate them into the traditional resource-based policy to schedule activities and allocate 3D space. Secondly, a novel hyper-heuristic based on surrogate genetic programming (HH-SGP) designed to evolve rules automatically for the 3D-sRCPSPSAD. The main goal of the surrogate model HH-SGP is to construct an approximate model of the fitness function based on the random forest technique. Therefore, it can be used as an efficient alternative to the more expensive fitness function in the evolutionary process. More importantly, the weak elitism mechanism and other modified techniques are designed to improve the performance of HH-SGP. Thirdly, we configure the parameters of 3D spatial resources and generate numerical instances. Finally, from the aspects of solution quality and stability, we verify the efficiency, quality and convergence rate of HH-SGP under different uncertain environments. The effectiveness of the surrogate model, and the performance of the first-fit and the best-fit strategies are also analyzed through extensive numerical experiments. The results indicate that our designed HH-SGP algorithm performs better than traditional heuristics for the 3D-sRCPSPSAD, and the performance of the fitness

关键词： Project schedule 3D spatial resource genetic programming Fitness function surrogate Random forest technique

来源：评论

学校读者我要写书评

暂无评论

Customized crop feature construction using genetic programming for early-and in-season crop mapping☆

引用

COMPUTERS AND ELECTRONICS IN AGRICULTURE 2025年 231卷

作者： Wen, Caiyun Lu, Miao Bi, Ying Xia, Lang Sun, Jing Shi, Yun Wei, Yanbing Wu, Wenbin Chinese Acad Agr Sci Inst Agr Resources & Reg Planning State Key Lab Efficient Utilizat Arid & Semiarid A Beijing 100081 Peoples R China Natl Ctr Technol Innovat Comprehens Utilizat Salin Dongying 257345 Peoples R China Zhengzhou Univ Sch Elect & Informat Engn Zhengzhou 450001 Peoples R China State Key Lab Intelligent Agr Power Equipment Luoyang 471000 Peoples R China

Early- and in-season crop mapping provides vital information for precision agriculture. It is still a challenge for early- and in-season crop mapping because of the limited available images and similar spectral information. This study aims to enhance early- and in-season crop mapping by developing a genetic programming (GP) method to construct customized crop features. GP automatically generated candidate features for the target-crop using early- or in-season images, selected programs with substantial value disparities between target and non-target crops through the fitness function, and finally outputted the customized feature after the evolutionary process. These customized features were then compared with commonly used spectral bands and vegetation indices to evaluate their effectiveness for early- and in-season crop mapping. The results proved that the customized crop features had significant advantages in both early- and in-season crop mapping. The early-season accuracy in April after crop planting was 3.97% to 9.53% higher than spectral features and vegetation indices. Based on the incremental classification for the in-season crop mapping, the customized crop features maintained the best performance. Advantages of customized crop features include the ability to automatically select effective bands of useful months without requiring expert knowledge, the ability to catch and enlarge the subtle spectral differences with the early- and in-season images, and the little information redundancy compared with spectral features and vegetation indices. It can be concluded that the customized crop features are outstanding for early- and in-season crop mapping.

关键词： Remote Sensing Crop mapping genetic programming Feature Construction Customized feature

来源：评论

学校读者我要写书评

暂无评论

Adaptive Operators for genetic programming to Identify Optimal Energy Flow Controllers

引用

Procedia Computer Science 2025年 253卷 1991-2002页

作者： Kathrin Kefer Michael Affenzeller Stephan Winkler Fronius International GmbH Günter-Fronius-Straße 1 4600 Thalheim Austria University of Applied Sciences Upper Austria Campus Hagenberg Evolutionary Computation and Algorithms Lab Softrwarepark 11 4232 Hagenberg Austria

genetic programming can find nearly optimal solutions for complex problems like minimizing a building’s energy costs by optimally controlling its energy flows. For such problems, usually multiple controllers are necessary. In order to allow a faster convergence in combination with a more fine-grained and directed search, this work presents new adaptive crossover and mutation operators. Instead of applying the operators always to all symbolic regression trees in a solution candidate, the new operators are applied to all trees only in the beginning and then to a randomly chosen group of them as soon as a threshold is reached. Towards the end of the training, the adaptive operators then switch to applying crossover and mutation to only one of the trees in a solution candidate for a more fine-grained search. Additionally, a new crossover is proposed where the children solution candidates are themselves evaluated for their performance before promoting one of them to the next generation in order to assure a more directed search. To evaluate these new operators, a total of twelve energy management controllers is trained with the Offspring Selection genetic Algorithm and are evaluated for training results in form of the needed number of evaluated solutions and generations as well as their ability to reduce the energy costs and their learned behaviour. Results show that the proposed adaptive operators achieve very similar results to the baseline optimization and that the Best Child crossover is the fastest to converge.

关键词： genetic programming genetic programming Operators Symbolic Regression Adaptive genetic programming Operators Energy Flow Controller Optimization Building Energy Management Renewable Energy

来源：评论

学校读者我要写书评

暂无评论

Phenotype and Genotype Based Sample Aware Surrogate-Assisted genetic programming in Dynamic Flexible Job Shop Scheduling

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年

作者： Zhu, Luyao Zhang, Fangfang Zhu, Xiaodong Chen, Ke Zhang, Mengjie Zhengzhou University School of Electrical and Information Engineering Zhengzhou450001 China Victoria University of Wellington Centre for Data Science and Artificial Intelligence School of Engineering and Computer Science Wellington6140 New Zealand Longmen Laboratory Luoyang471000 China

genetic programming (GP) has been widely applied to evolve scheduling heuristics for dynamic flexible job shop scheduling (DFJSS). However, the evaluation of GP individuals is computationally expensive, especially in large scale DFJSS scenarios. A k-nearest neighbor (KNN) based surrogate has been successfully used to reduce individual evaluation time for GP by predicting the fitness of an individual with the most similar sample in KNN. Particularly, the phenotypes of GP individuals have been utilised to generate samples for KNN-based surrogates with a precondition that the fitness of individuals with the same phenotype is the same or similar. However, their real fitness may differ greatly due to different input decision situations for fitness calculations in DFJSS. Thus, only considering phenotypes of GP individuals to extract samples could decrease the accuracy of KNN surrogates. This paper proposes a KNN-based surrogate assisted GP algorithm by considering both the phenotype and genotype of GP individuals to generate samples. Specifically, a genotypic characterisation based on terminal frequency is designed to measure the similarity of individual genotypes. The results show that with the same training time, the proposed algorithm can converge fast and achieve better scheduling heuristics than the state-of-the-art algorithms in most examined scenarios. With the same number of generations, the proposed algorithm can obtain comparable performance but only needs about one third training time of baseline GP. The effectiveness of the proposed algorithm is also verified from different aspects, e.g., relation between genotype correlation and fitness difference of individuals, and population diversity. © 2025 IEEE.

关键词： genetic programming

来源：评论

学校读者我要写书评

暂无评论

Health prediction for king salmon via evolutionary machine learning with genetic programming

引用

JOURNAL OF THE ROYAL SOCIETY OF NEW ZEALAND 2025年第1期55卷 166-191页

作者： Zhang, Fangfang Zhang, Yuye Casanovas, Paula Schattschneider, Jessica Walker, Seumas P. Xue, Bing Zhang, Mengjie Symonds, Jane E. Victoria Univ Wellington Ctr Data Sci & Artificial Intelligence Wellington New Zealand Victoria Univ Wellington Sch Engn & Comp Sci Wellington New Zealand Cawthron Inst Nelson New Zealand

King (Chinook) salmon is the only salmon species farmed in Aotearoa New Zealand and accounts for over half of the world's production of king salmon. Determining the health status of king salmon effectively is important for farming. However, it is a challenging task due to the complex biotic and abiotic factors that influence health. Evolutionary machine learning algorithms have shown their superiority in learning models for challenging tasks. However, they have not been investigated for health prediction in king salmon farming. This paper focuses on data processing and machine learning algorithm design to develop king salmon health prediction models in Aotearoa New Zealand. Particularly, this paper proposes a king salmon health prediction method based on genetic programming which is an evolutionary machine learning algorithm. The results show that genetic programming achieves the best overall performance among all examined typical machine learning algorithms for most trials. Further analyses show that genetic programming can automatically detect important features for learning classifiers for king salmon health classification tasks effectively, and can also learn potentially interpretable models. Our results are an important step forward in developing health prediction tools to automatically assess health status of farmed king salmon in Aotearoa New Zealand.

关键词： Evolutionary machine learning genetic programming king salmon health prediction classification

来源：评论

学校读者我要写书评

暂无评论

Multi-Tree genetic programming with Rule Reconstruction for Dynamic Task Scheduling in Integrated Cloud-Edge Satellite-Terrestrial Networks

引用

IEEE Internet of Things Journal 2025年

作者： Zhang, Changzhen Yang, Jun Wang, Ning Beihang University School of Reliability and Systems Engineering Beijing100191 China

Satellite-Terrestrial Networks (STNs) are a promising paradigm for providing internet services for users globally. Since the dynamics of service resources and the uncertainty of computational requests, how the service resources in STNs can be efficiently exploited to execute differentiated computational tasks is an essential challenge. In this work, we investigate the dynamic task scheduling in the integrated cloud-edge STNs. Firstly, we propose a cloud-edge collaborative computing framework in STNs, where the computational tasks of users can be processed collaboratively by satellite edge servers, terrestrial edge servers, and cloud servers. Based on this framework, a dynamic task scheduling problem is formulated with the objective of maximizing the task success rate. Secondly, to make effective real-time decisions at decision points in the dynamic scheduling process, we develop a scheduling heuristic with the routing rule and queuing rule, which incorporates dynamic features related to servers, computational tasks, and network environments. Thirdly, to automatically learn the scheduling heuristic, we propose a Multi-Tree genetic programming with Rule Reconstruction (MTGPRR), which introduces a selective reconstruction operator. This operator increases the chance of matching good rules with other rules by recombining common individuals and elites. Experimental results demonstrate that the proposed MTGPRR performs significantly better than the state-of-the-art methods in improving the task success rate. Moreover, the evolved scheduling heuristic has good interpretability, which is important for practical applications. © 2025 IEEE.

关键词： genetic 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：