期刊,Genetic programming and evolvable machines 2025年26卷1期_国家学术搜索

Review: 'Computational evolution of neural and morphological development'

Renske Vroomans

1.1-1.2页

查看更多>>摘要：This book is an extended collection of Jin's research works in the field of evolutionary algorithms, with a focus on evolution of gene regulatory networks (GRNs), neural networks and cellular morphologies. It discusses several models, from small GRNs to models of multicellular structure evolution, and evolutionary robotics.

原文链接:

NETL
NSTL
Springer Nature

Review: 'Computational evolution of neural and morphological development'

Renske Vroomans

1.1-1.2页

查看更多>>摘要：This book is an extended collection of Jin's research works in the field of evolutionary algorithms, with a focus on evolution of gene regulatory networks (GRNs), neural networks and cellular morphologies. It discusses several models, from small GRNs to models of multicellular structure evolution, and evolutionary robotics.

原文链接:

NETL
NSTL
Springer Nature

A survey on batch training in genetic programming

Liah RosenfeldLeonardo Vanneschi

2.1-2.28页

查看更多>>摘要：In Machine Learning (ML), the use of subsets of training data, referred to as batches, rather than the entire dataset, has been extensively researched to reduce computational costs, improve model efficiency, and enhance algorithm generalization. Despite extensive research, a clear definition and consensus on what constitutes batch training have yet to be reached, leading to a fragmented body of literature that could otherwise be seen as different facets of a unified methodology. To address this gap, we propose a theoretical redefinition of batch training, creating a clearer and broader overview that integrates diverse perspectives. We then apply this refined concept specifically to Genetic Programming (GP). Although batch training techniques have been explored in GP, the term itself is seldom used, resulting in ambiguity regarding its application in this area. This review seeks to clarify the existing literature on batch training by presenting a new and practical classification system, which we further explore within the specific context of GP. We also investigate the use of dynamic batch sizes in ML, emphasizing the relatively limited research on dynamic or adaptive batch sizes in GP compared to other ML algorithms. By bringing greater coherence to previously disjointed research efforts, we aim to foster further scientific exploration and development. Our work highlights key considerations for researchers designing batch training applications in GP and offers an in-depth discussion of future research directions, challenges, and opportunities for advancement.

原文链接:

NETL
NSTL
Springer Nature

A survey on batch training in genetic programming

Liah RosenfeldLeonardo Vanneschi

2.1-2.28页

查看更多>>摘要：In Machine Learning (ML), the use of subsets of training data, referred to as batches, rather than the entire dataset, has been extensively researched to reduce computational costs, improve model efficiency, and enhance algorithm generalization. Despite extensive research, a clear definition and consensus on what constitutes batch training have yet to be reached, leading to a fragmented body of literature that could otherwise be seen as different facets of a unified methodology. To address this gap, we propose a theoretical redefinition of batch training, creating a clearer and broader overview that integrates diverse perspectives. We then apply this refined concept specifically to Genetic Programming (GP). Although batch training techniques have been explored in GP, the term itself is seldom used, resulting in ambiguity regarding its application in this area. This review seeks to clarify the existing literature on batch training by presenting a new and practical classification system, which we further explore within the specific context of GP. We also investigate the use of dynamic batch sizes in ML, emphasizing the relatively limited research on dynamic or adaptive batch sizes in GP compared to other ML algorithms. By bringing greater coherence to previously disjointed research efforts, we aim to foster further scientific exploration and development. Our work highlights key considerations for researchers designing batch training applications in GP and offers an in-depth discussion of future research directions, challenges, and opportunities for advancement.

原文链接:

NETL
NSTL
Springer Nature

Hardware real-time individualised blood glucose predictor generator based on grammars and cartesian genetic programming

Jorge CanoJ. Ignacio HidalgoOscar Garnica

3.1-3.26页

查看更多>>摘要：In this paper, we introduce a novel grammar-guided technique based on genetic programming for on-chip, real-time, configurable hardware design of model generators on an FPGA. The technique integrates grammar-based design, Cartesian Genetic Programming, and a (1+λ) Evolutionary Strategy and is demonstrated through the implementation of a wearable hardware predictor for blood glucose prediction. People with diabetes need to manage their blood glucose levels to prevent life-threatening situations and long-term complications. Effective glucose management requires accurate blood glucose predictions, yet most existing methods rely on heuristic estimators. This system enables the training and testing of personalized models using real patient data. We validated the approach by generating and evaluating models for 30- and 60-min forecasting predictions on ten patients, creating a total of 200 models. The system achieved state-of-the-art results, with 98% and 90% of predictions falling within clinically acceptable regions according to Clarke error grid analysis, for 30- and 60-min horizons, respectively. Unlike software implementations, our technique does not suffer from hardware limitations and provides an efficient, adaptable solution through wearable hardware with minimal errors and low power consumption. This is the first demonstration of combining Cartesian Genetic Programming with a hardware implementation for grammar-based blood glucose prediction, potentially enabling real-time embedded systems for portable devices.

原文链接:

NETL
NSTL
Springer Nature

Hardware real-time individualised blood glucose predictor generator based on grammars and cartesian genetic programming

Jorge CanoJ. Ignacio HidalgoOscar Garnica

3.1-3.26页

查看更多>>摘要：In this paper, we introduce a novel grammar-guided technique based on genetic programming for on-chip, real-time, configurable hardware design of model generators on an FPGA. The technique integrates grammar-based design, Cartesian Genetic Programming, and a (1+λ) Evolutionary Strategy and is demonstrated through the implementation of a wearable hardware predictor for blood glucose prediction. People with diabetes need to manage their blood glucose levels to prevent life-threatening situations and long-term complications. Effective glucose management requires accurate blood glucose predictions, yet most existing methods rely on heuristic estimators. This system enables the training and testing of personalized models using real patient data. We validated the approach by generating and evaluating models for 30- and 60-min forecasting predictions on ten patients, creating a total of 200 models. The system achieved state-of-the-art results, with 98% and 90% of predictions falling within clinically acceptable regions according to Clarke error grid analysis, for 30- and 60-min horizons, respectively. Unlike software implementations, our technique does not suffer from hardware limitations and provides an efficient, adaptable solution through wearable hardware with minimal errors and low power consumption. This is the first demonstration of combining Cartesian Genetic Programming with a hardware implementation for grammar-based blood glucose prediction, potentially enabling real-time embedded systems for portable devices.

原文链接:

NETL
NSTL
Springer Nature

Harnessing evolutionary algorithms for enhanced characterization of ENSO events

Ulviya AbdulkarimovaRodrigo Abarca-del-RioPierre Collet

4.1-4.24页

查看更多>>摘要：The El Nino-Southern Oscillation (ENSO) significantly influences the complexity and variability of the global climate system, driving its variability. ENSO events' irregularity and unpredictability arise from intricate ocean-atmosphere interactions and nonlinear feedback mechanisms, complicating their prediction of timing, intensity, and geographic impacts. This study applies Genetic Programming and Genetic Algorithms within the EASEA (EAsy Specification of Evolutionary Algorithms) Evolutionary Algorithms (EA) framework to develop a repository of symbolic equations for El Nino and La Nina events, spanning their various intensities. By analyzing data from the Oceanic Nino Index, this approach yields equation-based characterizations of ENSO events. This methodology not only enhances ENSO characterization strategies but also contributes to expanding the use of EAs in climate event analysis. The resulting equations have the potential to offer insights beyond academia, benefiting education, climate policy, and environmental management. This highlights the importance of ongoing refinement, validation, and exploration in these fields through EAs.

原文链接:

NETL
NSTL
Springer Nature

Harnessing evolutionary algorithms for enhanced characterization of ENSO events

Ulviya AbdulkarimovaRodrigo Abarca-del-RioPierre Collet

4.1-4.24页

查看更多>>摘要：The El Nino-Southern Oscillation (ENSO) significantly influences the complexity and variability of the global climate system, driving its variability. ENSO events' irregularity and unpredictability arise from intricate ocean-atmosphere interactions and nonlinear feedback mechanisms, complicating their prediction of timing, intensity, and geographic impacts. This study applies Genetic Programming and Genetic Algorithms within the EASEA (EAsy Specification of Evolutionary Algorithms) Evolutionary Algorithms (EA) framework to develop a repository of symbolic equations for El Nino and La Nina events, spanning their various intensities. By analyzing data from the Oceanic Nino Index, this approach yields equation-based characterizations of ENSO events. This methodology not only enhances ENSO characterization strategies but also contributes to expanding the use of EAs in climate event analysis. The resulting equations have the potential to offer insights beyond academia, benefiting education, climate policy, and environmental management. This highlights the importance of ongoing refinement, validation, and exploration in these fields through EAs.

原文链接:

NETL
NSTL
Springer Nature

A comparison of representations in grammar-guided genetic programming in the context of glucose prediction in people with diabetes

Leon IngelseJ. Ignacio HidalgoJ. Manuel ColmenarNuno Lourenco...

5.1-5.25页

查看更多>>摘要：The representation of individuals in Genetic Programming (GP) has a large impact on the evolutionary process. In previous work, we investigated the evolutionary process of three Grammar-Guided GP (GGGP) methods, Context-Free Grammars GP (CFG-GP), Grammatical Evolution (GE) and Structured Grammatical Evolution (SGE), in the context of the complex, real-world problem of predicting the glucose level of people with diabetes two hours ahead of time. We concluded that representation choice is more impactful with a higher maximum depth, and that CFG-GP better explores the search space for deeper trees, achieving better results. Furthermore, we find that CFG-GP relies more on feature construction, whereas GE and SGE rely more on feature selection. Additionally, we altered the GGGP methods in two ways: using ε-lexicase selection, which solved the overfitting problem of CFG-GP and helps it to adapt to patients with high glucose variability; and with a penalization of complex trees, to create more interpretable trees. Combining ε-lexicase selection with CFG-GP performed best. In this work, we extend on the previous work and evaluated the impact of initialization methods in the quality of solutions. We found that they have no significant impact, even when the change of representation has.

原文链接:

NETL
NSTL
Springer Nature

A comparison of representations in grammar-guided genetic programming in the context of glucose prediction in people with diabetes

Leon IngelseJ. Ignacio HidalgoJ. Manuel ColmenarNuno Lourenco...

5.1-5.25页

查看更多>>摘要：The representation of individuals in Genetic Programming (GP) has a large impact on the evolutionary process. In previous work, we investigated the evolutionary process of three Grammar-Guided GP (GGGP) methods, Context-Free Grammars GP (CFG-GP), Grammatical Evolution (GE) and Structured Grammatical Evolution (SGE), in the context of the complex, real-world problem of predicting the glucose level of people with diabetes two hours ahead of time. We concluded that representation choice is more impactful with a higher maximum depth, and that CFG-GP better explores the search space for deeper trees, achieving better results. Furthermore, we find that CFG-GP relies more on feature construction, whereas GE and SGE rely more on feature selection. Additionally, we altered the GGGP methods in two ways: using ε-lexicase selection, which solved the overfitting problem of CFG-GP and helps it to adapt to patients with high glucose variability; and with a penalization of complex trees, to create more interpretable trees. Combining ε-lexicase selection with CFG-GP performed best. In this work, we extend on the previous work and evaluated the impact of initialization methods in the quality of solutions. We found that they have no significant impact, even when the change of representation has.

原文链接:

NETL
NSTL
Springer Nature