Genetic Programming Method Research Articles

A genetic programming approach with adaptive region detection to skin cancer image classification

Dermatologists typically require extensive experience to accurately classify skin cancer. In recent years, the development of computer vision and machine learning has provided new methods for assisted diagnosis. Existing skin cancer image classification methods have certain limitations, such as poor interpretability, the requirement of domain knowledge for feature extraction, and the neglect of lesion area information in skin images. This paper proposes a new genetic programming (GP) approach to automatically learn global and/or local features from skin images for classification. To achieve this, a new function set and a new terminal set have been developed. The proposed GP method can automatically and flexibly extract effective local/global features from different types of input images, thus providing a comprehensive description of skin images. A new region detection function has been developed to select the lesion areas from skin images for feature extraction. The performance of this approach is evaluated on three skin cancer image classification tasks, and compared with three GP methods and six non-GP methods. The experimental results show that the new approach achieves significantly better or similar performance in most cases. Further analysis validates the effectiveness of our parameter settings, visualizes the multiple region detection functions used in the individual evolved by the proposed approach, and demonstrates its good convergence ability.

Artificial Intelligence Advancements for Accurate Groundwater Level Modelling: An Updated Synthesis and Review

Artificial Intelligence (AI) methods, including Artificial Neural Networks (ANNs), Adaptive Neuro-Fuzzy Inference Systems (ANFISs), Support Vector Machines (SVMs), Deep Learning (DL), Genetic Programming (GP) and Hybrid Algorithms, have proven to be important tools for accurate groundwater level (GWL) modelling. Through an analysis of the results obtained in numerous articles published in high-impact journals during 2001–2023, this comprehensive review examines each method’s capabilities, their combinations, and critical considerations about selecting appropriate input parameters, using optimisation algorithms, and considering the natural physical conditions of the territories under investigation to improve the models’ accuracy. For example, ANN takes advantage of its ability to recognise complex patterns and non-linear relationships between input and output variables. In addition, ANFIS shows potential in processing diverse environmental data and offers higher accuracy than alternative methods such as ANN, SVM, and GP. SVM excels at efficiently modelling complex relationships and heterogeneous data. Meanwhile, DL methods, such as Long Short-Term Memory (LSTM) and Convolutional Neural Networks (CNNs), are crucial in improving prediction accuracy at different temporal and spatial scales. GP methods have also shown promise in modelling complex and nonlinear relationships in groundwater data, providing more accurate and reliable predictions when combined with optimisation techniques and uncertainty analysis. Therefore, integrating these methods and optimisation techniques (Hybrid Algorithms), tailored to specific hydrological and hydrogeological conditions, can significantly increase the predictive capability of GWL models and improve the planning and management of water resources. These findings emphasise the importance of thoroughly understanding (a priori) the functionalities and capabilities of each potentially beneficial AI-based methodology, along with the knowledge of the physical characteristics of the territory under investigation, to optimise GWL predictive models.

A method to standardize the temperature for near infrared spectra of the indigo pigment in non-dairy cream based on symbolic regression

Near infrared (NIR) spectroscopy is sensitive to physical conditions such as sample temperature, meaning that rapid detection methods based on NIR spectroscopy are significantly influenced by temperature. To address this challenge, symbolic regression was employed to mitigate the effects of temperature. The Weighted Windowed Adaptive Optimization algorithm was proposed and combined with the Sequential Projection Algorithm to extract temperature-related feature points and remove redundant data. Subsequent 3D modeling of these feature points revealed that absorbance alterations due to temperature comprised two distinct segments. Consequently, based on symbolic regression, the temperature standardization algorithm was devised to generate piecewise equations. This algorithm surpassed genetic programming and non-segmented methods in performance metrics. The piecewise function equations generated by the algorithm were used to regress the absorbance at different temperatures to the standard temperature. Non-dairy cream, with different indigo pigment contents, was temperature standardized using a piecewise function to obtain spectra at two standard temperatures; 18°C and 28°C. The r2 for the quantitative regression model improved from 0.71 to 0.95 at 18°C and from 0.63 to 0.85 at 28°C. The temperature standardization method offers interpretable equations for spectra that model the complex changes with temperature, factoring out the temperature variation, thereby facilitating the practical use of NIR spectroscopy in rapid detection applications.

Enhancing Program Synthesis with Large Language Models Using Many-Objective Grammar-Guided Genetic Programming

The ability to automatically generate code, i.e., program synthesis, is one of the most important applications of artificial intelligence (AI). Currently, two AI techniques are leading the way: large language models (LLMs) and genetic programming (GP) methods—each with its strengths and weaknesses. While LLMs have shown success in program synthesis from a task description, they often struggle to generate the correct code due to ambiguity in task specifications, complex programming syntax, and lack of reliability in the generated code. Furthermore, their generative nature limits their ability to fix erroneous code with iterative LLM prompting. Grammar-guided genetic programming (G3P, i.e., one of the top GP methods) has been shown capable of evolving programs that fit a defined Backus–Naur-form (BNF) grammar based on a set of input/output tests that help guide the search process while ensuring that the generated code does not include calls to untrustworthy libraries or poorly structured snippets. However, G3P still faces issues generating code for complex tasks. A recent study attempting to combine both approaches (G3P and LLMs) by seeding an LLM-generated program into the initial population of the G3P has shown promising results. However, the approach rapidly loses the seeded information over the evolutionary process, which hinders its performance. In this work, we propose combining an LLM (specifically ChatGPT) with a many-objective G3P (MaOG3P) framework in two parts: (i) provide the LLM-generated code as a seed to the evolutionary process following a grammar-mapping phase that creates an avenue for program evolution and error correction; and (ii) leverage many-objective similarity measures towards the LLM-generated code to guide the search process throughout the evolution. The idea behind using the similarity measures is that the LLM-generated code is likely to be close to the correct fitting code. Our approach compels any generated program to adhere to the BNF grammar, ultimately mitigating security risks and improving code quality. Experiments on a well-known and widely used program synthesis dataset show that our approach successfully improves the synthesis of grammar-fitting code for several tasks.

Анализ компромисса между точностью и сложностью идентифицированных моделей динамических систем

One of the rapidly developing areas of the modern control theory is the identification of systems associated with the construction of mathematical models of systems in the form of a set of mathematical relationships that adequately reflect the basic properties of the system. Symbolic regression methods are becoming more and more popular in the problems of structural-parametric identification of systems based on available observations and experimental data, which allow building regression models in the form of codes of mathematical expressions in a symbolic form. Among the known numerical evolutionary methods of symbolic regression, the universally acknowledged “favorite” is the method of genetic programming”, the application of which allows us to describe the search for solving a problem as the construction of a regression model by enumerating various arbitrary superpositions of functions from some predetermined set. In this case, the important indicators determining the quality of identification of the mathematical model of the system are the accuracy and complexity of the identified model. Often, the system model obtained as a result of solving identification problem is not accurate enough or excessively complex. As a result, the solution to the identification problem is inextricably linked to ensuring sufficient accuracy and simplicity of the identified model. In this connection, it is natural to adhere to the principle of balanced identification, which indicates the search for a compromise between the accuracy of reproduction and the measure of complexity of the identified model. The purpose of this paper, which develops the concept of balanced identification, is to analyze the trade-off between the accuracy and complexity of models of dynamic systems identified by genetic programming. In this paper we introduce a functional "accuracy-complexity", which allows us to balance the trade-off between these key indicators of the identified models when solving the identification problem. The effectiveness of the proposed functional is demonstrated on the example of computer identification by genetic programming of a Lorentz dynamical system.

Risk based design optimization via scenario generation and genetic programming under hybrid uncertainties

Abstract The design of complex systems often requires the incorporation of uncertainty optimization strategies to mitigate system failures resulting from multiple uncertainties during actual operation. Risk-based design optimization, as an alternative methodology that accounts for the balance between design cost and performance, has garnered significant attention and recognition. This paper proposes a risk design optimization method for tackling hybrid uncertainties via scenario generation and genetic programming. The hybrid uncertainties are quantified through scenario generation method to obtain risk assessment indicators. The genetic programming method is used to simulate the real output of the objective or constraints. To drive the optimization process, the sample-based discrete gradient expression is constructed, and the optimal scheme aligning the risk requirements is obtained. Three calculation examples of varying computing complexity are presented to verify the efficacy and usability of the suggested approach.

Modeling of ionic liquids viscosity via advanced white-box machine learning.

Ionic liquids (ILs) are more widely used within the industry than ever before, and accurate models of their physicochemical characteristics are becoming increasingly important during the process optimization. It is especially challenging to simulate the viscosity of ILs since there is no widely agreed explanation of how viscosity is determined in liquids. In this research, genetic programming (GP) and group method of data handling (GMDH) models were used as white-box machine learning approaches to predict the viscosity of pure ILs. These methods were developed based on a large open literature database of 2813 experimental viscosity values from 45 various ILs at different pressures (0.06-298.9MPa) and temperatures (253.15-573K). The models were developed based on five, six, and seven inputs, and it was found that all the models with seven inputs provided more accurate results, while the models with five and six inputs had acceptable accuracy and simpler formulas. Based on GMDH and GP proposed approaches, the suggested GMDHmodel with seven inputs gave the most exact results with an average absolute relative deviation (AARD) of 8.14% and a coefficient of determination (R2) of 0.98. The proposed techniques were compared with theoretical and empirical models available in the literature, and it was displayed that the GMDH model with seven inputs strongly outperforms the existing approaches. The leverage statistical analysis revealed that most of the experimental data were located within the applicability domains of both GMDH and GP models and were of high quality. Trend analysis also illustrated that the GMDH and GP models could follow the expected trends of viscosity with variations in pressure and temperature. In addition, the relevancy factor portrayed that the temperature had the greatest impact on the ILs viscosity. The findings of this study illustrated that the proposed models represented strong alternatives to time-consuming and costly experimental methods of ILs viscosity measurement.

More Numerically Accurate Algorithm for Stiff Matrix Exponential

In this paper, we propose a novel, highly accurate numerical algorithm for matrix exponentials (MEs). The algorithm is based on approximating Putzer’s algorithm by analytically solving the ordinary differential equation (ODE)-based coefficients and approximating them. We show that the algorithm outperforms other ME algorithms for stiff matrices for several matrix sizes while keeping the computation and memory consumption asymptotically similar to these algorithms. In addition, we propose a numerical-error- and complexity-optimized decision tree model for efficient ME computation based on machine learning and genetic programming methods. We show that, while there is not one ME algorithm that outperforms the others, one can find a good algorithm for any given matrix according to its properties.

Modeling CO2 loading capacity of triethanolamine aqueous solutions using advanced white-box approaches: GMDH, GEP, and GP

The equilibrium solubility of carbon dioxide (CO2) in the solvents is a key essential characteristic that has to be evaluated for successful absorption-based CO2 capture procedures. In this study, the CO2 loading capacity of triethanolamine (TEA) aqueous solutions was estimated using three famous white-box algorithms namely gene expression programming (GEP), genetic programming (GP), and group method of data handling (GMDH). For achieving the aim of this study, 258 data in a wide range of pressure, temperature, and amine concentration were collected from literature. Temperature, partial pressure of CO2, and amine concentration were used as input parameters. The results demonstrated that GMDH correlation is more accurate than GEP and GP with a determination coefficient (R2) of 0.9813 and root mean square error of 0.0222. The R2 values of 0.9713 and 0.9664 for the GEP and GP, respectively, demonstrated that the GEP and GP also showed accurate predictions. In addition, GMDH approach accurately predicted the anticipated trends of the CO2 loading in response to changes in the partial pressure of CO2 and temperature. The Pearson and Spearman correlation analyses were also incorporated in this research which showed that temperature and CO2 partial pressure have almost the same relative effect on CO2 loading, while amine concentration has the lowest effect on it.

Ufuk Amaçlı Genetik Programlama ile Hava Durumu Tahminine Güven Aralıklı Yaklaşım

Being able to forecast events has always been important for humans. Humans did forecasting by inspecting movements of material and non-material objects in ancient times. However, thanks to the technological developments and the increasing amount of data in recent years, forecasting is now done by computers, especially by machine learning methods. One of the areas where these methods are used frequently is numerical weather forecasting. In this type of forecast, short, medium and long-term weather forecasts are made using historical data. However, predictions are inherently error-prone phenomena and should be stated which error range the predictions fall. In this study, numerical weather forecasting was done by combining Genetic Programming and Inductive Conformal Prediction method. The effect of 10 and 20 days of historical data on short (1-day), medium (3-days) and long-term (5-days) weather forecasts was examined. Results suggested that Genetic Programming has a good potential to be used in this area. However, when Genetic Programming was combined with the Inductive Conformal Prediction method, it was shown that forecasts gave meaningful results only in short-term; forecasts made for medium and long-term did not produce meaningful results.

Modeling hydrogen solubility in water: Comparison of adaptive boosting support vector regression, gene expression programming, and cubic equations of state

Predicting the solubility of hydrogen (H2) in aqueous solutions is crucial for studying reactions of hydrogen in the formation, which also affects the security and optimal design of hydrogen storage. In this research, five robust machine learning (ML) algorithms, namely adaptive boosting decision tree (AdaBoost-DT), adaptive boosting support vector regression (AdaBoost-SVR), gradient boosting decision tree (GB-DT), gradient boosting support vector regression (GB-SVR), and k-nearest neighbors (KNN) and three powerful white-box techniques, namely gene expression programming (GEP), genetic programming (GP), and group method of data handling (GMDH) were developed to accurately predict H2 solubility in pure and saline water systems. To this aim, a widespread databank containing 427 experimental data points was collected, and temperature, pressure, and salt concentration (mSalt) were considered as input variables. The validity and precision of the developed models were assessed utilizing several statistical and graphical tests. Results demonstrate that the AdaBoost-SVR smart model could obtain a superior performance and provides precise predictions with root mean square error (RMSE) of 0.000115 and determination coefficient (R2) of 0.9973. Among the white-box models, the GEP provided the best results with an RMSE of 0.000362 and an R2 of 0.9542. Although the accuracy of GEP is slightly lower than that of AdaBoost-SVR, it offers explicit and simple mathematical formula for calculating H2 solubility, which is the main advantage of white box models. The results also demonstrated that AdaBoost-SVR outperforms cubic equations of state (EOSs) such as Peng-Robinson (PR), Redlich-Kwong (RK), Soave-Redlich-Kwong (SRK), and Zudkevitch-Joffe (ZJ). Besides, trend analysis showed that AdaBoost-SVR model could match actual trends of H2 solubility change versus temperature and pressure. Finally, outlier detection analysis using the Leverage technique indicated that the majority of data points used for modeling (nearly 94 %) are reliable and placed in the valid zone.

Influence of Cutting Parameters in Hard Turning 40X Steel with Self-Driven Rotary Tool on Surface Roughness using Genetic Programming Method and Artificial Ecosystem-based Optimisation

Influence of Cutting Parameters in Hard Turning 40X Steel with Self-Driven Rotary Tool on Surface Roughness using Genetic Programming Method and Artificial Ecosystem-based Optimisation

Multitask Linear Genetic Programming with Shared Individuals and its Application to Dynamic Job Shop Scheduling

Multitask genetic programming methods have been applied to various domains, such as classification, regression, and combinatorial optimization problems. Most existing multitask genetic programming methods are designed based on tree-based structures, which are not good at reusing building blocks since each sub-tree passes its outputs to only one parent. It may limit the design and performance of knowledge sharing in multitask optimization. Different from tree-based genetic programming, building blocks in linear genetic programming can be easily reused by more than one parent. Besides, existing multitask genetic programming methods always allocate each individual to a specific task and have to duplicate genetic materials from task to task in knowledge transfer, which is inefficient and often produces redundancy. Contrarily, it is natural for a linear genetic programming individual to produce multiple distinct outputs, which enables each linear genetic programming individual to solve multiple tasks simultaneously. With this in mind, we propose a new multitask linear genetic programming method that transfers knowledge via multi-output individuals (i.e., shared individuals among tasks). By integrating different solutions into one multi-output individual, the proposed method efficiently reuses common knowledge among tasks and maintains distinct behaviors for each task. The empirical results show that the proposed method has a significantly better test performance than state-of-the-art multitask genetic programming methods. Further analyses verify that the new knowledge transfer mechanism can adjust the transfer rate automatically and thus improves its effectiveness.

Оптимизация мероприятий технической эксплуатации оросительных систем методами искусственного интеллекта

The purpose of the study is to develop a constructive solution for choosing priority objects of repair and restoration works using artificial intelligence methods in conditions of limited budget financing of operational measures of irrigation systems. The paper uses methods of system analysis and mathematical modeling, including binary variables for discrete optimization using evolutionary genetic programming methods. Based on the analysis of management decision support by means of mathematical support, the use of optimization methods for predicted impacts is justified, including the choice of discrete options to increase the functionality and effectiveness of planned technical operation measures. The allocation of limited financial resources is carried out on the model of multi-criteria optimization, including minimizing irrigation water losses, while increasing the area of irrigated land and increasing the financial indicators of the water management organization, which improves the quality of management impacts. The practical significance of research is determined by the development of innovative tools to solve the problem of allocating limited resources for carrying out repair and restoration work of the municipal water management complex using artificial intelligence methods. The approbation of the proposed solutions, carried out on the materials of the operation service of the State Budgetary Institution of the Republic of Crimea “Crimean Department of Water Management and Melioration”, proved the expediency of large-scale implementation of methods for quantitative assessment of management decisions. The technical and economic indicators of the planned activities correspond to the expected values and ensure the fulfillment of the following requirements: completeness, ensuring that they provide the necessary and sufficient information for decision-making; availability of reliable sources of reliable and accessible data for the information content of indicators and criteria.

Development and comparison of different artificial intelligence-based models for viscosity of in-situ cross-linked acids

The use of in-situ cross-linked acids (ICAs) is common in stimulating oil and gas reservoirs. However, their rheological models have not been widely incorporated into simulation software due to their complex behavior and lack of valid data. Accordingly, in this study, development of new models for estimation of viscosity of ICAs as a function of pH and shear rate was intended. For this purpose, 33 experimental data points were collected from literature and methods of genetic programming, neural network (NN), and fuzzy logic (FL) were used to develop models. In summary, all three models performed equally well and better than a previously published model, with an R 2 = 0.99 and an average absolute percent error of 7%. In terms of computational costs, genetic programming correlation was found to be 76 and 786% faster than NN and FL, respectively. Therefore, the model developed by genetic programming was suggested to be used in numerical solvers for estimation the viscosity of ICAs as a function of pH and shear. Sensitivity analysis on temperature, pH, and shear rate showed that pH would have the highest impact on the apparent viscosity of the considered ICAs.

Systematic framework for handling uncertainty in probabilistic failure analysis of corroded concretes

Due to ambiguous correlations between input random variables and multi-source uncertainties from the electrochemical model, significant differences between deterministic corrosion prediction models and actual measurements are often observed. A systematic framework of quantification of uncertainties is developed for structures with correlated random variables originated from multiple sources, which allows efficiently estimating the failure probability distribution of the steel corrosion over time considering the randomness of the cover depth, the surface chloride concentration, and the chloride diffusion coefficient. After partitioning correlated random variables into different groups based on their uncertain sources, the Morris one-step-at-a-time and Sobol model is established to rank with respect to the importance of each correlated random variable. Based on polynomial chaos expansions and genetic programming methods, a more condensed set of random variables is created to propagate parametric problems. The unknown probability distribution of the input random variables is formulated by the Markov chain Monte Carlo to realize rigorous uncertainty quantification of the structural reliability. The application of the systematic framework to a set of numerical examples of steel corrosion includes experimental validation and uncertainty quantification and propagation of environmental, material and geometric properties. The results show that the framework can be integrated with parametric electrochemical models to allow robustness and reliability of corrosion prediction.

A genetic programming-based method for image classification with small training data

Genetic programming (GP) has been considerably used for image classification because of its ability to learn simple and effective models. However, most GP methods require a large amount of training data to learn informative features for classification, where the generalization performance might be poor when only a few training instances are available. In addition to using classification accuracy to assess the goodness of GP individuals/solutions like in most GP methods, this paper proposes a new fitness function containing distance measures. The proposed method uses different distance measures to deal with binary and multi-class classification automatically. By simultaneously minimizing the within-class distance and maximizing the between-class distance, the generalization performance can be improved. Furthermore, existing GP methods typically employ standard crossover to search for the best individuals from the whole search space. However, these methods might not completely exploit the potential local search space. Based on the niching technique, this paper develops a new crossover operator, which enables better exploitation of the global and local search space, improving learning effectiveness and classification accuracy. The new approach achieves significantly better generalization performance than almost all benchmark methods on eight datasets and is also computationally efficient. Further analysis demonstrates the significance of the new fitness function and crossover operator and shows the potentially good interpretability of the learned models.

Predicting the Compressive Strength of Pervious Cement Concrete based on Fast Genetic Programming Method

Predicting the Compressive Strength of Pervious Cement Concrete based on Fast Genetic Programming Method

A genetic programming approach for the prediction of solar chimney power plant power

This study empirically examines the effectiveness of the solar chimney power plants (SCPP), which is an innovative method for the use of solar energy, in the middle latitude region (37.88° N) in the northern hemisphere. Experimental measurement parameters of temperature, velocity, and radiation obtained from four cardinal directions (north, south, east, and west) and from 26 different locations were recorded throughout the day (08:00 am-07:30 pm). These measurements were used to calculate and estimate the power values used to measure the energy efficiency of the solar chimney. In the study, the genetic programming method was used to estimate the power value. In the five different forecast models developed, 15 different parameters were used diagonally. The obtained power estimation equations were cross-checked using statistical methods. Determination coefficient value is higher than >0.90 in all equations and is close to the ideal. In the comparison of all statistical models, the Global Performance Indicator (GPI) was used, with the best result obtained from Model 2. The results of this model are MAPE:6.5233, MBE: −0.0124, RMSE:1.1036 ve t-stat:0.0374, which is quite close to zero. In addition, the power values obtained from both the calculated and developed models were dimensioned and compared over the power-time factor of eight different studies in the literature. The mean relative error value nof the values calculated as a result of this comparison varies between 2.3% and 21.3%. This study provides a model for the different geometries of solar chimney prototypes and provides an example for measuring the design and performance of solar chimney systems to be installed in the middle latitudes and in regions with “Csa” climate characteristics, and is recommended for academic and industrial users. The mathematical models developed can be considered as a step to increase the efficiency of the solar chimney power plants.

Cooperative Double-Layer Genetic Programming Hyper-Heuristic for Online Container Terminal Truck Dispatching

In a marine container terminal, truck dispatching is a crucial problem that impacts on the operation efficiency of the whole port. Traditionally, this problem is formulated as an offline optimisation problem, whose solutions are, however, impractical for most real-world scenarios primarily because of the uncertainties of dynamic events in both yard operations and seaside loading–unloading operations. These solutions are either unattractive or infeasible to execute. Herein, for more intelligent handling of these uncertainties and dynamics, a novel cooperative double-layer genetic programming hyper-heuristic (CD-GPHH) is proposed to tackle this challenging online optimisation problem. In this new CD-GPHH, a novel scenario genetic programming (GP) approach is added on top of a traditional GP method that chooses among different GP heuristics for different scenarios to facilitate optimised truck dispatching. In contrast to traditional arithmetic GP (AGP) and GP with logic operators (LGP) which only evolve on one population, our CD-GPHH method separates the scenario and the calculation into two populations, which improved the quality of solutions in multi-scenario problems while reducing the search space. Experimental results show that our CD-GPHH dominates AGP and LGP in solving a multi-scenario function fitting problem as well as a truck dispatching problem in container terminal.