Genetic Neural Network Research Articles

Predictive method for poultry carcass visceral dimensions using 3D point cloud and Genetic Algorithm-based Wavelet Neural Network

Predictive method for poultry carcass visceral dimensions using 3D point cloud and Genetic Algorithm-based Wavelet Neural Network

Improved prediction accuracy for compressive strength of recycled aggregate concrete using optimization-based algorithms and cascade forward neural network

This study proposed a data driven approach to predict the compressive strength (CS) of recycled aggregate concrete (RAC) for sustainable construction using an elite single genetic optimization algorithm-based cascade forward neural network (ESGA-CFNN) model. It was applied to 272 RAC samples under different conditions and compositions focusing on key parameters for CS prediction: water-to-cement ratio (WCR), water absorption (WA), recycled coarse aggregate (RCA) density, fine aggregate (FA) density, naturally occurring coarse aggregate (NCA) density and water-to-total material ratio (WTMR). These parameters were used to develop the ESGA-CFNN model which was then evaluated for its performance. To compare the ESGA-CFNN model, two other models were developed and compared: particle swarm optimization-based CFNN (PSO-CFNN) and artificial bee colony-based CFNN (ABC-CFNN). K-fold cross-validation was used during model development to prevent overfitting. Results showed that ESGA-CFNN model performed better with an RMSE (root-mean-squared error) of 1.144, R2 (determination coefficient) of 0.991 and a10-index of 1.000. ABC-CFNN model had an RMSE of 1.434, R2 of 0.987 and a10-index of 0.982 while PSO-CFNN had an RMSE of 1.561, R2 of 0.984 and a10-index of 0.982. Practical validation with 6 RAC samples confirmed the real world applicability of these models. The findings of this study showed that the proposed ESGA-CFNN model is important for quality control in RAC production and optimizing mix designs to achieve required compressive strength to meet standards and reduce cost and increase sustainability in concrete construction. This study introduces a novel hybrid approach combining ESGA-CFNN, PSO-CFNN, and ABC-CFNN algorithms for accurately predicting the compressive strength of RAC. These models outperform traditional methodologies by offering enhanced predictive accuracy and generalization capability, especially in complex, real-world datasets.

Research on in-vivo electron paramagnetic resonance spectrum classification and radiation dose prediction based on machine learning

The in-vivo electron paramagnetic resonance (EPR) method can be used for on-site, rapid, and non-invasive detection of radiation dose to casualties after nuclear and radiation emergencies. For in-vivo EPR spectrum analysis, manual labeling of peaks and calculation of signal intensity are often used, which have problems such as large workload and interference by subjective factors. In this study, a method for automatic classification and identification of in-vivo EPR spectra was established using support vector machine (SVM) technology, which can in-batch and automatically identify and screen out invalid spectra due to vibration and dental surface water interference during in-vivo EPR measurements. In this study, a spectrum analysis method based on genetic algorithm optimization neural network (GA-BPNN) was established, which can automatically identify the radiation-induced signals in in-vivo EPR spectra and predict the radiation doses received by the injured. The experimental results showed that the SVM and GA-BPNN spectrum processing methods established in this study could effectively accomplish the automatic spectra classification and radiation dose prediction, and could meet the needs of dose assessment in nuclear emergency. This study explored the application of machine learning methods in EPR spectrum processing, improved the intelligence level of EPR spectrum processing, and would help to enhance the efficiency of mass EPR spectra processing.

Spatio-temporal evolution of social-ecological system resilience in ethnic tourism destinations in mountainous areas and trend prediction: a case study in Wuling, China

Mountainous ethnic tourism lands are important social-ecological system types. With tourism as the main disturbance factor, the theory of social-ecological system resilience provides a new way to realize the sustainable development of ethno-tourism in mountainous areas. This study divides the social-ecological system into social, economic, and ecological subsystems. It constructs an evaluation index system to assess the resilience of ethnic tourism destinations in mountainous areas, considering vulnerability and adaptability. We investigate 64 counties in the Wuling Mountain area and use set-pair analysis to assess the resilience index of the social-ecological system from 2000 to 2020 and reveal the temporal and spatial characteristics. Obstacle degree models and a genetic algorithm-back propagation neural network are utilized to determine the influencing factors and predict future development trends. The following results were obtained: (1) Temporally, the resilience index shows a steady upward trend, reaching a moderate level. The resilience of the social subsystem fluctuates and rises; the economic subsystem exhibits slow, fast, and slow growth rates with occasional abrupt changes; and the ecological subsystem demonstrates a stable, slightly increasing trend. (2) Spatially, the resilience index is high at the edges and low in the central area, exhibiting a concave distribution. Most counties have moderate or higher resilience. The social and ecological subsystems have low resilience in the south and high resilience in the north. The resilience of the economic subsystem is high at the edges and low in the central area. (3) On the distribution of major obstacle factors, the first two are similar at the county level, and the last three are significantly different. The similarity of the barrier factors is related to the degree of regional proximity of the county, and overall, the similarity is decreasing from north to south and from west to east in the distribution pattern within the area. and to a certain extent, it is affected by terrain and geomorphology. (4) The spatial distribution of the resilience index is similar in 2025 and 2030. The index decreases slightly and then increases annually, with a lower growth rate in the south than in the north. Lower values occur in the northern and southwestern parts, whereas higher values are observed around high-value areas. The region as a whole will develop in a coordinated and integrated manner in the future.

Optimal operation model of ecological flow of hydropower station based on genetic algorithm and neural network

Amid diverse water demands, the conflict between ecological flow adjustments and power generation flow adjustments in hydropower station water resource dispatching, coupled with an increasing diversity of constraints, complicates the issue of water resource optimization and dispatching. How to scientifically develop feedback regulation mechanisms to promote a virtuous ecological cycle, fine tune existing hydropower station scheduling plans, and achieve multi-objective optimization scheduling is the core issue in researching the comprehensive utilization of water resources. This study establishes a reservoir flow regulation model with the objective functions of maximizing power generation and achieving optimal average ecological protection. The model, constrained by water balance, reservoir capacity, unit output, and unit overflow, was optimized and solved using the genetic algorithm-backpropagation neural network (GA-BPNN) approach. This study establishes a reservoir flow regulation model with the GA-BPNN algorithm was applied in multi-objective optimization to identify an optimal solution that maximizes overall system performance while adhering to ecological flow constraints. The results indicate that the optimized plan has performed effectively in hydropower station operations. It not only satisfies ecological flow requirements, but also significantly enhances power generation efficiency. Specifically, power generation increased by 32,680 kw·h, a 23.85% growth rate. The optimized plan significantly enhances the comprehensive utilization efficiency of water resources. It offers a scientific basis for the rational planning, dispatching and utilization of water resources in hydropower stations and reservoirs.

Research on Topology Optimization of Building Digital Supply Chain Based on Genetic Neural Network

In order to maximize the benefit of building supply chain, the topology optimization method of building digital supply chain based on genetic neural network is studied. According to the overall structural characteristics of the building digital supply chain, customer demand data, supplier sales data, manufacturer production management data, and environmental policy exception data are collected to form a building digital supply chain data set. As input data, a building digital supply chain demand prediction model based on improved genetic LSTM neural network is constructed. Capture the needs of the building digital supply chain; according to the demand of suppliers, manufacturers and customers in building digital supply chain, a nonlinear 0–1 mixed integer programming model based on the newsboy model is established. According to the various information provided by the supplier, the ant colony algorithm is used to calculate the optimal supplier. After all suppliers are identified, the topology of the digital supply chain is constructed. So far, the optimization of the supply chain has been completed. The experimental data show that this method can accurately predict the demand of construction projects, the maximum error is less than 1.5%, and can obtain the best supplier selection results. Compared with before optimization, the profit of the structural digital supply chain after topology optimization increases the most.

Regression prediction of critical exhaust volumetric flow rate in tunnel fire with two-point extraction ventilation based on neural network method

In this study, a Genetic Algorithm-Backpropagation Neural Network (GA-BPNN) model was developed to predict critical exhaust volumetric flow rate in tunnel fires with two-point extraction ventilation system. Seven influencing factors served as inputs for the model, while the critical exhaust volumetric flow rate was the output. Experimental data from two reduced-scale tunnels were utilized to both train and validate the GA-BPNN model. The results demonstrate a satisfactory prediction performance, with key metrics such as Mean Absolute Percentage Error (MAPE), Relation Coefficient (R2), and Root Mean Square Error (RMSE) achieving values of 0.0384, 0.9989, and 3.5258, respectively. Importantly, the model maintains a maximum Absolute Percentage Error (APE) below 10 %. In contrast, the traditional BPNN model exhibited an APE of approximately 18.9 %. Moreover, the predictive results of the GA-BPNN model were compared with those of a previously semi-empirical formula. It was observed that the semi-empirical predictions exhibited APE exceeding 20 % for certain data points. This further underscores the superiority of the GA-BPNN model in predicting critical exhaust volumetric flow rates in tunnel fires with two-point ventilation system. These findings affirm the feasibility and effectiveness of GA-BPNN regression model as a reliable method for predicting critical exhaust volumetric flow rates under multiple factors.

Research on Failure Pressure Prediction of Water Supply Pipe Based on GA-BP Neural Network

The water supply pipeline is regarded as the “lifeline” of the city. In recent years, pipeline accidents caused by aging and other factors are common and have caused large economic losses. Therefore, in order to avoid large economic losses, it is necessary to analyze the failure prediction of pipelines so that the pipelines that are going to fail can be replaced in a timely manner. In this paper, we propose a method for predicting the failure pressure of pipelines, i.e., a genetic algorithm was used to optimize the weights and thresholds of a BP neural network. The first step was to determine the topology of the neural network and the number of input and output variables. The second step was to optimize the weights and thresholds initially set for the back propagation neural network using a genetic algorithm. Finally, the optimized back-propagation neural network was used to simulate and predict pipeline failures. It was proved by examples that compared with the separate back propagation neural network model and the optimized and trained genetic algorithm-back propagation neural network, the model performed better in simulation prediction, and the prediction accuracy could reach up to 91%, whereas the unoptimized back propagation neural network model could only reach 85%. It is feasible to apply this model for fault prediction of pipelines.

Appendicular Skeletal Muscle Mass in Older Adults Can Be Estimated With a Simple Equation Using a Few Zero-Cost Variables.

Assessing appendicular skeletal muscle (ASM) mass is crucial for the diagnosis of numerous pathologies related to the decline of muscle mass in old age, such as sarcopenia, malnutrition, or cachexia. The dual-energy X-ray absorptiometer (DEXA) radiological technique, which is the gold standard for its assessment, is particularly costly and not routinely used in clinical practice. The aim of this study was to derive computationally simple equations capable of estimating the DEXA-measured ASM at zero cost in older adult populations. We used the cross-sectional data collected by the National Health and Nutrition Examination Survey (NHANES) over 7years (1999-2006). The study sample included 16,477 individuals aged 18years and over, of which 4401 were over 60years old. We considered 38 nonlaboratory variables. For the derivation of the equations, we employed the Brain Project, an innovative artificial intelligence tool that combines genetic programming and neural networks. The approach searches simultaneously for the mathematical expression and the variables to use in the equation. The derived equations are useful to estimate the DEXA-measured ASM. A simple equation that includes the body weight of the patient as the sole variable can estimate the outcome of DEXA with an accuracy equivalent to previously published equations. When used to identify individuals over 60years old with muscle mass loss, it achieved an area under the curve (AUC) value of 0.85 for both males and females. The inclusion of sex and anthropometric data (thigh and arm circumference) improved the accuracy for male individuals (AUC 0.89). The model is also suitable to be applied to the general adult population of 18years of age or older. Using more than 3 variables does not lead to better accuracy. The newly proposed equations have better diagnostic accuracy than previous equations for the estimation of DEXA-measured ASM. They are readily applicable in clinical practice for the screening of muscle mass loss in the over 60-year-old population with nearly zero-cost variables. The most complex model proposed in this study requires only the inspection of a simple diagnostic chart to estimate the status of muscle mass loss.

Parameters prediction for Low-Plasticity ultrasonic rolling strengthening process of blades based on Few-Shot Genetic Bayesian-Back Propagation intelligent learning

This study aims to reduce titanium alloy blade surface roughness and enhance compressive residual stress (CRS) using the low-plasticity ultrasonic rolling strengthening process (URSP). Due to the URSP’s multifactorial complexity and characteristics of few and irregular test samples, this study proposes a Genetic Bayesian-Back Propagation neural network (GB-BP) for a few sample parameters optimization for low-plasticity URSP of the blade, which combines a back propagation (BP) neural network with genetic algorithm (GA) and Bayesian Optimization (BO). The proposed approach establishes a robust correlation between processing parameters, blade surface roughness, and CRS. Firstly, an orthogonal test with three factors, rolling depth, feeding speed, and rolling distance, is designed. The signal-to-noise ratio (S/N) analysis and mean value analysis identify rolling distance and depth as the primary factors influencing surface roughness and CRS. Furthermore, BP complement with BO is employed to predict blade surface roughness and CRS after URSP. Finally, GB-BP is proposed to predict parameters, and experimental validation demonstrates the superior predictive accuracy of the GB-BP network. Compared to traditional BP models, the mean error percentages for GB-BP prediction dropped by 51.286% for surface roughness and 69.818% for CRS. The root mean square error (RMSE) decreased by 51.864% for surface roughness and 71.982% for CRS. This network model can provide accurate parameters optimization for low-plasticity URSP of blades.

Seismic vulnerability assessment of buildings using rapid visual screening for hybrid UMNN-RFO approach

This chapter proposes a hybrid approach for seismic vulnerability assessment of buildings using rapid visual screening (RVS). The Unconstrained Monotonic Neural Network (UMNN) and Red Fox Optimisation (RFO) are combined to create the hybrid technique, thus, the term ‘UMNN-RFO approach’. The UMNN algorithm predicts the RVS score and the RFO algorithm optimizes the RVS score. The RVS methods via Google Maps are being used to examine the Andaman and Nicobar Islands because it is one of the main earthquake prone regions in the world. A score was given after a screening that looked at Reinforced Concrete moment-resisting frames, load-bearing structures, steel frames (SF) and wooden frames (WF). By then, the MATLAB platform will have the proposed model implemented. The proposed approach outperforms all current techniques, including Granular Computing Artificial Neural Network (GrC-ANN), Particle Swarm Optimization-Back Propagation Neural Network (PSO-BPNN) and Genetic Algorithm-Artificial Neural Network (GA-ANN). The proposed method’s accuracy is 90%, determination coefficient is 0.91 and the Root Mean Square error is 0.27%. From the result, the proposed method concluded that older structures are more likely to sustain greater damage shortly than more recently built ones based on the score.

Parameter optimisation of the ventilation system for an underground power space using a hybrid model

The ventilation system is one of the essential safety systems in underground power spaces. Over the years, active ventilation has been widely employed for heat dissipation in underground power spaces. In operation, high-power equipment generates significant heat, necessitating sufficient heat dissipation for smooth and efficient functioning. The effectiveness of the ventilation system is influenced by airflow, making aerodynamics a crucial aspect of studying underground power spaces. This study establishes a comprehensive hybrid model (a combination of physical and data-driven models) representing underground power spaces. Ansys Fluent and MATLAB are used to simulate and calculate temperature fields for various structures. The physical model employs model order reduction to achieve efficient computation without compromising accuracy. For the data-driven model, a genetic neural network is developed for multifactor nonlinear optimisation to evaluate and analyse thermal behaviour within the space. The integrated hybrid model enables efficient and high-precision calculations for the underground power space’s ventilation system. The research outcomes provide a theoretical foundation for practical construction and design schemes of underground power spaces, contributing significantly to ensuring their safety and optimal functionality in real-world applications.

Resolution of Glycerol, Ethanol and Methanol Employing a Voltammetric Electronic Tongue

This paper reports the use of nanoparticles (NPs)-modified voltammetric sensors for the rapid determination of glycerol in the presence of ethanol and methanol, which are used in the transesterification reaction of biodiesel production. Two different modified electrodes have been prepared to form the electronic tongue (ET): copper hexacyanoferrate NPs obtained by chemical synthesis and mixed into graphite/epoxy (GEC) electrode, and nickel hydroxide NPs electrodeposited in reduced graphene oxide onto a GEC electrode. The response characteristics of these electrodes were first evaluated by building the respective calibration against glycerol, ethanol, and methanol. The electrodes demonstrated good stability during their analytical characterization, while principal component analysis confirmed the differentiated response against the different alcohols. Finally, the quantification of mixtures of these substances was achieved by a genetic algorithm-artificial neural networks (GA-ANNs) model, showing satisfactory agreement between expected and obtained values.

Monitoring Soybean Soil Moisture Content Based on UAV Multispectral and Thermal-Infrared Remote-Sensing Information Fusion.

By integrating the thermal characteristics from thermal-infrared remote sensing with the physiological and structural information of vegetation revealed by multispectral remote sensing, a more comprehensive assessment of the crop soil-moisture-status response can be achieved. In this study, multispectral and thermal-infrared remote-sensing data, along with soil-moisture-content (SMC) samples (0~20 cm, 20~40 cm, and 40~60 cm soil layers), were collected during the flowering stage of soybean. Data sources included vegetation indices, texture features, texture indices, and thermal-infrared vegetation indices. Spectral parameters with a significant correlation level (p < 0.01) were selected and input into the model as single- and fuse-input variables. Three machine learning methods, eXtreme Gradient Boosting (XGBoost), Random Forest (RF), and Genetic Algorithm-optimized Backpropagation Neural Network (GA-BP), were utilized to construct prediction models for soybean SMC based on the fusion of UAV multispectral and thermal-infrared remote-sensing information. The results indicated that among the single-input variables, the vegetation indices (VIs) derived from multispectral sensors had the optimal accuracy for monitoring SMC in different soil layers under soybean cultivation. The prediction accuracy was the lowest when using single-texture information, while the combination of texture feature values into new texture indices significantly improved the performance of estimating SMC. The fusion of vegetation indices (VIs), texture indices (TIs), and thermal-infrared vegetation indices (TVIs) provided a better prediction of soybean SMC. The optimal prediction model for SMC in different soil layers under soybean cultivation was constructed based on the input combination of VIs + TIs + TVIs, and XGBoost was identified as the preferred method for soybean SMC monitoring and modeling, with its R2 = 0.780, RMSE = 0.437%, and MRE = 1.667% in predicting 0~20 cm SMC. In summary, the fusion of UAV multispectral and thermal-infrared remote-sensing information has good application value in predicting SMC in different soil layers under soybean cultivation. This study can provide technical support for precise management of soybean soil moisture status using the UAV platform.

Root phenotype detection of rice seedling under nitrogen conditions based on terahertz imaging technique

Root phenotype detection is the basis for screening of dominant root and improving of seed breeding. The efficiency of root phenotype detection is restricted by the concealment and complexity of crop roots. In this paper, a new method based on terahertz imaging technology was proposed to detect the phenotypic characteristics of rice root and quantitatively predict root nitrogen content. First, the terahertz imaging spectral data of rice root were preprocessed with de-overlapping, reconstruction, enhancement, and segmentation. Then, the phenotypic characteristics of root length, diameter and surface area of rice roots were extracted according to the refinement algorithm. In addition, three linear regression models were fitted between root phenotype and root nitrogen content. Finally, Convolutional Neural Network (CNN), Genetic Algorithm-Back Propagation Neural Network (GA-BPNN), and Sparrow Search Algorithm-Support Vector Regression (SSA-SVR) were used to predict nitrogen content in rice roots by training and testing terahertz time domain data. Compared with two kinds of root phenotypic analysis software, the average errors of root length, diameter and root surface area calculated in this paper were 10.68 %, 7.29 % and 3.49 %, respectively. The fitting determination coefficients between root length, root surface area and the root nitrogen content were 0.88 and 0.87 after removing three groups of high-nitrogen data and one group of contrast data. The prediction accuracy of SSA-SVR model was 0.99 and the root mean square error was 0.05. Studies show that terahertz imaging technique can provide an effective analytical way for qualitative analysis of root phenotype.

The surrogate model for short-term extreme response prediction based on ANN and Kriging algorithm

Numerical simulation is a common method for calculating the short-term extreme response of floating offshore wind turbines (FOWTs). However, it requires significant computational resources. This study presents a dynamic response database for a 5MW semi-submersible FOWT under complex environmental conditions, including wind speed, effective wave height, and wave spectral peak period, using a numerical model. The peak over threshold (POT) method can be used to obtain the parametric database of short-term extreme responses, which includes the short-term extreme response distribution parameters for four responses: float surge, mooring tension, outward bending moment at the leaf root surface (OoPBM) and tower base pitching moment (TBPM). And the parameter database is applied to train models such as the Genetic Algorithm optimization Back Propagation neural network (GA-BP) and Kriging algorithm models. The research indicates that a correlation can be established between environmental conditions and short-term extreme response parameters using two algorithms. The accuracy of surrogate model prediction for some parameters can be improved by grouping the data based on wind speed and training separately. Additionally, selecting the appropriate surrogate model for each parameter separately can improve the accuracy of short-term extreme response prediction.

Real-Time Prediction of Oil-Type Gas Emissions in Coal-Oil-Gas Coexistence Mines.

Oil-type gas disasters are a frequently occurring concern in coal-oil-gas coexistence mines. In order to actively predict the volume of oil-type gas emissions from floor rocks, this study presents an investigative methodology to forecast the geological conditions of floor rocks in front of the roadway face by utilizing the Direct Current (DC) method. The assessment of electrical resistance in rock formations, which is widely employed for identifying geological characteristics, serves as the basis for proposing a geological anomaly index derived from rock resistivity. This index effectively characterizes the stability of rock strata, providing an indirect evaluation of fracture development. As a real-time geological detection index for floor rocks that are 100 m ahead of the roadway face, it enhances predictive capabilities. Moreover, when combined with parameters such as floor rock thickness and permeability, the paper presents simulations of oil-type gas emissions under varying geological conditions. Subsequently, an adaptive optimization of the Back Propagation (BP) neural network is achieved through the Genetic Algorithm Back Propagation Neural Network (GA-BP) model to evaluate the quantity of oil-type gas emissions in roadways. This advanced real-time prediction method is applied in Huangling coal mining to predict the oil-type gas emissions from the floor rocks in the excavation roadway area. The results show consistency with field monitoring outcomes, confirming the accuracy of the predictive model. In conclusion, this advanced real-time prediction technique enables continuous monitoring and real-time forecasting of oil-type gas emissions in front of roadways. This capability facilitates the implementation of specific measures for pre-extraction in gas disaster prevention and control, thereby ensuring the safety of coal mine production. Moreover, the versatility of this advanced real-time prediction method extends to early warnings of rock mass instability-related disasters. Through a comprehensive understanding of subsurface conditions, continuous monitoring of changes, and the application of predictive models, timely actions can be taken to reduce risks and uphold safety standards.

COVID-19 seroprevalence estimation and forecasting in the USA from ensemble machine learning models using a stacking strategy

The COVID-19 pandemic exposed the importance of research on the spread of epidemic diseases. In this paper, we apply Artificial Intelligence and statistics techniques to build prediction models to estimate the SARS-CoV-2 seroprevalence in the United States, using multiple estimates of COVID-19 prevalence and other explanatory variables. We propose the use of stacking techniques based on multiple model building techniques (Linear and Beta Regression, Genetic Programming and Neural Networks) to obtain Predictive Ensemble Models. There has been extensive research on this field, but there has not been in-depth research on the application of stacking methods to estimate and forecast seroprevalence in the USA specifically. This paper provides a novel comparison of the behaviour and performance of different building techniques for stacking ensemble models and presents which methods are better for different scenarios. We find that Genetic Programming and Neural Networks are the best models with trained data within single states, and when multiple states are considered Genetic Programming is still better than the Regression models, but Neural Networks fail to estimate the seroprevalence accurately. Another novelty of our work is the use of cross-state validation to evaluate the models with new data, as well as temporal forecasting. Depending on how the data is processed, Linear Regression performs very well with cross-state validation and temporal forecasting, and Genetic Programming is very accurate with the former while Neural Networks work better with the latter.

Development of machine learning models for forecasting the strength of resilient modulus of subgrade soil: genetic and artificial neural network approaches

Accurately predicting the Modulus of Resilience (MR) of subgrade soils, which exhibit non-linear stress–strain behaviors, is crucial for effective soil assessment. Traditional laboratory techniques for determining MR are often costly and time-consuming. This study explores the efficacy of Genetic Programming (GEP), Multi-Expression Programming (MEP), and Artificial Neural Networks (ANN) in forecasting MR using 2813 data records while considering six key parameters. Several Statistical assessments were utilized to evaluate model accuracy. The results indicate that the GEP model consistently outperforms MEP and ANN models, demonstrating the lowest error metrics and highest correlation indices (R2). During training, the GEP model achieved an R2 value of 0.996, surpassing the MEP (R2 = 0.97) and ANN (R2 = 0.95) models. Sensitivity and SHAP (SHapley Additive exPlanations) analysis were also performed to gain insights into input parameter significance. Sensitivity analysis revealed that confining stress (21.6%) and dry density (26.89%) are the most influential parameters in predicting MR. SHAP analysis corroborated these findings, highlighting the critical impact of these parameters on model predictions. This study underscores the reliability of GEP as a robust tool for precise MR prediction in subgrade soil applications, providing valuable insights into model performance and parameter significance across various machine-learning (ML) approaches.

Optimized phenol degradation and lipid production by Rhodosporidium toruloides using response surface methodology and genetic algorithm-optimized artificial neural network

Oleaginous yeast can produce lipids while degrading phenol in wastewater treatment. In this study, a Plackett-Burman Design (PBD) was adopted to identify key factors of phenol degradation and lipid production using R toruloides 9564T. While temperature, inoculum size, and agitation were significant for both the processes (p < 0.05), pH and incubation were significant for lipid production, and phenol removal, respectively. Results from four factors (pH, temperature, inoculum size, and incubation period) central composite design (CCD) experiment were used to formulate quadratic and genetic algorithm-optimized ANN models. The reduced quadratic model for phenol degradation (R2: 0.993) and lipid production (R2: 0.958) were marginally inferior to ANN models (R2: 0.999, 0.982, respectively) on training sets. Multi-objective optimization with equal importance suggests phenol degradation between 106.4 and 108.76%, and lipid production of 0.864–0.903 g/L, by polynomial and ANN models. Complete phenol degradation (100%) and 3.35-fold increment (0.918 g/L) in lipid production were obtained at pH 6.07, inoculum size 14.68% v/v, at 29.5 °C in 92.17 h experimentally.