Mesona chinensis Benth (MCB) is the source of the most commonly consumed herbal beverage in Southeast Asia and China and is thus an economically important agricultural plant. Therefore, optimal extraction and production procedures have significant commercial value. Currently, in terms of green chemistry, researchers are investigating the use of greener solvents and innovative extraction techniques to increase extract yields. This study represents the first investigation of the optimal conditions for ultrasound-assisted deep eutectic solvent (DES) extraction from MCB. The major factors influencing ultrasound-assisted DESs were optimized using the response surface methodcentral-genetic algorithm-back propagation neural networks. This model demonstrated superior predictability and accuracy compared to the RSM model. Various types of DESs were used for the extraction of MCB constituents, with choline chloride-ethylene glycol resulting in the highest yield. The optimal conditions for maximal extraction were the use of choline chloride-ethylene glycol (1:4) as the solvent with a 40% water content, an extraction duration of 60 min at 60°C, and maintaining a leaf-to-solvent ratio of 20 mL/g. Noticeable enhancements in Van der Waals forces and more robust interactions between DESs and the target chemicals were observed relative to those seen with ethanol (70%, v/v) or water. This investigation not only introduced an environmentally friendly approach for highly efficient extraction from MCB but also identified the mechanisms underlying the improved extraction efficacy. These findings have the potential to contribute to the broader utilization of MCB and provide valuable insights into the extraction mechanisms utilizing deep eutectic solvents. PRACTICAL APPLICATION: This work describes an efficient and green ultrasound-assisted deep eutectic solvent (DES) method for Mesona chinensis Benth (MCB) extraction. Molecular dynamics was used to examine the intermolecular interactions between the solvent and the extracted compounds. It is anticipated that green and environmentally friendly solvents, such as DESs, will be used in further research on foods and their bioactive components. With the development of the herbal tea industry, new products made of MCB are becoming increasingly popular, thus gradually making it a research hotspot.

This study aimed to optimize the accelerated solvent extraction (ASE) condition of zeaxanthin from orange paprika using a response surface methodology (RSM) or an artificial neural network (ANN) with a genetic algorithm (GA). Input variables were ethanol concentration, extraction time, and extraction temperature, while output variable was zeaxanthin. The mean squared error and regression correlation coefficient of the developed ANN model were 0.3038 and 0.9983, respectively. Predicted optimal extraction conditions from ANN-GA for maximum zeaxanthin were 100% ethanol, 3.4 min, and 99.2 °C. The relative errors under the optimal extraction conditions were RSM for 10.46% and ANN-GA for 2.18%. We showed that the recovery of hydrophobic zeaxanthin could be performed using ethanol, an eco-friendly solvent, via ASE, and the extraction efficiency could be improved by ANN-GA modeling than RSM. Therefore, combining ASE and ANN-GA might be desirable for the efficient and eco-friendly extraction of hydrophobic functional materials from food resources.
UNASSIGNED: The online version contains supplementary material available at 10.1007/s10068-023-01514-8.

Collision-free path planning and task scheduling optimization in multi-region operations of autonomous agricultural robots present a complex coupled problem. In addition to considering task access sequences and collision-free path planning, multiple factors such as task priorities, terrain complexity of farmland, and robot energy consumption must be comprehensively addressed. This study aims to explore a hierarchical decoupling approach to tackle the challenges of multi-region path planning. Firstly, we conduct path planning based on the A* algorithm to traverse paths for all tasks and obtain multi-region connected paths. Throughout this process, factors such as path length, turning points, and corner angles are thoroughly considered, and a cost matrix is constructed for subsequent optimization processes. Secondly, we reformulate the multi-region path planning problem into a discrete optimization problem and employ genetic algorithms to optimize the task sequence, thus identifying the optimal task execution order under energy constraints. We finally validate the feasibility of the multi-task planning algorithm proposed by conducting experiments in an open environment, a narrow environment and a large-scale environment. Experimental results demonstrate the method\'s capability to find feasible collision-free and cost-optimal task access paths in diverse and complex multi-region planning scenarios.

Genomic selection (GS) has emerged as an effective technology to accelerate crop hybrid breeding by enabling early selection prior to phenotype collection. Genomic best linear unbiased prediction (GBLUP) is a robust method that has been routinely used in GS breeding programs. However, GBLUP assumes that markers contribute equally to the total genetic variance, which may not be the case. In this study, we developed a novel GS method called GA-GBLUP that leverages the genetic algorithm (GA) to select markers related to the target trait. We defined four fitness functions for optimization, including AIC, BIC, R2, and HAT, to improve the predictability and bin adjacent markers based on the principle of linkage disequilibrium to reduce model dimension. The results demonstrate that the GA-GBLUP model, equipped with R2 and HAT fitness function, produces much higher predictability than GBLUP for most traits in rice and maize datasets, particularly for traits with low heritability. Moreover, we have developed a user-friendly R package, GAGBLUP, for GS, and the package is freely available on CRAN (https://CRAN.R-project.org/package=GAGBLUP).

This study aims to develop an automated framework for the characterization of materials which are both hyper-elastic and viscoelastic. This has been evaluated using human articular cartilage (AC). AC (26 tissue samples from 5 femoral heads) underwent dynamic mechanical analysis with a frequency sweep from 1 to 90 Hz. The conversion from a frequency- to time-domain hyper-viscoelastic material model was approximated using a modular framework design where finite element analysis was automated, and a genetic algorithm and interior point technique were employed to solve and optimize the material approximations. Three orders of approximation for the Prony series were evaluated at N = 1, 3 and 5 for 20 and 50 iterations of a genetic cycle. This was repeated for 30 simulations of six combinations of the above all with randomly generated initialization points. There was a difference between N = 1 and N = 3/5 of approximately ~5% in terms of the error estimated. During unloading the opposite was seen with a 10% error difference between N = 5 and 1. A reduction of ~1% parameter error was found when the number of generations increased from 20 to 50. In conclusion, the framework has proved effective in characterizing human AC.

Cervical cancer is a prevalent and concerning disease affecting women, with increasing incidence and mortality rates. Early detection plays a crucial role in improving outcomes. Recent advancements in computer vision, particularly the Swin transformer, have shown promising performance in image classification tasks, rivaling or surpassing traditional convolutional neural networks (CNNs). The Swin transformer adopts a hierarchical and efficient approach using shifted windows, enabling the capture of both local and global contextual information in images. In this paper, we propose a novel approach called Swin-GA-RF to enhance the classification performance of cervical cells in Pap smear images. Swin-GA-RF combines the strengths of the Swin transformer, genetic algorithm (GA) feature selection, and the replacement of the softmax layer with a random forest classifier. Our methodology involves extracting feature representations from the Swin transformer, utilizing GA to identify the optimal feature set, and employing random forest as the classification model. Additionally, data augmentation techniques are applied to augment the diversity and quantity of the SIPaKMeD1 cervical cancer image dataset. We compare the performance of the Swin-GA-RF Transformer with pre-trained CNN models using two classes and five classes of cervical cancer classification, employing both Adam and SGD optimizers. The experimental results demonstrate that Swin-GA-RF outperforms other Swin transformers and pre-trained CNN models. When utilizing the Adam optimizer, Swin-GA-RF achieves the highest performance in both binary and five-class classification tasks. Specifically, for binary classification, it achieves an accuracy, precision, recall, and F1-score of 99.012, 99.015, 99.012, and 99.011, respectively. In the five-class classification, it achieves an accuracy, precision, recall, and F1-score of 98.808, 98.812, 98.808, and 98.808, respectively. These results underscore the effectiveness of the Swin-GA-RF approach in cervical cancer classification, demonstrating its potential as a valuable tool for early diagnosis and screening programs.

Ballistic impacts on human thorax without penetration can produce severe injuries or even death of the carrier. Soft tissue finite element models must capture the non-linear elasticity and strain-rate dependence to accurately estimate the dynamic human mechanical response. The objective of this work is the calibration of a visco-hyperelastic model for soft tissue simulants. Material model parameters have been calculated by fitting experimental stress-strain relations obtained from the literature using genetic algorithms. Several parametric analyses have been carried out during the definition of the optimization algorithm. In this way, we were able to study different optimization strategies to improve the convergence and accuracy of the final result. Finally, the genetic algorithm has been applied to calibrate two different soft tissue simulants: ballistic gelatin and styrene-ethylene-butylene-styrene. The algorithm is able to calculate the constants for visco-hyperelastic constitutive equations with high accuracy. Regarding synthetic stress-strain curves, a short computational time has been shown when using the semi-free strategy, leading to high precision results in stress-strain curves. The algorithm developed in this work, whose code is included as supplementary material for the reader use, can be applied to calibrate visco-hyperelastic parameters from stress-strain relations under different strain rates. The semi-free relaxation time strategy has shown to obtain more accurate results and shorter convergence times than the other strategies studied. It has been also shown that the understanding of the constitutive models and the complexity of the stress-strain objective curves is crucial for the accuracy of the method.

The first step in comprehending the properties of Au10 clusters is understanding the lowest energy structure at low and high temperatures. Functional materials operate at finite temperatures; however, energy computations employing density functional theory (DFT) methodology are typically carried out at zero temperature, leaving many properties unexplored. This study explored the potential and free energy surface of the neutral Au10 nanocluster at a finite temperature, employing a genetic algorithm coupled with DFT and nanothermodynamics. Furthermore, we computed the thermal population and infrared Boltzmann spectrum at a finite temperature and compared it with the validated experimental data. Moreover, we performed the chemical bonding analysis using the quantum theory of atoms in molecules (QTAIM) approach and the adaptive natural density partitioning method (AdNDP) to shed light on the bonding of Au atoms in the low-energy structures. In the calculations, we take into consideration the relativistic effects through the zero-order regular approximation (ZORA), the dispersion through Grimme\'s dispersion with Becke-Johnson damping (D3BJ), and we employed nanothermodynamics to consider temperature contributions. Small Au clusters prefer the planar shape, and the transition from 2D to 3D could take place at atomic clusters consisting of ten atoms, which could be affected by temperature, relativistic effects, and dispersion. We analyzed the energetic ordering of structures calculated using DFT with ZORA and single-point energy calculation employing the DLPNO-CCSD(T) methodology. Our findings indicate that the planar lowest energy structure computed with DFT is not the lowest energy structure computed at the DLPN0-CCSD(T) level of theory. The computed thermal population indicates that the 2D elongated hexagon configuration strongly dominates at a temperature range of 50-800 K. Based on the thermal population, at a temperature of 100 K, the computed IR Boltzmann spectrum agrees with the experimental IR spectrum. The chemical bonding analysis on the lowest energy structure indicates that the cluster bond is due only to the electrons of the 6 s orbital, and the Au d orbitals do not participate in the bonding of this system.

This paper proposes a knowledge-based decision-making system for energy bill assessment and competitive energy consumption analysis for energy savings. As humans have a tendency toward comparison between peers and self-groups, the same concept of competitive behavior is utilized to design knowledge-based decision-making systems. A total of 225 house monthly energy consumption datasets are collected for Maharashtra state, along with a questionnaire-based survey that includes socio-demographic information, household appliances, family size, and some other parameters. After data collection, the pre-processing technique is applied for data normalization, and correlation technique-based key features are extracted. These features are used to classify different house categories based on consumption. A knowledge-based system is designed based on historical datasets for future energy consumption prediction and comparison with actual usage. These comparative studies provide a path for knowledgebase system design to generate monthly energy utilization reports for significant behavior changes for energy savings. Further, Linear Programming and Genetic Algorithms are used to optimize energy consumption for different household categories based on socio-demographic constraints. This will also benefit the consumers with an electricity bill evaluation range (i.e., normal, high, or very high) and find the energy conservation potential (kWh) as well as a cost-saving solution to solve real-world complex electricity conservation problem.

The Fenton process is widely employed for decolorizing industrial wastewater. Therefore, it is imperative to construct a model for optimizing the operational parameters and estimating the efficiency of decolorization within this process. In this study, an artificial neural network (ANN) model was created based on experimental data provided by a previous researcher who examined the decolorization of Direct Red 16 dye (DR16) using a heterogeneous Fenton process within a microchannel reactor. This model was utilized to optimize and forecast the efficiency of decolorization in the Fenton process. The accuracy of the model was validated by comparing its outcomes with actual experimental data. To further improve the efficiency of decolorization, optimal operational parameters were ascertained utilizing the genetic algorithm method. The study revealed that as dye concentrations increased from 10 to 40 mg/l, decolorization efficiencies improved proportionately, peaking at 89.78 %. Optimal operational parameters for maximizing efficiency were identified as a feed flow rate of 1 ml/min, H2O2 concentration at 500 mg/l, Fe2+ concentration of 4 mg/l, and maintaining pH between 2.6 and 2.8. Insights derived from both experimental and model-generated data were used to analyze the impact of operational parameters on decolorization efficiency.