Real-time milk analysis integrated with stacking ensemble learning as a tool for the daily prediction of cheese-making traits in Holstein cattle

BackgroundDespite extensive research on keratoconus (KC) detection with traditional machine learning models, stacking ensemble learning approaches remain underexplored. This paper presents a stacking ensemble learning method to enhance automated KC screening.MethodsThis study utilizes a clinical dataset containing detailed corneal data from 2491 cases classified as non-KC (NKC), subclinical KC (SCKC) and clinical KC (CKC). Each cornea is represented by 79 features extracted from Pentacam imaging. Following extensive pre-processing, key corneal features that are strongly correlated with the target diagnosis are identified. These features are the keratometry of the steepest anterior point, surface variance index, vertical asymmetry index, height decentration index, and height asymmetry index. A novel stacking ensemble model is developed using the selected features to improve corneal classification into NKC, SCKC, and CKC by integrating top tree-based classifiers (random forest, gradient boosting, decision trees) with a support vector machine meta-classifier.ResultsThe pre-processing and feature selection techniques reduced the model's parameters to just 6.33% of the original dataset, improving classification performance, and cutting over 85% of the training time. The performance of the developed model was validated and tested on unseen data. Experimental results showed that the model outperforms existing studies, achieving 99.72% accuracy, precision, sensitivity, F1, and F2 scores, with a Matthews correlation coefficient of 0.995. It accurately classified all NKC and CKC cases, with just one misclassification involving an SCKC case. The model also demonstrated consistent performance on 100 additional unseen test cases, underscoring its generalizability and robustness in KC screening.ConclusionsBy combining the strengths of diverse base models and key Pentacam indices, the stacking ensemble approach ensures reliable, accurate KC screening, providing clinicians with an automated tool for early detection and better patient management.

Photodetectors are essential components in modern optoelectronic technologies, yet experimental characterization of nanomaterial-based devices is often time-consuming and resource-intensive. To address this challenge, this study presents a stacking ensemble learning approach to predict the performance of bismuth-doped graphene quantum dots-based photodetectors under illumination levels ranging from 22 to 110 mW/mm². Four boosting algorithms—Adaptive Boosting, Gradient Boosting, Extreme Gradient Boosting, and Categorical Boosting—were trained on datasets obtained under dark, 22, 66, and 110 mW/mm², while 44 and 88 mW/mm² data were reserved for testing. A stacking ensemble learning model further enhanced prediction accuracy. The final model achieved a coefficient of determination of 0.9874 and a mean absolute error of 0.1840 at 88 mW/mm², effectively predicting the logarithmic current–voltage characteristics. The model also estimated key photodetector metrics, including sensitivity (1589.27), responsivity (2.389 mA/W), and specific detectivity (1.16 × 10¹⁰ Jones). This study explores the use of a stacking ensemble of four boosting algorithms to model the performance of Bi-GQD/p-Si photodetectors across different illumination levels, offering a data-driven alternative to traditional characterization.

Outage duration prediction under typhoon disaster with stacking ensemble learning

Accurately classifying bank term deposit acceptance is critical for optimizing marketing strategies. This study proposes a novel Stacked Ensemble Learning (SEL) approach to improve classification accuracy in this domain. The proposed SEL leverages six diverse base learners namely Decision Tree (DT), Random Forest (RF), Gradient Boosting (GB), XGBoost (XGB), K-Nearest Neighbors (KNN), and Support Vector Machine (SVM) to exploit their complementary strengths and mitigate individual weaknesses. Each base learner generates predictions that are then used as features to sequentially train the six algorithms as meta-classifiers. This iterative process aims to harness the collective knowledge of all base learners. Evaluated on a resampled Bank Marketing Dataset using ENN undersampling, the SEL approach achieved its highest performance utilizing Random Forest as the final meta-classifier, with an accuracy of 96.75%, an F1-score of 96.72%, and an AUC-ROC of 0.9038. These findings highlight the effectiveness of SEL for bank term deposit classification. Our work contributes to the field by exploring a novel SEL architecture and demonstrating its success in a financial context. Future research can investigate alternative ensemble architectures and explore the factors influencing the performance of specific algorithms within this domain.

Genome-wide association studies (GWAS) have been a successful tool for identifying quantitative trait loci (QTL) for economically important traits in dairy cows. However, the availability of QTLs linked to phenotypic traits is limited in the literature. In this study, we used GWAS, haplotype association, and fine-mapping analyses to identify candidate variants associated with milk production, health, and reproductive traits in 380 Chinese Holstein cattle from Southern China using whole-genome sequence data. GWAS identified 91 genome-wide significant signals that were annotated to 63 genes associated with milk production, health, and reproductive traits in dairy cattle. Haplotype association analysis further revealed that eight GWAS signals within three QTLs were associated with milk production and health traits of cows. Fine-mapping analysis revealed that 3 GWAS signals (6_92530313_G_A, 10_17185230_G_A, and 10_17209112_T_G) were the potential causal variants. Several candidate genes, including ANKS1B, IL17RD, CNOT6L, AOC1, and TLE3, have been confirmed to be associated with milk production, health, and reproductive traits in dairy cows. These findings significantly contribute to unraveling the genetic basis of economically important traits in Holstein cattle.

Given the limitations of traditional single prediction models in dealing with complex influencing factors on academic performance in universities, this study proposes an academic performance prediction method based on Stacking multi model fusion. Taking college students majoring in digital media as the research object, a learning engagement measurement scale is introduced to provide targeted data support for model construction, and the principle of Stacking ensemble learning and its advantages in improving model generalization ability and stability are systematically explained. Provide a detailed description of the construction process for Stacking ensemble learning models. Select candidate algorithms from random forest, XGBoost, and KNN machine learning algorithms in the selection of basic learners; Using linear regression algorithm as a meta learner, optimizing model parameters through cross validation strategy; At the same time, strict preprocessing is carried out on the collected data, and raverse all combinations of base classifier algorithms for ensemble training, and construct a Stacking ensemble classifier. In the experimental stage, based on students' grades in digital media courses, the effectiveness of the model is evaluated by comparing the predictive performance of Stacking ensemble classifiers and single classifiers. The experimental results show that the Stacking ensemble classifier performs excellently in prediction accuracy and robustness, significantly better than a single classifier. The R² Score has increased by approximately 10.42% to 16.82%. This model can objectively and accurately reflect students' learning status, providing scientific basis for blended course teaching design, digital media professional teaching management strategy formulation, and personalized guidance for students' academic careers.

Determination of malathion content in sorghum grains using hyperspectral imaging technology combined with stacked machine learning models

Sheep milk is mainly intended to manufacture a wide variety of high-quality cheeses. The ovine cheese industry would benefit from an improvement, through genetic selection, of traits related to the milk coagulation properties (MCPs) and cheese yield-related traits, broadly denoted as "cheese-making traits." Considering that routine measurements of these traits needed for genetic selection are expensive and time-consuming, this study aimed to evaluate the accuracy of a cheese-making phenotype imputation method based on the information from official milk control records combined with the pH of the milk. For this study, we analyzed records of milk production traits, milk composition traits, and measurements of cheese-making traits available from a total of 1,145 dairy ewes of the Spanish Assaf sheep breed. Cheese-making traits included five related to the MCPs and two cheese yield-related traits. The milk and cheese-making phenotypes were adjusted for significant effects based on a general linear model. The adjusted phenotypes were used to define a multiple-phenotype imputation procedure for the cheese-making traits based on multivariate normality and Markov chain Monte Carlo sampling. Five of the seven cheese-making traits considered in this study achieved a prediction accuracy of 0.60 computed as the correlation between the adjusted phenotypes and the imputed phenotypes. Particularly the logarithm of curd-firming time since rennet addition (logK20) (0.68), which has been previously suggested as a potential candidate trait to improve the cheese ability in this breed, and the logarithm of the ratio between the rennet clotting time and the curd firmness at 60 min (logRCT/A60) (0.65), which has been defined by other studies as an indicator trait of milk coagulation efficiency. This study represents a first step toward the possible use of the phenotype imputation of cheese-making traits to develop a practical methodology for the dairy sheep industry to impute cheese-making traits only based on the analysis of a milk sample without the need of pedigree information. This information could be also used in future planning of specific breeding programs considering the importance of the cheese-making efficiency in dairy sheep and highlights the potential of phenotype imputation to leverage sample size on expensive, hard-to-measure phenotypes.

In comparison to other methodologies, Machine Learning has proven to be an effective tool for making reasonable predictions. Initially, a single machine learning model is used on data to make predictions; however, instead of using a single machine learning model, a collection of ML models is employed instead. Models can reduce prediction variance, bias, or both. The result provided will be more appealing and correct if appropriate features affecting the prediction values are supplied. This study presents a framework for selecting feature subsets using the L2 regularization feature selection technique. The study took into account 11 crops and 15 characteristics from 300 districts across India. For predicting yield, basic learners' models such as Linear Regression, LASSO Regression, Decision Trees, Random Forests, Extreme Gradient Boosting (XGBoost), and Support Vector Machines are initially trained and tested. Base learners are used to create the stacking ensemble and the proposed optimum stacking ensemble. In terms of the performance measures employed, the proposed Optimized stacking ensemble shows approximately (MSE =6408, Accuracy=85%) outperforms the Normal stacking ensemble (MSE=8315, Accuracy=83%).

Modern power systems incorporate ultra-high-voltage transmission lines with series compensation to enhance their reliability and stability. These configurations generate complex data patterns in electrical signals, which present challenges for accurate fault diagnosis. This complexity arises from various potential faults, such as high-impedance faults and inductive-capacitive interactions, compounded by data scarcity owing to privacy and cybersecurity constraints. This study employs a simulation-based analysis to facilitate fault detection, classification, and localization as unified Multi-Classification tasks. The methodology improves the time-frequency domain data through meta-feature engineering and utilizes consensus-based feature selection by combining gradient boosting, variance thresholding, and mutual information. Model learning is conducted using Bayesian optimization within a Stacking Ensemble, integrating Extra Trees, Light Gradient Boosting Machine, and Extreme Gradient Boosting with an optimized Random Forest meta-classifier. The evaluation considers the accuracy, computational time, inference speed, and memory usage under challenging conditions to address practical limitations. The results indicate that the Stacking Ensemble achieves the highest performance despite its greater computational demand. Extra Trees offers the fastest execution but shows decreased accuracy with increased classification complexity. The Light Gradient Boosting Machine and Extreme Gradient Boosting demonstrate optimized performance across tasks owing to enhanced data processing. These findings confirm the practical applicability of the proposed fault diagnosis framework to modern ultra-high-voltage power systems.

Weather forecasting is an important factor affecting production and life. With the development of technology, weather forecasting methods such as weather map forecasting, numerical weather forecasting, and quantitative forecasting methods have emerged. However, these traditional data analysis methods have shortcomings such as incomplete analysis, insufficient objectivity, inability to quantitatively predict the weather, and low prediction accuracy. The import of neural networks into the field of weather forecasting helps to alleviate the above shortcomings and improve the accuracy of weather forecasting. In this paper, the LSTM network and the CNN network are used to predict the sand-dust storm weather. In order to improve the prediction performance, we use the Stacking integration algorithm to fuse the LSTM and CNN models. To improve the experimental scientific and comprehensive, using fully connected network and support vector machine as meta-classifiers, two LSTM-CNN integrated sand-dust storm prediction models are established. At last, the above integrated model is used in the prediction of sand-dust storms in Inner Mongolia. The experimental results show that compared with a single LSTM or CNN model, the Stacking ensemble model has different degrees of improvement in model evaluation indicators such as accuracy, precision, recall, and f1-score. The Stacking ensemble model uses the fully connected network model as the meta-classifier is even better. These prove that the Stacking ensemble algorithm improves the sand-dust storm classification effect and generalization ability of a single neural network to a certain extent.

Background: Neuropeptide Y (NPY), a 36-AA neurotransmitter involved in the control of appetite, feeding and energy homeostasis. The bovine NPY gene is located on chromosome 4 and consists of four exons. Earlier studies have reported that genes involved in feed intake regulation, energy production and energy regulation may affect different growth and production traits in cattle. Information associating NPY SNP to reproduction and production traits in dairy cattle is, however, limited. Hence, the present study was planned to explore SNPs in NPY gene and its possible association with reproduction and first lactation production traits in Sahiwal cattle. Methodology: DNA samples were isolated from blood that has collected from hundred and three Sahiwal cows. Three regions of NPY were amplified using designed primer pairs. The sequencing of the targeted regions was done in 103 Sahiwal cows. Least squares analysis of variance was carried out for unequal and non-orthogonal data using the technique described by Harvey (1990) to study effect of non-genetic factors. Significance of differences based on genotypes effect of growth, reproduction and production traits were tested by general linear models.Result: Sequence data analysis revealed two transversions in NPY gene. For these identified nucleotide variations, positions were A72073973C (intron 3) and C72068620A (intron 3). This is the first report of the presence of NPY gene polymorphism in purebred Bos indicus of Indian origin. For SNP A72073973C, performances of animals with homozygote AA genotype exhibited significantly higher milk production (P≤0.01) and growth performance (P≤0.05) than heterozygote genotype. Heterozygous genotype exhibited superior performance for the SNP C72068620A which was found to be significantly associated (P≤0.05) with 18M wt, WFS, WFC, FCI and FL305DMY.

Non-additive genetic effects are usually ignored in animal breeding programs due to data structure (e.g., incomplete pedigree), computational limitations and over-parameterization of the models. However, non-additive genetic effects may play an important role in the expression of complex traits in livestock species, such as fertility and reproduction traits. In this study, components of genetic variance for additive and non-additive genetic effects were estimated for a variety of fertility and reproduction traits in Holstein cattle using pedigree and genomic relationship matrices. Four linear models were used: (a) an additive genetic model; (b) a model including both additive and epistatic (additive by additive) genetic effects; (c) a model including both additive and dominance effects; and (d) a full model including additive, epistatic and dominance genetic effects. Nine fertility and reproduction traits were analysed, and models were run separately for heifers (N=5,825) and cows (N=6,090). For some traits, a larger proportion of phenotypic variance was explained by non-additive genetic effects compared with additive effects, indicating that epistasis, dominance or a combination thereof is of great importance. Epistatic genetic effects contributed more to the total phenotypic variance than dominance genetic effects. Although these models varied considerably in the partitioning of the components of genetic variance, the models including a non-additive genetic effect did not show a clear advantage over the additive model based on the Akaike information criterion. The partitioning of variance components resulted in a re-ranking of cows based solely on the cows' additive genetic effects between models, indicating that adjusting for non-additive genetic effects could affect selection decisions made in dairy cattle breeding programs. These results suggest that non-additive genetic effects play an important role in some fertility and reproduction traits in Holstein cattle.

SummaryThe objective of this study was to compare accuracies of different Bayesian regression models in predicting molecular breeding values for health traits in Holstein cattle. The dataset was composed of 2505 records reporting the occurrence of retained fetal membranes (RFM), metritis (MET), mastitis (MAST), displaced abomasum (DA), lameness (LS), clinical endometritis (CE), respiratory disease (RD), dystocia (DYST) and subclinical ketosis (SCK) in Holstein cows, collected between 2012 and 2014 in 16 dairies located across the US. Cows were genotyped with the Illumina BovineHD (HD, 777K). The quality controls for SNP genotypes were HWE P‐value of at least 1 × 10−10; MAF greater than 0.01 and call rate greater than 0.95. The fimpute program was used for imputation of missing SNP markers. The effect of each SNP was estimated using the Bayesian Ridge Regression (BRR), Bayes A, Bayes B and Bayes Cπ methods. The prediction quality was assessed by the area under the curve, the prediction mean square error and the correlation between genomic breeding value and the observed phenotype, using a leave‐one‐out cross‐validation technique that avoids iterative cross‐validation. The highest accuracies of predictions achieved were: RFM [Bayes B (0.34)], MET [BRR (0.36)], MAST [Bayes B (0.55), DA [Bayes Cπ (0.26)], LS [Bayes A (0.12)], CE [Bayes A (0.32)], RD [Bayes Cπ (0.23)], DYST [Bayes A (0.35)] and SCK [Bayes Cπ (0.38)] models. Except for DA, LS and RD, the predictive abilities were similar between the methods. A strong relationship between the predictive ability and the heritability of the trait was observed, where traits with higher heritability achieved higher accuracy and lower bias when compared with those with low heritability. Overall, it has been shown that a high‐density SNP panel can be used successfully to predict genomic breeding values of health traits in Holstein cattle and that the model of choice will depend mostly on the genetic architecture of the trait.

introduction 23 2 -Genome-wide association studies for genetic effects that change during lactation in dairy cattle 55 3 -Genome-wide association study for genotype by lactation stage interaction of milk production traits in dairy cattle 85 4 -Phenotypic and genetic effects of pregnancy on milk production traits in Holstein-Friesian cattle 105 5 -Phenotypic and genetic effects of season on milk production traits in dairy cattle in the Netherlands