Conventional Linear Model Research Articles

Comparative Analysis of Machine Learning Models for Weather Forecasting: A Heathrow Case Study

Accurate weather forecasting, especially temperature prediction, is fundamental for various segments within the UK, including agriculture, energy, and policy planning, as the nation adapts to the effects of climate change. This study addresses the limitations of conventional linear models in capturing the complex, non-linear relationships within meteorological data by comparing the effectiveness of different Machine Learning (ML) strategies. This study evaluates the performance of baseline ML models, such as Linear Regression (LR), Support Vector Regression (SVR), and K-Nearest Neighbors (KNN). It also examines advanced ensemble and boosting models such as Decision Tree (DT), Random Forest (RF), XGBoost (XGB), LightGBM (LGBM), and CatBoost, using a comprehensive dataset from Heathrow Airport. Detailed preprocessing, model training, and optimization through cross-validation were conducted, with performance assessed using Mean Squared Error (MSE) and Coefficient of Determination (R²) metrics. The results demonstrate that ensemble methods, particularly XGB and LGBM, offer superior predictive accuracy for weather forecasting tasks, highlighting their potential to enhance predictive models in meteorological applications.

Predicting e-commerce product prices through the integration of variational mode decomposition and deep neural networks

Product prices frequently manifest nonlinear and nonstationary time-series attributes, indicating potential variations in their behavioral patterns over time. Conventional linear models may fall short in adequately capturing these intricate properties. In addressing this, the present study leverages the adaptive and non-recursive attributes of the Variational Mode Decomposition (VMD) methodology. It employs VMD to dissect the intricate time series into multiple Intrinsic Mode Functions (IMF). Subsequently, a method rooted in the minimum fuzzy entropy criterion is introduced for determining the optimal modal number (K) in the VMD decomposition process. This method effectively mitigates issues related to modal confusion and endpoint effects, thereby enhancing the decomposition efficacy of VMD. In the subsequent phase, deep neural networks (DNN) are harnessed to forecast the identified modes, with the cumulative modal predictions yielding the ultimate e-commerce product price prognostications. The predictive efficacy of the proposed Variational Mode Decomposition-deep neural network (VMD-DNN) decomposition model is assessed on three public datasets, wherein the mean absolute percentage error (MAPE) on the E-commerce Price Prediction Dataset and Online Retail Dataset is notably low at 0.6578 and 0.5414, respectively. This corresponds to a remarkable error reduction rate of 66.5% and 70.4%. Moreover, the VMD-DNN decomposition model excels in predicting e-commerce product prices through DNN, thereby amplifying the VMD decomposition capability by 4%. The VMD-DNN model attains superior results in terms of directional symmetry, boasting the highest Directional Symmetry (DS) score of 86.25. Notably, the forecasted trends across diverse price ranges closely mirror the actual trends.

The effect of multiband sequences on statistical outcome measures in functional magnetic resonance imaging using a gustatory stimulus

Recent technical developments have led to the invention of multiband functional magnetic resonance imaging (fMRI) sequences that allow for faster sampling rates. However, some studies have highlighted problems with these sequences, leading to a decreased temporal signal-to-noise ratio (tSNR). In addition, this temporal noise may interfere with detecting reward-related responses in mesolimbic regions. The blood-oxygen-level-dependent signal utilized in the majority of fMRI measurements is relatively slow. Furthermore, the cerebral response to gustatory stimuli would also be relatively slow. Therefore, given the temporal noise issues with multiband sequences, it is unclear whether multiband sequences are necessary for fMRI studies using gustatory stimuli. We thus conducted an fMRI experiment using a gustatory stimulus to investigate the effects of multiband sequences and increased sampling rates on statistical outcome measures. A single-band sequence with a repetition time (TR) of 2 s of phantom fMRI data and gustatory fMRI data from the gustatory regions exhibited the highest tSNR, although the tSNR of this sequence of gustatory fMRI was not statistically different from tSNR of multiband sequences with a TR of 2 s in any of the selected region of interests. Conventional general linear model analysis of fMRI showed that single-band sequences are more advantageous than multiband sequences for detecting brain responses to gustatory stimuli in the primary gustatory cortex. In addition, a Bayesian data comparison showed that data derived from a single-band sequence with a TR of 2 s was optimal for inferring neuronal connectivity in gustatory processing. Therefore, a conventional single-band sequence with a TR of 2 s is more appropriate for fMRI with gustatory stimuli. Image acquisition sequences should be selected aligned with the study objectives and target brain regions.

Improving Business Insurance Loss Models by Leveraging InsurTech Innovation

Recent transformative and disruptive advancements in the insurance industry have embraced various InsurTech innovations. In particular, with the rapid progress in data science and computational capabilities, InsurTech is able to integrate a multitude of emerging data sources, shedding light on opportunities to enhance risk classification and claims management. This article presents a collaborative effort as we combine real-life proprietary insurance claims information together with InsurTech data to enhance the loss model, a fundamental component of insurance companies’ risk management. Our study further utilizes a tree-based model and a conventional linear model to quantify the predictive improvement of the InsurTech-enhanced loss model over that of the insurance in-house model. The quantification process provides a deeper understanding of the value of InsurTech innovation and advocates potential risk factors that are unexplored in traditional insurance loss modeling. This study represents a successful undertaking of an academic–industry collaboration, suggesting an inspiring path for future partnerships between industry and academic institutions.

Machine learning insights: probing the variable importance of ex-ante information

PurposeEmpirical examinations of initial public offering (IPO) initial returns often rely heavily on linear regression models. However, these models can prove inefficient owing to their susceptibility to outliers, a common occurrence in IPO data. This study introduces a machine learning method, known as random forest, to address issues that linear regression may struggle to resolve.Design/methodology/approachThe study’s sample comprises 352 fixed-priced IPOs from the year 2004 until 2021. A unique aspect of this research is its application of the random forest method. The accuracy of random forest in comparison to other methods is evaluated. The findings indicate that the random forest model significantly outperforms other methods in all of the evaluated aspects.FindingsThe variable importance measure indicates that investors’ demand, divergence of opinion among investors and offer price are the most crucial predictors of IPO initial returns. These determinants hold particular significance due to the widespread use of the fixed-price method in Malaysia, as this method amplifies the information asymmetry in the IPO market.Originality/valueTo the best of the authors’ knowledge, this study is among the pioneering works in Malaysian literature to apply the random forest method to address the constraints of conventional linear regression models. This is achieved by considering a more extensive array of factors and acknowledging the influence of outliers. Additionally, this study adds value to Malaysian literature by ranking and identifying the ex-ante information that best signals the issuing firm’s quality. This contribution facilitates prospective investors’ decision-making processes and provides issuing firms with effective means to communicate their value and quality to the IPO market.

Separating group- and individual-level brain signatures in the newborn functional connectome: A deep learning approach

Recent studies indicate that differences in cognition among individuals may be partially attributed to unique brain wiring patterns. While functional connectivity (FC)-based fingerprinting has demonstrated high accuracy in identifying adults, early studies on neonates suggest that individualized FC signatures are absent. We posit that individual uniqueness is present in neonatal FC data and that conventional linear models fail to capture the rapid developmental trajectories characteristic of newborn brains. To explore this hypothesis, we employed a deep generative model, known as a variational autoencoder (VAE), leveraging two extensive public datasets: one comprising resting-state functional MRI (rs-fMRI) scans from 100 adults and the other from 464 neonates. VAE models trained on rs-fMRI from both adults and newborns produced superior age prediction performance (with r between predicted- and actual age ∼ 0.7) and individual identification accuracy (∼45 %) compared to models trained solely on adult or neonatal data. The VAE model also showed significantly higher individual identification accuracy than linear models (=10∼30 %). Importantly, the VAE differentiated connections reflecting age-related changes from those indicative of individual uniqueness, a distinction not possible with linear models. Moreover, we derived 20 latent variables, each corresponding to distinct patterns of cortical functional network (CFNs). These CFNs varied in their representation of brain maturation and individual signatures; notably, certain CFNs that failed to capture neurodevelopmental traits, in fact, exhibited individual signatures. CFNs associated with neonatal neurodevelopment predominantly encompassed unimodal regions such as visual and sensorimotor areas, whereas those linked to individual uniqueness spanned multimodal and transmodal brain regions. The VAE's capacity to extract features from rs-fMRI data beyond the capabilities of linear models positions it as a valuable tool for delineating cognitive traits inherent in rs-fMRI and exploring individualized imaging phenotypes.

Handling Volatility and Nonlinearity in Wind Speed Data: A Comparative Analysis between ARIMA-GARCH and ARIMA-MLP

One of the notable features of wind speed is its volatility and nonlinearity. Thorough assessment on the presence of these features is crucial to obtain a wind speed forecasting model with higher accuracy. In this study, the conventional time series linear model; ARIMA model was applied to assess the internal structure of the wind speed daily data in two stations in Johor; Senai and Mersing. Due to the existence of some nonlinearity features in the residuals part of ARIMA modelling, two nonlinear models were introduced to capture the internal structure of the residual data. Both conventional time series models; GARCH, and machine learning model; MLP was applied to model the residuals of ARIMA model. The out-sample performance in forecasting accuracy was compared between the ARIMA-GARCH model and the ARIMA-MLP model. The findings proves that MLP model has outperformed GARCH model in capturing the dynamics in the residual data by providing the lowest error measurements. Thus, the machine learning approaches has proven its superiority against the conventional time series nonlinear model in handling the nonlinearity in the daily wind speed series for wind speed forecasting.

Machine learning-assisted performance prediction from the synthesis conditions of nanofiltration membranes

Optimizing membrane fabrication conditions, including monomer and catalyst concentrations, reaction time, etc., is crucial for achieving high-performance membranes. However, the multitude of variables involved can result in a complex and laborious permutation process, making trial-and-error optimization challenging. To address this issue, we developed a conventional multiple linear regression model and machine learning (ML) models, specifically random forest (RF) and multi-layer perceptron (MLP), to predict the performance of nanofiltration membranes in terms of key parameters such as pure water permeance or PWP (LMH/bar), Na2SO4 rejection (%), and NaCl rejection (%), based on specified input variable ranges. The input variables utilized to construct the models are the concentration of piperazine (PIP) (0.01–2 wt%), the concentration of trimesoyl chloride (TMC) (0.05–0.15 wt%), the concentration of sodium lauryl sulfate (SLS) (0–10 mM), and reaction time (5–1200 s). The conventional regression model failed to predict the membrane performance. The RF model exhibited the best prediction capability for PWP and NaCl rejection with the R2 of 0.9806 and 0.9812 for training, and 0.9669 and 0.9082 for testing, respectively. Similarly, the MLP model outperformed the RF model in predicting Na2SO4 rejection with an R2 of 0.9972 for testing and 0.9844 for training. The best membrane exhibited permeance ranging from 16 to 20 LMH/bar and selectivity between NaCl and Na2SO4 of over 4000, was facilitated by specific conditions. These conditions included lower concentrations of PIP (0.05–0.1 wt%), intermediate concentration of TMC (0.1 wt%), lower concentration of SLS (1 mM), and shorter reaction times (5–30 s). The best-performing ML-based models have been used to provide insights into the relative importance of these input variables in determining membrane performance, thereby aiding in correlating model predictions with fundamental principles of membrane fabrication processes.

Improved MTPA and MTPV Optimal Criteria Analysis Based on IPMSM Nonlinear Flux-Linkage Model

The use of interior permanent-magnet synchronous machines (IPMSMs) is prevalent in automotive and vehicle traction applications due to their high efficiency over a wide speed range. Given the high-power-density requirements of automotive IPMSMs, it is imperative to consider the effect of nonlinearities, such as saturation and cross-coupling, on the motor model. The aforementioned nonlinearities render conventional linear motor models incapable of accurately describing the operating characteristics of the IPMSM, including the maximum torque per ampere (MTPA) trajectory, the flux-weakening (FW) trajectory, and the maximum torque per volt (MTPV) trajectory. With respect to the linear motor model, the nonlinear flux-linkage model is gradually receiving attention from researchers. This modeling method represents the nonlinear behavior of the motor through the direct establishment of a bidirectional mapping relationship between flux-linkage and current. It is capable of naturally incorporating the effects of magnetic saturation and cross-coupling factors. However, the analysis of the current trajectory optimal criteria based on this model has not yet been reported. In this paper, the optimal criteria for the MTPA and MTPV current trajectories are analyzed based on the nonlinear flux-linkage model of IPMSMs. Firstly, the nonlinear flux-linkage model of the tested IPMSM is established by the experimental calibration method. The mathematical analytical expressions of the MTPA and MTPV optimal criteria are then analyzed by constructing and solving optimal problems with different objectives. Finally, the current command table applicable to actual motor control is constructed by calculating the current command for different operating conditions according to the optimal criteria proposed in this paper. The validity and feasibility of the optimal criteria proposed in this paper are verified through experimental tests on different operating conditions.

Machine learning-based causal inference for evaluating intervention in travel behaviour research: A difference-in-differences framework

Causal inference with the difference-in-differences (DID) framework is popular in identifying causal effects with observational data and has started to be applied in recent travel behaviour studies. Most relevant transportation research adopts the conventional linear parametric DID model, which is known to be inflexible and restrictive. This study applies non-parametric DID estimators facilitated by machine learning (ML) models for causal inference in a variety of data scenarios. Semi-parametric and doubly robust estimators are established and integrated with the ML-based cross-fitting pipeline. Simulation studies and empirical case studies are conducted to showcase the ability of ML-based DID to detect causal effects from both simulated and real-world datasets. Results suggest that the proposed methods outperform conventional DID models in all data scenarios. Light working models are generally preferred over hyperparameter-dependent ones for their comparable performance, lower computational burden, and higher levels of compatibility to real-world empirical analysis. Empirical case studies also demonstrate how the proposed DID method could be applied to evaluate the impacts of various interventions on travel behaviour in different contexts. The present study adds to the existing travel behaviour literature by leveraging machine learning algorithms and non-parametric estimators to the impact evaluation of external interventions on travel characteristics and expanding the application of causal inference approaches in transportation research.

A study of forecasting the Nephila clavipes silk fiber's ultimate tensile strength using machine learning strategies

Recent advancements in biomaterial research conduct artificial intelligence for predicting diverse material properties. However, research predicting the mechanical properties of biomaterial based on amino acid sequences have been notably absent. This research pioneers the use of classification models to predict ultimate tensile strength from silk fiber amino acid sequences, employing logistic regression, support vector machines with various kernels, and a deep neural network (DNN). Remarkably, the model demonstrates a high accuracy of 0.83 during the generalization test. The study introduces an innovative approach to predicting biomaterial mechanical properties beyond traditional experimental methods. Recognizing the limitations of conventional linear prediction models, the research emphasizes the future trajectory toward DNNs that can adeptly capture non-linear relationships with high precision. Moreover, through comprehensive performance comparisons among diverse prediction models, the study offers insights into the effectiveness of specific models for predicting the mechanical properties of certain materials. In conclusion, this study serves as a pioneering contribution, laying the groundwork for future endeavors and advocating for the seamless integration of AI methodologies into materials research.

Unveiling ecological/evolutionary insights in HIV viral load dynamics: Allowing random slopes to observe correlational changes to CpG-contents and other molecular and clinical predictors

In the context of infectious diseases, the dynamic interplay between ever-changing host populations and viral biology demands a more flexible modeling approach than common fixed correlations. Embracing random-effects regression models allows for a nuanced understanding of the intricate ecological and evolutionary dynamics underlying complex phenomena, offering valuable insights into disease progression and transmission patterns. In this article, we employed a random-effects regression to model an observed decreasing median plasma viral load (pVL) among individuals with HIV in Mexico City during 2019–2021. We identified how these functional slope changes (i.e. random slopes by year) improved predictions of the observed pVL median changes between 2019 and 2021, leading us to hypothesize underlying ecological and evolutionary factors. Our analysis involved a dataset of pVL values from 7325 ART-naïve individuals living with HIV, accompanied by their associated clinical and viral molecular predictors. A conventional fixed-effects linear model revealed significant correlations between pVL and predictors that evolved over time. However, this fixed-effects model could not fully explain the reduction in median pVL; thus, prompting us to adopt random-effects models. After applying a random effects regression model—with random slopes and intercepts by year—, we observed potential "functional changes" within the local HIV viral population, highlighting the importance of ecological and evolutionary considerations in HIV dynamics: A notably stronger negative correlation emerged between HIV pVL and the CpG content in the pol gene, suggesting a changing immune landscape influenced by CpG-induced innate immune responses that could impact viral load dynamics. Our study underscores the significance of random effects models in capturing dynamic correlations and the crucial role of molecular characteristics like CpG content. By enriching our understanding of changing host-virus interactions and HIV progression, our findings contribute to the broader relevance of such models in infectious disease research. They shed light on the changing interplay between host and pathogen, driving us closer to more effective strategies for managing infectious diseases. Significance of the studyThis study highlights a decreasing trend in median plasma viral loads among ART-naïve individuals living with HIV in Mexico City between 2019 and 2021. It uncovers various predictors significantly correlated with pVL, shedding light on the complex interplay between host-virus interactions and disease progression. By employing a random-slopes model, the researchers move beyond traditional fixed-effects models to better capture dynamic correlations and evolutionary changes in HIV dynamics. The discovery of a stronger negative correlation between pVL and CpG content in HIV-pol sequences suggests potential changes in the immune landscape and innate immune responses, opening avenues for further research into adaptive changes and responses to environmental shifts in the context of HIV infection. The study's emphasis on molecular characteristics as predictors of pVL adds valuable insights to epidemiological and evolutionary studies of viruses, providing new avenues for understanding and managing HIV infection at the population level.

The Presence of Chaos in a Viscoelastic Harmonically Forced Von Mises Truss

Abstract This work investigates how viscoelasticity affects the dynamic behavior of a lumped-parameter model of a bistable von Mises truss. The system is controlled by a linear first-order equation and a second-order nonlinear Duffing equation with a quadratic nonlinearity that governs mechanical behavior. The second-order equation controls mechanical oscillations, while the linear first-order equation controls viscoelastic force evolution. Combined, the two equations form a third-order jerk equation that controls system dynamics. Viscoelasticity adds time scales and degrees-of-freedom to material behavior, distinguishing it from viscosity-only systems. Due to harmonic excitation, the system exhibits varied dynamic responses, from periodic to quasi-periodic to chaotic. We explore the dynamics of a harmonically forced von Mises truss with viscous damping to address this purpose. We demonstrate this system's rich dynamic behavior due to driving amplitude changes. This helps explain viscoelastic system behavior. A viscoelastic unit replaces the viscous damper, and we show that, although viscous damping merely changes how fast the trajectory decays to an attractor, viscoelasticity modifies both the energy landscape and the rate of decay. In a conventional linear solid model, three viscoelastic parameters control the system's behavior instead of one, as in pure viscous damping. This adds degrees-of-freedom that affect system dynamics. We present the parameter space for chaotic behavior and the shift from regular to irregular motion. Finally, Melnikov's criteria identify the regular-chaotic threshold. The system's viscous and elastic components affect the chaotic threshold amplitude

Shoulder viscoelasticity in a raptor-inspired model alleviates instability and enhances passive gust rejection

Recent experiments with gliding raptors reveal a perplexing dichotomy: remarkably resilient gust rejection, but, at the same time, an exceptionally high degree of longitudinal instability. To resolve this incompatibility, a multiple degree of freedom model is developed with minimal requisite complexity to examine the hypothesis that the bird shoulder joint may embed essential stabilizing and preflexive mechanisms for rejecting rapid perturbations while simplifying and reducing control effort. Thus, the formulation herein is centrally premised upon distinct wing pitch and body pitch angles coupled via a Kelvin–Voigt viscoelastic shoulder joint. The model accurately exhibits empirical gust response of an unstable gliding raptor, generates biologically plausible equilibrium configurations, and the viscoelastic shoulder coupling is shown to drastically alleviate the high degree of instability predicted by conventional linear flight dynamics models. In fact, stability analysis of the model predicts a critical system timescale (the time to double amplitude of a pitch divergence mode) that is commensurate with in vivo measured latency of barn owls (Tyto alba). Active gust mitigation is studied by presupposing the owl behaves as an optimal controller. The system is under-actuated and the feedback control law is resolved in the controllable subspace using a Kalman decomposition. Importantly, control-theoretic analysis precisely identifies what discrete gust frequencies may be rapidly and passively rejected versus disturbances requiring feedback control intervention.

Clarifications on the intersectional MAIHDA approach: A conceptual guide and response to Wilkes and Karimi (2024)

Intersectional Multilevel Analysis of Individual Heterogeneity and Discriminatory Accuracy (MAIHDA) has been welcomed as a new gold standard for quantitative evaluation of intersectional inequalities, and it is being rapidly adopted across the health and social sciences. In their commentary “What does the MAIHDA method explain?”, Wilkes and Karimi (2024) raise methodological concerns with this approach, leading them to advocate for the continued use of conventional single-level linear regression models with fixed-effects interaction parameters for quantitative intersectional analysis.In this response, we systematically address these concerns, and ultimately find them to be unfounded, arising from a series of subtle but important misunderstandings of the MAIHDA approach and literature. Since readers new to MAIHDA may share confusion on these points, we take this opportunity to provide clarifications. Our response is organized around four important clarifications: (1) At what level are the additive main effect variables defined in intersectional MAIHDA models? (2) Do MAIHDA models have problems with collinearity? (3) Why does the Variance Partitioning Coefficient (VPC) tend to be small, and the Proportional Change in Variance (PCV) tend to be large in MAIHDA? and (4) What are the goals of MAIHDA analysis?

Enhancing selection of alcohol consumption-associated genes by random forest.

Machine learning methods have been used in identifying omics markers for a variety of phenotypes. We aimed to examine whether a supervised machine learning algorithm can improve identification of alcohol-associated transcriptomic markers. In this study, we analysed array-based, whole-blood derived expression data for 17873 gene transcripts in 5508 Framingham Heart Study participants. By using the Boruta algorithm, a supervised random forest (RF)-based feature selection method, we selected twenty-five alcohol-associated transcripts. In a testing set (30 % of entire study participants), AUC (area under the receiver operating characteristics curve) of these twenty-five transcripts were 0·73, 0·69 and 0·66 for non-drinkers v. moderate drinkers, non-drinkers v. heavy drinkers and moderate drinkers v. heavy drinkers, respectively. The AUC of the selected transcripts by the Boruta method were comparable to those identified using conventional linear regression models, for example, AUC of 1958 transcripts identified by conventional linear regression models (false discovery rate < 0·2) were 0·74, 0·66 and 0·65, respectively. With Bonferroni correction for the twenty-five Boruta method-selected transcripts and three CVD risk factors (i.e. at P < 6·7e-4), we observed thirteen transcripts were associated with obesity, three transcripts with type 2 diabetes and one transcript with hypertension. For example, we observed that alcohol consumption was inversely associated with the expression of DOCK4, IL4R, and SORT1, and DOCK4 and SORT1 were positively associated with obesity, and IL4R was inversely associated with hypertension. In conclusion, using a supervised machine learning method, the RF-based Boruta algorithm, we identified novel alcohol-associated gene transcripts.

A novel linear time clustering using heuristically improved mrk-medoids based on modified squirrel search algorithm

ABSTRACT The rapid development of different techniques and the data are accumulated with distinctive properties with high dimensions and huge size. The most essential approach in data mining is clustering, which groups a set of data into clusters. The training of high-dimensional data and huge volume data in clustering models exhibits low computational efficiency and high computational cost. These clustering methods clarify the inherent properties and discover new information from the data. This proposal plans to design and develop the novel Heuristic-mrk-medoids (H-mrk-medoids) clustering for handling the linear time clustering of big data. The aggregation of data into chunks and optimisation of the centroid is done in the map phase, and clustering is performed by optimising the weighted centroid in the reduce phase. As a main contribution of the paper, the mrk-medoids are optimally tuned by the Modified Squirrel Search Algorithm (M-SSA), which ensures efficient clustering based on the fitness quality measure. The accuracy rate of the designed method is 99% and also the RMSE rate of the offered approach is 0.393095%. The result of the proposed approach has shown major improvements in the efficiency of clustering when compared to conventional linear time clustering models.

Application of deep learning with bivariate models for genomic prediction of sow lifetime productivity-related traits.

Pig breeders cannot obtain phenotypic information at the time of selection for sow lifetime productivity (SLP). They would benefit from obtaining genetic information of candidate sows. Genomic data interpreted using deep learning (DL) techniques could contribute to the genetic improvement of SLP to maximize farm profitability because DL models capture nonlinear genetic effects such as dominance and epistasis more efficiently than conventional genomic prediction methods based on linear models. This study aimed to investigate the usefulness of DL for the genomic prediction of two SLP-related traits; lifetime number of litters (LNL) and lifetime pig production (LPP). Two bivariate DL models, convolutional neural network (CNN) and local convolutional neural network (LCNN), were compared with conventional bivariate linear models (i.e., genomic best linear unbiased prediction, Bayesian ridge regression, Bayes A, and Bayes B). Phenotype and pedigree data were collected from 40,011 sows that had husbandry records. Among these, 3,652 pigs were genotyped using the PorcineSNP60K BeadChip. The best predictive correlation for LNL was obtained with CNN (0.28), followed by LCNN (0.26) and conventional linear models (approximately 0.21). For LPP, the best predictive correlation was also obtained with CNN (0.29), followed by LCNN (0.27) and conventional linear models (approximately 0.25). A similar trend was observed with the mean squared error of prediction for the SLP traits. This study provides an example of a CNN that can outperform against the linear model-based genomic prediction approaches when the nonlinear interaction components are important because LNL and LPP exhibited strong epistatic interaction components. Additionally, our results suggest that applying bivariate DL models could also contribute to the prediction accuracy by utilizing the genetic correlation between LNL and LPP.

Assessing the Financial Viability and Sustainability of Circular Business Models in the Wine Industry: A Comparative Analysis to Traditional Linear Business Model—Case of Georgia

In the contemporary global context, waste management and the judicious utilization of resources have emerged as pressing concerns. Consequently, the concept of a circular business model has gained prominence as a viable solution. This innovative model reframes waste not as a disposable byproduct but as an opportunity to generate new value, setting it apart from the conventional linear business model, particularly in financial, economic, and operational dimensions. Numerous industries grapple with the issue of excessive waste generation, among them the wine industry, notable for its substantial water and grape waste outputs. This predicament holds significant ramifications both on a global scale and within the specific context of Georgia. Yet, it also presents an innovative avenue for waste recycling. This study draws upon a comprehensive review of internationally recognized literature, noted for their scholarly significance and citation prevalence. In its practical segment, two distinct investment projects have been meticulously developed which seek to evaluate the financial viability of the circular business model in contrast to the conventional linear business model. The investment projects considered are as follows: 1. Under the framework of a linear business model, the company exclusively engages in the production and sale of wine. 2. Within the circular business model paradigm, the company not only produces wine but also harnesses waste processing to yield grape seed oil, which is subsequently marketed alongside wine bottles. Both models undergo rigorous scrutiny, employing a comprehensive analysis of key financial indicators essential for assessing project profitability and efficiency. The outcomes of this investigation reveal that, under identical capital investment conditions, the circular business model surpasses the linear model in terms of profitability. This underscores the potential for sustainable practices within the wine industry and the broader business landscape.

Data-Driven Dynamic Inversion Method for Complex Fractures in Unconventional Reservoirs

Abstract Hydraulic fracturing is a crucial technology for enhancing the recovery of oil and gas from unconventional reservoirs. Accurately describing fracture morphology is essential for accurately predicting production dynamics. This article proposes a new fracture inversion model based on dynamic data-driven methods, which is different from the conventional linear elastic fracture mechanics model. This method eliminates the need to consider complex mechanical mechanisms, resulting in faster simulation speeds. In the model, the fracture morphology is constrained by combining microseismic data and fracturing construction data, and the fracture tip propagation domain is introduced to characterize the multi-directionality of fracture propagation. The simulated fracture exhibits a multi-branch fracture network morphology, aligning more closely with geological understanding. In addition, the influence of microseismic signal intensity on the direction of fracture propagation is considered in this study. The general stochastic approximation (GSA) algorithm is employed to optimize the direction of fracture propagation. The proposed method is applied to both the single-stage fracturing model and the whole well fracturing model. The research findings indicate that in the single-stage fracturing model, the inverted fracture morphology aligns closely with the microseismic data, with a fitting rate of the fracturing construction curve exceeding 95%, and a microseismic data fitting rate exceeding 93%. In the whole well fracturing model, a total of 18 sections were inverted. The fitting rate between the overall fracture morphology and the microseismic data reached 90%. The simulation only took 5 minutes, demonstrating high computational efficiency and meeting the needs of large-scale engineering fracture simulation. This method can effectively support geological modeling and production dynamic prediction.