Random Regression Models Research Articles

Influence of different environmental challenges on the expression of reproductive traits in Holstein cattle in Southern Brazil.

The aim of this study was to assess the impact of genotype-environment interaction (GEI) on the manifestation of traits such as age at first calving (AFC), age at first service (AFS), and calving interval (CI) through the application of the reaction norm model in Holstein cattle raised in Paraná state, Brazil. Utilizing data from the milk testing service of the Paraná Association of Holstein Cattle Breeders (APCBRH), this study analyzed records from 179,492 animals undergoing their first, second, and third lactations from the years 2012 to 2022. These animals were part of 513 herds spread across 72 municipalities in Paraná. The environmental gradient was established by normalizing contemporary group solutions, derived from the animal model, with the 305-day-corrected milk yield serving as the dependent variable. Subsequently, reaction norms were determined utilizing a Random Regression Model. Spearman's correlation was then applied to compare the estimates of breeding values across different environmental gradients for the studied traits. The highest EG (+ 4) indicates the least challenging environments, where animals experience better environmental conditions. Conversely, lower EG (-4) values represent the most challenging environments, where animals endure worse conditions. The only trait that exhibited a moderate heritability magnitude was AFC (0.23) in the least challenging environmental condition. The other traits were classified as having low heritability magnitudes regardless of the evaluated environmental gradient. While minimal evidence was found for the influence of GEI on CI, a clear GEI effect was observed for AFC and AFS across all environmental gradients examined. A reversal in genotype ranking occurred under extreme environmental conditions. The findings suggest that the best-performing genotype under one environmental gradient may not necessarily excel under another.

Genetic Parameter Estimates for Growth of Hāpuku (Groper, Polyprion oxygeneios) in Land-Based Aquaculture Using Random Regression Models

Hāpuku (Polyprion oxygeneios) is a promising candidate for aquaculture production in New Zealand. Methods for spawning, juvenile production, and growout to harvest entirely on land, where water quality, pathogens, environmental impacts, and genetic “pollution” can be tightly controlled, have been developed, and genetic improvement to optimise land-based production is the obvious next step. However, estimates of genetic parameters are required to design a rigorous, disciplined, and effective selective breeding program. By using existing data consisting of irregularly spaced repeated measurements of fork length and live body weight collected on wild-collected founders and two generations of captively reared progeny, we evaluated the species’ genetic potential for improvement in growth. We first tested a range of univariate random regression models to identify the best-fitting models for these data. Subsequently, using a bivariate model, we estimated variance components for growth trajectories of fork length and whole body weight. With one to six records available per fish, the best-fitting univariate models included only a fixed effect for contemporary groups and fixed and random genetic third-order Legendre polynomials. More complex models that included full-sib family and/or permanent environmental effects produced unacceptable constrained and/or non-positive-definite solutions. Both traits are moderately heritable at all stages of the growout phase (~0.4–0.5), and the genetic correlation patterns between daily breeding values estimated via the covariance function are different for length and weight. Genetic correlations for length between all pairs of age-specific breeding values are positive and strong (>0.7) and change gradually and smoothly with increasing temporal separation. For weight, these correlations deteriorate more rapidly with increasing time lags between measurements and become negative for some age pairings. We conclude that random regression analyses are a valuable tool for extracting genetic information from irregularly spaced repeated measurements of fish size, speculate that emerging technologies for high-throughput genotyping and phenotyping will add to the value of this approach in the near future, and reason that a breeding strategy that rigorously takes into account the potentially unfavourable genetic correlations between breeding values for weight at some ages will further adapt hāpuku to land-based systems and enhance the profitability commercial-scale production.

A field investigation of 3 masks proposed as respiratory protection for wildland firefighters: a randomized controlled trial in British Columbia, Canada.

Wildland firefighters are exposed through the lungs and skin to particulate matter, fumes, and vapors containing polycyclic aromatic hydrocarbons (PAH). Wearing respiratory protection should reduce pulmonary exposure, but there is uncertainty about the most effective and acceptable type of mask. Firefighters from 6 unit crews working with the British Columbia Wildfire Service were approached and those consenting were randomly allocated within each crew to a "no mask" control group or to use 1 of 3 types of masks: X, half-face respirator with P100/multi gas cartridge; Y, cloth with alpaca filter; Z mesh fabric with a carbon filter. Crews were followed for 3 consecutive firefighting days. The mask allocated was constant for each firefighter throughout. All participants completed a brief questionnaire at the start and end of each day, giving information on mask use, respiratory symptoms, and assessment of mask qualities. Spot urine samples were collected pre and post shift to assess 1-hydroxypyrene (1-HP) concentration as an indicator of total PAH absorption. Skin wipe samples from the hands and throat were collected pre and post shift and analyzed for PAH concentration. On each day monitored, 4 participants carried sampling pumps to measure total particulates and PAHs on particles and in vapor phase. The primary outcome was the concentration of urinary 1-HP at the end of the fire day. Secondary outcomes were changes in respiratory and eye symptoms during the course of the shift, reported mask use, and perception of mask qualities. The analysis used a 3-level random intercept regression model that clustered observations within individuals and crews. We aimed to detect any relation of allocated mask type to the 4 outcomes, having allowed for estimated exposure. Information was collected from 89 firefighters, including 14 women: 49% (37/75) of male firefighters were bearded. Nineteen fire days were monitored for a total of 263 firefighter × days, 64 to 68 for each intervention group. The end of shift 1-HP was higher than the start of the shift. Urinary 1-HP was more strongly related to PAHs on the skin than in the breathing zone. Men with beards had higher end-of-shift urinary log 1-HP/creat (ng/g) than other firefighters. None of the groups allocated a mask had lower 1-HP than the no-mask group, either in the study group overall or when stratified by beard-wearing. Among those without either beards or a failed fit-test, Mask Z reduced at the end of shift 1-HP where airborne PAH concentration was high. End-of-shift symptoms were related to particle mass in the breathing zone but was not mitigated by any of the masks. Hours electing not to wear a mask increased from the first to third shift for all mask types. Mask Z was rated as more comfortable than other types. Mask X was rated highest on fit and perceived protection. Mask Y gained the lowest ratings on fit, comfort and feelings of protection. Allocated masks did not provide protection overall, but the results highlighted the need for a wider understanding of the circumstances in which wearing efficient protection is well-advised.

Machine Learning Approach to Investigate High Temperature Corrosion of Critical Infrastructure Materials

AbstractDegradation of coatings and structural materials due to high temperature corrosion in the presence of molten salt environment is a major concern for critical infrastructure applications to meet its commercial viability. The choice of high value coatings and structural (construction parts) materials comes with challenges, and therefore data centric approach may accelerate change in discovery and data practices. This research aims to use machine learning (ML) approach to estimate corrosion rates of materials when operated at high temperatures conditions (e.g., nuclear, geothermal, oxidation (dry/wet), solar applications) but geared towards nuclear thermochemical cycles. Published data related to materials (structural and coatings materials), their composition and manufacturing, including corrosion environment were gathered and analysed. Analysis demonstrated that random forest regression model is highly precise compared to other models. Assessment indicates that very limited sets of materials are likely to survive high temperature corrosive environment for extended period of exposure. While a higher quality and larger dataset are required to accurately predict the corrosion rate, the findings demonstrated the value of ML’s regression and data mining capabilities for corrosion data analysis. With the research gap in material selection strategies, proposed research will be critical to advancing data analytics approach exploiting their properties for high temperature corrosion applications. Graphical Abstract

Abstract A089: Intersecting burdens: The role of social barriers and perceived stress in moderating cortisol reactivity among African American breast cancer survivors

Abstract Background: Disparities in breast cancer morbidity and mortality persist in African Americans. Social determinants and their subsequent effect on stress reactivity may impact the biological mechanisms associated with the onset and progression of cancer. However, stress reactivity has not been examined specifically among African American breast cancer survivors. Objective: To evaluate within-subject variation in stress reactivity among African American breast cancer survivors and determine whether this reactivity is influenced by social stressors, such as financial strain and social isolation, known to be associated with cancer outcomes. Methods: We conducted a laboratory intervention study using the Trier Social Stress Test on African American breast cancer survivors. We measured stress reactivity using salivary cortisol levels; socioeconomic, social, and psychological stressors were estimated by self-report. We performed multi-level random effect repeated-measures linear regression models to estimate within-subject changes in cortisol levels. We tested the moderating effects of social factors and cumulative social stressors on reactivity outcomes. Results: Sixty African American breast cancer survivors were included in the study. There were significant increases in mean cortisol levels at 30 minutes (beta=0.054, 95%CI=0.026, 0.082; p<0.001) and 40 minutes (beta=0.040, 95% CI=0.015, 0.065; p=.002) post-stress during the recovery period. We identified significant interactions between time and social stressors on cortisol levels for financial strain (χ2/df=15.83/4, p=.003), social isolation (χ2/df=9.67/4, p=.04), negative life events (χ2/df=12.75/4, p=.01), perceived stress (χ2/df=11.93/4, p=.02), and cumulative index of social stressors (χ2/df=11.14/4, p=.03). Conclusion: Social risk factors moderate the effects of stressors on cortisol reactivity among African American breast cancer survivors. There is a need to understand the lived experiences of Black women and develop interventions that mitigate the impact of social stressors on stress responses. Citation Format: Dr. Fatimata Sanogo, Dr. Junhan Cho, Dr. Trista Beard, Dr. Chanita Hughes Halbert. Intersecting burdens: The role of social barriers and perceived stress in moderating cortisol reactivity among African American breast cancer survivors [abstract]. In: Proceedings of the 17th AACR Conference on the Science of Cancer Health Disparities in Racial/Ethnic Minorities and the Medically Underserved; 2024 Sep 21-24; Los Angeles, CA. Philadelphia (PA): AACR; Cancer Epidemiol Biomarkers Prev 2024;33(9 Suppl):Abstract nr A089.

Tiered maize and wheat nutrient removal coefficients estimated from available data

AbstractEstimates of cropland nutrient budgets at national to global scale generally rely on regional or global mean coefficients for quantifying nutrients removed in crop yield and by-products. Use of such mean values masks the variability in these coefficients. Using maize and wheat as examples, we assessed variation in nutrient removal coefficients, namely harvest index (HI), nitrogen (N), phosphorus (P) and potassium (K) concentrations of crop products (Grain N, Grain P and Grain K respectively) and N, P and K concentrations of crop residues (Residue N, Residue P, and Residue K respectively). Variation in these coefficients was assessed by three categories (Tiers) of estimation. Statistical (mixed-effects) and machine learning (random forest regression) models (Tier 3) were used to predict the coefficients using generally available predictor variables at a global level. Mean prediction accuracies (R2) of the mixed-effects and random forest models were 0.32 for maize coefficients and 0.45 for wheat coefficients when based on a random sub-selection of mainly replicated field experiment data. When predictions were applied to on-farm data only, prediction accuracies were lower (mean R2 values of 0.08 and 0.36 for maize and wheat respectively). Variation in, and dearth of on-farm data for the coefficients contributed to these poor prediction accuracies. Until the limitations of on-farm data are overcome, it is recommended to use Tier 2 (regional) coefficient estimates in country and global cropland nutrient balance and nutrient use efficiency estimates. Where Tier 2 values are not available, then global average (Tier 1) coefficients can be used.

Machine learning-enabled attapulgite/polyimide nanofiber composite aerogels-based colorimetric sensor array for real-time monitoring of balsa fish freshness

This paper presents the development and application of attapulgite/polyimide nanofiber composite aerogels (ATP/PI NFAs) integrated with a range of acid-base indicators, fabricated using electrospinning and freeze-drying technologies. A detailed characterization of the ATP/PI NFAs revealed a 3D multi-level pore structure that enhanced the mass transfer of target gas molecules and their interaction with probe molecules. Utilizing machine learning approaches, we designed an ATP/PI NFAs-based colorimetric sensor array capable of real-time evaluation of balsa fish freshness. Color features sensitive to changes in freshness were selected using principal component analysis and random forest. Partial least squares regression and random forest regression models were established, achieving the prediction of total volatile basic nitrogen content in balsa fish. The system was validated using a national standard method to demonstrate its accuracy and practicality. The combination of advanced ATP/PI NFAs-based colorimetric sensor array with robust machine learning models paves the way for food safety monitoring.

Mapping Field-Level Maize Yields in Ethiopian Smallholder Systems Using Sentinel-2 Imagery

Remote sensing offers a low-cost method for estimating yields at large spatio-temporal scales. Here, we examined the ability of Sentinel-2 satellite imagery to map field-level maize yields across smallholder farms in two regions in Oromia district, Ethiopia. We evaluated how effectively different indices, the MTCI, GCVI, and NDVI, and different models, linear regression and random forest regression, can be used to map field-level yields. We also examined if models improved by adding weather and soil data and how generalizable our models were if trained in one region and applied to another region, where no data were used for model calibration. We found that random forest regression models that used monthly MTCI composites led to the highest yield prediction accuracies (R2 up to 0.63), particularly when using only localized data for training the model. These models were not very generalizable, especially when applied to regions that had significant haze remaining in the imagery. We also found that adding soil and weather data did little to improve model fit. Our results highlight the ability of Sentinel-2 imagery to map field-level yields in smallholder systems, though accuracies are limited in regions with high cloud cover and haze.

Vegetation restoration enhancing soil carbon sequestration in karst rocky desertification ecosystems: A meta-analysis

Vegetation restoration measures have been increasingly employed to alleviate rocky desertification in karst ecosystems. However, the comprehensive effects of these interventions on soil properties and soil organic carbon (SOC) remain poorly understood. Herein, we gathered 644 paired observations from 68 studies and conducted a meta-analysis to quantify the performance of different vegetation restoration measures including moss (MS), grassland (GL), cash crop (CP), shrub (SH), and secondary forest (SF) through soil properties and SOC. Our results demonstrated significant effects of MS, GL, CP, SH, and SF on soil biotic and abiotic factors, each with distinct response characteristics. Particularly, MS significantly enhanced all soil properties (excluding a slight decrease in soil pH by 10.8%). Moreover, MS, GL, CP, SH, and SF could elevate SOC by 32.1%, 17.6%, 24.9%, 59.2%, and 48.7% respectively. Utilizing random forest and linear regression models, we identified primary drivers for SOC in MS, GL, CP, SH, and SF as soil moisture content, arbuscular mycorrhizal fungi, soil microbial phosphorus, total nitrogen, and β-1,4-glucosidase, respectively. This meta-analysis underlined the varied effects of vegetation restoration measures on soil properties and advocates for restoration measures that prioritize plant productivity and reduce soil temperature during the karst rocky desertification restoration process. Additionally, this study underscores the pivotal role of vegetation rehabilitation in environmental conservation and carbon sequestration of ecologically vulnerable regions.

Hyperspectral Imaging for Phenotyping Plant Drought Stress and Nitrogen Interactions Using Multivariate Modeling and Machine Learning Techniques in Wheat

Accurate detection of drought stress in plants is essential for water use efficiency and agricultural output. Hyperspectral imaging (HSI) provides a non-invasive method in plant phenotyping, allowing the long-term monitoring of plant health due to sensitivity to subtle changes in leaf constituents. The broad spectral range of HSI enables the development of different vegetation indices (VIs) to analyze plant trait responses to multiple stresses, such as the combination of nutrient and drought stresses. However, known VIs may underperform when subjected to multiple stresses. This study presents new VIs in tandem with machine learning models to identify drought stress in wheat plants under varying nitrogen (N) levels. A pot wheat experiment was set up in the glasshouse with four treatments: well-watered high-N (WWHN), well-watered low-N (WWLN), drought-stress high-N (DSHN) and drought-stress low-N (DSLN). In addition to ensuring that plants were watered according to the experiment design, photosynthetic rate (Pn) and stomatal conductance (gs) (which are used to assess plant drought stress) were taken regularly, serving as the ground truth data for this study. The proposed VIs, together with known VIs, were used to train three classification models: support vector machines (SVM), random forest (RF), and deep neural networks (DNN) to classify plants based on their drought status. The proposed VIs achieved more than 0.94 accuracy across all models, and their performance further increased when combined with known VIs. The combined VIs were used to train three regression models to predict the stomatal conductance and photosynthetic rates of plants. The random forest regression model performed best, suggesting that it could be used as a stand-alone tool to forecast gs and Pn and track drought stress in wheat. This study shows that combining hyperspectral data with machine learning can effectively monitor and predict drought stress in crops, especially in varying nitrogen conditions.

Discovery of optimal silver nanowires synthesis conditions using machine learning

Silver nanowires (AgNWs) are essential nanomaterials for diverse applications, including medical devices. Their morphology, like length and diameter, significantly affects conductivity, which is crucial for effective electrical signal transmission. Traditional trial-and-error approaches to adjust synthesis conditions for morphology control are time consuming. To overcome the limitation, this study integrates machine learning (ML) with experimental approaches to investigate how nucleants affect AgNWs synthesis. Random forest regression models are developed to analyze the effect of varying nucleant concentrations on morphology. Our approach builds a new framework to optimize synthesis conditions for morphology control, accelerating advancements in manufacturing capabilities.

Rational Design of Lipid Nanoparticles for Enhanced mRNA Vaccine Delivery via Machine Learning.

Since the coronavirus pandemic, mRNA vaccines have revolutionized the field of vaccinology. Lipid nanoparticles (LNPs) are proposed to enhance mRNA delivery efficiency; however, their design is suboptimal. Here, a rational method for designing LNPs is explored, focusing on the ionizable lipid composition and structural optimization using machine learning (ML) techniques. A total of 213 LNPs are analyzed using random forest regression models trained with 314 features to predict the mRNA expression efficiency. The models, which predict mRNA expression levels post-administration of intradermal injection in mice, identify phenol as the dominant substructure affecting mRNA encapsulation and expression. The specific phospholipids used as components of the LNPs, as well as the N/P ratio and mass ratio, are found to affect the efficacy of mRNA delivery. Structural analysis highlights the impact of the carbon chain length on the encapsulation efficiency and LNP stability. This integrated approach offers a framework for designing advanced LNPs and has the potential to unlock the full potential of mRNA therapeutics.

High-resolution mapping of grassland canopy cover in China through the integration of extensive drone imagery and satellite data

Canopy cover is a crucial indicator for assessing grassland health and ecosystem services. However, achieving accurate high-resolution estimates of grassland canopy cover at a large spatial scale remains challenging due to the limited spatial coverage of field measurements and the scale mismatch between field measurements and satellite imagery. In this study, we addressed these challenges by proposing a regression-based approach to estimate large-scale grassland canopy cover, leveraging the integration of drone imagery and multisource remote sensing data. Specifically, over 90,000 10 × 10 m drone image tiles were collected at 1,255 sites across China. All drone image tiles were classified into grass and non-grass pixels to generate ground-truth canopy cover estimates. These estimates were then temporally aligned with satellite imagery-derived features to build a random forest regression model to map the grassland canopy cover distribution of China. Our results revealed that a single classification model can effectively distinguish between grass and non-grass pixels in drone images collected across diverse grassland types and large spatial scales, with multilayer perceptron demonstrating superior classification accuracy compared to Canopeo, support vector machine, random forest, and pyramid scene parsing network. The integration of extensive drone imagery successfully addressed the scale-mismatch issue between traditional ground measurements and satellite imagery, contributing significantly to enhancing mapping accuracy. The national canopy cover map of China generated for the year 2021 exhibited a spatial pattern of increasing canopy cover from northwest to southeast, with an average value of 56 % and a standard deviation of 26 %. Moreover, it demonstrated high accuracy, with a coefficient of determination of 0.89 and a root-mean-squared error of 12.38 %. The resulting high-resolution canopy cover map of China holds great potential in advancing our comprehension of grassland ecosystem processes and advocating for the sustainable management of grassland resources.

Towards Share Price Volatility: Does Capital Structure Choices Really Matter?

The study was conducted to assess the impact of capital structure on the share price volatility in Tanzania. The study utilized quantitative secondary data spanning a ten (10) year period from 2013 to 2022, sourced from the Dar es Salaam Stock Exchange (DSE) and annual reports of six (6) chosen manufacturing companies. The data was analysed using the random effect panel regression model. Findings revealed that all independent variables (Short term, long term and total debt) have a negative statistically significant effect on share price volatility. On the basis of the study’s findings, the research suggested that, listed companies should adopt effective debt management strategy to mitigate share price volatility. Also, Capital market and security authorities (CMSA) are advised to provide regulatory guidance and enforce transparent reporting requirements for listed companies. Furthermore, Investors are encouraged to adopt a strategic investment approach, considering companies with effective debt management in their decisions. Future researches should use Autoregressive Distributed Lag (ARDL) model to capture both short- and long-term impact of capital structure changes, and include additional debt related metrics and microeconomic factors for a more nuanced understanding of share price volatility.

Examining worry and secondary stressors on grief severity using machine learning

ABSTRACT Background & objectives Worry and loss-related secondary stressors appear to be important correlates of problematic grief responses. However, the relative importance of these variables in the context of established correlates of grief responding, ranging from indicators of identity disruption and demographic characteristics of the bereaved to characteristics of the loss of quality of the relationship with the deceased, is unknown. Modeling the relative associations of these factors can be problematic, given the high degree of collinearity between these variables. This study used a machine learning approach to provide accurate estimations of the relative importance of these correlates for post-loss symptom severity. Methods and Results A convenience sample of 428 bereaved people who had lost a parent, spouse, or child in the last 30 to 365 days completed an online survey. Random forest regression modeling examined the effects of worry and secondary stressors on symptom severity in the context of established correlates. Results indicated worry and the number of secondary stressors experienced were among the factors most strongly associated with severity of grief, depression, posttraumatic stress and problems functioning. Conclusions These results also provide insight into the relative importance of worry and secondary stressors affecting grief severity to guide future research.

Quantifying the heterogeneity impact of risk factors on regional bicycle crash frequency: A hybrid approach of clustering and random parameter model

The existence of internal and external heterogeneity has been established by numerous studies across various fields, including transportation and safety analysis. The findings from these studies underscore the complexity of crash data and the multifaceted nature of risk factors involved in accidents. However, most studies consider the effects of unobserved heterogeneity from one perspective −- either within clusters (internal) or between clusters (external) −- and do not investigate the biases from both simultaneously on crash frequency analysis. To fill this gap, this study proposes a hybrid approach combining latent class cluster analysis with the random parameter negative binomial regression model (LCA-RPNB) to explore the association between risk factors and bicycle crash frequency. First, the bicycle crash data is categorized into three clusters using LCA based on crash features such as gender, trip purposes, weather, and light conditions. Then, the separated crash frequency models for different clusters and the overall model are developed based on RPNB using regional factors of crash locations as independent variables and the crash frequency of different clusters respectively as dependent variables. The hybrid approach enables a comprehensive examination of internal and external heterogeneities among bicycle crash frequency factors simultaneously. Results suggest that the proposed hybrid approach exhibits superior fitting and predictive performance compared to the model only considers the effects of unobserved heterogeneity from one perspective with the lower values of Akaike Information Criterion (AIC), Bayesian Information Criterion (BIC), Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE). This approach can help policymakers and urban planners to design more effective safety interventions by understanding the distinct needs of different bicyclist clusters and the specific factors that contribute to crash risk in each group.

Person explanatory multidimensional item response theory with the instrument package in R.

We present the new R package instrument to perform Bayesian estimation of person explanatory multidimensional item response theory. The package implements an exploratory multidimensional item response theory model and a higher-order multidimensional item response theory model, a type of confirmatory multidimensional item response theory. Explanation of person parameters is accomplished by fixed and random effect linear regression models. Estimation is carried out using Hamiltonian Monte Carlo in Stan. In this article, we provide a detailed description of the models; we use the instrument package to demonstrate fitting explanatory item response models with fixed and random effects (i.e., mixed modeling) of person parameters in R; and, we perform a simulation study to evaluate the performance of our implementation of the models.

Prediction of Urban House Rental Prices in Lagos - Nigeria: A Machine Learning Approach

Often, prospective tenants need to know the rental price of an apartment, and homeowners need to know how best to price their apartments. This work aims to predict house rental prices in Lagos, Nigeria, using machine learning by examining the relationship between the rental price and features such as the number of bedrooms, bathrooms, toilets, location and house status(newly built, furnished, and/or serviced). Five machine learning models were trained and evaluated using mean absolute error (MAE), root mean squared error (RMSE) and r-square (R2); the random forest regression model outperformed the other four models with the lowest MAE, RMSE and the highest R2. This study also revealed that the number of bedrooms and the apartment's location are the most significant predictors, confirmed using the feature importance analysis. The developed model can be used to estimate the rental price of a property in Lagos, Nigeria.

Modelling heat stress effects on milk production traits in Tunisian Holsteins using a random regression approach.

This study investigated the impact of temperature and humidity on milk production traits in Tunisian dairy cows, analysing population-level trends and individual cow responses using various modelling techniques and heat stress (HS) indices. Two distinct datasets were used for this purpose: the first included 551,139; 331,654 and 302,396 test-day records for milk, fat and protein yields, respectively. The second supplemented the production information with daily average (THIavg) and maximum (THImax) temperature-humidity index (THI) data. Three main parts of analyses were conducted simultaneously: classical least squares, identification of HS thresholds and associated production losses and assessment of individual cow responses using random regression models (RRM) fitting various continuous functions that include/exclude individual effects. The best model, determined by goodness-of-fit measurements, was a cubic polynomial function that accounted for individual variation and THIavg as a heat load measure. HS thresholds were established at THIavg/THImax of 70/74 for milk yield, 50/55 for fat percentage, 59/66 for protein percentage, 54/63 for fat yield and 56/66 for protein yield. According to the fitted polynomial models, daily milk production traits showed a curvilinear decline with accelerated loss rates beyond the established thermal thresholds. However, for all models and thermal indices, maximum daily production losses remained below 164 g/day, 4.4 g/day and 6.1 g/day for milk, fat and protein yields, respectively. Despite these losses, the relatively high thermal thresholds and lower associated production losses suggest that Tunisian dairy cows can tolerate high heat loads. Moreover, observed variations in response patterns indicate potential for selecting heat-tolerant individuals within this population.

Sensing emotional valence and arousal dynamics through automated facial action unit analysis

Information about the concordance between dynamic emotional experiences and objective signals is practically useful. Previous studies have shown that valence dynamics can be estimated by recording electrical activity from the muscles in the brows and cheeks. However, whether facial actions based on video data and analyzed without electrodes can be used for sensing emotion dynamics remains unknown. We investigated this issue by recording video of participants’ faces and obtaining dynamic valence and arousal ratings while they observed emotional films. Action units (AUs) 04 (i.e., brow lowering) and 12 (i.e., lip-corner pulling), detected through an automated analysis of the video data, were negatively and positively correlated with dynamic ratings of subjective valence, respectively. Several other AUs were also correlated with dynamic valence or arousal ratings. Random forest regression modeling, interpreted using the SHapley Additive exPlanation tool, revealed non-linear associations between the AUs and dynamic ratings of valence or arousal. These results suggest that an automated analysis of facial expression video data can be used to estimate dynamic emotional states, which could be applied in various fields including mental health diagnosis, security monitoring, and education.