Bayesian empirical likelihood for ridge and lasso regressions

Unified estimation of rice canopy leaf area index over multiple periods based on UAV multispectral imagery and deep learning

BACKGROUND

Rice is one of the major food crops in the world, and the monitoring of its growth condition is of great significance for guaranteeing food security and promoting sustainable agricultural development. Leaf area index (LAI) is a key indicator for assessing the growth condition and yield potential of rice, and the traditional methods for obtaining LAI have problems such as low efficiency and large error. With the development of remote sensing technology, unmanned aerial multispectral remote sensing combined with deep learning technology provides a new way for efficient and accurate estimation of LAI in rice.

RESULTS

In this study, a multispectral camera mounted on a UAV was utilized to acquire rice canopy image data, and rice LAI was uniformly estimated over multiple periods by the multilayer perceptron (MLP) and convolutional neural network (CNN) models in deep learning. The results showed that the CNN model based on five-band reflectance images (490, 550, 670, 720, and 850 nm) as input after feature screening exhibited high estimation accuracy at different growth stages. Compared with the traditional MLP model with multiple vegetation indices as inputs, the CNN model could better process the original multispectral image data, effectively avoiding the problem of vegetation index saturation, and improving the accuracies by 4.89, 5.76, 10.96, 1.84 and 6.01% in the rice tillering, jointing, booting, and heading periods, respectively, and the overall accuracy was improved by 6.01%. Moreover, the model accuracies (MLP and CNN) before and after variable screening showed noticeable changes. Conducting variable screening contributed to a substantial improvement in the accuracy of rice LAI estimation.

CONCLUSIONS

UAV multispectral remote sensing combined with CNN technology provides an efficient and accurate method for the unified multi-period estimation of rice LAI. Moreover, the generalization ability and adaptability of the model were further improved by rational variable screening and data enhancement techniques. This study can provide a technical support for precision agriculture and a more accurate solution for rice growth monitoring. More feature extraction and variable screening methods can be further explored in future studies by optimizing the model structure to improve the accuracy and stability of the model.

The association between physical exercise and health care seeking behavior in older adults: the mediating role of self-perceived health

Background

As global aging accelerates, the health of older adults has become a critical issue. Physical exercise has long been recognized for positive effects on health, particularly among the older adults. However, the specific impact of physical activity on health care seeking behavior, as well as the mechanisms underlying this relationship, remains insufficiently explored. This study investigates the effect of physical activity on health care seeking behavior in older adults and explores the mediating roles of physical and mental health.

Methods

Using data from the 2021 China General Social Survey (CGSS), this study employs regression analysis, and mediation analysis to examine how physical activity influences the health care seeking behavior of older adults. The analysis includes the evaluation of physical and mental health as mediators in this relationship. Additionally, heterogeneity analysis is conducted to explore differences across various age groups, and robustness tests are performed using lasso regression and ridge regression to ensure the stability of the results.

Results

This study finds that physical activity negatively influences health care seeking behavior in older adults (β = -0.100, p < 0.001, 95%CI = [-0.154, -0.046]), with physical health (β = -0.026, 95%CI = [-0.087, -0.010]) and mental health (β = -0.008, 95%CI = [-0.074, -0.001]) acting as significant mediators. The effect of physical activity on health care seeking behavior is particularly pronounced in older adults aged 60-69 (β = -0.083, p = 0.027, 95%CI = [-0.158, -0.009]) and 70-79 (β = -0.154, p = 0.001, 95%CI = [-0.248, -0.060]). Robustness tests confirm the stability and reliability of the findings, with lasso regression and ridge regression further supporting the conclusions.

Conclusion

The findings highlight the importance of physical activity in reducing health care seeking behavior and health management in older adults. By improving both physical and mental health, physical exercise can effectively reduce the medical seeking behavior of older adults. This study provides valuable insights for developing targeted health interventions and policies aimed at improving the health of older adults.

Objective Priors for Invariant e-Values in the Presence of Nuisance Parameters

This paper aims to contribute to refining the e-values for testing precise hypotheses, especially when dealing with nuisance parameters, leveraging the effectiveness of asymptotic expansions of the posterior. The proposed approach offers the advantage of bypassing the need for elicitation of priors and reference functions for the nuisance parameters and the multidimensional integration step. For this purpose, starting from a Laplace approximation, a posterior distribution for the parameter of interest is only considered and then a suitable objective matching prior is introduced, ensuring that the posterior mode aligns with an equivariant frequentist estimator. Consequently, both Highest Probability Density credible sets and the e-value remain invariant. Some targeted and challenging examples are discussed.

Discovering genotype-phenotype relationships with machine learning and the Visual Physiology Opsin Database (VPOD)

BACKGROUND

Predicting phenotypes from genetic variation is foundational for fields as diverse as bioengineering and global change biology, highlighting the importance of efficient methods to predict gene functions. Linking genetic changes to phenotypic changes has been a goal of decades of experimental work, especially for some model gene families, including light-sensitive opsin proteins. Opsins can be expressed in vitro to measure light absorption parameters, including λmax-the wavelength of maximum absorbance-which strongly affects organismal phenotypes like color vision. Despite extensive research on opsins, the data remain dispersed, uncompiled, and often challenging to access, thereby precluding systematic and comprehensive analyses of the intricate relationships between genotype and phenotype.

RESULTS

Here, we report a newly compiled database of all heterologously expressed opsin genes with λmax phenotypes that we call the Visual Physiology Opsin Database (VPOD). VPOD_1.0 contains 864 unique opsin genotypes and corresponding λmax phenotypes collected across all animals from 73 separate publications. We use VPOD data and deepBreaks to show regression-based machine learning (ML) models often reliably predict λmax, account for nonadditive effects of mutations on function, and identify functionally critical amino acid sites.

CONCLUSION

The ability to reliably predict functions from gene sequences alone using ML will allow robust exploration of molecular-evolutionary patterns governing phenotype, will inform functional and evolutionary connections to an organism's ecological niche, and may be used more broadly for de novo protein design. Together, our database, phenotype predictions, and model comparisons lay the groundwork for future research applicable to families of genes with quantifiable and comparable phenotypes.

Qualitative–Quantitative Warning Modeling of Energy Consumption Processes in Inland Waterway Freight Transport on River Sections for Environmental Management

The article concerns the assessment of the energy consumption of inland waterway freight transport on river sections in the context of environmental management. The research question was: Does the choice of the route determine the total energy consumption of inland waterway transport and therefore affect the potential of cargo transport of this mode? The article aims to indicate the directions of energy consumption by inland waterway freight transport depending on the route selection, the volume of transport, and the length of the route. The study was carried out on nine sections of the Odra River in Poland during the years 2015–2020. Statistical and econometric techniques were used, i.e., ANOVA, generalized linear models, Eta coefficients, Lasso and Ridge regularization, and X-average control charts (Six Sigma tool). Based on early warning models, river sections were identified that favor the rationalization of energy consumption in terms of the network. The sensitivity of the energy consumption of inland waterway transport to changes in the average distance and in the volume of transport was examined. With the use of Six Sigma tools, the instability of the energy consumption processes of inland waterway transport was identified, paying attention to the source of the mismatch, which was the increase in the average transport distance in the sections, where energy consumption increased due to the operational and navigation conditions of these sections.

Evaluation of spatial Bayesian Empirical Likelihood models in analysis of small area data

Bayesian empirical likelihood (BEL) models are becoming increasingly popular as an attractive alternative to fully parametric models. However, they have only recently been applied to spatial data analysis for small area estimation. This study considers the development of spatial BEL models using two popular conditional autoregressive (CAR) priors, namely BYM and Leroux priors. The performance of the proposed models is compared with their parametric counterparts and with existing spatial BEL models using independent Gaussian priors and generalised Moran basis priors. The models are applied to two benchmark spatial datasets, simulation study and COVID-19 data. The results indicate promising opportunities for these models to capture new insights into spatial data. Specifically, the spatial BEL models outperform the parametric spatial models when the underlying distributional assumptions of data appear to be violated.