Article
Plant Sciences
Alison Smith, Adam Norman, Haydn Kuchel, Brian Cullis
Summary: This paper addresses the challenge in analyzing multi-environment datasets in plant breeding by fitting a factor analytic linear mixed model (FALMM) to define interaction classes (iClasses), allowing for predictions of overall variety performance within each iClass for selection and matching purposes.
FRONTIERS IN PLANT SCIENCE
(2021)
Article
Mathematics, Applied
Dario Ferreira, Sandra S. Ferreira, Celia Nunes, Joao T. Mexia
Summary: Prime basis factorial models allow the simultaneous study of a larger number of interactions and a recurrence method for obtaining the sums of squares in these models is presented in this work. The method can be applied in cases with any number of factors and levels, and it is validated with an application to real data.
MATHEMATICAL METHODS IN THE APPLIED SCIENCES
(2022)
Article
Chemistry, Analytical
Ziwei Yi, Wenqi Lu, Xu Qu, Linheng Li, Peipei Mao, Bin Ran
Summary: Connected vehicle (CV) technologies are transforming traditional traffic models, with the proposal of bidirectional vehicle information structure (BDVIS) and derived multiple vehicles information structure (DMVIS) to enhance car-following models using acceleration information of preceding and following vehicles. Both BDVIS and DMVIS demonstrate better performance in improving traffic flow stability compared to the original car-following model, and provide advantages for differently positioned vehicles within a platoon.
Article
Automation & Control Systems
Lorenzo Rimella, Nick Whiteley
Summary: This paper proposes algorithms for approximate filtering and smoothing in high-dimensional Factorial hidden Markov models. The approximation involves discarding likelihood factors based on a notion of locality in a factor graph associated with the emission distribution, thus avoiding the high computational cost of exact filtering and smoothing. The paper proves that the approximation accuracy is dimension-free, meaning that it does not degrade as the overall dimension of the model increases. The paper also analyzes the error introduced by localizing the likelihood function in a Bayes' rule update, and demonstrates the application of the new algorithms on synthetic examples and a London Underground passenger flow problem.
JOURNAL OF MACHINE LEARNING RESEARCH
(2022)
Article
Pharmacology & Pharmacy
Lucie Fayette, Romain Leroux, France Mentre, Jeremy Seurat
Summary: Informative studies for nonlinear mixed effect models can be obtained by performing design optimization based on Fisher Information Matrix and using candidate models for model selection or model averaging. A new two-stage adaptive design strategy is proposed and applied to a clinical trial simulation in ophthalmology to optimize doses and time measurements.
Article
Computer Science, Information Systems
Luigi Riso, Maria G. Zoia, Consuelo R. Nava
Summary: This paper proposes a new algorithm called Best-Path Algorithm (BPA) for automatic feature selection in High Dimensional Graphical Models. The BPA, based on mutual information, selects the best subset of features using a filter method. By taking advantage of the links between variables brought to the fore by the Edwards's algorithm, the BPA overcomes the limitations of existing filter algorithms. The BPA application to simulated and real-world benchmark datasets demonstrates its potential and greater effectiveness compared to alternative methods.
INFORMATION SCIENCES
(2023)
Article
Engineering, Industrial
Somayeh Khalili, Rassoul Noorossana
Summary: Multivariate multiple profile monitoring has been extensively studied, with the proposal of a multivariate linear mixed model allowing correlation among observations. Three control charts are suggested for monitoring random effects and process variability in phase II, showing superiority over existing methods. The applicability of the proposed method is illustrated through a real case demonstration.
QUALITY TECHNOLOGY AND QUANTITATIVE MANAGEMENT
(2022)
Article
Biology
Shuangshuang Xu, Marco A. R. Ferreira, Erica M. Porter, Christopher T. Franck
Summary: We propose a Bayesian model selection approach for generalized linear mixed models (GLMMs) that uses a pseudo-likelihood method to approximate the integrated likelihood function. Our approach includes flat priors for fixed effects and offers choices of approximate reference priors and half-Cauchy priors for random effects variances. We introduce a fractional Bayes factor approach to obtain posterior probabilities of competing models. Simulation studies demonstrate the favorable performance of our approach compared to other commonly used Bayesian methods.
Article
Mathematics
Belmiro P. M. Duarte
Summary: We propose mixed-integer semidefinite programming formulations for finding exact optimal designs for linear models and locally optimal designs for nonlinear models. The strategy involves generating candidate treatments, formulating the optimal design problem as a mixed-integer semidefinite program, and solving it using appropriate solvers. We also use semidefinite programming-based formulations to find equivalent approximate optimal designs for comparison.
Article
Multidisciplinary Sciences
Martin A. Stoffel, Shinichi Nakagawa, Holger Schielzeth
Summary: The coefficient of determination R-2 quantifies the variance explained by regression coefficients in a linear model. partR2 is an R package based on linear mixed-effects models that quantifies part R-2 for fixed effect predictors, providing reliable estimates and confidence intervals for each predictor.
Article
Psychology, Applied
Andrew B. Speer, Andrew P. Tenbrink, Lauren J. Wegmeyer, Caitlynn C. Sendra
Summary: Biodata inventories are standardized questionnaires that assess a person's history. They are highly predictive for pre-employment assessment and can be used for school admissions. The validity of biodata scores in predicting school success varies based on scoring method and construct domain.
JOURNAL OF VOCATIONAL BEHAVIOR
(2023)
Article
Computer Science, Theory & Methods
Wanting Lu, Heping Wang
Summary: We study multivariate approximation in the average case setting with the error measured in the weighted L-2 norm. We investigate the equivalences of various notions of algebraic and exponential tractability for standard information and general linear information for the absolute error criterion, and show that the power of standard information is the same as that of general linear information for all notions of algebraic and exponential tractability without any condition.
JOURNAL OF COMPLEXITY
(2022)
Article
Statistics & Probability
Soren Asmussen, Mogens Bladt
Summary: This article discusses the calculation of factorial moments and point probabilities in integer-valued matrix analytic models. It focuses on the maxima of integer-valued downward skipfree Levy processes and Markovian point processes with batch arrivals (BMAPs). The finite-time maxima are approximated using an Erlang distributed time horizon T and solved using the matrix Wiener-Hopf factorization problem. The factorial moments of N(T) in BMAP are represented using a structural matrix-exponential representation. Moments are then used to compute converging Gram-Charlier series for point probabilities. Change-of-measure techniques and time inhomogeneity are also discussed.
STOCHASTIC PROCESSES AND THEIR APPLICATIONS
(2022)
Article
Genetics & Heredity
Jiefang Duan, Jiayu Zhang, Long Liu, Yalu Wen
Summary: This study aims to predict AD-related brain imaging outcomes using genetic and demographic risk factors. The relationship between genetic architecture and prediction accuracy was explored through visualization of Manhattan plots. For traits without significant signals, the gBLUP model was recommended, while the latent Dirichlet process regression model was preferred for traits with spiked signals. Genetic factors explained only a small proportion of the heritability for AD-related traits, and known AD risk factors greatly improved the prediction model.
FRONTIERS IN GENETICS
(2022)
Article
Automation & Control Systems
Deepak Maurya, Arun K. Tangirala, Shankar Narasimhan
Summary: This article proposes a novel identification algorithm for the errors-in-variables autoregressive model with exogenous input (EIV-ARX) in the presence of colored noise. The algorithm jointly estimates the error variances, process order, delay, and model parameters by transforming the lagged measurements using the appropriate error covariance matrix.
JOURNAL OF THE FRANKLIN INSTITUTE-ENGINEERING AND APPLIED MATHEMATICS
(2022)
Article
Multidisciplinary Sciences
Gururaj Pralhad Kadkol, Jess Meza, Steven Simpfendorfer, Steve Harden, Brian Cullis
Summary: The study investigated Fusarium crown rot tolerance in 34 durum wheat genotypes and found that some conventional durum wheat genotypes as well as those derived from crosses exhibited comparable tolerance to Suntop. Suntop was identified as the most tolerant genotype, while EGA Bellaroi was identified as very intolerant based on FCR tolerance index.
Article
Agronomy
Paul Telfer, James Edwards, Adam Norman, Dion Bennett, Alison Smith, Jason A. Able, Haydn Kuchel
Summary: The study suggests that adapting to heat stress should be viewed as a combination of total performance and responsiveness, with QTL mapping identifying genomic regions associated with both aspects. Understanding these regions will be crucial for breeders in selecting plants with consistent performance under stress and non-stress conditions.
THEORETICAL AND APPLIED GENETICS
(2021)
Article
Plant Sciences
Alison Smith, Aanandini Ganesalingam, Christopher Lisle, Gururaj Kadkol, Kristy Hobson, Brian Cullis
Summary: This paper presents an approach for constructing MET datasets that optimizes the information available for selection decisions by using contemporary groups and data bands. The methods are demonstrated to be superior in selecting superior lines compared to other forms, particularly those related to a single year.
FRONTIERS IN PLANT SCIENCE
(2021)
Article
Fisheries
Rick D. Tate, Brendan P. Kelaher, Craig P. Brand, Brian R. Cullis, Christopher R. Gallen, Stephen D. A. Smith, Paul A. Butcher
Summary: White sharks are primary species responsible for unprovoked shark bites, and traditional management practices of culling target shark species have led to high levels of bycatch and mortality. A study in New South Wales, Australia, found that SMART drumlines are effective in catching target shark species with low bycatch and mortality rates compared to historical methods.
FISHERIES MANAGEMENT AND ECOLOGY
(2021)
Article
Plant Sciences
Ariel Ferrante, Brian R. Cullis, Alison B. Smith, Jason A. Able
Summary: The study explores genotypic differences to frost damage through multi-environment trial analysis, providing insights into identifying varieties with increased cold tolerance. It also demonstrates how advanced analysis methods can guide growers and plant breeding programs effectively.
FRONTIERS IN PLANT SCIENCE
(2021)
Article
Plant Sciences
Alison Smith, Adam Norman, Haydn Kuchel, Brian Cullis
Summary: This paper addresses the challenge in analyzing multi-environment datasets in plant breeding by fitting a factor analytic linear mixed model (FALMM) to define interaction classes (iClasses), allowing for predictions of overall variety performance within each iClass for selection and matching purposes.
FRONTIERS IN PLANT SCIENCE
(2021)
Article
Plant Sciences
Janine Croser, Dili Mao, Nicole Dron, Simon Michelmore, Larn McMurray, Christopher Preston, Dylan Bruce, Francis Chuks Ogbonnaya, Federico Martin Ribalta, Julie Hayes, Judith Lichtenzveig, William Erskine, Brian Cullis, Tim Sutton, Kristy Hobson
Summary: Accelerating genetic gain in crop improvement is crucial for ensuring improved yield and yield stability under challenging climatic conditions. This case study demonstrates the effective use of innovative breeding technologies within a collaborative breeding framework to rapidly introgress herbicide tolerance traits into an adapted chickpea genetic background.
FRONTIERS IN PLANT SCIENCE
(2021)
Article
Plant Sciences
Harsh Raman, Rosy Raman, Ramethaa Pirathiban, Brett McVittie, Niharika Sharma, Shengyi Liu, Yu Qiu, Anyu Zhu, Andrzej Kilian, Brian Cullis, Graham D. Farquhar, Hilary Stuart-Williams, Rosemary White, David Tabah, Andrew Easton, Yuanyuan Zhang
Summary: This study identified quantitative trait loci (QTL) associated with water-use efficiency (WUE) in canola through analysis of a doubled haploid population. Sequencing data and RNA sequencing were used to develop markers and analyze gene expression related to carbon isotope discrimination (Delta C-13), a trait linked to WUE. The study also identified QTLs influencing Delta C-13 and yield, and discovered a multiple-trait QTL on chromosome A09. Transcriptome analysis revealed differentially expressed genes related to Delta C-13 QTL.
PLANT CELL AND ENVIRONMENT
(2022)
Article
Plant Sciences
Beverley Gogel, Sue Welham, Brian Cullis
Summary: Plant breeding field trials are often arranged in a row by column lattice pattern. Linear mixed models, including low order ARIMA time series models and separable lattice processes, are commonly used to account for spatial dependence. Recently, TPS has been proposed as a non-stochastic smoothing approach for two-dimensional smooth variation in field trial data. Empirical comparison shows that AR models are a better fit for most trials, and there can be significant differences in the ranking of genotypes between AR and TPS models. Mis-classification of entries for selection is greater with TPS models, which has practical implications for breeder selection decisions.
FRONTIERS IN PLANT SCIENCE
(2023)
Article
Plant Sciences
Harsh Raman, Nawar Shamaya, Ramethaa Pirathiban, Brett McVittie, Rosy Raman, Brian Cullis, Andrew Easton
Summary: Canola plants have reduced crop yield and oil content under water-deficit conditions, especially during reproductive stages. This study analysed the genetic factors affecting seed yield and related traits in canola under well-watered and water-deficit conditions. The analysis revealed multiple genomic regions associated with flowering time, plant height, and seed yield under different water regimes. The study identified specific QTLs that were stable across environments and showed potential for improving water-use efficiency in canola breeding programs.
Article
Agronomy
Kedar N. Adhikari, Lucy Burrows, Abdus Sadeque, Christopher Chung, Brian Cullis, Richard Trethowan
Summary: The study found that segregating the different varieties of faba beans in blocks with a distance of more than 150 meters can limit the outcrossing rate to below 0.5%, despite the volatile and unpredictable nature of bee flights.
Article
Plant Sciences
Muhammad A. Asif, Sean L. Bithell, Ramethaa Pirathiban, Brian R. Cullis, David Glyn Dionaldo Hughes, Aidan Mcgarty, Nicole Dron, Kristy Hobson
Summary: Phytophthora root rot (PRR) is a major constraint to chickpea production in Australia. Current management options are limited. Traditional phenotyping methods are labor intensive and time consuming. In this study, a new hydroponics-based phenotyping method was developed, which proved to be space saving, rapid, and effective.
Article
Plant Sciences
Chris Lisle, Alison Smith, Carole L. Birrell, Brian Cullis
Summary: This paper explores the use of D-optimality criterion as a diagnostic to improve the accuracy of genetic variance parameter estimation and reliability of predictions, in the context of multi-environment trials in plant breeding programs.
FRONTIERS IN PLANT SCIENCE
(2021)
Article
Agriculture, Dairy & Animal Science
S. A. Barwick, D. J. Brown, B. R. Cullis, A. K. Bell, T. J. May, M. W. Lollback, I. M. Rogan, I. D. Killeen, G. Caffery, L. R. Piper, B. M. Bindon, J. F. Wilkins, D. G. Fowler
Summary: The average performance of Border Leicester (BL) flocks in Australia's sheep performance recording system has shown modest gains in growth since 2000, with improved worm resistance and a slightly improved net reproductive rate. Research by the New South Wales Department of Primary Industry revealed that improved BL flocks had advantages over purebred BLs in various aspects of performance. Maintaining BL's position in the Australian lamb industry requires emphasizing traits important to commercial lamb production and broadening the genetic base of the breed.
ANIMAL PRODUCTION SCIENCE
(2021)