Article
Mathematics, Applied
Weinuo Jiang, Shihong Wang
Summary: Reconstructing network connections aids in understanding node interactions, but hidden nodes pose challenges. This paper proposes a general theoretical method for detecting hidden nodes based on the random variable resetting. A new time series containing hidden node information is constructed, and the autocovariance is analyzed to provide a quantitative criterion. Simulation results confirm the theoretical derivation and demonstrate the method's robustness under different conditions.
Article
Automation & Control Systems
Luong-Ha Nguyen, James-A Goulet
Summary: This paper introduces a method that utilizes approximate Gaussian inference to infer the hidden states of neural networks, not just their parameters. By imposing constraints designed to achieve specific objectives, it is possible to infer the hidden states, providing a new approach for tasks that were previously tackled using gradient optimization methods.
JOURNAL OF MACHINE LEARNING RESEARCH
(2022)
Article
Astronomy & Astrophysics
Elisa Maggio, Hector O. Silva, Alessandra Buonanno, Abhirup Ghosh
Summary: The plunge-merger stage of the binary-black hole coalescence provides a unique opportunity to probe gravity in the dynamical regime. A parametrized waveform model is developed to explore deviations from general relativity in this stage. The results demonstrate the importance of waveform systematics and glitch mitigation procedures when interpreting tests of general relativity with gravitational wave observations.
Review
Multidisciplinary Sciences
Arnaud Doucet, Eric Moulines, Achille Thin
Summary: Latent variable models are popular and have been combined with neural networks to create deep latent variable models. However, the intractability of their likelihood function requires approximations for inference. The article reviews recent strategies such as importance sampling, Markov chain Monte Carlo, and sequential Monte Carlo to improve the bounds of the evidence lower bound (ELBO) for these models.
PHILOSOPHICAL TRANSACTIONS OF THE ROYAL SOCIETY A-MATHEMATICAL PHYSICAL AND ENGINEERING SCIENCES
(2023)
Article
Physics, Multidisciplinary
Seongyu Park, Samudrajit Thapa, Yeongjin Kim, Michael A. Lomholt, Jae-Hyung Jeon
Summary: A hidden Markov model for Levy walks was proposed to successfully extract the power-law exponent of the flight-time distribution. Bayesian inference was performed for parameter estimation and model classification using simulated LW trajectories under various conditions.
JOURNAL OF PHYSICS A-MATHEMATICAL AND THEORETICAL
(2021)
Article
Engineering, Mechanical
Yi-Chen Zhu, Paul Gardner, David J. Wagg, Robert J. Barthorpe, Elizabeth J. Cross, Ramon Fuentes
Summary: This paper proposes a novel approach to reduce model discrepancy and improve parameter estimation accuracy. By combining a sparse Bayesian model and a Gaussian process model, the method provides physical insights into system behavior and compensates for model discrepancy. The proposed method outperforms conventional approaches in equation selection and parameter estimation.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2022)
Article
Physics, Multidisciplinary
Saulo D. S. D. Reis, Lucas Boettcher, Joao P. da C. Nogueira, Geziel S. Sousa, Antonio S. Lima S. Neto, Hans J. J. Herrmann, Jose S. Andrade
Summary: Based on a dataset of dengue cases in Fortaleza from 2011 to 2016, this study examines the spatio-temporal characteristics of dengue outbreaks and identifies differences between epidemic and non-epidemic years. The research suggests that factors like citizen mobility play a significant role in the spatial spread of the disease and that there are higher spatial correlations in epidemic years.
FRONTIERS IN PHYSICS
(2022)
Article
Environmental Sciences
Lindsay R. Morris, Nokuthaba Sibanda
Summary: Gaussian processes are widely used in geostatistics for modelling spatial and spatio-temporal data. While there are many estimation methods for the mean and covariance of such processes, there has been less focus on developing goodness-of-fit tests for model adequacy. This study presents a modified and generalized statistical test, using pivotal discrepancy measures, to assess goodness-of-fit in a Bayesian context. The proposed method involves spatial partitioning of the data and incorporates unequal partition sizes using K-means clustering. The viability of the method is demonstrated through simulation studies and an application to hoki catch data.
ENVIRONMENTAL AND ECOLOGICAL STATISTICS
(2022)
Article
Geosciences, Multidisciplinary
Jonathan R. Bradley, Shijie Zhou, Xu Liu
Summary: Discrepancy error covariance refers to the cross-covariance between the signal and the noise terms in an additive model. A model has recently been proposed that allows for discrepancy error covariances and avoids confounding issues by introducing a telescoping sum. This model, known as the deep hierarchical generalized transformation (DHGT) model, can be efficiently implemented and allows for exact Bayesian implementation without the need for MCMC.
SPATIAL STATISTICS
(2023)
Article
Engineering, Environmental
Ana C. Cebrian, Jesus Asin, Alan E. Gelfand, Erin M. Schliep, Jorge Castillo-Mateo, Maria A. Beamonte, Jesus Abaurrea
Summary: This study aims to formalize the spatial extent of extreme heat events using time series and spatial information, conducting risk assessment in the Comunidad Autonoma de Aragon in northeastern Spain. The research finds that the extent of extreme heat events may increase over time as evidenced by comparisons across decades.
STOCHASTIC ENVIRONMENTAL RESEARCH AND RISK ASSESSMENT
(2022)
Article
Engineering, Environmental
Poshan Niraula, Jorge Mateu, Somnath Chaudhuri
Summary: This study proposes a neural network model embedded in a Bayesian framework for modeling and predicting the number of infectious disease cases in areal units. The model takes into account the impact of human movement, spatial neighborhood, and temporal correlation on disease spread. The results show that the model is able to predict the number of COVID-19 cases in space and time, with human mobility playing a significant role.
STOCHASTIC ENVIRONMENTAL RESEARCH AND RISK ASSESSMENT
(2022)
Review
Multidisciplinary Sciences
Andreas Christ Solvsten Jorgensen, Ciaran Scott Hill, Marc Sturrock, Wenhao Tang, Saketh R. Karamched, Dunja Gorup, Mark F. Lythgoe, Simona Parrinello, Samuel Marguerat, Vahid Shahrezaei
Summary: Mathematical oncology plays a crucial role in understanding glioblastoma and its clinical applications. By connecting mathematical models with molecular and imaging data, it provides valuable insights into tumor progression and serves as computational tools for cancer researchers.
ROYAL SOCIETY OPEN SCIENCE
(2023)
Article
Engineering, Mechanical
Andrew Loeb, Christopher Earls
Summary: This work focuses on a thermographic inspection setup for detecting and characterizing corrosion in steel structures, specifically pitting corrosion. The study utilizes Bayesian mathematical analysis for rigorous inference on the locations and geometric forms of hidden corrosion pits. Numerical experiments demonstrate reliable inference on corrosion pits and the effectiveness of the Bayesian inference method in complex structural geometries.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2021)
Article
Statistics & Probability
Naoki Awaya, Li Ma
Summary: The Polya tree (PT) process is a versatile Bayesian nonparametric model that has been widely used in inference problems. Recent developments have shown that the performance of PT models can be improved by adapting the partition tree to the underlying distributions and incorporating latent state variables. However, there are still important limitations, including sensitivity to the choice of the partition tree and lack of scalability with respect to dimensionality.
JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION
(2022)
Article
Geosciences, Multidisciplinary
Jorge Sosa, Alvaro Briz-Redon, Miguel Flores, Mauricio Abril, Jorge Mateu
Summary: This paper presents a statistical model for analyzing violent deaths at the level of parroquia in Ecuador. The model is based on a multinomial distribution with fixed and random effects structured in space and time. Inference is performed using a Bayesian framework. The model provides a practical interpretation and is applied to the real crime context and scenario in Ecuador.
SPATIAL STATISTICS
(2023)
Article
Public, Environmental & Occupational Health
Emily Walker, Melen Leclerc, Jean-Francois Rey, Remy Beaudouin, Samuel Soubeyrand, Antoine Messean
Article
Multidisciplinary Sciences
Celia Bordier, Helene Dechatre, Severine Suchail, Mathilde Peruzzi, Samuel Soubeyrand, Maryline Pioz, Michel Pelissier, Didier Crauser, Yves Le Conte, Cedric Alaux
SCIENTIFIC REPORTS
(2017)
Article
Geosciences, Multidisciplinary
Tomas Mrkvicka, Samuel Soubeyrand
SPATIAL STATISTICS
(2017)
Article
Plant Sciences
Samuel Soubeyrand, Pauline de Jerphanion, Olivier Martin, Mathilde Saussac, Charles Manceau, Pascal Hendrikx, Christian Lannou
Article
Environmental Sciences
Melen Leclerc, Emily Walkera, Antoine Messean, Samuel Soubeyrand
SCIENCE OF THE TOTAL ENVIRONMENT
(2018)
Article
Biochemical Research Methods
David R. J. Pleydell, Samuel Soubeyrand, Sylvie Dallot, Gerard Labonne, Joel Chadoeuf, Emmanuel Jacquot, Gael Thebaud
PLOS COMPUTATIONAL BIOLOGY
(2018)
Article
Multidisciplinary Sciences
Loup Rimbaud, Claude Bruchou, Sylvie Dallot, David R. J. Pleydell, Emmanuel Jacquot, Samuel Soubeyrand, Gael Thebaud
ROYAL SOCIETY OPEN SCIENCE
(2018)
Article
Biology
M. Alamil, J. Hughes, K. Berthier, C. Desbiez, G. Thebaud, S. Soubeyrand
PHILOSOPHICAL TRANSACTIONS OF THE ROYAL SOCIETY B-BIOLOGICAL SCIENCES
(2019)
Article
Biology
Lionel Roques, Etienne K. Klein, Julien Papaix, Antoine Sar, Samuel Soubeyrand
Article
Multidisciplinary Sciences
Samuel Soubeyrand, Melina Ribaud, Virgile Baudrot, Denis Allard, Denys Pommeret, Lionel Roques
Article
Multidisciplinary Sciences
L. Roques, O. Bonnefon, V. Baudrot, S. Soubeyrand, H. Berestycki
ROYAL SOCIETY OPEN SCIENCE
(2020)
Article
Mathematics, Applied
Olivier Martin, Yasmil Fernandez-Diclo, Jerome Coville, Samuel Soubeyrand
Summary: This article introduces a spatially-explicit compartmental model adapted to pathosystems with fixed hosts and mobile vectors for disease dissemination. The behavior of the model is analyzed through theoretical and numerical studies, and the implications for disease surveillance and control over a medium-to-long temporal horizon are discussed.
NONLINEAR ANALYSIS-REAL WORLD APPLICATIONS
(2021)
Article
Mathematical & Computational Biology
Melina Ribaud, Edith Gabriel, Joseph Hughes, Samuel Soubeyrand
Summary: In this article, a permutation-based approach is proposed to identify factors significantly correlated with zero-inflated proportion data (ZIPD) which are dependent, continuous and bounded. A performance indicator is introduced to quantify the percentage of correlation explained by the subset of significant factors. The methodology is demonstrated on simulated data and two real data sets in epidemiology, dealing with Influenza transmission probabilities between horses and COVID-19 mortality dynamics in geographic entities.
STATISTICS IN MEDICINE
(2023)
Article
Plant Sciences
Samuel Soubeyrand, Vincent Garreta, Caroline Monteil, Frederic Suffert, Henriette Goyeau, Julie Berder, Jacques Moinard, Elisabeth Fournier, Didier Tharreau, Cindy E. Morris, Ivan Sache
Article
Ecology
Samuel Soubeyrand, Anna-Liisa Laine
ANNALES ZOOLOGICI FENNICI
(2017)