**28** Publications

- Page
**1**of**6** - Next Page

Sci Rep 2021 12 1;11(1):23209. Epub 2021 Dec 1.

Ecole Polytechnique Fédérale de Lausanne (EPFL), 1950, Sion, Switzerland.

Many ecological studies rely on count data and involve manual counting of objects of interest, which is time-consuming and especially disadvantageous when time in the field or lab is limited. However, an increasing number of works uses digital imagery, which opens opportunities to automatise counting tasks. In this study, we use machine learning to automate counting objects of interest without the need to label individual objects. By leveraging already existing image-level annotations, this approach can also give value to historical data that were collected and annotated over longer time series (typical for many ecological studies), without the aim of deep learning applications. We demonstrate deep learning regression on two fundamentally different counting tasks: (i) daily growth rings from microscopic images of fish otolith (i.e., hearing stone) and (ii) hauled out seals from highly variable aerial imagery. In the otolith images, our deep learning-based regressor yields an RMSE of 3.40 day-rings and an [Formula: see text] of 0.92. Initial performance in the seal images is lower (RMSE of 23.46 seals and [Formula: see text] of 0.72), which can be attributed to a lack of images with a high number of seals in the initial training set, compared to the test set. We then show how to improve performance substantially (RMSE of 19.03 seals and [Formula: see text] of 0.77) by carefully selecting and relabelling just 100 additional training images based on initial model prediction discrepancy. The regression-based approach used here returns accurate counts ([Formula: see text] of 0.92 and 0.77 for the rings and seals, respectively), directly usable in ecological research.

## Download full-text PDF |
Source |
---|---|

http://dx.doi.org/10.1038/s41598-021-02387-9 | DOI Listing |

http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8636638 | PMC |

December 2021

Am Nat 2021 08 24;198(2):E37-E52. Epub 2021 Jun 24.

AbstractCentral place foragers often segregate in space, even without signs of direct agonistic interactions. Using parsimonious individual-based simulations, we show that for species with spatial cognitive abilities, individual-level memory of resource availability can be sufficient to cause spatial segregation in the foraging ranges of colonial animals. The shapes of the foraging distributions are governed by commuting costs, the emerging distribution of depleted resources, and the fidelity of foragers to their colonies. When colony fidelity is weak and foragers can easily switch to colonies located closer to favorable foraging grounds, this leads to space partitioning with equidistant borders between neighboring colonies. In contrast, when colony fidelity is strong-for example, because larger colonies provide safety in numbers or individuals are unable to leave-it can create a regional imbalance between resource requirements and resource availability. This leads to nontrivial space-use patterns that propagate through the landscape. Interestingly, while better spatial memory creates more defined boundaries between neighboring colonies, it can lower the average intake rate of the population, suggesting a potential trade-off between an individual's attempt for increased intake and population growth rates.

## Download full-text PDF |
Source |
---|---|

http://dx.doi.org/10.1086/715014 | DOI Listing |

August 2021

Phys Rev E 2020 Nov;102(5-1):053306

Department of Mathematics, Swansea University, Bay Campus, SA1 8EN, Swansea, Wales, United Kingdom.

We demonstrate, by means of a convolutional neural network, that the features learned in the two-dimensional Ising model are sufficiently universal to predict the structure of symmetry-breaking phase transitions in considered systems irrespective of the universality class, order, and the presence of discrete or continuous degrees of freedom. No prior knowledge about the existence of a phase transition is required in the target system and its entire parameter space can be scanned with multiple histogram reweighting to discover one. We establish our approach in q-state Potts models and perform a calculation for the critical coupling and the critical exponents of the ϕ^{4} scalar field theory using quantities derived from the neural network implementation. We view the machine learning algorithm as a mapping that associates each configuration across different systems to its corresponding phase and elaborate on implications for the discovery of unknown phase transitions.

## Download full-text PDF |
Source |
---|---|

http://dx.doi.org/10.1103/PhysRevE.102.053306 | DOI Listing |

November 2020

Phys Rev E 2020 Sep;102(3-1):033303

Department of Mathematics, Swansea University, Bay Campus, SA1 8EN, Swansea, Wales, United Kingdom.

We propose the use of Monte Carlo histogram reweighting to extrapolate predictions of machine learning methods. In our approach, we treat the output from a convolutional neural network as an observable in a statistical system, enabling its extrapolation over continuous ranges in parameter space. We demonstrate our proposal using the phase transition in the two-dimensional Ising model. By interpreting the output of the neural network as an order parameter, we explore connections with known observables in the system and investigate its scaling behavior. A finite-size scaling analysis is conducted based on quantities derived from the neural network that yields accurate estimates for the critical exponents and the critical temperature. The method improves the prospects of acquiring precision measurements from machine learning in physical systems without an order parameter and those where direct sampling in regions of parameter space might not be possible.

## Download full-text PDF |
Source |
---|---|

http://dx.doi.org/10.1103/PhysRevE.102.033303 | DOI Listing |

September 2020

Neth Heart J 2020 Aug;28(Suppl 1):88-92

Department of Cardiology, Radboud University Medical Centre, Nijmegen, The Netherlands.

In the past year, a number of important papers have been published on non-ST-elevation acute coronary syndrome, highlighting progress in clinical care. The current review focuses on early diagnosis and risk stratification using biomarkers and advances in intracoronary imaging.

## Download full-text PDF |
Source |
---|---|

http://dx.doi.org/10.1007/s12471-020-01457-3 | DOI Listing |

http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7419413 | PMC |

August 2020

-->