A Multi-Layer Perceptron With a Hierarchical Prior for Operating State Recognition of Ship Propulsion Systems

To define more clearly vibration-related problems of ship propulsion systems, a procedure incorporating operating state recognition into conventional vibration analysis is proposed in this paper. Emphasis is placed on identifying operating modes and decay levels through a multi-layer perceptron (MLP) with a hierarchical prior. First, a variant of stochastic gradient descent (SGD) with momentum is presented for integrating a hierarchical prior into the parameter learning of an MLP network. Then, the MLP network, governing information representation through multiple levels of abstraction is designed, and the hierarchical prior, representing a clear explanation in physics of system operating for an operator or maintainer, is also constructed. Finally, the operating data from a combined diesel or gas turbine (CODOG) system validate that the accuracy improvement of operating state recognition can be achieved by MLP with a hierarchical prior when the sample size is relatively small. Meanwhile, the vibration signals from the CODOG system verify the effectiveness of the vibration analysis procedure coupled with operating state recognition.

Bayesian Harmonic Modelling of Sparse and Irregular Satellite Remote Sensing Time Series of Vegetation Indexes: A Story of Clouds and Fires

Vegetation index time series from Landsat and Sentinel-2 have great potential for following the dynamics of ecosystems and are the key to develop essential variables in the realm of biodiversity. Unfortunately, the removal of pixels covered mainly by clouds reduces the temporal resolution, producing irregularity in time series of satellite images. We propose a Bayesian approach based on a harmonic model, fitted on an annual base. To deal with data sparsity, we introduce hierarchical prior distribution that integrate information across the years. From the model, the mean and standard deviation of yearly Ecosystem Functional Attributes (i.e., mean, standard deviation, and peak’s day) plus the inter-year standard deviation are calculated. Accuracy is evaluated with a simulation that uses real cloud patterns found in the Peneda-Gêres National Park, Portugal. Sensitivity to the model’s abrupt change is evaluated against a record of multiple forest fires in the Bosco Difesa Grande Regional Park in Italy and in comparison with the BFAST software output. We evaluated the sensitivity in dealing with mixed patch of land cover by comparing yearly statistics from Landsat at 30m resolution, with a 2m resolution land cover of Murgia Alta National Park (Italy) using FAO Land Cover Classification System 2.

Bayesian 3D X-Ray Computed Tomography with a Hierarchical Prior Model for Sparsity in Haar Transform Domain

In this paper, a hierarchical prior model based on the Haar transformation and an appropriate Bayesian computational method for X-ray CT reconstruction are presented. Given the piece-wise continuous property of the object, a multilevel Haar transformation is used to associate a sparse representation for the object. The sparse structure is enforced via a generalized Student-t distribution ( S t g ), expressed as the marginal of a normal-inverse Gamma distribution. The proposed model and corresponding algorithm are designed to adapt to specific 3D data sizes and to be used in both medical and industrial Non-Destructive Testing (NDT) applications. In the proposed Bayesian method, a hierarchical structured prior model is proposed, and the parameters are iteratively estimated. The initialization of the iterative algorithm uses the parameters of the prior distributions. A novel strategy for the initialization is presented and proven experimentally. We compare the proposed method with two state-of-the-art approaches, showing that our method has better reconstruction performance when fewer projections are considered and when projections are acquired from limited angles.

Probabilistic inference of bifurcations in single-cell data using a hierarchical mixture of factor analysers

Modelling bifurcations in single-cell transcriptomics data has become an increasingly popular field of research. Several methods have been proposed to infer bifurcation structure from such data but all rely on heuristic non-probabilistic inference. Here we propose the first generative, fully probabilistic model for such inference based on a Bayesian hierarchical mixture of factor analysers. Our model exhibits competitive performance on large datasets despite implementing full MCMC sampling and its unique hierarchical prior structure enables automatic determination of genes driving the bifurcation process.