Search results for "dimensionality"

Optimized Class-Separability in Hyperspectral Images

2016

International audience; Image visualization techniques are mostly based on three bands as RGB color composite channels for human eye to characterize the scene. This, however, is not effective in case of hyper-spectral images (HSI) because they contain dozens of informative spectral bands. To eliminate redundancy of spectral information among these bands, dimensionality reduction (DR) is applied while at the same trying to retain maximum information. In this paper, we propose a new method of information-preserved hyper-spectral satellite image visualization that is based on fusion of unsupervised band selection techniques and color matching function (CMF) stretching. The results show consist…

Statistical retrieval of atmospheric profiles with deep convolutional neural networks

2019

Abstract Infrared atmospheric sounders, such as IASI, provide an unprecedented source of information for atmosphere monitoring and weather forecasting. Sensors provide rich spectral information that allows retrieval of temperature and moisture profiles. From a statistical point of view, the challenge is immense: on the one hand, “underdetermination” is common place as regression needs to work on high dimensional input and output spaces; on the other hand, redundancy is present in all dimensions (spatial, spectral and temporal). On top of this, several noise sources are encountered in the data. In this paper, we present for the first time the use of convolutional neural networks for the retr…

Spectral alignment of multi-temporal cross-sensor images with automated kernel canonical correlation analysis

2015

In this paper we present an approach to perform relative spectral alignment between optical cross-sensor acquisitions. The proposed method aims at projecting the images from two different and possibly disjoint input spaces into a common latent space, in which standard change detection algorithms can be applied. The system relies on the regularized kernel canonical correlation analysis transformation (kCCA), which can accommodate nonlinear dependencies between pixels by means of kernel functions. To learn the projections, the method employs a subset of samples belonging to the unchanged areas or to uninteresting radiometric differences. Since the availability of ground truth information to p…

Hyperspectral dimensionality reduction for biophysical variable statistical retrieval

2017

Abstract Current and upcoming airborne and spaceborne imaging spectrometers lead to vast hyperspectral data streams. This scenario calls for automated and optimized spectral dimensionality reduction techniques to enable fast and efficient hyperspectral data processing, such as inferring vegetation properties. In preparation of next generation biophysical variable retrieval methods applicable to hyperspectral data, we present the evaluation of 11 dimensionality reduction (DR) methods in combination with advanced machine learning regression algorithms (MLRAs) for statistical variable retrieval. Two unique hyperspectral datasets were analyzed on the predictive power of DR + MLRA methods to ret…

Spatially-induced nestedness in a neutral model of phage-bacteria networks

2017

[EN] Ecological networks, both displaying mutualistic or antagonistic interactions, seem to share common structural traits: the presence of nestedness and modularity. A variety of model approaches and hypothesis have been formulated concerning the significance and implications of these properties. In phage-bacteria bipartite infection networks, nestedness seems to be the rule in many different contexts. Modeling the coevolution of a diverse virus¿host ensemble is a difficult task, given the dimensionality and multi parametric nature of a standard continuous approximation. Here, we take a different approach, by using a neutral, toy model of host¿phage interactions on a spatial lattice. Each …

Host-manipulation by parasites: towards a neuroethological approach?

2009

2 pages; International audience

Image retrieval system for citizen services using penalized logistic regression models

2020

This paper describes a procedure to deal with large image collections obtained by smart city services based on interaction with citizens providing pictures. The semantic gap between the low-level image features and represented concepts and situations has been addressed using image retrieval techniques. A relevance feedback procedure is proposed for Content-Based Image Retrieval (CBIR) based on the modelling of user responses. One of the novelties of the proposal is that the feedback learning procedure can use the information that citizens themselves can provide when using these services.The proposed algorithm considers the probability of an image belonging to the set of those sought by the …

Health Indicator for Low-Speed Axial Bearings Using Variational Autoencoders

2020

This paper proposes a method for calculating a health indicator (HI) for low-speed axial rolling element bearing (REB) health assessment by utilizing the latent representation obtained by variational inference using Variational Autoencoders (VAEs), trained on each speed reference in the dataset. Further, versatility is added by conditioning on the speed, extending the VAE to a conditional VAE (CVAE), thereby incorporating all speeds in a single model. Within the framework, the coefficients of autoregressive (AR) models are used as features. The dimensionality reduction inherent in the proposed method lowers the need of expert knowledge to design good condition indicators. Moreover, the sugg…

2021

Classification approaches that allow to extract logical rules such as decision trees are often considered to be more interpretable than neural networks. Also, logical rules are comparatively easy to verify with any possible input. This is an important part in systems that aim to ensure correct operation of a given model. However, for high-dimensional input data such as images, the individual symbols, i.e. pixels, are not easily interpretable. Therefore, rule-based approaches are not typically used for this kind of high-dimensional data. We introduce the concept of first-order convolutional rules, which are logical rules that can be extracted using a convolutional neural network (CNN), and w…

LipidMS: An R Package for Lipid Annotation in Untargeted Liquid Chromatography-Data Independent Acquisition-Mass Spectrometry Lipidomics.

2018

High resolution LC-MS untargeted lipidomics using data independent acquisition (DIA) has the potential to increase lipidome coverage, as it enables the continuous and unbiased acquisition of all eluting ions. However, the loss of the link between the precursor and the product ions combined with the high dimensionality of DIA data sets hinder accurate feature annotation. Here, we present LipidMS, an R package aimed to confidently identify lipid species in untargeted LC-DIA-MS. To this end, LipidMS combines a coelution score, which links precursor and fragment ions with fragmentation and intensity rules. Depending on the MS evidence reached by the identification function survey, LipidMS provi…