Search

Computational methods to leverage topological features occurring in signals and images are currently one of the most innovative trends in applied mathematics. In this paper a pipeline of topological machine learning is applied to the challenging task of classifying four specific marine mesoscale patterns from remote sensing data, i.e., Sea Surface Temperature maps of the southwestern region of the Iberian Peninsula. Our preliminary study achieves an accuracy of 56% in the 4-label classification. Such results are encouraging, especially considering that the data are affected by noise and that there are low-quality/missing data. Also, the paper devises directions for future improvements.

Remote sensing technologies allow for continuous and valuable monitoring of the Earth's various environments. In particular, coastal and ocean monitoring presents an intrinsic complexity that makes such monitoring the main source of information available. Oceans, being the largest but least observed habitat, have many different factors affecting theirs faunal variations. Enhancing the capabilities to monitor and understand the changes occurring allows us to perform predictions and adopt proper decisions. This paper proposes an automated classification tool to recognise specific marine mesoscale events. Typically, human experts monitor and analyse these events visually through remote sensing imagery, specifically addressing Sea Surface Temperature data. The extended availability of this kind of remote sensing data transforms this activity into a time-consuming and subjective interpretation of the information. For this reason, there is an increased need for automated or at least semi-automated tools to perform this task. The results presented in this work have been obtained by applying the proposed approach to images captured over the southwestern region of the Iberian Peninsula.

Questo rapporto tecnico di progetto è il risultato del contributo fornito dal Laboratorio Segnali e Immagini dell'ISTI-CNR per il documento di progetto RTOD-SYS-SDD-010-INT per il progetto RTOD (Real-Time Object Detection mediante Machine Learning basato su tecnologia Low-Power GPU). In particolare, il rapporto studia e discute delle varie possibilità di architetture di reti convolutive che sono state valutate e che potranno essere utilizzate nel contesto del progetto per effettuare delle categorizzazioni di immagini mediante algoritmi di machine learning.

This document describes the formalization of a "spaghetti plot" (i.e. a graph that captures the sea surface temperature trends in a target area) as a Python object, for which we defined two custom classes (SpaghettiData and SpaghettiPlot). In particular, we list the attributes and methods of these classes, together with the utilities that we use to create objects belonging to them.

The Signal & Images Laboratory is an interdisciplinary research group in computer vision, signal analysis, intelligent vision systems and multimedia data understanding. It is part of the Institute of Information Science and Technologies (ISTI) of the National Research Council of Italy (CNR). This report accounts for the research activities of the Signal and Images Laboratory of the Institute of Information Science and Technologies during the year 2021.

This deliverable will consist of the implementation of image analysis tools based on methods and algorithms designed explicitly to perform different automatic classifications. These tools will be used and applied both on already available and acquired images during the project. An accompanying report describing the tools will be produced.

This document describes the usage of a tool that produces plots of the evolution of the sea surface temperature in a specified space-time window, extracting data from a series of NetCDF files.

The objective of our work is to detect and classify mesoscale patterns in an upwelling ecosystem by analysing Sea Surface Temperature (SST) maps coming from satellite data. The poster shows how we organize this information in a "spaghetti plot", a tool that we use to analyse different trends of the SST in a target area for a period of time, and how we can associate those trends with different mesoscale patterns.

The notion of stability in semi-graphoid independency models was introduced to describe the dynamics of (probabilistic) independency upon inference. We revisit the notion in view of establishing compact representations of semi-graphoid models in general. Algorithms for this purpose typically build upon dedicated operators for constructing new independency statements from a starting set of statements. In this paper, we formulate a generalised strong-contraction operator to supplement existing operators, and prove its soundness. We then embed the operator in a state-of-the-art algorithm and illustrate that the thus enhanced algorithm may establish more compact model representations.

This paper presents the use of soft methods in image mining. Image mining considers the chain from object identification on natural or man-made processes from remote sensing images through modelling, tracking on a series of images and prediction, towards communication to stakeholders. Attention is given to image mining for vague and uncertain objects. Aspects of up- and downscaling are addressed. We further consider in this paper both spatial interpolation and decision making. The paper is illustrated with several case studies.

electronic version (12 pp.); International audience

The paper presents an interdisciplinary project which is the first step towards a 3D Geographical Information System (GIS) dedicated to Cultural Heritage with a specific focus application on the Castle of Shawbak, also known as the "Crac de Montral" in Jordan. The project continues to grow thanks to a synergy between a set of laboratories: The LSIS laboratory, France in charge of the photogrammetric survey phase connected with the knowledge based approach; ITABC, CNR lab in Roma, Italy in charge of the topometric survey, with DGPS and aerial photography with gas balloon, National Institute of Information and Communications Technology, Kyoto, Japan for the 3D view point seek connected to the database, the image processing aspect managed by Stratos documentation, SimVis from The Department of Computer Science, University of Hull, UK, for the virtual reality aspect and of course the Dipartimento di Studi storici e Geografici from the University of Florence, Italy, in charge of the archaeological part. Our project focuses on a building scale encompassing its atomic elements such as ashlars blocks, cement, stratigraphic units and architectonic elements. At this scale we need a full 3D interface in order to manage accurate measurements, a huge quantity of observations and a mainly heterogeneous archaeological documentation. This project described in this paper is work in progress. After four photogrammetric campaigns in Jordan the first results are available on the project web site: http://www.shawbak.net

National audience; This paper proposes a conceptually simple but expressive framework for handling propositional information stemming from several sources, namely a two-tiered propositional logic augmented with classical modal axioms (BC-logic), a fragment of the non-normal modal logic EMN, whose semantics is expressed in terms of two-valued monotonic set-functions called Boolean capacities. We present a theorem-preserving translation of Belnap logic in this setting. As special cases, we can recover previous translations of three-valued logics such as Kleene and Priest logics. Our translation bridges the gap between Belnap logic, epistemic logic, and theories of uncertainty like possibility theory or belief functions, and paves the way to a unified approach to various inconsistency handling methods.

Modus ponens (from A and “if A then C” infer C) is one of the most basic inference rules. The probabilistic modus ponens allows for managing uncertainty by transmitting assigned uncertainties from the premises to the conclusion (i.e., from P(A) and P(C|A) infer P(C)). In this paper, we generalize the probabilistic modus ponens by replacing A by the conditional event A|H. The resulting inference rule involves iterated conditionals (formalized by conditional random quantities) and propagates previsions from the premises to the conclusion. Interestingly, the propagation rules for the lower and the upper bounds on the conclusion of the generalized probabilistic modus ponens coincide with the respective bounds on the conclusion for the (non-nested) probabilistic modus ponens.

In the process of ontology management, it is important to be able to add or remove onsequences, while preserving as much of the original ontology as possible. When these updates are made iteratively, this minimum change criterion is harder to satisfy. We propose a context-based method that stores the information about all the possible outcomes of an update compactly. Using it, we are guaranteed to find all the optimal solutions for an iterative update problem, and reason directly over them. We present a prototype implementation that can be used as a Protégé plug-in.

Conceptual blending is understood to be a process that serves a variety of cognitive purposes, including creativity, and has been highly influential in cognitive linguistics. In this line of thinking, human creativity is modeled as a blending process that takes different mental spaces as input and combines them into a new mental space, called a blend. According to this form of combinatorial creativity, a blend is constructed by taking the existing commonalities among the input mental spaces—known as the generic space—into account, and by projecting their structure in a selective way. Since input spaces for interesting blends are often initially incompatible, a generalisation step is needed before they can be blended. In this paper, we apply this idea to blend input spaces specified in the description logic EL++ and propose an upward refinement operator for generalising EL++ concepts. We show how the generalisation operator is translated to Answer Set Programming (ASP) in order to implement a search process that finds possible generalisations of input concepts. We exemplify our approach in the domain of computer icons., COINVENT European Commission FP7 - 611553

A LC/MS/MS method for the quantitative determination of lorazepam in human plasma and urine samples was developed and validated. The enantioselective assay allowed to separate the enantiomers and to verify the stereochemical instability of lorazepam. The linearity assessed for lorazepam unchanged was 0.2-20 ng of each enantiomer/ml plasma and 0.2-15 ng of each enantiomer/ml urine. The linearity assessed for total lorazepam (after enzymatic hydrolysis) was 1-30 ng of each enantiomer/ml plasma and 10-150 ng of each enantiomer/ml urine. The coefficients of variation obtained for the intra- and interassay precision were less than 15%. The method was applied to the investigation of the kinetic disposition and metabolism of racemic lorazepam administered as a single oral dose of 2 mg to a parturient. The occurrence of racemization required the calculation of the pharmacokinetic parameters as enantiomeric mixtures of lorazepam (t(1/2a) 3.5h; K(a) 0.198 ngh(-1); t(1/2) 11.5h; beta 0.060 h(-1); AUC(0-infinity) 192.1ngh/ml; CLt/f 2.41ml/minkg; Vd/f 173.5l; Fel 0.41%, and Cl(R) 0.0099 ml/minkg) and its metabolite lorazepam-glucuronide (t(1/2f) 1.2h; K(f) 0.578 h(-1); t(1/2) 16.6h; beta 0.042 h(-1); AUC(0-infinity) 207.6 ngh/ml; Fel 51.80%, and Cl(R) 98.32 ml/minkg). However, the determined confidence limits make the method suitable for application to clinical pharmacokinetic studies, even if the quantification of both the enantiomers is required.

Paradigmes de l’apprentissage artificiel

National audience

International audience; Spatial information is pervaded by uncertainty. Indeed, geographical data is often obtained by an imperfect interpretation of remote sensing images, while people attach ill-defined or ambiguous labels to places and their properties. As another example, medical images are often the result of measurements by imprecise sensors (e.g. MRI scans). Moreover, by processing spatial information in real-world applications, additional uncertainty is introduced, e.g. due to the use of interpolation/extrapolation techniques or to conflicts that are detected in an information fusion step. To the best of our knowledge, this book presents the first overview of spatial uncertainty which goes beyond the setting of geographical information systems. Uncertainty issues are especially addressed from a representation and reasoning point of view. In particular, the book consists of 14 chapters, which are clustered around three central topics. The first of these topics is about the uncertainty in meaning of linguistic descriptions of spatial scenes. Second, the issue of reasoning about spatial relations and dealing with inconsistency in information merging is studied. Finally, interpolation and prediction of spatial phenomena are investigated, both at the methodological level and from an application-oriented perspective. The concept of uncertainty by itself is understood in a broad sense, including both quantitative and more qualitative approaches, dealing with variability, epistemic uncertainty, as well as with vagueness of terms.

inbook