Search results for "multivariate statistic"
showing 10 items of 327 documents
Multivariate Statistical Analysis for Water Demand Modeling
2014
The actual level of water demand is the driving force behind the hydraulic dynamics in water distribution systems. Consequently, it is crucial to estimate it as accurately as possible in order to result in reliable simulation models. In this paper, a copula-based multivariate analysis has been proposed and used for demand prediction for given return period. The analysis is applied to water consumption data collected in the water distribution network of Palermo (Italy). The approach showed to produce consisted demand patterns and to be a powerful tool to be coupled with water distribution network models for design or analysis problems. (C) 2014 Published by Elsevier Ltd.
The Multilevel Model in the Computer-Generated Appraisal: A Case in Palermo
2017
The construction of a mass appraisal model requires the preliminary study of the real estate market, the sampling of sold properties, the development of a forecasting model and the verification of the appraisal results. They are generally computerised methods, that work with geo-referenced data. This experimental work has proceeded to build a mass appraisal model, collecting a data sample of sales of apartments in the city of Palermo, in the five years 2008–2012, using a multivariate statistical model (multilevel), testing the results and providing the operating applications in a scheme of online real estate valuations.
The Hydrothermal System of Solfatara Crater (Campi Flegrei, Italy) Inferred From Machine Learning Algorithms
2019
Two machine learning algorithms were applied to three multivariate datasets acquired at Solfatara volcano. Our aim was to find an unbiased and coherent synthesis among the large amount of data acquired within the crater and along two orthogonal vertical NNE- and WNW-trending cross-sections. The first algorithm includes a new approach for a soft K-means clustering based on the use of the silhouette index to control the color palette of the clusters. The second algorithm which uses the self-organizing maps incorporates an alternative method for choosing the number of nodes of the neural network which aims to avoid the need for downstream clustering of the results of the classification. Both m…
Solution Using Clustering Methods
1987
The main aim of this analysis is to find out typical morphologies from the multivariate and longitudinal data set on growing children and to describe the morphological evolution of the found groups of girls. The finding out of typical morphologies is, in our opinion, strictly linked to the search of structures in the individuals and in the variables.
Analysis and assessment of trace element contamination in offshore sediments of the Augusta Bay (SE Sicily): A multivariate statistical approach base…
2014
Abstract An application of multivariate statistical methods is provided to identify anthropogenic contaminants and lithogenic elements in offshore sediments collected near the heavily industrialized Augusta Bay, Sicily. An exploratory statistical technique, based on canonical correlation analysis (CCA) and mixture density estimation approach, is used for distinguishing between natural and anthropogenic contributions of trace elements in the investigated sediments. Following the intensive industrialization of Augusta area, marine sediments reveal the severe impact of local anthropogenic activities for many elements (e.g. As, Cd, Hg, Pb, and Sb), which are considered very dangerous for the en…
The silver collection of San Gennaro treasure (Neaples): A multivariate statistic approach applied to X-ray fluorescence data
2021
Abstract In this work we report an X-ray fluorescence spectroscopy (XRF) study combined with a multivariate approach allowing to detect compositional differences and similarities among the alloys used in realization of silver collection of San Gennaro items collection. The San Gennaro treasure in Naples (Italy) represents, in fact, one of the most important silver collections in the world. The classification of the collection items is very complex, not only for the large number of objects, but also in consideration that between 1600 and 1700, in Naples, more than 350 laboratories were active, most of them specialized in specific art of work. As a consequence, a given collection object could…
Análisis de la realidad sociolingüística del valenciano
2011
Se analiza la situación actual del uso y la percepción social del valenciano entre los habitantes del País Valenciano a partir de los estudios realizados por el Centro de Investigaciones Sociológicas. Para ello, se presta especial atención a variables sociodemográficas a partir de análisis estadístico multivariante con distribuciones de frecuencias bivariadas, análisis de segmentación y regresión logística. El estudio concluye que se produce un estancamiento en el porcentaje de hablantes del valenciano y que las personas de izquierdas y con mayor nivel de estudios son quienes se postulan más a favor de la unidad del valenciano con el catalán. Palabras clave: sociolingüística; diglosia; esta…
A typology of theatre audiences based on the impact of various sources of influence and the use of information channels
2020
En: Doxa Comunicación: revista interdisciplinar de estudios de comunicación y ciencias sociales. e-ISSN 2386-3978 n. 30, 2020, pp 127-143. Este estudio presenta una tipología de espectadores teatrales que contempla la influencia de los medios de comunicación y otras instancias de prescripción en sus decisiones de asistencia al teatro, un aspecto no abordado por ninguna investigación previa. La investigación se basa en una encuesta a 210 asistentes a representaciones teatrales de tres salas de la ciudad de Valencia. La aplicación de diversas técnicas estadísticas multivariables ha permitido identificar una tipología de cuatro perfiles de consumidores escénicos: los informados-alternativos, l…
Joint Graph Learning and Signal Recovery via Kalman Filter for Multivariate Auto-Regressive Processes
2018
In this paper, an adaptive Kalman filter algorithm is proposed for simultaneous graph topology learning and graph signal recovery from noisy time series. Each time series corresponds to one node of the graph and underlying graph edges express the causality among nodes. We assume that graph signals are generated via a multivariate auto-regressive processes (MAR), generated by an innovation noise and graph weight matrices. Then we relate the state transition matrix of Kalman filter to the graph weight matrices since both of them can play the role of signal propagation and transition. Our proposed Kalman filter for MAR processes, called KF-MAR, runs three main steps; prediction, update, and le…
The Multivariate Individual Selection of Diagnostic Tests and the Reserved Diagnostic Statement: An Optimum Combination of Two New Methods for the Co…
1984
A combination of two new methods for the diagnostic procedure in computer-aided differential diagnosis is presented. It is constructed on the basis of new results of our own in the field of mathematical decision theory and is demonstrated by the differential diagnosis of congenital heart diseases by means of ECG features.