Search results for " Trees"
showing 10 items of 214 documents
First report of Phytophthora palmivora as a pathogen of olive in Italy
2000
Olive (Olea europea L.) is an economically important crop in Italy and is planted on about 1 million ha. The Apulia, Calabria, and Sicily regions of Southern Italy account for about 70% of the production. Many new plantations have been established during the last 10 years. In summer 1999, 1- to 2-year-old olive trees (cv. Carolea) with decline symptoms were observed in new plantations in Catanzaro Province (Calabria). The symptoms associated with the root rot were leaf chlorosis, defoliation, wilting, twig dieback, and eventual plant collapse. In some cases, more than 40% of the trees were affected. A Phytophthora sp. was isolated consistently from rotted rootlets of diseased trees using a…
Boosting for ranking data: an extension to item weighting
2021
Gli alberi decisionali sono una tecnica predittiva di machine learning particolarmente diffusa, utilizzata per prevedere delle variabili discrete (classificazione) o continue (regressione). Gli algoritmi alla base di queste tecniche sono intuitivi e interpretabili, ma anche instabili. Infatti, per rendere la classificazione più affidabile si `e soliti combinare l’output di più alberi. In letteratura, sono stati proposti diversi approcci per classificare ranking data attraverso gli alberi decisionali, ma nessuno di questi tiene conto ne dell’importanza, ne delle somiglianza dei singoli elementi di ogni ranking. L’obiettivo di questo articolo `e di proporre un’estensione ponderata del metodo …
Deep Learning for Resource-Limited Devices
2020
In recent years, deep neural networks have revolutionized the development of intelligent systems and applications in many areas. Despite their numerous advantages and potentials, these intelligent models still suffer from several issues. Among them, the fact that they became very complex with millions of parameters. That is, requiring more resources and time, and being unsuitable for small restricted devices. To contribute in this direction, this paper presents (1) some state-of-the-art lightweight architectures that were specifically designed for small-sized devices, and (2) some recent solutions that have been proposed to optimize/compress classical deep neural networks to allow their dep…
A Methodology for Protection of Trees Against Lightning Strikes as a Measure to Prevent Fires and Loss of Human Life
2021
Some regions may be characterized by a very low annual lightning ground flash density, and yet lightning strikes seem to have been in those areas the cause of widespread wildfires in forested areas. Due to global climate change, these occurrences seem to be an increasing threat. In this paper, the authors discuss the withstand capability of trees against lightning and introduce the criteria for the deployment of tree lightning protection systems (TLPS) to protect forested areas, where deemed necessary by the tree risk assessment. This work analytically identifies the critical trunk radius of the tree below which the tree may explode in the case of a lightning strike and ignite the surroundi…
KERNEL ESTIMATION OF THE TRANSITION DENSITY IN BIFURCATING MARKOV CHAINS
2023
We study the kernel estimator of the transition density of bifurcating Markov chains. Under some ergodic and regularity properties, we prove that this estimator is consistent and asymptotically normal. Next, in the numerical studies, we propose two data-driven methods to choose the bandwidth parameters. These methods are based on the so-called two bandwidths approach.
Operations Management GADE Decision Trees Technique Lesson 4
2023
El document forma part dels materials docents programats mitjançant l'ajut del Servei de Política Lingüística de la Universitat de València. A refresher on the use of decision trees in Operations Management
Monumental chestnut trees: source of genetic diversity, cultural and landscape value
2019
The mtonumental trees are unique individuals tof venerable age and ctonsiderable size, which represent a heritage tof inestimable histtorical, cultural, landscape, and scientific value ftor the territtory. They alsto ctonstitute a stource tof genetic diversity which ctonfers them ltongevity and ability tto adapt tto climate and envirtonmental changes. In this ctontext, studies ton centennial trees can be useful ftor interpretatiton tof species histtory as migratiton events, selectiton and anthrtoptogenic actiton. The aim tof this research was tto evaluate the genetic variability tof ancient Castanea sativa trees and relate them tto actual natural/naturalized ptopulatitons and varieties in t…
Two Relevant Forecasting Problems for Practitioners in Finance: Equity Risk Premium and Non-Performing Loans
2021
The thesis aims to substantiate whether macroeconomic factors indicators are relevant to predict both in-sample and out-of-sample assets' future performance focusing on two well-studied themes in financial economics and banking: First, the ability to predict the equity risk premium, and second, the macroeconomic determinants of non-performing loans (NPL) rates. The dissertation is divided in three chapters. Chapter 1, entitled "Forecasting the equity risk premium in the European Monetary Union", investigates the capacity of multiple economic and technical variables to predict the Euro area equity risk premium. The chapter examines the performance of several variables that could be good pred…
Item Response Trees: a recommended method for analyzing categorical data in behavioral studies
2015
Behavioral data are notable for presenting challenges to their statistical analysis, often due to the difficulties in measuring behavior on a quantitative scale. Instead, a range of qualitative alternative responses is recorded. These can often be understood as the outcome of a sequence of binary decisions. For example, faced by a predator, an individual may decide to flee or stay. If it stays, it may decide to freeze or display a threat and if it displays a threat, it may choose from several alternative forms of display. Here we argue that instead of being analyzed using traditional nonparametric statistics or a series of separate analyses split by response categories, this kind of data ca…
Machine learning for mortality analysis in patients with COVID-19
2020
This paper analyzes a sample of patients hospitalized with COVID-19 in the region of Madrid (Spain). Survival analysis, logistic regression, and machine learning techniques (both supervised and unsupervised) are applied to carry out the analysis where the endpoint variable is the reason for hospital discharge (home or deceased). The different methods applied show the importance of variables such as age, O2 saturation at Emergency Rooms (ER), and whether the patient comes from a nursing home. In addition, biclustering is used to globally analyze the patient-drug dataset, extracting segments of patients. We highlight the validity of the classifiers developed to predict the mortality, reaching…