Search results for "Decision tree"
showing 10 items of 170 documents
Creación de un modelo estadístico predictivo para la determinación de las funciones de atenuación en español hablado
2018
Recientemente, algunos autores han definido distintas variables para caracterizar la atenuación lingüística en el marco de una base de datos multidimensional (Briz/Albelda; Albelda/otros). En este estudio se han seleccionado 982 elementos de atenuación de dieciocho entrevistas de español hablado; todos ellos han sido supervisados por hasta cuatro entrevistadores del proyecto Es.VaG.Atenuación. Finalmente, los datos se han evaluado mediante tres pruebas estadísticas para la clasificación y la reducción de variables: el análisis múltiple de correspondencias, el árbol de clasificaciones y el Random Forest. Las variables más determinantes en la discriminación de las funciones de atenuación han …
Accurate estimation of retinal vessel width using bagged decision trees and an extended multiresolution Hermite model.
2012
We present an algorithm estimating the width of retinal vessels in fundus camera images. The algorithm uses a novel parametric surface model of the cross-sectional intensities of vessels, and ensembles of bagged decision trees to estimate the local width from the parameters of the best-fit surface. We report comparative tests with REVIEW, currently the public database of reference for retinal width estimation, containing 16 images with 193 annotated vessel segments and 5066 profile points annotated manually by three independent experts. Comparative tests are reported also with our own set of 378 vessel widths selected sparsely in 38 images from the Tayside Scotland diabetic retinopathy scre…
Active learning strategies for the deduplication of electronic patient data using classification trees.
2012
Graphical abstractDisplay Omitted Highlights? Active learning for medical record linkage is used on a large data set. ? We compare a simple active learning strategy with a more sophisticated variant. ? The active learning method of Sarawagi and Bhamidipaty (2002) 6] is extended. ? We deliver insights into the variations of the results due to random sampling in the active learning strategies. IntroductionSupervised record linkage methods often require a clerical review to gain informative training data. Active learning means to actively prompt the user to label data with special characteristics in order to minimise the review costs. We conducted an empirical evaluation to investigate whether…
ActRec: A Wi-Fi-Based Human Activity Recognition System
2020
In this paper, we develop a Wi-Fi-based activity recognition system called ActRec, which can be used for the remote monitoring of elderly. ActRec comprises two parts: radio-frequency (RF) sensing and machine learning. In the RF sensing part, two laptops act as transmitter and receiver to record the channel transfer function of an indoor environment. This RF data is collected in the presence of seven human participants performing three activities: walking, falling, and sitting. The RF data containing the fingerprints of user activity is then pre-processed with various signal processing algorithms to reduce noise effects and to estimate the mean Doppler shift (MDS) of each data sample. We pro…
Combining Benford's Law and machine learning to detect money laundering. An actual Spanish court case.
2017
Abstract Objectives This paper is based on the analysis of the database of operations from a macro-case on money laundering orchestrated between a core company and a group of its suppliers, 26 of which had already been identified by the police as fraudulent companies. In the face of a well-founded suspicion that more companies have perpetrated criminal acts and in order to make better use of what are very limited police resources, we aim to construct a tool to detect money laundering criminals. Methods We combine Benford’s Law and machine learning algorithms (logistic regression, decision trees, neural networks, and random forests) to find patterns of money laundering criminals in the conte…
Improved usability of the minimal model of insulin sensitivity based on an automated approach and genetic algorithms for parameter estimation.
2006
Minimal model analysis of glucose and insulin data from an IVGTT (intravenous glucose tolerance test) is widely used to estimate insulin sensitivity; however, the use of the model often requires intervention by a trained operator and some problems can occur in the estimation of model parameters. In the present study, a new method for minimal model analysis, termed GAMMOD, was developed based on genetic algorithms for the estimation of model parameters. Such an algorithm does not require the fixing of initial values for the parameters (that may lead to unreliable estimates). Our method also implements an automated weighting scheme not requiring manual intervention of the operator, thus impro…
A finite element-based machine learning approach for modeling the mechanical behavior of the breast tissues under compression in real-time
2017
[EN] This work presents a data-driven method to simulate, in real-time, the biomechanical behavior of the breast tissues in some image-guided interventions such as biopsies or radiotherapy dose delivery as well as to speed up multimodal registration algorithms. Ten real breasts were used for this work. Their deformation due to the displacement of two compression plates was simulated off-line using the finite element (FE) method. Three machine learning models were trained with the data from those simulations. Then, they were used to predict in real-time the deformation of the breast tissues during the compression. The models were a decision tree and two tree-based ensemble methods (extremely…
Negative biopsy of focal hepatic lesions: Decision tree model for patient management
2019
OBJECTIVE. The purpose of this study was to investigate patient- and procedure-related variables affecting the false-negative rate of ultrasound (US)-guided liver biopsy and to develop a standardized patient-tailored predictive model for the management of negative biopsy results. MATERIALS AND METHODS. We retrospectively included 389 patients (mean age ± SD, 62 ± 12 years old) who had undergone US-guided liver biopsy of 405 liver lesions between January 1, 2013, and June 30, 2015. We collected multiple patient- and procedure-related variables. By comparing pathology reports of biopsy and the reference standard (further histology or imaging follow-up), we were able to categorize the biopsy r…
Factors of local recurrence and organ preservation with transoral laser microsurgery in laryngeal carcinomas; CHAID decision-tree analysis.
2018
BACKGROUND Indications of transoral laser microsurgery (TLM) are conditioned by the risk of local relapse. OBJECTIVE To evaluate prognostic factors of local relapse and local control with TLM (LC-TLM). METHODS Local relapse and LC-TLM were evaluated in 1119 patients. Logistic regression and CHAID decision tree analysis were performed. RESULTS Local relapse correlated to previous radiotherapy failure (8.45, CI 95%: 2.64-27.03; P < .001), paraglottic involvement (2.42, CI: 1.41-4.15; P = .001), anterior commissure involvement (2.12, CI: 1.43-3.14; P < .001), grade of differentiation (1.74, CI: 1.18-2.57; P = .005), and alcohol consumption (1.4, CI: 0.99-1.98; P = .057). Local relapse tended t…
A decision tree to help determine the best timing and antiretroviral strategy in HIV-infected patients.
2011
SUMMARYOptimal antiretroviral strategies for HIV-infected patients still need to be established. To this end a decision tree including different antiretroviral strategies that could be adopted for HIV-infected patients was built. A 10-year follow-up was simulated by using transitional probabilities estimated from a large cohort using a time-homogeneous Markov model. The desired outcome was for patients to maintain a CD4 cell count of >500 cells/mm3without experiencing AIDS or death. For patients with a baseline HIV viral load ⩾5 log10copies/ml, boosted protease inhibitor-based immediate highly active antiretroviral therapy (HAART) allowed them to spend 12% more time with CD4 ⩾500/mm3than…