Search results for "Decision Tree"
showing 10 items of 170 documents
Jason Intentional Learning: An Operational Semantics
2013
This paper introduces an operational semantics for defining Intentional Learning on Jason, the well known Java-based implementation of AgentSpeak(L). This semantics enables Jason to define agents capable of learning the reasons for adopting intentions based on their own experience. In this work, the use of the term Intentional Learning is strictly circumscribed to the practical rationality theory where plans are predefined and the target of the learning processes is to learn the reasons to adopt them as intentions. Top-Down Induction of Logical Decision Trees (TILDE) has proved to be a suitable mechanism for supporting learning on Jason: the first-order representation of TILDE is adequate t…
Automatic detection and agronomic characterization of olive groves using high-resolution imagery and LIDAR data
2014
The Common Agricultural Policy of the European Union grants subsidies for olive production. Areas of intensified olive farming will be of major importance for the increasing demand for oil production of the next decades, and countries with a high ratio of intensively and super-intensively managed olive groves will be more competitive than others, since they are able to reduce production costs. It can be estimated that about 25-40% of the Sicilian oliviculture must be defined as “marginal”. Modern olive cultivation systems, which permit the mechanization of pruning and harvest operations, are limited. Agronomists, landscape planners, policy decision-makers and other professionals have a grow…
A Scheme for Continuous Input to the Tsetlin Machine with Applications to Forecasting Disease Outbreaks
2019
In this paper, we apply a new promising tool for pattern classification, namely, the Tsetlin Machine (TM), to the field of disease forecasting. The TM is interpretable because it is based on manipulating expressions in propositional logic, leveraging a large team of Tsetlin Automata (TA). Apart from being interpretable, this approach is attractive due to its low computational cost and its capacity to handle noise. To attack the problem of forecasting, we introduce a preprocessing method that extends the TM so that it can handle continuous input. Briefly stated, we convert continuous input into a binary representation based on thresholding. The resulting extended TM is evaluated and analyzed…
RETROVESICAL MASS IN MEN
1999
We review the differential diagnosis and treatment of retrovesical masses in men.During the last 8 years 21 male patients 3 to 79 years old (mean age 47.1) presented with symptoms or signs of a retrovesical mass. Clinical features and diagnostic findings were reviewed, and related to surgical and histopathological findings.The retrovesical masses included prostatic utricle cyst in 3 cases, prostatic abscess in 1, seminal vesicle hydrops in 6, seminal vesicle cyst in 2, seminal vesicle empyema in 3, large ectopic ureterocele in 1, myxoid liposarcoma in 1, malignant fibrous histiocytoma in 1, fibrous fossa obturatoria cyst in 1, hemangiopericytoma in 1 and leiomyosarcoma in 1. In 17 patients …
Deterministic Linkage as a Preceding Filter for Other Record Linkage Methods
2015
Deterministic record linkage (RL) is frequently regarded as a rival to more sophisticated strategies like probabilistic RL. We investigate the effect of combining deterministic linkage with other linkage techniques. For this task, we use a simple deterministic linkage strategy as a preceding filter: a data pair is classified as ‘match' if all values of attributes considered agree exactly, otherwise as ‘nonmatch'. This strategy is separately combined with two probabilistic RL methods based on the Fellegi–Sunter model and with two classification tree methods (CART and Bagging). An empirical comparison was conducted on two real data sets. We used four different partitions into training data a…
Association between MICA Gene Variants and the Risk of Hepatitis C Virus-Induced Hepatocellular Cancer in a Sicilian Population Sample
2018
There are currently no biomarkers that predict hepatocellular carcinoma (HCC) risk in patients with hepatitis C virus (HCV)-related cirrhosis. We investigated the relationships among major histocompatibility complex (MHC) class I chain-related gene A (MICA) polymorphisms, plasma levels of soluble MICA (sMICA), and HCC risk in patients with HCV-related HCC. One hundred fifty-four HCV-related HCC patients, 93 HCV-related liver cirrhosis (LC) cases, and 244 healthy controls, all sampled from the native Sicilian population, were genotyped using the KASP™ single-nucleotide polymorphism genotyping method. The MICA rs2596542 polymorphism showed that the G/G genotype was significantly more frequent…
Choice of second-line disease-modifying antirheumatic drugs after failure of methotrexate therapy for rheumatoid arthritis: A decision tree for clini…
2009
Objective To survey rheumatologists' preferences for the choice of a second-line disease-modifying antirheumatic drug (DMARD) after inadequate response with methotrexate (MTX) therapy in rheumatoid arthritis (RA). Methods Thirty-six rheumatologists stated their preferences for RA treatment after inadequate response with MTX therapy (optimal dose at least 6 months). From the initial scenario, we derived 54 vignettes varying by rheumatoid factor or anti–cyclic citrullinated peptide antibody presence, swollen joint count, Disease Activity Score in 28 joints, and structural damage. Respondents stated their preference among 5 therapeutic options: MTX continuation, switch to another conventional …
Comparative performances of machine learning methods for classifying Crohn Disease patients using genome-wide genotyping data
2019
Crohn Disease (CD) is a complex genetic disorder for which more than 140 genes have been identified using genome wide association studies (GWAS). However, the genetic architecture of the trait remains largely unknown. The recent development of machine learning (ML) approaches incited us to apply them to classify healthy and diseased people according to their genomic information. The Immunochip dataset containing 18,227 CD patients and 34,050 healthy controls enrolled and genotyped by the international Inflammatory Bowel Disease genetic consortium (IIBDGC) has been re-analyzed using a set of ML methods: penalized logistic regression (LR), gradient boosted trees (GBT) and artificial neural ne…
Cost-effectiveness of optimized adherence to prevention guidelines in European patients with coronary heart disease : results from the EUROASPIRE IV …
2018
Background: This study aims to assess the cost-effectiveness of optimized guideline adherence in patients with a history of coronary heart disease. Methods: An individual-based decision tree model was developed using the SMART risk score tool which estimates the 10-year risk for recurrent vascular events in patients with manifest cardiovascular disease (CVD). Analyses were based on the EUROASPIRE IV survey. Outcomes were expressed as an incremental cost-effectiveness ratio (ICER). Results: Data from 4663 patients from 13 European countries were included in the analyses. The mean estimated 10-year risk for a recurrent vascular event decreased from 20.13% to 18.61% after optimized guideline a…
Longitudinal changes in physical activity, sedentary behavior and body mass index in adolescence: Migrations towards different weight cluster
2016
This study examined longitudinal changes in physical activity, sedentary behavior and body mass index in adolescents, specifically their migrations towards a different weight cluster. A cohort of 755 adolescents participated in a three-year study. A clustering Self-Organized Maps Analysis was performed to visualize changes in subjects' characteristics between the first and second assessment, and how adolescents were grouped. Also a classification tree was used to identify the behavioral characteristics of the groups that changed their weight cluster. Results indicated that boys were more active and less sedentary than girls. Boys were especially keen to technological-based activities while …