Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 78 for “"Boosted decision trees"”.
-
Enhancing Influence Estimation in Gradient Boosted Decision Trees Through Hierarchical Analysis
… presents a novel influence function for gradient-boosted decision trees (GBDTs), a widely-used class of predictive models. Influence estimation aims to quantify how individual training samples affect a model’s predictions, offering valuable insights for model debugging, data quality analysis, and …
-
Χρήση της μεθόδου των Boosted Decision Trees στην αναβάθμιση του σκανδαλιστή πρώτης τάξης (run 2)
… ευκρίνεια χρησιμοποιήσαμε την μέθοδο των Boosted Decision Trees(BDT), για τον διαχωρισμό πιδάκων από σήμα και από pile-up. Τα BDT εκπαιδεύονται με την χρήση ήδη ταξινομημένων γεγονότων. Αφού ρυθμίζονται όλες οι παράμετροι, συγκρίνουμε την απόδοση της μεθόδου των BDT με την μέθοδο που …
-
Efficient FPGA implementations for gradient boosted decision trees with applications in real-time medical imaging systems
… contribution focuses on optimising gradient boosted decision tree models for deployment on field-programmable gate arrays. By introducing training methods that consider the impact of reduced precision during model development, this work reduces the computational and memory demands of these …
-
Sistema web para la predicción de puntos de actividad delictiva en el Gobierno Regional Del Callao utilizando Gradient Boosted Decision Trees
… avanzado basado en el algoritmo Gradient Boosted Decision Trees para identificar y predecir puntos de alta actividad delictiva. La metodología de investigación comprende tres fases: planificación, desarrollo y validación. La implementación del modelo busca optimizar la asignación de …
-
Study of W Boson Production in Association with Two Jets using Boosted Decision Trees with Data Collected by the ATLAS Detector.
… the precision and accuracy of the measurements, boosted decision trees are employed. Firstly, the joint electroweak and strong production rate of Wjj events is evaluated, resulting in a detector-level cross section of 4629 ± 6 (stat.) ± 137 (syst.) ± 80 (lumi.) fb. Secondly, a measure of the …
-
Application of Artificial Neural Networks, Gradient Boosted Decision Trees, and Multilevel Logistic Models in a Supervised Learning Environment to Investigate Differences in Classification Performance when Predicting College Enrollment
… of Artificial Neural Networks and Gradient Boosted Decision Trees, at predicting college enrollment using data collected as students progressed through high school. Because of the immense amount of data that data mining algorithms can interact with, the emphasis is placed on, but not limited …
-
An Empirical Analysis on Point-wise Machine Learning Techniques using Regression Trees for Web-search Ranking
… Many different kinds of classifiers, including boosted decision trees, neural networks, and SVMs have proven successful in the field. This thesis surveys traditional point-wise techniques that use regression trees for web-search ranking. The thesis contains empirical studies on Random Forests …
-
PREDICTING FILL RATES FOR NAVSUP SITE DEMAND-BASED LEVEL INVENTORY OPTIMIZATION MODEL
… planners’ ability to make timely, data-driven decisions when incorporating updated historical demand. This thesis considers using predictive analysis techniques to predict the fill rate for non-simulated (s,Q) candidates, using simulated (s,Q) candidates as the training data. Four different …
-
Characteristic Classification of Walkers via Underfloor Accelerometer Gait Measurements through Machine Learning
… machine learning algorithms included are Bagged Decision Trees, Boosted Decision Trees, Support Vector Machines (SVMs), and Neural Networks. Data reduction techniques achieve a higher gender classification accuracy of 93 % and classify weight with 64% accuracy. The data reduction techniques are …
-
Identification of the w-boson associated higgs boson production events with the cms detector at 13tev proton collision energy /
… used to train multivariate analysis method - Boosted Decision Trees. The BDT were tested with independent test samples adjusted by the luminosity, respective cross-sections and branching fractions. These trained boosted decision trees will be used to analyze the data in proton-proton …
-
Object categorization using collections of parts and second order pooling features
… Vector Machines, L1 Logistic Regression and Boosted Decision Trees are presented and discussed. Methods to analyze confusion in these results are developed and results are presented. The Collections of Parts model is augmented with features from features generated by Second Order Pooling …
-
Antibiotic resistance and disease burden of gram-negative bloodstream infections in neonates: enhancing targeted empiric treatment
… and resistance patterns. Logistic regression, decision trees, boosted decision trees, eXtreme boosted decision trees, and random forest models were developed to predict the effectiveness of ampicillin, gentamicin, and ceftriaxone.<br/><br/>Findings from the reviews reinforced that ampicillin …
-
Machine learning techniques for calorimeter cluster calibration of the CMS particle flow algorithm.
… excess. Machine learning techniques, such as Boosted Decision Trees (BDT) and Graph Neural Networks (GNN), are employed to calibrate PF energy clusters, improving both the response and the resolution of the measured energy. This thesis applies BDT to calibrate PF ECAL clusters, while GNN is …
-
Entwicklung und Testung eines datenbasierten Diagnosealgorithmus für vestibuläre Erkrankungen im Bereich der hausarztzentrierten Versorgung
… die Modelle Deep Neural Networks [13] und der Boosted Decision Trees [29]. Für die Klassifizierung mit möglichst großer Transparenz zur Entscheidung und die Ermittlung der Relevanz der Variablen wählten wir Classification and Regression Trees und Random Forests aus. CART bieten den Vorteil, …
-
A search for ZH-μμbb production at the Tevatron
… In order to improve the power of the analysis boosted decision trees are used to increase the separation between signal and background. Not observing an excess over the expected background, limits on the Higgs boson production cross-section at the Tevatron are set.
-
Search for Weakly-Produced Supersymmetry in Same-Sign Di-Lepton Final State at $\sqrt{s}=8$ Tev With The atlas Detector
… and discriminated against background using Boosted Decision Trees trained on compressed supersymmetric simplified models. No significant excesses above background expectations are observed. The 95% confidence limits are placed on Chargino1 Neutralino2 pairs decaying via W and Z bosons and …
-
Measurement of a New Half-Lifetime Lower Limit for Neutrinoless Double-Beta Decay in Xe-136 Using the Full EXO-200 Phase 1 Data Set and Improvements to Barium Tagging for nEXO
… technique for EXO-200 is developed using Boosted Decision Trees, leading to a 12% improvement to sensitivity and a 13% improvement to the 0νββ half-life lower limit. Furthermore, improvements are made to the nEXO barium tagging system producing a 50% improvement in signal-to-background …
-
FORECASTING INTERMITTENT DEMAND FOR AIRCRAFT SPARE PARTS USING MACHINE LEARNING
… traditional time-series baselines, and gradient boosted decision trees (XGBoost), and artificial neural networks as machine learning models. Accuracy is assessed using MASE as the primary metric, complemented by error distributions.Results demonstrate that machine learning models, particularly …
-
Analysis of regional effects on market segment production
… develops general linear regression and gradient boosted decision tree models to determine the regional factors that contribute to the variance of recruit production. In particular, the gradient boosted decision tree delivers predictive results that allow analysts to identify regions that have …
-
Search for a Higgs-like boson decaying to two photons in proton antiproton collisions at center of mass energy of 1.96 TeV
… This thesis employs a multivariate technique, boosted decision trees, to optimize the discrimination of signal from background. No significant excess of data above theoretical prediction is observed, so limits on the ratio of the production cross section times the branching ratio to the SM …
Page 1 of 4