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 28 for “"Boruta"”.
-
Comparing Prediction Accuracies of Cancer Survival Using Machine Learning Techniques and Statistical Methods in Combination with Data Reduction Methods
… data reduction methods. Lasso regression and the Boruta algorithm were used for variables selection, and Principal Component Analysis (PCA) was used for dimensionality reduction. We used one statistical method Logistic regression (LR) and several machine learning methods including Decision Tree …
-
Kazio Borutos egodokumentai: kairysis intelektualas totalitarizmo akivaizdoje /
Egodocuments of Kazys Boruta: A Left-wing Intellectual Facing Totalitarianism This master’s thesis analyses the personality and views of Kazys Boruta as they reveal themselves in the writer’s late egodocuments (1940–1965). Different types of egodocuments (diaries, letters, an autobiography, drafts …
-
Software Engineering Development of Machine Learning Approaches for Alzheimer’s Disease Classification
… testing, principal component analysis, and the Boruta algorithm to iden- tify key predictors of AD. The selected features were then applied to wide and deep neural network models, which maintained high accuracy despite the dimensionality reduction highlighting the robustness of the approach. …
-
Ανάλυση του μικροβιώματος σιέλου σε ασθενείς με μη αντιρροπούμενη κίρρωση ήπατος
… Analysis of Variance (PERMANOVA) test, p=0.008]. Boruta wrapper algorithm selected the most representative genera able to classify controls and patients (ROC analysis- AUC= 0.815). CONCLUSIONS: Patients with stable decompensated cirrhosis of various etiology and history of complications, have …
-
Temporal Changes in Symptom-Behavior Dynamics: A Process-Focused Network Modeling Approach
… using resampling procedures (i.e., the Boruta feature selection and regression tree algorithms) in order to more accurately capture processes of change at the individual level at both baseline and post-treatment. Next, group- and sub-group level processes were derived by identifying …
-
Early Developmental Impacts on Male traits and Female Preference in Zebra Finches (Taeniopygia guttata)
Some male sexually selected traits are sensitive to stressors early in life and provide females with information to discriminate among males with different developmental experiences. Moreover, female early life experiences could also impact which males they choose. Females might either choose …
-
Estimating Historical Streamflow at Ungauged Watersheds
… specifically Random Forests coupled with Boruta feature selection, is utilized to extend this classification to ungauged basins by establishing relationships between watershed attributes and class memberships determined based on streamflow time series clustering. Second, a hydrologic …
-
Perfiles estratégicos de turistas extranjeros en Perú: un enfoque de segmentación basado en variables clave del gasto
… de selección de variables (Random Forest y Boruta) con modelos de segmentación avanzados (Clases Latentes y Clases Latentes Multinivel). El análisis permitió identificar factores sociodemográficos, de organización de viaje y de comportamiento en destino que explican significativamente el …
-
Cardiometabolic biomarkers in blood and the risk of cerebrovascular disease
… metabolites over traditional risk factors. The Boruta algorithm was used to procure the relevant metabolites related to ischaemic stroke. Finally, bidirectional two-sample Mendelian randomisation (MR) was used to evaluate the causal relationship of identified metabolites with ischaemic stroke. …
-
Smart optical networks enabled by performance monitoring and machine learning
… operations. Random Forest (RF) classifiers with Boruta-Shapley additive explanation (Boruta-SHAP) automated feature selection and transfer learning achieve 98.64%-99.65% accuracy for QoT estimation across four datasets while providing superior computational efficiency (reductions of training time …
-
NEW ADVANCES IN QUANTITATIVE RADIOLOGY: RADIOMICS IN NEURORADIOLOGY APPLIED TO PRIMARY BRAIN TUMORS USING A MACHINE LEARNING APPROACH
… patients). Results: Feature selection methods (Boruta, RFE and LR-EL) identified age and 3 radiomics features for MGMT prediction and 3 features for IDH prediction. For IDH prediction, SVM classifier achieved average 96.8% accuracy and 0.929 AUC during the training phase, and 84.6% accuracy and …
-
Improving prediction of opioid use disorder with machine learning algorithms
… by utilizing two feature selection techniques, Boruta and Recursive Feature Elimination (RFE), to identify the best predictor through a majority voting system. The selected feature, combined with 10 demographic, socioeconomic, physical, and psychological predictors (gender, age, employment …
-
La propuesta de valor en la oferta de alojamiento turístico entre particulares. Una perspectiva desde la lógica del dominio del servicio
… para ello métodos de Machine Learning: Boruta, Lasso y Elastic Net para la selección de características y SVM para la predicción. La operacionalización de la propuesta de valor muestra, adicionalmente, las posibilidades y la contribución del aprendizaje automático en el campo del turismo …
-
Advanced Deep Learning Architectures for Quadratic Polarimetric Synthetic Aperture RADAR Image Classification
… a feature selection workflow that combines Boruta and Shapley Additive Explanations (BorutaSHAP) with Pearson and bootstrapped-correlation screening, extracting a compact set of non-redundant decomposition descriptors primarily from PauliRGB, Cloude-Pottier, and van Zyl representations. …
-
Epidemiology and risk factor analysis of avian influenza virus
… through the logistic regression method and Boruta algorithm method.Results: Based on data collated from four databases (Scopus, Web of Science Core Correlation, PubMed and SpringerLink electronic journal) and a global electronic reporting system (ProMED mail), one hundred and seventy-three …
-
The Diagnostic Potential of miRNAs in Pulmonary Arterial Hypertension
… 0 miRNAs from whole blood were identified by the Boruta algorithm compared to 56 miRNAs from plasma. 11 miRNAs were selected for qPCR verification as constituents of potential biomarker panels. Mir-483-5p, miR-584-5p and miR-638 had acceptable amplification profiles and were tested in the larger …
-
MACHINE LEARNING METHODS FOR PREDICTION OF HUMAN INFECTIOUS VIRUS AND IMPUTATION OF HLA ALLELES
… if it can affect humans. We further employed the Boruta algorithm to select the important features, then fed those important features into the Random Forest method to train the model and make predictions. After utilizing a dataset that is independent of the training dataset in the test procedure, …
-
O conteúdo de insumo em tarefas que integram leitura e escrita no Celpe-Bras : uma abordagem informada por corpus
… de redução de multivariáveis com o algoritmo Boruta. O corpus de estudo, constituído por 90 tarefas aplicadas entre 1998 e 2020 no Celpe Bras, dois corpora de referência, documentos oficiais e estudos prévios foram utilizados nas análises. Com as 33 métricas preditivas selecionadas pelo …
-
Métodos de aprendizado de máquina aplicados a modelagem de florestas inequiâneas
… climáticas e topográficas. O Algoritmo de Boruta foi aplicado para selecionar o melhor conjunto de variáveis. Máquina de Vetor de Suporte (MVS), Redes Neurais Artificiais (RNA), Random Forests (RF) e Modelo Linear Generalizado (MLG) foram os métodos de aprendizado de máquina avaliados. Em …
-
Application of Predictive Analytics in Estimating Mechanical Properties for Investment Castings
… techniques used in this proposed model include Boruta, Variable Selection Using Random Forest (VSURF), and Recursive Feature Elimination (RFE). They were employed to reduce the redundancy in the large dataset and find a best reduced dataset which can improve the prediction capability of DLMs. …
Page 1 of 2