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 30 for “"forest models"”.
-
On Mining Time Series Data with Random Forest Models: Perspectives from Classification, Anomaly Detection, and Distance Measures
L'abstract è presente nell'allegato / the abstract is in the attachment
-
Landscape & meteorological drivers of burn severity in the southern Rockies
… drivers of burn severity. This study uses Random Forest models to analyze the relative importance of landscape and meteorological variables in determining burn severity across the Southern Rockies Ecoregion from 2001 to 2020. Key landscape variables and parameters included latitude, elevation, …
-
Measuring the Impact of Elections on Judge Behavior Using Machine Learning and Economics Tools
… including lasso, decision tree and random forest models. In the context of prior research, these findings suggest that electoral pressure induces harsher treatment by judges across all stages of the judicial system.
-
Inductive logic programming with gradient descent for supervised binary classification
… interpretability has become a major concern for models making important decisions. In contrast to Local Interpretable Model-Agnostic Explanations (LIME), this thesis seeks to develop an interpretable model using logical rules, rather than explaining existing blackbox models. We extend recent …
-
Automated Prediction of Hepatic Arterial Stenosis
… invasive diagnostic procedure. Machine learning models have shown promise in determining stenosis in the carotid artery; however, they have yet to be tested on the less ideal data hepatic arteries generate. Software has been created to extract liver artery Doppler ultrasound information in an …
-
USING DCGAN TO GENERATE SYNTHETIC PACKET FLOWS FOR THREAT DETECTION
… is needed in the training of machine learning models used in threat detection. Such traffic is scarce and often imbalanced as the labeling is intensive and requires domain expertise. Deep Convolutional Generative Adversarial Networks (DCGAN) are known for their image recognition and generation …
-
Application of machine learning methods to predict phytoplankton blooms and determine microbial biomarkers using marine microbiomes
… sparse, and noisy. In this project, Random Forest classifiers based on diversity data were used to predict coastal phytoplankton blooms and search for their biomarkers. After joining two oceanographic campaigns data, samples were classified as bloom or normal depending on the total …
-
Incorporating Climate Sensitivity for Southern Pine Species into the Forest Vegetation Simulator
… global warming on North American forests have led to increasing calls to address climate change effects on forest vegetation in management and planning applications. The objectives of this project are to model contemporary conditions of soils and climate associated with the …
-
Assessing models for de-identification of Electronic Discharge Summary Using Machine Learning tools
… (CRF), Long Short Term Memory (LSTM) and Random Forest models were used, and the performance of each model was assessed. Findings: In order to assess each model’s performance, evaluation metrics were used to compare F-measure, Recall and Precision at token level to determine which Machine …
-
Drivers and Impacts of Smoldering Peat Fires in the Great Dismal Swamp
… did so by leveraging satellite imagery, random forest models, LiDAR data, and water table observations. Our results suggest that P. australis is aided by a hydrologic regime generated, in part, from the combined effects of drainage and deep smoldering fires. Our conclusions from these two …
-
Identifying Biophysical Drivers of Evapotranspiration for Forest Cover in a Mountainous Region
… relative differences among land covers. Within forested land covers specifically, I further examined how topographic, soil, and vegetative factors influence ET variability. Generalized Least Squares and Random Forest models were employed to assess the relationships between selected biophysical …
-
Technology in ecology: determining the location, behaviour, and energy expenditure of free-ranging carnivores
… maintains accuracy. Additionally, random forest models more accurately identify animal behaviours from accelerometer data after simple processing such as calculating extra variables, improving data evenness, and matching data frequencies to behaviours.<br/><br/>In the field, I investigate …
-
Corn tissue nutrient response related to soil health and fertility
… health metrics to fertility results using random forest models improved prediction of a positive tissue response to K fertilization, but did not improve predictions for P or S. along with soil-test K, two soil health measurements emerged as important, soil respiration and beta-glucosidase. …
-
The diversity and functioning of coastal microbial communities
… dataset used here is one such dataset. Random forest analysis, a type of machine learning, was applied here to an expansive dataset of microbial metabarcode reads and environmental measures across multiple spatial scales. Two different coastal habitats were used to create further distinctions. …
-
Automated Bug Severity Prediction using Source Code Metrics, Static Analysis, and Code Representation
… finding the effectiveness of machine learning models in predicting bug severity, we train 8 different models on code metrics only as a baseline and evaluate them based on different evaluation metrics. The overall result was not promising, but the Decision Tree and Random Forest models have …
-
Neurologic And Metabolic Safety Of Fluoroquinolones
… and PNS dysfunction. Cox proportional hazards models were estimated after matching. The hazard ratio associated with fluoroquinolone exposure was 1.08 (95% confidence interval [CI]: 1.05-1.11) for CNS dysfunction, and 1.09 (95% CI: 1.07-1.11) for PNS dysfunction. In Chapter 2, our outcome was …
-
Structure-based Predictions for Molecular Initiating Events
… In this project, new structural alert-based models for receptor binding MIEs have been constructed that create accurate, transparent and interpretable predictions. The alerts have been constructed with an automated workflow that uses Bayesian statistics to iteratively select substructures …
-
UNDERSTANDING THE SOURCES OF GENDER DISPARITIES IN STEM
… we estimate logistic and nonparametric Random Forest models. The estimates reveal that a combination of mathematics and mechanical skills, along with intensive high school exposure to science and math courses, are key predictors of choosing STEM majors and careers. A nonparametric decomposition …
-
Ecologically-focused calibration of hydrological models for environmental flow applications
… sites are frequently ungaged and hydrological models must be used to characterize flow alteration. Physically-based rainfall-runoff models typically utilize a "best overall fit" calibration criterion, such as the Nash-Sutcliffe Efficiency (NSE), that does not focus on specific aspects of the …
-
EVALUATING THE POTENTIAL OF TEMPERATE INLAND MINERAL SOIL WETLANDS AS NATURAL CLIMATE SOLUTIONS
… and CH₄ emission; (2) biogeochemical models to predict long term wetland carbon fluxes under varying biotic and abiotic conditions; and (3) process-based models to simulate wetland climate feedback under diverse future climate scenarios. This thesis responds to these crucial needs by …
Page 1 of 2