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 22 for “"Synthetic Data Augmentation"”.
-
Financial AI: Synthetic Data Augmentation for Deep Reinforcement Learning and Graph Neural Networks
… and distributions from a large amount of data due to their non-linearity and enormous parameter settings in Deep Neural Networks (DNNs). While traditional statistical models may struggle and often fail to capture them, especially in high-dimensional space. Thus, by leveraging the power of …
-
Development and validation of multi-sensor embedded system for low-cost pavement monitoring
… advanced computer vision methodologies with synthetic data augmentation for automated distress detection, and develops practical deployment strategies for transportation agencies. The methodology combines embedded systems engineering, sensor fusion techniques, computer vision, and machine …
-
TOWARDS ROBUST COMPUTER VISION USING SYNTHETIC DATA AND GENERATIVE MODELS
… The need for large amounts of training data and the black-box nature of discriminative deep networks are two major challenges for robustness. In this dissertation, I propose to pursue robust vision in two directions: 1) leveraging synthetic data and 2) generative modeling. In the first …
-
Toward Robust Semantic Segmentation in Levee Infrastructure Monitoring: Enhancing Accuracy with High-Fidelity Synthetic Data and Ensemble Learning
… the identification of sand boils. To address dataset limitations, high-fidelity synthetic images are generated using DreamBooth for fine-tuning, while ControlNet adds structural constraints to enhance realism and consistency. A semi-automatic convex hull annotation technique enhances labeling …
-
Sintetinių duomenų naudojimas finansinių laiko eilučių analizėje /
… market, faces challenges from limited historical data and high price volatility. This thesis investigates whether the use of synthetic data during the training of deep learning models improves cryptocurrency price forecasting accuracy. Three synthetic data generation methods: the stationary …
-
Scientific machine learning for astrophysical and cosmological inference.
… increasingly rely on large, high-dimensional datasets that challenge traditional analysis techniques. This dissertation investigates machine-learning methods for astrophysical and cosmological inference with emphasis on interpretability, robustness, uncertainty quantification, and …
-
Advanced Anomaly Detection and Quality Control in PCB Manufacturing
… of the PCB labeling process, integrating data from Solder Paste Inspection (SPI) and Automatic Optical Inspection (AOI) datasets. The research is structured into distinct phases, each addressing different aspects of the PCB manufacturing process. The initial phase focuses on improving the …
-
Artificial Intelligence for automated decision-making in error-pattern recognition
… Learning, focusing on "Neural Architecture & Data Representation", "Manifold & Embedding Learning", and "Data Integration & Analysis". The contributions of this thesis include: (1) a novel neural architecture based on complex-valued neural networks, (2) a framework for encoding hierarchical …
-
Artificial Intelligence for automated decision-making in error-pattern recognition
… Learning, focusing on "Neural Architecture & Data Representation", "Manifold & Embedding Learning", and "Data Integration & Analysis". The contributions of this thesis include: (1) a novel neural architecture based on complex-valued neural networks, (2) a framework for encoding hierarchical …
-
Τεχνητή νοημοσύνη και γυναικολογικό υπερηχογράφημα
… borderline ovarian tumors), incorporating synthetic data augmentation using generative adversarial networks to address class imbalance. All images underwent anonymization, normalization, and data augmentation prior to model training. RESULTS: Model performance was assessed using accuracy, …
-
Cost-Effective Data Augmentation through Large Language Models for Foodborne Illness Detection on Social Media
… recognized or disclosed. Utilizing social media data could provide crucial early warnings and significantly benefit public health responses. Nevertheless, this data is inherently noisy and may include deceptive or irrelevant information, which can lead to false positives or missed warnings. …
-
Automated data analysis for bridge visual inspection using deep learning techniques
… visual inspection. The captured inspection data (such as images and point clouds) need to be further analyzed to identify damage types, magnitude, location, and extent. Among these, automated raw data analysis including automated semantic segmentation of bridge point clouds and damage …
-
Responsible Generative and Agentic Artificial Intelligence Frameworks for Autonomous Electric Vehicle Adoption
… transportation and the supporting energy and data infrastructures. Electric Vehicles (EVs) introduce new load patterns, infrastructure constraints, and opportunities for mobility assets to serve as flexible distributed energy resources (DER). Autonomous Vehicles (AVs) intensify reliance on …
-
Predicting injury outcomes in mining industry - a machine learning approach
… going to be away from work (DAFW) using the MSHA dataset. These predictive models would be helpful for the safety experts in their efforts to create a safer work environment. Predicting days away from work would help the supervisor to plan for a temporary replacement. We compare the performance of …
-
Multi-server federated learning in vehicular edge computing
… multiple challenges: highly non-IID and noisy data across vehicles, heterogeneous computation and communication resources, private training costs, intermittent connectivity, and the need to coordinate multiple servers. This thesis addresses these challenges through three complementary …
-
Data Augmentation Methods for the Simulation of Energy Conversion Devices
… thesis presents a systematic investigation into synthetic data augmentation for improving machine learning-based fault diagnosis of induction machines, with a focus on broken rotor bar faults. The research addresses the fundamental challenge of data scarcity and poor model generalization caused …
-
Drones, combinatorial Optimization and deep Learning for inspecting solar thermal power Plants
… inspection. RTSet is introduced as the first dataset for broken-glass detection in PT receiver tubes. Through feature selection, class balancing, and dual optimization with advanced training techniques, we significantly boost classification recall. We further enhance inspection through …
-
Jointly Mining News and User-Generated Content: Machine Learning, Information and Social Network Perspective
… studies 1) jointly mining massive user-generated data, 2) from multiple sources and platforms, and 3) the unpredictable quality of user-generated content. To address these issues, we tackle the problem of jointly learning and mining valuable information from online news articles and user-generated …
-
Generative AI for Hardening Security: From Training Data Augmentation, Language Alignment, to Code Vulnerability Demonstration
… cybersecurity systems face fundamental data limitations that constrain their effectiveness across diverse threat environments. Training data for security classifiers is inherently scarce, imbalanced, and subject to distributional shift, degrading generalization under evolving threat …
-
Modifiable risk factors in administrative health data: validity of smoking identification algorithms and patterns of social determinants of health documentation
… such as hypertension. Administrative health data (AHD), including hospital discharge abstracts and physician billing claims, can be used to identify these risk factors and monitor disease burden. However, since AHD is primarily intended for healthcare management, validating algorithms that …
Page 1 of 2