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 21 for “"Two-stage Learning"”.
-
Physics-Informed Two-Stage Learning Framework for Engine Ignition Frequency and RPM Estimation
… short analysis windows. A physics-informed, two-stage machine-learning framework is developed to estimate the ignition frequency of four-stroke engines using synchronized sound and vibration measurements. A nonlinear product signal (xprod(t) = xsound(t) xvib(t)) is introduced to emphasize …
-
A Two-Stage Learning Approach for Goalie, Net and Stick Pose Estimation in Ice Hockey
… into goalie pose estimation using both One-Stage and Two-Stage Learning GoalieNet architectures. The One-Stage Learning GoalieNet predicts all keypoints simultaneously, while the Two-Stage Learning GoalieNet employs a Keypoint Predictor Network (KPN) to predict 26 out of 29 keypoints and a …
-
A Rate of Convergence for Learning Theory with Consensus
This thesis poses and solves a distribution free learning problem with consensus that arises in the study of estimation and control strategies for distributed sensor networks. Each node i for i = 1, . . . , n of the sensor network collects independent and identically distributed local measurements …
-
Medical Image Segmentation by Deep Convolutional Neural Networks
… to be a challenging problem. Recently, deep learning techniques, especially Convolution Neural Networks (CNNs) have received extensive research and achieve great success in many vision tasks. Specifically, with the advent of Fully Convolutional Networks (FCNs), automatic medical image …
-
Learning-Based Approaches for Intelligent Cognitive Radio
… for more data transmissions and increased network capacities, cognitive radio technology is ever more relevant. Traditional static spectrum allocation is no longer a feasible option. Through dynamic spectrum access, cognitive devices are able to tap into unused licensed spectrum bands. Thus, …
-
SAMPLE EFFICIENT REPRESENTATION LEARNING FOR VISUAL RECOGNITION
… specifically focuses on the representation learning problem in practical scenarios and makes efforts to deal with imbalanced data distribution and unlabeled data. Our studies show that the commonly adopted joint (or end-to-end) learning scheme substantially harms the quality of the learned …
-
LEARNING ACTIONS FROM DEMONSTRATIONS FOR MANIPULATION TASK PLANNING
… The main contributions of this thesis are: (1) a two-stage learning from demonstration technique for robots: a. learning actions from demonstrations, and b. using the learned actions for planning, (2) a general model to represent the geometric constraints of actions and a method to learn the …
-
Real-time sensing and control of multi-degree-of-freedom soft balloon actuators using data driven techniques
… underwater. Controllers based on neural networks have been proposed as one of the methods that could be applied to these robotic systems. This thesis focuses on learning-based sensing and control for an underwater Stacked Balloon Actuator (SBA) with three chambers and 25 layers. The …
-
Layered controllable video generation
… We address these challenges by proposing a two-stage learning procedure. In the first stage, with the rich set of losses and dynamic foreground size prior, we learn how to separate the frame into foreground and background layers and, conditioned on these layers, how to generate the next …
-
From pixels to pulse: enhancing trust, quality and robustness in remote video-based pulse measurement
… study across signal processing, machine learning, video quality assessment and uncertainty quantification. We explore traditional signal processing techniques for rPPG, establishing a baseline for pulse estimation while highlighting their sensitivity to motion artifacts. To address these …
-
Data analytics for real-time event identification using real phasor measurement unit data
… between multiple PMUs. Firstly, we propose a two-stage learning-based framework to identify PMU events. We utilize the Markov transition field (MTF) algorithm to extract latent data features by encoding temporal dependency and transition statistics of PMU data in graphs. Next, we establish a …
-
Navigating to Objects: Simulation, Data, and Models
… which are hard to learn using Reinforcement Learning (RL). In this thesis, we focus on learning such embodied object-search strategies from human demonstrations which implicitly captures intelligent behavior we wish to impart to our agents. In Part I, we present a large-scale study of …
-
New Solutions for Chip Physical Design in the Era of Artificial Intelligence
… disconnections in global routing tasks. Deep learning-based routers often generate disconnected routes due to insufficient accuracy. This work proposes a two-stage learning method: first, it generates key hub points using a conditional generative model, and second, it connects hubs to pins …
-
On Body Mass Index Analysis from Human Visual Appearance
… BMI estimation from frontal view face images via two key aspects: facial representation extracting and BMI estimator learning. First, we investigate the visual BMI estimation problem from the aspect of the characteristics and performance of different facial representation extracting methods by …
-
Learning in the Multi-Robot Pursuit Evasion Game
This thesis investigates the learning issue for mobile robots playing the differential forms of the pursuit-evasion (PE) game by proposing different learning algorithms. The intended learning algorithms are used to reduce (1) the computational requirements as much as possible, without affecting the …
-
Neural Networks for Music Emotion Recognition and Social Tags Emotion Representation
… to this area. With the emergence of neural networks, MER research has evolved from traditional machine learning methods combined with acoustic features to neural network learning methods combined with multi-source features. However, research gaps still exist in the following aspects. First, …
-
Motion Imitation and Adaptive Sim-to-Real Transfer for Robot Control
Deep reinforcement learning (RL) combined with motion imitation has emerged as a powerful paradigm for learning control policies, enabling robots to acquire diverse motor skills by tracking reference motions. These methods, however, face two fundamental challenges: obtaining or generating …
-
A Framework of Detection, Counting, Classification, and Advanced Processing Techniques for Objects in Multi-Resolution Imagery
… to analyze their advantages and shortcomings via two sets of evaluation metrics; ii) derived three post-processing schemes on object detection and classification using low-resolution wide-area aerial datasets, conducted quantitative analysis based on two sets of classical metrics and some enhanced …
-
IoT traffic modelling and QoS prediction framework using advanced deep learning
… leading to increased latency within IoT networks. Adding to this intricate communication framework is the variable network connectivity of mobile IoT devices such as drones or robots, which contributes to the existing complications. Therefore, it becomes imperative to predict the …
-
New methods for protein structure prediction using machine learning and deep learning
… important. In this dissertation, new machine learning and deep learning methods have been proposed for protein model quality assessment, protein contact prediction, protein model refinement, and loop modeling. The goal of model quality assessment (QA) is to estimate the quality of predicted …
Page 1 of 2