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 67 for “"U-Net"”.
-
An Attention LSTM U-Net Model for Drosophila Melanogaster Heart Tube Segmentation
… Our most recent heart segmentation model, FlyNet 2.0+, is a fully convolutional LSTM U-Net model. However, the performance of the model diminishes in the presence of artifacts, such as image reflection and heart movement, resulting in time-consuming manual intervention for mask correction. …
-
U-Net Network Enhancements to Facilitate Rapid Electron Microscopy Imaging for Connectomics
… segmentation using a convolutional neural network, identify those areas of interest that require more detailed imaging through a learning-based error detection network, and then rescan only those identified high interest areas to produce a fused image for segmentation. The proposed thesis …
-
Transforming Medical Image Segmentation with Enhanced U-Net Architectures and Adaptive Transfer Learning
… modalities, such as computed tomography (CT), magnetic resonance imaging (MRI), and ultrasound, visualize diverse anatomical structures and pathological conditions. However, challenges arise in medical image segmentation due to increasing complexity, variability, noise, artifacts, and scarcity of …
-
Applications of U-net to diffuse optical tomography data: Image reconstruction and superresolution
… and its applications in medical imaging, a U-net based architecture is proposed to learn the mapping and estimate a higher resolution image. This work shows that the proposed deep learning model trained on simulated images from real-world fMRI images of the human brain can reconstruct higher …
-
Automated Segmentation and Analysis of High-Speed Video Phase-Detection Data for Boiling Heat Transfer Characterization Using U-Net Convolutional Neural Networks and Uncertainty Quantification
… analysis of HSV phase-detection images using U-Net Convolutional Neural Networks (CNNs) and uncertainty quantification techniques. The proposed methodology involves the development of specialized U-Net CNN models for segmenting HSV data of boiling phenomena in different fluids, including liquid …
-
Improving the Interpretation of Magnetic Tensor Data Using Deep Learning
The accurate interpretation of magnetic tensor data can be difficult to perform without a strong knowledge of local geology and experience in reading magnetic data. I examined ways in which machine learning techniques can be applied to magnetic tensor data to automatically locate possible …
-
Automated quantification of plant water transport network failure using deep learning
… models were considered for this task, namely U-Net, U-Net (ResNet34), and W-Net. The sample consisted of four unique leaves, each with its own sequence of images. Using these leaves, three experiments were conducted. They considered whether a leaf could generalise across samples from the same …
-
CFD and Deep Learning Based Natural Ventilation Analysis in Buildings
… building, using both a Vanilla U‑Net and a U-Net with an attention mechanism for the neural network architectures. The models obtain training data from CFD simulations performed on a generic building with multiple opening sizes and impacts from different wind directions. The …
-
Deep Learning Based Crop Row Detection
… based semantic segmentation method, namely U-net, although successful in many tasks related to precision agriculture, performs poorly for solving this task. The reasons include paucity of large scale labeled datasets in this domain, diversity in crops, and the diversity of appearance of the …
-
Fast Large-Scale Electromagnetic Simulation of Doubly Periodic Structures in Layered Media
<p>This work focuses on the electromagnetic simulation of doubly periodic structures embedded in layered media, which can be commonly found in extreme ultraviolet (EUV) lithography, metasurfaces, and frequency selective surfaces. Such problems can be solved by rigorous numerical methods like …
-
Neural Enhancement Strategies for Robust Speech Processing
… we experiment with the performance of the Wave-U-Net model, a solid and superior time-domain approach for speech enhancement. First, we attempt to improve the performance of back-end speech-based classification tasks in noisy conditions. In detail, we propose a pipeline that integrates the …
-
Detection and tracking of cells and focal adhesions in microscopy images
… we propose several convolutional neural network architectures to detect and segment cells. The proposed networks have the advantage of being able to learn with very limited and incomplete training data. Moreover, we present a U-Net based multi-task learning architecture for simultaneously …
-
Algorithm and Hardware Co-optimization for Image Segmentation in Wearable Ultrasound Devices: Continuous Bladder Monitoring
… segmentation and urine volume calculation. U-Net is the state-of-the artneural network (NN) for biomedical image segmentation [1]. We trained two binarized models with 4-bits and 6-bits skip connections. They achieved an accuracy within 3.8% and 2.6% of the floating-point U-Net without any …
-
SAMPLS: A prompt engineering approach using Segment-Anything-Model for PLant Science research
… image analysis called PlantSeg utilized U-Net for cell wall segmentation. U-Net is a neural network model that requires training with a large amount of manually labeled confocal images and lacks generalizability. In this research, we test a foundation model called the Segment Anything Model …
-
Seismic Data Processing and Interpretation via Deep Learning
… times of shot gathers are predicted using a U-Net deep learning architecture. Then, a workflow is developed to detect the seismic traces that were inaccurately predicted first arrival time. Next, an algorithm is proposed to pick the first arrival time for those seismic traces that have …
-
Measuring Machine Learning Model Uncertainty with Applications to Aerial Segmentation
… epistemic uncertainty and the Bayesian neural network. The latter replaces each trained weight with a random variable with which we approximate the true, unknown distribution of each weight with a two parameter (mean and variance) normal distribution. Bayes by Backprop trains these parameters …
-
Machine Learning for 3D Visualisation Using Generative Models
… is the introduction of generative adversarial networks (GANs), which had achieved great success in their ability to generate images comparable to real photos with minimum human intervention. These networks can generalise to a multitude of desired outputs, especially in image-to-image problems …
-
Machine Learning for 3D Visualisation Using Generative Models
… is the introduction of generative adversarial networks (GANs), which had achieved great success in their ability to generate images comparable to real photos with minimum human intervention. These networks can generalise to a multitude of desired outputs, especially in image-to-image problems …
-
Automated detection of ultrastructural features at neuronal synapses
… microscope images of synapses. We train a U-Net inspired model to perform pixel-wise segmentation of the vesicles against background pixels. We then use contour detection on the resulting segmentation maps to determine individual vesicle centers and effective diameters. To our knowledge, …
-
Single magnetic resonance image super-resolution using generative adversarial network
… images, we have adapted a Generative Adversarial Network (GAN) model where the generator has a DenseNet type structure and the discriminator is based on the U-Net model. We have used a combination of loss functions to ensure the generated images are consistent with ground truth. To train and …
Page 1 of 4