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 32 for “"CNN Deep Learning"”.

  1. Deep learning application for population forecasting using aerial imagery and data compression on local hardware /

    … GeoTIFF aerial images, which are then used for deep learning model training for population forecasting on two local computers, depending on various metrics collected, energy consumed and carbon emitted. Three different data compression algorithms were chosen and used Deflate and Zstandard (ZSTD) …

    vilnius Repository record for Deep learning application for population forecasting using aerial imagery and data compression on local hardware / (opens in a new tab)

  2. Machine Learning Based Disease Gene Identification and MHC Immune Protein-peptide Binding Prediction

    Machine learning and deep learning methods have been increasingly applied to solve challenging and important bioinformatics problems such as protein structure prediction, disease gene identification, and drug discovery. However, the performances of existing machine learning based predictive models …

    south-carolina Repository record for Machine Learning Based Disease Gene Identification and MHC Immune Protein-peptide Binding Prediction (opens in a new tab)

  3. Examining cerebrovascular burden using neuroimaging techniques in ageing brains

    … convolutional neural network (3D-CNN) deep learning model. Findings showed that WM brain age is sensitive to most vascular risk factors and cognitive domains related to vascular dysfunction. In the fourth study, the impacts of high blood pressure on grey matter (GM) and WM, …

    unsw Repository record for Examining cerebrovascular burden using neuroimaging techniques in ageing brains (opens in a new tab)

  4. Investigation of Granular Media Properties and their Influence on Environmental Systems

    … soil science research. Recently, shallow machine learning models, such as partial least squared regression, have been demonstrated for predicting soil parameters, such as total carbon content, from mid-infrared (MIR) spectroscopy. However, these models have limitations, including data …

    houston Repository record for Investigation of Granular Media Properties and their Influence on Environmental Systems (opens in a new tab)

  5. Disaster and infrastructure scene understanding

    … enabled real-time hyperspectral imaging and learning of structural damage. Two specific situations are considered when dealing with mobile images. First, in engineering practice, even with the abundance of imaging capabilities, semantically labeled engineering damage datasets either are too …

    umkc Repository record for Disaster and infrastructure scene understanding (opens in a new tab)

  6. Pattern Recognition and Machine Learning as a Morphology Characterization Tool for Assessment of Placental Health

    … large city centres. The development of machine learning algorithms tailored to placenta histopathology applications may allow for automation and/or standardization of this important clinical exam – expanding its appropriate usage and impact on the health of mothers and infants. The primary …

    ottawa-retro Repository record for Pattern Recognition and Machine Learning as a Morphology Characterization Tool for Assessment of Placental Health (opens in a new tab)

  7. Spatial Stereo Sound Source Localization Optimization and CNN Based Source Feature Recognition

    … At this time, the system can be used to perform deep learning of convolutional neurons on the information of the target sound source, and finally strip off the undesired sound signal. The realization of this research will be able to help better machine learning algorithms in the audio field and …

    usf Repository record for Spatial Stereo Sound Source Localization Optimization and CNN Based Source Feature Recognition (opens in a new tab)

  8. Brain tumor segmentation with multimodal magnetic resonance imaging

    Made available in DSpace on 2021-09-17T02:34:43Z (GMT). No. of bitstreams: 2 WANG-THESIS-2021.pdf: 1892077 bytes, checksum: fe6bc0de2dfc1d1451e42c22f85e49e1 (MD5) LICENSE.txt: 4204 bytes, checksum: 4e619a5d0afe426aea11320e559f16a5 (MD5) Previous issue date: 2021-04-26

    uiuc Repository record for Brain tumor segmentation with multimodal magnetic resonance imaging (opens in a new tab)

  9. Texture-based Deep Neural Network for Histopathology Cancer Whole Slide Image (WSI) Classification

    … WSIs is time-consuming and tiresome. Recently, deep convolutional neural networks have succeeded in histopathological image analysis. In this paper, we propose a novel cancer texture-based deep neural network (CAT-Net) that learns scalable texture features from histopathological WSIs. The …

    kennesaw Repository record for Texture-based Deep Neural Network for Histopathology Cancer Whole Slide Image (WSI) Classification (opens in a new tab)

  10. Self-Supervised Stereo Depth Estimation: Depth estimation in multiple environments through an adaptive CNN and IR light

    … during recent years. The reason is because deep learning reduces the computational effort considerably compared to previous methods. However, the existing deep learning methods do not evaluate the depth measurements but rather the disparity estimation accuracy on available benchmark …

    chalmers Repository record for Self-Supervised Stereo Depth Estimation: Depth estimation in multiple environments through an adaptive CNN and IR light (opens in a new tab)

  11. Enhancing State-of-the-Art Motor Imagery Classification with Reinforcement Learning

    … EEGNet, a compact Convolutional Neural Network (CNN), has long been considered the state-of-the-art (SOTA) for MI classification, demonstrating strong performance even with limited data. However, recent studies advocate for integrating Deep Reinforcement Learning (RL) to further enhance …

    usf Repository record for Enhancing State-of-the-Art Motor Imagery Classification with Reinforcement Learning (opens in a new tab)

  12. Desarrollo y validación conceptual de modelos de reconocimiento de las especies usando deep learning

    El reconocimiento de imágenes es una tarea importante en el campo de la visión por computadora y por muchos investigadores en los últimos años. Con la aparición del aprendizaje profundo, se ha logrado un gran avance en el desarrollo de modelos de reconocimiento de imágenes. El desarrollo y la …

    upc-peru Repository record for Desarrollo y validación conceptual de modelos de reconocimiento de las especies usando deep learning (opens in a new tab)

  13. 3D Deep Learning for Pulmonary Nodule Malignancy Classification in CT Imaging

    … variability. This thesis proposes a reproducible deep learning framework for pulmonary nodule malignancy classification using volumetric CT data. Using the LIDC-IDRI dataset, a standardized preprocessing pipeline is developed, including isotropic resampling, intensity normalization, and 3D patch …

    rit Repository record for 3D Deep Learning for Pulmonary Nodule Malignancy Classification in CT Imaging (opens in a new tab)

  14. An Analysis of Short-Term Load Forecasting on Residential Buildings Using Deep Learning Models

    … since the residential load is highly stochastic. Deep learning models have showed tremendous promise in the fields of time-series and sequential data and have been successfully used in the field of short-term load forecasting at the building level. Although, other studies have looked at using deep …

    vt Repository record for An Analysis of Short-Term Load Forecasting on Residential Buildings Using Deep Learning Models (opens in a new tab)

  15. Accelerated Discovery of Cell Migration Regulators Using Label-Free Deep Learning-Based Automated Tracking

    … We developed and validated a machine-vision and deep-learning analysis method, DeepBIT, to automatically detect and track the migration of individual cells from time-lapsed videos without cell labeling and user bias. We demonstrate that our assay can examine cancer cell motility behavior in many …

    jhu Repository record for Accelerated Discovery of Cell Migration Regulators Using Label-Free Deep Learning-Based Automated Tracking (opens in a new tab)

  16. Self-Supervised Video Representation Learning by Recurrent Networks and Frame Order Prediction

    The success of deep learning models in challenging tasks of computer vision and natural language processing depend on good vector representations of data. For example, learning efficient and salient video representations is one of the fundamental steps for many tasks like action recognition and …

    rit Repository record for Self-Supervised Video Representation Learning by Recurrent Networks and Frame Order Prediction (opens in a new tab)

  17. Deep Learning with Diversity Imaging from AdaptiSPECT System for Estimation Tasks

    This dissertation introduces a novel machine-learning method in deep learning for medical imaging for a signal estimation task of an adaptive Single-Photon Emission Computed Tomography (SPECT) system. In SPECT, estimation tasks aim to measure or quantify features of the object that has been imaged. …

    arizona-thes Repository record for Deep Learning with Diversity Imaging from AdaptiSPECT System for Estimation Tasks (opens in a new tab)

  18. Virtual Multimodal Object Detection and Classification with Deep CNNs

    … when used in tandem as inputs to supervised learning (machine learning) tasks. We begin with a simple score fusion scheme, based on the OpenBR face recognition suite, that evaluates similarity (match-scores) between subject faces in different images. Combining the face matching estimations of …

    houston Repository record for Virtual Multimodal Object Detection and Classification with Deep CNNs (opens in a new tab)

  19. Estimating top-of-atmosphere thermal infrared radiance using MERRA-2 atmospheric data

    … namely physics-based approach and a supervised learning approach, using Terra/MODIS band 31 thermal infrared data as reference. The first physics-based model uses forward modeling to predict TOA thermal radiance. The second model infers the presence of clouds from the MERRA-2 atmospheric data, …

    rit Repository record for Estimating top-of-atmosphere thermal infrared radiance using MERRA-2 atmospheric data (opens in a new tab)

Page 1 of 2