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 1035 for “"Convolutional Neural Network (CNN)"”.

  1. Convolutional Neural Network (CNN) for Digital Radio Frequency Memory (DRFM)

    … approach to design and analyze radar systems. Convolutional Neural Networks (CNN) have gained popularity in the last few years with the advent of faster high-performance computer systems which rely on GPUs for the best computational performance. A CNN operates from a mathematical perspective …

    jhu Repository record for Convolutional Neural Network (CNN) for Digital Radio Frequency Memory (DRFM) (opens in a new tab)

  2. Automated Pavement Condition Assessment using Unmanned Aerial Vehicles (UAVs) and Convolutional Neural Network (CNN)

    … image classification model is developed using Convolutional Neural Network (CNN), a deep learning approach. The results of the developed model indicate an accuracy of 96.7% in classifying the two categories of pavement distress. The developed model was further tested on a set of test images …

    ecu Repository record for Automated Pavement Condition Assessment using Unmanned Aerial Vehicles (UAVs) and Convolutional Neural Network (CNN) (opens in a new tab)

  3. A hybrid Convolutional Neural Network (CNN) and Support Vector Machine (SVM) for detecting Keratoconus in patients using genetic algorithm

    … through the training of deep learning networks for the early detection of eye diseases. This research presents a novel, integrated machine learning approach for diagnosing Keratoconus disease by combining feature extraction through Convolutional Neural Networks (CNN) with a Support …

    laurentian Repository record for A hybrid Convolutional Neural Network (CNN) and Support Vector Machine (SVM) for detecting Keratoconus in patients using genetic algorithm (opens in a new tab)

  4. Automated Diagnosis of Seven Major Skin Tumors in Canines Using a Convolutional Neural Network (CNN) on H&E-Stained Whole Slide Images (WSI)

    … wurde ein neuronales Faltungsnetzwerk (CNN) entwickelt und die Effizienz des Algorithmus an 140 neuen WSIs (20 pro Tumorart) getestet. Die Klassifizierungsgenauigkeit auf Objektträgerebene erreichte 95 % (133/140 WSIs), die Präzision auf Patch-Ebene lag bei 85 %. Dieselben 140 WSIs …

    fu-berlin Repository record for Automated Diagnosis of Seven Major Skin Tumors in Canines Using a Convolutional Neural Network (CNN) on H&E-Stained Whole Slide Images (WSI) (opens in a new tab)

  5. Heat Flux Model Validation Utilizing Convolutional Neural Networks and Sub-surface Thermocouples for NSTX-U

    <p>A proof of concept convolutional neural network (CNN) has been developed to assist in operating tokamaks outside of existing empirical scalings for the heat flux width, λ<sub>q</sub> [lambda-q]. NSTX-U has designed new plasma facing components (PFCs) to withstand increased halo current forces as …

    ut-knoxville Repository record for Heat Flux Model Validation Utilizing Convolutional Neural Networks and Sub-surface Thermocouples for NSTX-U (opens in a new tab)

  6. Strategic Resource Planning in Gold Mining: Optimizing Supply Chain Management with Neural Networks-Based Gold Price Forecasting

    … Unit (GRU) and Long Short-Term Memory (LSTM), Convolutional Neural Network (CNN), and Artificial Neural Network (ANN), to predict gold prices and analysed how these predictions can inform strategic decisions in the gold mining supply chain. Our approach includes evaluating the performance of …

    concordia Download PDF for Strategic Resource Planning in Gold Mining: Optimizing Supply Chain Management with Neural Networks-Based Gold Price Forecasting (opens in a new tab)

  7. Defect Detection of Photovoltaic Panels by Image Processing

    … these problems is its aim. The project used Convolutional neural network (CNN). We will use ResNet50. ResNet50 is a convolutional neural network (CNN). It is a specific architecture within the CNN family that is designed for tasks related to computer vision, such as image classification, …

    rit Repository record for Defect Detection of Photovoltaic Panels by Image Processing (opens in a new tab)

  8. WELD PENETRATION IDENTIFICATION BASED ON CONVOLUTIONAL NEURAL NETWORK

    … machine vision algorithms, we propose using convolutional neural network (CNN) to automatically extract key features and determine penetration status. Data-label pairs are needed to train a CNN. Therefore, an image acquiring system is designed to collect reflected laser pattern and the image …

    uky-thes Repository record for WELD PENETRATION IDENTIFICATION BASED ON CONVOLUTIONAL NEURAL NETWORK (opens in a new tab)

  9. Vehicle detection using morphological shared-weight neural network in the multiple instance learning framework

    … images based on the morphological shared-weight neural network (MSNN). The multiple instance learning (MIL) framework is used to avoid the labeling problem required in a supervised learning framework. Using the MIL, each image was given a single label. We rely on the MSNN's ability to detect …

    missouri Repository record for Vehicle detection using morphological shared-weight neural network in the multiple instance learning framework (opens in a new tab)

  10. Identification of Wi-Fi-enabled drones via software-defined radio (SDR) and artificial intelligence (AI)

    … analysis was first implemented, followed by a convolutional neural network (CNN) classifier trained on power spectral density (PSD) features. The system successfully identified drone signals in real time under test conditions, demonstrating that SDR combined with AI provides a cost-effective …

    chalmers Repository record for Identification of Wi-Fi-enabled drones via software-defined radio (SDR) and artificial intelligence (AI) (opens in a new tab)

  11. FEATURE SELECTION IN HIGH-DIMENSIONAL MODELS AND INTERPRETING DEEP NEURAL NETWORKS

    … of techniques, high-dimensional data and deep neural networks have become increasingly important in real-world situations. My research focuses on two parts: 1) propose the feature selection method, a generalization of correlation search, in two high dimensional regression models - instrumental …

    nus Repository record for FEATURE SELECTION IN HIGH-DIMENSIONAL MODELS AND INTERPRETING DEEP NEURAL NETWORKS (opens in a new tab) Download file for FEATURE SELECTION IN HIGH-DIMENSIONAL MODELS AND INTERPRETING DEEP NEURAL NETWORKS (opens in a new tab)

  12. Refining Bounding-Box Regression for Object Localization

    For the last several years, convolutional neural network (CNN) based object detection systems have used a regression technique to predict improved object bounding boxes based on an initial proposal using low-level image features extracted from the CNN. In spite of its prevalence, there is little …

    portland-state Repository record for Refining Bounding-Box Regression for Object Localization (opens in a new tab)

  13. Integrating Machine Learning and Interactive Prototyping for Adaptive Public Space Design

    … while maintaining human oversight. A convolutional neural network (CNN), trained on spatial configuration data, predicts optimal gathering areas based on environmental factors such as temperature, sunlight, and tree placement. Using Grange Park as a case study, the model achieved 86.7% …

    guelph Repository record for Integrating Machine Learning and Interactive Prototyping for Adaptive Public Space Design (opens in a new tab)

  14. Applying Neural Networks for Tire Pressure Monitoring Systems

    … monitoring system is developed using neural net- works to identify the tire pressure of a vehicle tire. A quarter-car model was developed with Matlab and Simulink to generate simulated accelerometer output data. Simulation data are used to train and evaluate a recurrent neural network …

    calpoly Repository record for Applying Neural Networks for Tire Pressure Monitoring Systems (opens in a new tab)

  15. Χρήση τεχνητής νοημοσύνης για τον έλεγχο της δυναμικής απόκρισης των κατασκευών

    … internal cracks and flexible supports, employing neural networks for structural health assessment. The equations of motion are derived via the calculus of variations, offering a robust framework, particularly for internal cracks. Dynamic parameters, including modal damping ratios and …

    greece Repository record for Χρήση τεχνητής νοημοσύνης για τον έλεγχο της δυναμικής απόκρισης των κατασκευών (opens in a new tab)

  16. Analysis of Image Classification Deep Learning Algorithm

    … 2. This analysis of image classification neural network problems with the use of Convolutional Neural Network (CNN) on the German and the Chinese traffic sign datasets is an engineering task. Ultimately, this work provides step-by-step guidance for creating an image classification model …

    ndsu Repository record for Analysis of Image Classification Deep Learning Algorithm (opens in a new tab)

  17. Lipreading with convolutional and recurrent neural network models

    … by a talking head, given only the video using neural network classification models. Two neural network architectures are developed and tested on the AVICAR dataset, including one convolutional neural network (CNN) model with fully connected classification layer, and one recurrent neural network …

    uiuc Repository record for Lipreading with convolutional and recurrent neural network models (opens in a new tab)

  18. Medical Image Modality Synthesis and Resolution Enhancement Based on Machine Learning Techniques

    … To overcome these challenges, we developed a convolutional neural network (CNN) which is a modified U-net. With this deep network for synthesis, we developed the first segmentation method that provides detailed grey matter anatomical labels on CT neuroimages using synthetic MRI. The second …

    jhu Repository record for Medical Image Modality Synthesis and Resolution Enhancement Based on Machine Learning Techniques (opens in a new tab)

  19. Learning space-time structures for action recognition and localization

    … Term Memory (LSTM), which is a type of Recurrent Neural Network (RNN). Two novel ranking losses are proposed to train the model to better capture the temporal structures of actions for accurate action recognition and temporal localization. This model achieves state-of-art performance on a large …

    bu Repository record for Learning space-time structures for action recognition and localization (opens in a new tab)

  20. Taikomoji programa skirta epilepsijos priepuolių paieškai dirbtinio intelekto metodais /

    … results. The application uses EfficientNetV2, a convolutional neural network (CNN) architecture that automatically flags possible epileptic seizures in the EEG. The model was trained using the Siena Scalp EEG database, which consists of EEG recordings from 14 patients. The application reduces the …

    vilnius Repository record for Taikomoji programa skirta epilepsijos priepuolių paieškai dirbtinio intelekto metodais / (opens in a new tab)

Page 1 of 52