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 100 for “"Resnet 50"”.
-
A HYBRID RESNET-50 AND GRAPH RELATIONAL LEARNING APPROACH FOR PROSTHETIC HAND GRASP CLASSIFICATION
… my research proposes a model that uses ResNet-50 as the backbone to extract image features, followed by a Graph Neural Network (GNN) architecture to significantly enhance performance in predicting visual inputs. The proposed ResNet50-Graph model is evaluated on the HandCam dataset for …
-
A Study on Deepsea Fish Detection Using Convolutional Neural Networks
… using the DeepFish dataset. A pretrained ResNet-50 model attained a validation accuracy of 82.8% for multi-class habitat classification, demonstrating robust performance in most habitats based on 6,517 images, although exhibiting lower recall for visually similar or underrepresented …
-
A Cross-Layer Framework for Design Space Exploration and Variation Analysis of Compute-in-Memory DNN Accelerators using Non-Volatile Ferroelectric Capacitors
… accuracy of SwinV2-T vision transformer and ResNet-50 on the ImageNet dataset. Our framework further assesses the system's power, performance, and area (PPA) by considering cell design, circuit structure, and model selection. We explore the design space using an early stopping algorithm to …
-
Pre-trained CNN and bi-directional LSTM for no-reference video quality assessment
… we assess three pre-trained CNN, MobileNet, ResNet-50 and Inception-ResNet-V2, as feature extractors and select ResNet-50 since it showed the best performance. In this thesis, we assess the stability of our VQA method and conduct an ablation study to highlight the importance of the …
-
ONBOARD SHIP CLASSIFICATION FOR MARITIME SURVEILLANCE: BENCHMARKING CONVOLUTIONAL NEURAL NETWORK-BASED TRANSFER LEARNING ON THE NVIDIA JETSON ORIN NANO 8GB
… convolutional neural network architectures, ResNet-50 and EfficientNet-B0, are fine-tuned on the ShipRSImageNet dataset across five ship classes: warship, cargo, tanker, fishing, and other. Both models are compared under baseline and improved training configurations, across 13 image …
-
Pigs' BCS Estimation using Computer Vision and Deep Learning Approaches
… hybrid ensemble deep learning pipeline combining ResNet-50 and DenseNet-121 architectures with integrated depth information from Intel RealSense D435 cameras. The system was trained and validated on a dataset of 268 pigs across six pens collected from Virginia State University farms, with video …
-
3D Vision and Machine Learning for Precision Diagnostics in Hydroponic Crop Production
… study builds and compares four neural networks—ResNet-50, Vision Transformer (ViT), TomatoPCD, and PointNet—to predict key traits of tomato plants: height, fresh weight, leaf area, and the number of red fruits. By utilizing RGB-D (Red-Green-Blue-Depth) images and point cloud inputs, the research …
-
Deep Learning for Affect Recognition: A Comparative Study of Physiological Sensor-Based and Facial Image-Based Approaches
… recognition on AffectNet+ using pre-trained ResNet-50, EfficientNet-B3, and ConvNeXt-Tiny architectures across Easy, Challenging, and Difficult subsets representing different levels of expression ambiguity. Experimental results show that the proposed Multi-Branch Attention CNN-BiLSTM …
-
Lietuvių kalbos teksto atpažinimas /
… convolutional recurrent neural network and ResNet-50. Convolutional recurrent neural network model is adapted to recognize Lithuanian words with the help of a dictionary, and the ResNet-50 model is compared with the fine-tuned version. A photo dataset of Lithuanian alphabet was created to …
-
Rare disease classification from facial photographs using deep learning
… convolutional neural network models (AlexNet, ResNet-18, ResNet-34, ResNet-50, VGG-16, VGG-19, DenseNet121, MobileNetV2) are analyzed over two different transfer learning approaches. All the models, except VGG-16, achieved superior results when trained with fine-tuned transfer learning approach …
-
Design and Integration of Machine Learning-Based Vision System for Automated Power Line Inspection Using a Mobile Damping Robot
… Convolutional Neural Network and a ResNet-50 transfer learning model, were trained for multi-class classification. Experimental results validate the effectiveness of the ResNet-50 model, demonstrating the potential of vision-based inspection for enabling proactive, data-driven, and …
-
Doenças hereditárias da retina: aumento de dados, utilizando métodos generativos, para melhorar a deteção
… modelos do estado da arte (VGG19, Inception-V3 e ResNet-50) utilizando validação cruzada (5-fold). O modelo ResNet-50 apresentou o melhor desempenho, com acurácia de 56% e F1-score de 0,54, revelando boa capacidade discriminatória em classes com maior representatividade. Numa segunda fase, foi …
-
Automated meal analysis and realtime dietary recommender system - comparative analysis of machine learning models for benchmarking image recognition performance
… models, CLIP ViT-B/32, a vision transformer, and ResNet-50, a convolutional neural network, on a publicly available repository called Food-101, which is a curated, diverse dataset. The study evaluates the accuracy of the models in meal identification through food images. Both models achieved over …
-
Avaliação de desempenho preditivo de redes neurais em aprendizagem federada para classificação de estágios da doença de Alzheimer
… A prevalência global deve triplicar até 2050. Este estudo investiga a aplicação de Aprendizado Federado (FL) combinado com Aprendizado Dividido (SL) e Redes Neurais Convolucionais (CNNs) para classificar indivíduos em três estágios: AD, Comprometimento Cognitivo Leve (MCI) e Cognitivamente …
-
DEEP LEARNING FRAMEWORK FOR CHARACTER RECOGNITION IN LOW QUALITY LICENSE PLATE IMAGES
… Machine Learning models. The Faster R-CNN ResNet 50 network was found to have the best performance for character recognition on synthetically generated license plate images. On an ideal dataset, with no image degradation applied, the lower threshold of image size, on which the Faster R-CNN …
-
An Investigation of Scale Factor in Deep Networks for Scene Recognition
… parameters and 0.24% additional GFLOPs using ResNet-50 as the backbone. We further bring the scale factor implicitly into network backbone design by proposing a Deep-Narrow Network and Dilated Pooling module. The Deep-narrow architecture increased the depth of the network as well as decreased …
-
Visual Representation of Electronic Health Record’s Tabular Data for Predicting Sudden Cardiac Arrest
… deep convolutional neural networks (VGG-19, ResNet-50, DenseNet-121, and Inception-V3) to demonstrate its effectiveness compared to existing diagnosis techniques. The EHR data associated with the disease are collected from a publicly available, extensive MIMIC-III database, which consists of …
-
Identifikace zvěře pomocí umělé inteligence
… dosahuje velmi vysoké úspěšnosti detekce (mAP50 = 0,995). Při srovnání tří embeddingových architektur (ResNet-50, EfficientNet_B1, MobileNet_V3_Large) dosáhl nejlepší výsledků model MobileNet_V3_Large. Při optimálním rozhodovacím prahu pro daný dataset dosáhl celkové přesnosti 95,8 %, zatímco …
-
Optimalizace neuronové sítě pro detekci objektů s využitím NPU
… m modelu YOLOv8 a 3,5 mAP v případě modelu DETR-ResNet-50. Použitým datasetem byl COCO val2017. Práce zahrnuje také optimalizovanou implementaci algoritmu NMS, který je na procesorech AMD Ryzen 7900X a Rockchip RK3588 o 518 %, respektive o 656 % rychlejší, než konkurence.
-
Designing a Unity Plugin to Predict Expected Affect in Games Using Biophilia
… and found that the neural net that leveraged ResNet-50 was most effective. I then incorporated that model into a Unity plug-in so that designers can use it to predict affect of players in real time.
Page 1 of 5