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 114 for “"VGG16"”.
-
Beždžionių raupų sukeltų odos pakitimų atpažinimas naudojantis giliojo mokymosi modeliais /
… lesions caused by monkeypox were made using the VGG16 deep learning model. The VGG16 deep learning model showed promising results in recognising monkeypox virus from photographs, achieving an accuracy of 83%. When comparing the previous studies with the MSLD dataset, the best results were …
-
Neuroninių tinklų palyginimas rentgeno nuotraukų atpažinimui /
… neural network-based neural network models VGG16, DenseNet121 and ResNet50. Graphs depicting their results were formed according to which the calculation models of similarity metrics based on triplet neural networks were compared. The results of the different groups of images they achieved …
-
Advanced CNN architecture integrating machine learning algorithms for precise Alzheimer's disease classification
… deep learning models like ResNet50 and VGG16, as well as with more conventional machine learning algorithms like XG Boost, k-nearest neighbor (KNN), and Random Forest. The innovative CNN architecture is meticulously designed to maximize classification accuracy. The preprocessing steps …
-
Mašininio mokymosi algoritmų bei dimensijos mažinimo taikymas plaučių ligų diagnostikoje /
… on the classification accuracy. AlexNet and VGG16 convolutional neural networks were used to extract features from chest x-ray images and principal component analysis were applied to those extracted datasets. To classify data k-nearest neighbors algorithm, support vector machine and …
-
Improved Deep Learning Model Based on Integrated Convolutional Neural Networks and Transfer Learning for Shoeprint Image Classification
… comparing different pre-trained Inception V3, VGG16, and ResNet50 models. The results show that convolutional neural networks-transfer learning (CNN-TL) improved classification accuracy by approximately 3% compared to conventional convolutional neural networks (CNN). The study employed three …
-
An Ensemble Approach to Full Resolution Mammogram Classification
… for testing and a modified version of the VGG16 convolutional neural network to detect and classify suspected benign or malignant lesions within the breast mammogram. The modified VGG16 network accepts images of the mammogram without image size reduction or down-sampling so as to avoid …
-
Resiliency in Deep Convolutional Neural Networks
… architectures for image classification, AlexNet, VGG16, ResNet, GoogleNet, SqueezeNet and YOLO9000, when subjected to various degrees of failures. We introduce failures in a deep network by dropping a percentage of weights at each layer. We then assess the effects of these failures on …
-
DeepSkin: Mobile-based Skin Quality Assessment with Deep Learning
… for Dryness detection was achieved by VGG16 with an accuracy of 0.8606, while Frailty was best classified by VGG19 with an accuracy of 0.7929. Additionally, Hair was best detected by VGG16 with an accuracy of 0.8756 We believe our proposed and developed system creates a new research …
-
Satellite Image Analysis and Sidewalk Classification using Deep Learning Models
… tasks using pretrained CNN models including VGG16 and ResNet50. I extended these models by adding custom layers at the top of pretrained layers, employing various techniques to improve the classification accuracy. The dataset comprises 4,731 images of sidewalk based on occlusion levels, …
-
The Development of an Innovative Multimodal Biometrics System by Fusing Face and Infrared Information
… combining VIS and IR modalities. A new method, VGG16-PCA-SNNs, has been introduced, employing VGG16 for feature extraction, Principal Component Analysis (PCA) for dimensionality reduction, and Sequential Neural Networks (SNNs) for classification. Validated using the Sejong Face Database (SFD), …
-
Sensitivity of Feedforward Neural Networks to Harsh Computing Environments
… performance to be on par with random guessing. VGG16, ResNet50, and InceptionV3 were also tested for their robustness. ResNet50 and InceptionV3 were both more robust than VGG16. This could be due to their use of Batch Normalization or the fact that ResNet50 and InceptionV3 both use shortcut …
-
Rozpoznání druhu vozidla v obraze
… Na trénovanie sietí boli použité architektúry: VGG16, ResNet50, Xception, InceptionResNet-v2. Výsledkom práce je porovnanie architektúr. Všetky architektúry sa natrénovali a dosiahli výsledok nad 90%.
-
Parkinson's Disease Automated Hand Tremor Analysis from Spiral Images
… using extracted features from the ResNet-50 and VGG16 pre-trained deep network models. The VGG16 extracted features achieve 95.4% accuracy classifying images drawn by people with Parkinson’s Disease. The extracted features of both methods were also used to develop a tremor severity rating system …
-
Aplikace pro analýzu odolnosti algoritmů pro rozpoznávání podle obličeje vůči deepfake snímkům
… práce je vytvorených niekoľko konfigurácii sietí vgg16 a vgg19. Ku každej konfigurácií sú uvedené tabuľky s úspešnosťami jednotlivých modelov voči nami vytvorených deepfake snímkov. Práca obsahuje aj sekciu jednotlivých voľne dostupných algoritmov a prácu s nimi. Celá aplikácia je implementovaná v …
-
Dirbtinių neuroninių tinklų taikymas automobilio kėbulo švaros analizei /
… learning projects and comparison of models VGG16, InceptionV3, Xception. To achieve the goal of the thesis, 2 tasks are solved: automobile‘s body cleanliness classification to 3 classes and automobile‘s body type classification to 6 classes. Achieved results are 89% accuracy classifying body …
-
Identifikace typu obratlů z CT dat s využitím metod strojového učení
… a konvoluční neuronové sítě (CNN) AlexNet a VGG16. Dosažené výsledky jsou v závěru porovnány.
-
Segmentace chrupavčité tkáně ve 3D mikro CT snímcích myších embryí
… za enkóderovou část klasifikační neuronové sítě VGG16 s váhami byly předučenými na databázi označených obrazů ImageNet. Bylo dokázáno, že navržený postup segmentace dosahuje při porovnání s obrazy manuálně segmentovanými expertem v průměru Dice koeficientu 0,8731 ± 0,0326.
-
Mitotic cell detection in H&E stained meningioma histopathology slides
… by the domain knowledge, while the data-driven VGG16 models tend to be domain agnostic and attempt to learn additional feature bases that cannot be represented through any of the handcrafted features. Our work on detection of mitotic cells shows 100% recall , 9% precision and 0.17 F1 score. The …
-
Oil Spill Detection Using Deep Neural Networks
… artificial intelligence (AI) models, namely VGG16, YOLOv3 (you-only-look-once), and mask R-CNN (mask region-based convolutional neural network) are used in a transfer learning scheme to facilitate the process of detecting oil spills and surrounding objects such as vessels and oil rigs. …
-
Interpretable speaker diarisation for child language environment analysis
… natural language environment. Both the proposed VGG16 model trained on spectrograms and the SampleCNN model trained on raw waveforms are competitive compared to the existing state-of-the-art benchmark. The interpretations of these models are generated similarly to the gender perception problem, …
Page 1 of 6