VGG16 Architecture Research Articles

Indonesia rupiah currency detection for visually impaired people using transfer learning VGG-19

People with visual impairments often face difficulties in determining the authenticity of paper money, which is a crucial skill to avoid fraud. The limitations of traditional methods, like blind codes for visually impaired people, require a more advanced and efficient solution. Previous methods of currency detection using Convolutional Neural Network (CNN) techniques, including the VGG-19 architecture, have often encountered challenges, particularly the long training times required. Therefore, we propose using transfer learning techniques and modifying the top layers of the VGG-19 model, known as fully connected layers, within a mobile application with audio feedback built using Android Studio. These modifications involve substituting the three fully connected layers with dense and flattened layers. We also implemented hyperparameter tuning, including adjusting the batch sizes and setting the number of epochs. The datasets used Indonesian Rupiah paper currency from the 2022 emission year, specifically Rp 50,000 and Rp 100,000 denominations. The best transfer learning VGG-19 model achieved a batch size of 32 and an epoch of 50, resulting in a high accuracy of 88%. Response speed testing with performance profiling on Android Studio showed an overall average response time of 458 ms. The main advantage of using transfer learning with the VGG-19 model is that it significantly reduces training time while still achieving high accuracy, differentiating this work from previous studies that relied on training from scratch, which is more time-consuming and resource-intensive. Therefore, this mobile app can be categorized as having a fast response time.

Boosting Time Efficiency in Helmeted Face Recognition with Transfer Learning and k-NN

This research aims to optimize the retraining process of face recognition systems for motor vehicle parking areas using Transfer Learning and k-nearest Neighbors (k-NN). The system enhances efficiency by retraining only on new classes, identified by checking the encoding file, allowing it to skip pre-existing classes, thus significantly improving retraining speed. Face data from 100 individuals (2725 images) was collected and augmented, with the VGG16 architecture used to generate face embeddings through Transfer Learning. Achieving 95.62% accuracy, with a precision, recall, and F1-score of 0.96 at k=1, the system demonstrates high accuracy and speed in identifying registered faces while effectively rejecting unknown ones. These optimizations greatly increase the feasibility of face recognition in parking security systems, making them more responsive to new data. Future research should focus on increasing dataset diversity and exploring more complex conditions, such as varied lighting, to enhance system performance and robustness further.

Effectiveness of Hybrid Quantum-Classical and Quanvolutional Neural Networks for image classification

The article focuses on studying the effectiveness of two different Hybrid Neural Networks (HNNs) architectures for solving real-world image classification problems. The first approach investigated in the research is a hybridization technique that allows creation of HNN based on a classical neural network by replacing a number of hidden layers of the neural network with a variational quantum circuit, which allows to reduce the complexity of the classical part of the neural network and move part of computations to a quantum device. The second approach is a hybridization technique based on utilizing quanvolutional operations for image processing as the first quantum convolutional layer of the hybrid neural network, thus building a Quanvolutional Neural Network (QNN). QNN leverages quantum phenomena to facilitate feature extraction, enabling the model to achieve higher accuracy metrics than its classical counterpart. The effectiveness of both architectures was tested on several image classification problems. The first one is a classical image classification problem of CIFAR10 images classification, widely used as a benchmark for various imagery-related tasks. Another problem used for the effectiveness study is the problem of geospatial data analysis. The second problem represents a real-world use case where quantum computing utilization can be very fruitful in the future. For studying the effectiveness, several models were assembled: HNN with a quantum device that replaces one of the hidden layers of the neural network, QNN based on quanvolutional operation and utilizes VGG-16 architecture as a classical part of the model, and also an unmodified VGG-16 was used as a reference model. Experiments were conducted to measure the models' key efficiency metrics: maximal accuracy, complexity of a quantum part of the model and complexity of a classical part of the model. The results of the research indicated the feasibility of both approaches for solving both proposed image classification problems. Results were analyzed to outline the advantages and disadvantages of every approach in terms of selected key metrics. Experiments showed that QNN architectures proved to be a feasible and effective solution for critical practical tasks requiring higher levels of model prediction accuracy and, simultaneously, can tolerate higher processing time and significantly increased costs due to a high number of quantum operations required. Also, the results of the experiments indicated that HNN architectures proved to be a feasible solution for time-critical practical tasks that require higher processing speed and can tolerate slightly decreased accuracy of model predictions.

Comparison of Deep Learning and Yolov8 Models for Fox Detection Around the Henhouse

Human beings, who have been engaged in agriculture and animal husbandry for centuries, have to constantly track, take care and maintain their own agricultural lands and animals. This requires constant labor and time. The aim and originality of this study is to identify foxes that kidnap animals such as chickens, geese, ducks and turkeys that live in the coops of individuals engaged in poultry farming. In this way, even if the farmer is not in the henhouse at that moment, material and moral losses to the farmers will be prevented. To achieve this purpose, many images were collected to form dataset. The collected dataset was classified according to whether the fox was in the henhouse or not. Then, the outputs of DenseNet, MobileNet, ResNet50, VGG16, VGG19, Xception and Yolov8 architectures were fine tuned to be performed in transfer learning to detect existence of a fox in the henhouse. Then, the models were trained, and their performances were compared in terms of performance metrics such as loss, accuracy, precision and F1. In the results, Yolov8 architectures generally have demonstrated the best performances.

Leveraging deep transfer learning and explainable AI for accurate COVID-19 diagnosis: Insights from a multi-national chest CT scan study

The COVID-19 pandemic has emerged as a global health crisis, impacting millions worldwide. Although chest computed tomography (CT) scan images are pivotal in diagnosing COVID-19, their manual interpretation by radiologists is time-consuming and potentially subjective. Automated computer-aided diagnostic (CAD) frameworks offer efficient and objective solutions. However, machine or deep learning methods often face challenges in their reproducibility due to underlying biases and methodological flaws. To address these issues, we propose XCT-COVID, an explainable, transferable, and reproducible CAD framework based on deep transfer learning to predict COVID-19 infection from CT scan images accurately. This is the first study to develop three distinct models within a unified framework by leveraging a previously unexplored large dataset and two widely used smaller datasets. We employed five known convolutional neural network architectures, both with and without pretrained weights, on the larger dataset. We optimized hyperparameters through extensive grid search and 5-fold cross-validation (CV), significantly enhancing the model performance. Experimental results from the larger dataset showed that the VGG16 architecture (XCT-COVID-L) with pretrained weights consistently outperformed other architectures, achieving the best performance, on both 5-fold CV and independent test. When evaluated with the external datasets, XCT-COVID-L performed well with data with similar distributions, demonstrating its transferability. However, its performance significantly decreased on smaller datasets with lower-quality images. To address this, we developed other models, XCT-COVID-S1 and XCT-COVID-S2, specifically for the smaller datasets, outperforming existing methods. Moreover, eXplainable Artificial Intelligence (XAI) analyses were employed to interpret the models’ functionalities. For prediction and reproducibility purposes, the implementation of XCT-COVID is publicly accessible at https://github.com/cbbl-skku-org/XCT-COVID/.

Exploring Fish Species Exploring Fish Species Classification using Deep Learning

Fishes are intriguing creatures that live in a wide range of aquatic settings, including freshwater rivers and lakes, oceans, and deep-sea trenches. Freshwater fish are considered a poor man's protein supplement since they are readily available in lakes, rivers, natural ponds, rice fields, beels, and fisheries. Many freshwater fish species resemble one another, making it difficult to classify them based on their exterior appearance. Manual fish species identification is always error-prone since it requires knowledge. Recently, computer vision and deep learning have played a key role in underwater species classification and detection studies. This research focuses on fish species categorization with Convolutional Neural Networks (CNNs) and two popular architectures, ResNet50 and VGG16. The goal of this research is to create an automated system that can correctly recognize and classify different fish species based on dataset. The two architecture ResNet50 and VGG16 are fine-tuned and CNN for training and validation of the collected fish data. The suggested method entails preprocessing the image data, training the CNN models with ResNet50 and VGG16 architectures, and assessing their performance using measures such as accuracy, precision, recall, and F1 score. This study reports the best overall classification accuracy, precision, and recall rate, which is almost 95%. Comprehensive empirical investigation has proven that when the weight and bias learning rate increases, so does the classifier's validation loss.

DeepCervix: enhancing cervical cancer detection through transfer learning with VGG-16 architecture

Cervical cancer remains a significant global health concern, emphasizing the urgent need for improved detection methods to ensure timely treatment. This research introduces a sophisticated methodology leveraging recent advances in medical imaging and deep learning algorithms to enhance the accuracy and efficiency of cervical cancer detection. The proposed approach comprises meticulous data preprocessing to ensure the integrity of input images, followed by the training of deep learning models including ResNet-50, AlexNet, and VGG-16, renowned for their performance in computer vision tasks. Evaluation metrics such as accuracy, precision, recall, and F1-score demonstrate the efficacy of the methodology, with an outstanding accuracy rate of 98% achieved. The model’s proficiency in accurately distinguishing healthy cervical tissue from cancerous tissue is underscored by precision, recall, and F1-score values. The primary strength of this deep learning-based approach lies in its potential for early detection, promising significant impact on cervical cancer diagnosis and treatment outcomes. This methodology contributes to advancements in medical imaging techniques, facilitating improved outcomes in cervical cancer detection and treatment.

Guava fruit classification system design with convolutional neural networks

For the rapid and precise advancement of agriculture, artificial intelligence applications are of significant importance. Processes such as disease detection in the agricultural field, identification of soil types, and classification of plants and fruits are currently performed manually. Artificial intelligence enables the automation of these processes, leading to cost reduction and the minimization of human errors. In this study, a system for classifying the species of Guava fruit has been proposed. The proposed system is designed using four pre-trained convolutional neural networks. The convolutional neural networks used are GoogLeNet, Vgg19, ResNet50, and DenseNet201 architectures. The Guava fruit dataset was classified by both k-fold-stratified and an 80:20 split. All experimental studies were evaluated using six different performance metrics. The best result was achieved with the DenseNet201 architecture in the proposed method. The performance results for the DenseNet201 architecture in terms of accuracy, sensitivity, specificity, F1-score, MCC, and kappa are as follows: accuracy - 0.9658, sensitivity - 0.9677, specificity - 0.9954, F1-score - 0.9681, MCC - 0.9640, and Kappa - 0.8268.

Enhanced Fault Detection in Photovoltaic Panels Using CNN-Based Classification with PyQt5 Implementation.

Solar photovoltaic systems have increasingly become essential for harvesting renewable energy. However, as these systems grow in prevalence, the issue of the end of life of modules is also increasing. Regular maintenance and inspection are vital to extend the lifespan of these systems, minimize energy losses, and protect the environment. This paper presents an innovative explainable AI model for detecting anomalies in solar photovoltaic panels using an enhanced convolutional neural network (CNN) and the VGG16 architecture. The model effectively identifies physical and electrical changes, such as dust and bird droppings, and is implemented using the PyQt5 Python tool to create a user-friendly interface that facilitates decision-making for users. Key processes included dataset balancing through oversampling and data augmentation to expand the dataset. The model achieved impressive performance metrics: 91.46% accuracy, 98.29% specificity, and an F1 score of 91.67%. Overall, it enhances power generation efficiency and prolongs the lifespan of photovoltaic systems, while minimizing environmental risks.

Multimodal robot-assisted English writing guidance and error correction with reinforcement learning.

With the development of globalization and the increasing importance of English in international communication, effectively improving English writing skills has become a key focus in language learning. Traditional methods for English writing guidance and error correction have predominantly relied on rule-based approaches or statistical models, such as conventional language models and basic machine learning algorithms. While these methods can aid learners in improving their writing quality to some extent, they often suffer from limitations such as inflexibility, insufficient contextual understanding, and an inability to handle multimodal information. These shortcomings restrict their effectiveness in more complex linguistic environments. To address these challenges, this study introduces ETG-ALtrans, a multimodal robot-assisted English writing guidance and error correction technology based on an improved ALBEF model and VGG19 architecture, enhanced by reinforcement learning. The approach leverages VGG19 to extract visual features and integrates them with the ALBEF model, achieving precise alignment and fusion of images and text. This enhances the model's ability to comprehend context. Furthermore, by incorporating reinforcement learning, the model can adaptively refine its correction strategies, thereby optimizing the effectiveness of writing guidance. Experimental results demonstrate that the proposed ETG-ALtrans method significantly improves the accuracy of English writing error correction and the intelligence level of writing guidance in multimodal data scenarios. Compared to traditional methods, this approach not only enhances the precision of writing suggestions but also better caters to the personalized needs of learners, thereby effectively improving their writing skills. This research is of significant importance in the field of language learning technology and offers new perspectives and methodologies for the development of future English writing assistance tools.

Systematic Review of Deep Learning Techniques in Skin Cancer Detection

Skin cancer is a serious health condition, as it can locally evolve into disfiguring states or metastasize to different tissues. Early detection of this disease is critical because it increases the effectiveness of treatment, which contributes to improved patient prognosis and reduced healthcare costs. Visual assessment and histopathological examination are the gold standards for diagnosing these types of lesions. Nevertheless, these processes are strongly dependent on dermatologists’ experience, with excision advised only when cancer is suspected by a physician. Multiple approaches have surfed over the last few years, particularly those based on deep learning (DL) strategies, with the goal of assisting medical professionals in the diagnosis process and ultimately diminishing diagnostic uncertainty. This systematic review focused on the analysis of relevant studies based on DL applications for skin cancer diagnosis. The qualitative assessment included 164 records relevant to the topic. The AlexNet, ResNet-50, VGG-16, and GoogLeNet architectures are considered the top choices for obtaining the best classification results, and multiclassification approaches are the current trend. Public databases are considered key elements in this area and should be maintained and improved to facilitate scientific research.

Enhanced Multi-Class Skin Lesion Classification of Dermoscopic Images Using an Ensemble of Deep Learning Models

This study presents an advanced approach to multi-class skin lesion classification by leveraging an ensemble model comprising the Inception-V3, ResNet-50, and VGG16 architectures. The classification task focuses on categorizing skin lesions into distinct classes, including Melanoma, basal cell carcinoma (BCC), and squamous cell carcinoma (SCC), using the ISIC dataset, a comprehensive collection of dermoscopic images. In order to properly balance the dataset, the oversampling strategy is utilized, as some lesion types are underrepresented due to inherent imbalances in the dataset. By ensuring that the model is trained on a more representative dataset, this balancing improves the algorithm's capacity to categorize all lesion types properly and impartially. By combining the complementary features of ResNet-50, Inception-V3, and VGG16, the ensemble technique improves the overall classification performance. ResNet-50 is chosen for its deep feature extraction capabilities, which help capture fine details in lesion patterns. Inception-V3 is selected for its multi-scale processing, allowing it to effectively analyze lesions at varying resolutions and sizes. VGG16 is included due to its simple yet highly effective architecture for image classification tasks. The ensemble model with data augmentation significantly outperforms individual models in skin lesion classification for both the original and balanced ISIC datasets regarding accuracy, precision, recall, and F1-score. This method offers a robust solution for skin lesion classification, contributing to more accurate and reliable diagnostic tools in dermatology.

Milling Machine Fault Diagnosis Using Acoustic Emission and Hybrid Deep Learning with Feature Optimization

This paper presents a fault diagnosis technique for milling machines based on acoustic emission (AE) signals and a hybrid deep learning model optimized with a genetic algorithm. Mechanical failures in milling machines, particularly in critical components like cutting tools, gears, and bearings, account for a significant portion of operational breakdowns, leading to unplanned downtime and financial losses. To address this issue, the proposed method first acquires AE signals from the milling machine. AE signals, capturing the dynamic responses of machine components, are transformed into continuous wavelet transform (CWT) scalograms for further analysis. Gaussian filtering is applied to enhance the clarity of these scalograms, effectively reducing noise while maintaining essential features. A convolutional neural network (CNN) based on the VGG16 architecture is utilized for spatial feature extraction, followed by a bidirectional long short-term memory (BiLSTM) network to capture the temporal dependencies of the scalograms. The genetic algorithm (GA) is used to optimize feature selection and ensure the selection of the most relevant features to further improve the model’s performance. The optimized features are finally fed into a fully connected (FC) layer of the proposed hybrid model for fault classification. The proposed method achieves an accuracy of 99.6%, significantly outperforming traditional approaches. This method offers a highly accurate and efficient solution for fault detection in milling machines, allowing for more reliable predictive maintenance and operational efficiency in industrial settings.

Application of convolutional neural networks in image classification and applications of improved convolutional neural networks

Abstract. This paper reviews the application and improvement of convolutional neural networks (CNNs) in image classification. Firstly, a shallow CNN for interstitial lung disease image classification is presented. This model suppresses overfitting through a unique network architecture and optimisation algorithm. Next, the improved VGG16 architecture and MIDNet18 model are discussed and their superior performance in brain tumour image classification is demonstrated. Subsequently, a CNN-CapsNet model for cervical cancer image classification and its improvement are presented and the customised model is compared with the conventional VGG-16 CNN architecture in the paper. Next, the application of sparse convolutional kernels and hybrid sparse convolutional kernels (HDCs) in solving the problem of computational resource consumption is presented. Subsequently, methods for solving the problem of limited training data through transfer learning and network data augmentation techniques are discussed, as well as GAN-generated datasets for solving the overfitting problem. Finally, the effect of degraded images on the classification effectiveness of CNNs is explored. The results show that the improved CNN architecture and algorithms have significant effects in solving the problems of overfitting and computational resource consumption, and can significantly improve the accuracy and efficiency of image classification. And degraded images do adversely affect the accuracy of CNN for image classification.

Evaluation of burning detection using modified VGG19 for LULC classification changes

Abstract. This study aims to evaluate the effectiveness of a modified architecture of convolutional neural network (CNN) VGG19 for detecting fires and changes in land use and land cover classification (LULC). Remote sensing data from the Landsat 8 Operational Land Imagery (OLI) satellite was used to collect images from two distinct regions, one of which was used to obtain a dataset containing 1000 labeled images, and the other region was used to perform inference and verify the generalization of the model in an area with a high annual occurrence of fires. Analyses were conducted using a time series of normalized difference vegetation index (NDVI) and complementary cumulative distribution function (CCDF), to determine the potential for analysis in that area and define the periods of burning, pre-burning and post-burning. The VGG19 architecture was modified to maintain the input sizes of the images, resulting in a significant increase of 20.90 percentage points in the F1 score compared to the original architecture, as well as a 68.76% reduction in convergence time. In addition, the Gradient-weighted Class Activation Mapping (Grad-CAM) technique was used to improve the interpretability of the model at the moment of inference. The proposed methodology offers an approach for detecting burns by altering the LULC classification, and the modified VGG19 showed superior results.

High-Precision Detection of Lung Adenocarcinoma Using Augmented VGG16 and Transfer Learning

Objectives: The research aims to enhance the effectiveness of the deep learning model for detecting lung adenocarcinoma using VGG16 CNN with transfer learning on medical images. The proposed model addresses the overfitting issues of existing models, thereby improving lung cancer detection accuracy. Methods: The lung CT scan images are analyzed for detection and classification using VGG16, leveraging transfer learning techniques. The dataset includes labeled lung images from LUNA 16, Kaggle, and other datasets, which are augmented to introduce variability and reduce overfitting. The images are resized format to 224 × 224 pixels. During the validation and training phases, the model's performance is evaluated based on accuracy, and precision. Findings: The adjusted VGG16 model attains a training accuracy of 99.42%, a validation accuracy of 99.13%, and a validation precision of 95.45%, indicating strong generalization capabilities, outperforming other existing models. Novelty: This research presents a new method for detecting lung cancer by combining advanced preprocessing and data augmentation techniques with the VGG16 architecture using transfer learning. This combination greatly enhances the model's ability to detect cancer accurately, setting a new standard in the field. Keywords: Lung cancer, VGG16, Transfer learning, Data augmentation, medical imaging, CT (Computer Tomography)

사전학습 모델 기반 발화 동영상 멀티 모달 감정 인식

Recently, as the demand for non-face-to-face counseling has rapidly increased, the need for emotion recognition technology that combines various aspects such as text, voice, and facial expressions is being emphasized. In this paper, we address issues such as the dominance of non-Korean data and the imbalance of emotion labels in existing datasets like FER-2013, CK+, and AFEW by using Korean video data. We propose methods to enhance multimodal emotion recognition performance in videos by integrating the strengths of image modality with text modality. A pre-trained model is used to overcome the limitations caused by small training data. A GPT-4-based LLM model is applied to text, and a pre-trained model based on VGG-19 architecture is fine-tuned to facial expression images. The method of extracting representative emotions by combining the emotional results of each aspect extracted using a pre-trained model is as follows. Emotion information extracted from text was combined with facial expression changes in a video. If there was a sentiment mismatch between the text and the image, we applied a threshold that prioritized the text-based sentiment if it was deemed trustworthy. Additionally, as a result of adjusting representative emotions using emotion distribution information for each frame, performance was improved by 19% based on F1-Score compared to the existing method that used average emotion values for each frame.

Maize disease classification using transfer learning and convolutional neural network with weighted loss

Maize stands out as a versatile commodity, finding applications in food and animal feed industries. Notably, half of the total demand for maize is met through its utilization as animal feed. Despite its importance, maize cultivation often grapples with crop failures resulting from delayed disease management or insufficient knowledge about these diseases, impeding timely intervention. The advent of technological advancements, particularly in Machine Learning, presents solutions to address these challenges. This research focuses on employing a Convolutional Neural Network (CNN) to classify maize plant diseases. Two datasets form the foundation of this study. The first dataset encompasses 4144 images distributed across 4 classes, while the second dataset comprises 5155 images distributed among 7 to 8 classes. The second dataset encounters issues related to imbalanced class distribution, where certain classes possess substantially more data than others. To mitigate this imbalance, the weighted cross-entropy loss method is employed. During experimentation, three distinct architectural models—ResNet-18, VGG16, and EfficientNet—are rigorously tested. Additionally, various optimizers are explored, with noteworthy results indicating that both datasets achieve peak accuracy through the use of the SGD (Stochastic Gradient Descent) optimization. For the first dataset, optimal results are obtained with the VGG16 architecture, leveraging a frozen layer in the classification stage and achieving an impressive accuracy of 97.146 %. Shifting the focus to the second dataset, the most favorable outcome is realized by employing the EfficientNet architecture without a frozen layer, coupled with the implementation of weighted loss to address the class imbalance, resulting in an accuracy of 94.798 %.

Automatic animal monitoring systems based on AutoML technologies

In contemporary agricultural contexts, the sector is experiencing active processes of automation, underscoring the need for effective tools to develop such automated systems. The utilization of automation tools enhances the efficiency of numerous processes, including those in the domain of animal monitoring. This article examines the application of the AutoML approach as a means for automating the process of generating deep learning models employed in automatic monitoring systems. The VGG19 architecture has been chosen as a testbed for demonstrating the capabilities of the developed technologies. This well-established architecture for deep learning models is designed for object recognition in images.The present study implements a technology for automated structural-parametric synthesis of VGG19 models and the optimization of their hyperparameters. Such an approach allows for the automated creation of models tailored to specific applied problems, even for users lacking specialized knowledge in deep learning.The system delineated in this work is developed on the AutoGenNet software platform, which embodies the No-Code development concept. This concept conceals complex aspects of model creation and training processes from users, significantly lowering the entry barrier for newcomers. Additionally, the AutoGenNet platform incorporates a mechanism for the automatic generation of software wrappers, facilitating efficient interaction with trained models.All aforementioned aspects have contributed to the effective implementation of the AutoML approach for automating the generation and training processes of the VGG19 model. Consequently, the processes associated with solving automatic monitoring tasks reliant on deep learning models have been significantly simplified and expedited.The developed system has been tested on the task of recognizing individual cows. Test results indicated that the system possesses a high degree of scalability and can be adapted for the automated generation of other object recognition models, thereby opening avenues for addressing a diverse array of applied challenges related to the monitoring of various animal species.

Multiclass Classification of Covid-19 CT Scan Images With VGG-16 Architecture Using Transfer Learning System

COVID-19 is a respiratory disease caused by the coronavirus. The most common test technique used today for COVID-19 diagnosis is real-time reverse transcription-polymerase chain reaction (RT-PCR). However, compared to RT-PCR, radiological imaging such as X-rays and computer tomography (CT) may be a more precise, useful, and faster technology for COVID-19 classification. X-rays are more accessible because they are widely available in all hospitals in the world and are cheaper than CT scans, but the classification of COVID-19 using CT scan images is more sensitive than X-rays. Therefore, CT scan images can be used for the early detection of COVID-19 patients. One of them is using the deep learning method. In this study, a CNN algorithm with a VGG-16 architecture will be selected to classify COVID-19, intermediate, and non-COVID CT scan images using 2481 image datasets. First, pre-processing is done by resizing the image, converting the image channel into RGB, and dividing the dataset into a training dataset and a testing dataset. Then, the convolution process is continued by utilizing the pre-trained VGG-16 model from ImageNet. The results of testing the data with 97% accuracy were obtained. It is concluded that the model used to classify COVID-19, intermediate, and non-COVID CT scan images is effective and produces good results.