Transfer Learning-based Model Research Articles

Transfer learning for probabilistic localization of hidden cracks in concrete structures

AbstractThe utility of discriminative supervised learning models built using multiple training-data sources is investigated for hidden crack localization in concrete. Feed-forward neural network (FFNN) is chosen as the model architecture, and transfer learning is used to assimilate the information obtained from different sources (computational physics simulations and laboratory experiments). The labeled training data consists of values of a damage index and the known locations of hidden cracks. The classification models need to learn how the presence of damage (hidden cracks) affects the damage index at different sensors for different test conditions. To this end, diagnostic FFNN models are built by sequentially adding and training new hidden layers to assimilate labeled information from computer models (different model geometries, test conditions, crack lengths, crack locations) and laboratory experiments on a plain cement slab. These transfer learning-based models are then used to localize damage in concrete specimens that reflect real-world conditions (i.e., specimens with steel reinforcement and randomly distributed aggregate). The actual damage state in these specimens is determined by extracting cores and performing petrographic studies on the extracted cores. The damage probability estimated by transfer learning-based models is compared with the petrographic damage rating index (DRI) to identify the most suitable approach to train the diagnostic models. The transfer learning-based diagnostic methodology shows promise and could be used in various structural health monitoring applications, where sufficient labeled data are typically not available from a single data source.

2D Spectrogram analysis using vision transformer to detect mispronounced Arabic utterances for children

Pronunciation feedback is essential for teaching languages to children, urging the need to create computer-assisted pronunciation training (CAPT) systems to automate this process. Most of the current CAPT systems for Arabic Language examined a wide age range, including children, with a dominant adults’ portion. However, these systems did not consider many challenges facing children’s voice, in terms of the acoustic difference between children and adults. Moreover, due to the lack of publicly Arabic datasets, Arabic-related systems were evaluated on datasets consisting of the sound of Arabic letters, with minor efforts to contain words or sentences. In this paper, we propose the Arabic Utterance Mispronunciation Detector for Children (AUMD-Child) system that detects the mispronunciation of children for Arabic words at real-time. The proposed system is based on the fusion of Vision Transformer (ViT) and transfer learning-based model (AlexNet). A novel public dataset is constructed, in which 16 words have been collected from children aged between 7 and 12 years old to evaluate our proposed system. The experimental results, compared to the state-of-the-art models in literature, showed that the accuracy of our proposed AUMD-Child system exceeded the handcrafted features-based models by an average of 7 %, the CNN features-based models using AlexNet and SVM by 5 %, transfer learning-based model using AlexNet by 4 %, and transformers-based model using ViT by 2 %, achieving an average accuracy of 91.81 % for detecting the mispronunciation patterns in Arabic words but in an average processing time of 33 ms, exceeding the other state-of-the-art models with 13 %, 0.03 %, 0.06 %, and 23 % respectively.

Mask region-based convolutional neural network and VGG-16 inspired brain tumor segmentation

The process of brain tumour segmentation entails locating the tumour precisely in images. Magnetic Resonance Imaging (MRI) is typically used by doctors to find any brain tumours or tissue abnormalities. With the use of region-based Convolutional Neural Network (R-CNN) masks, Grad-CAM and transfer learning, this work offers an effective method for the detection of brain tumours. Helping doctors make extremely accurate diagnoses is the goal. A transfer learning-based model has been suggested that offers high sensitivity and accuracy scores for brain tumour detection when segmentation is done using R-CNN masks. To train the model, the Inception V3, VGG-16, and ResNet-50 architectures were utilised. The Brain MRI Images for Brain Tumour Detection dataset was utilised to develop this method. This work's performance is evaluated and reported in terms of recall, specificity, sensitivity, accuracy, precision, and F1 score. A thorough analysis has been done comparing the proposed model operating with three distinct architectures: VGG-16, Inception V3, and Resnet-50. Comparing the proposed model, which was influenced by the VGG-16, to related works also revealed its performance. Achieving high sensitivity and accuracy percentages was the main goal. Using this approach, an accuracy and sensitivity of around 99% were obtained, which was much greater than current efforts.

Transfer learning enables the rapid design of single crystal superalloys with superior creep resistances at ultrahigh temperature

Accelerating the design of Ni-based single crystal (SX) superalloys with superior creep resistance at ultrahigh temperatures is a desirable goal but extremely challenging task. In the present work, a deep transfer learning neural network with physical constraints for creep rupture life prediction at ultrahigh temperatures is constructed. Transfer learning enables deep learning model breaks through the generalization performance barrier in the extrapolation space of ultrahigh temperature creep properties in the case of a very small dataset, which is the key to achieving the above design goal. Transfer learning is demonstrated to be effective in utilizing the prior compositional sensitivities information contained in the pre-trained model, and motivates the fine-tuned model to capture the particular relationship between composition and creep rupture life at ultrahigh temperature. Aiming to find advanced SX superalloys applied at 1200 °C, the proposed transfer learning-based model guides us to design a superalloy with a verified creep rupture life of ~170 h at 80 MPa, which exceeds the state-of-art value by 30%. The improved γ/γ′ interface strengthening, which is effectively regulated by the Mo/Ta ratio to form γ′ rafting with longer, flatter interfaces and achieve stronger interfacial bonding, is revealed as the dominant mechanism behind combining experiments and first-principles calculations. Moreover, the excellent extrapolation ability of the proposed model is further confirmed to enhance the efficiency of active learning by reducing its dependence on the initial dataset size. This study provides a pioneering AI-driven approach for the rapid development of Ni-based SX superalloys applied in advanced aero-engine blades.

DEEPFAKE DETECTION USING TRANSFER LEARNING-BASED XCEPTION MODEL

Justification of the purpose of the research. In recent times, several approaches for face manipulation in videos have been extensively applied and availed to the public which makes editing faces in video easy for everyone effortlessly with realistic efforts. While beneficial in various domains, these methods could significantly harm society if employed to spread misinformation. So, it is also vital to properly detect whether a face has been distorted in a video series. To detect this deepfake, convolutional neural networks can be used in past works. However, it needs a greater number of parameters and more computations. So, to overcome these limitations and to accurately detect deepfakes in videos, a transfer learning-based model named the Improved Xception model is suggested. Obtained results. This model is trained using extracted facial landmark features with robust training. Moreover, the improved Xception model's detection accuracy is evaluated alongside ResNet and Inception, considering model loss, accuracy, ROC, training time, and the Precision-Recall curve. The outcomes confirm the success of the proposed model, which employs transfer learning techniques to identify fraudulent videos. Furthermore, the method demonstrates a noteworthy 5% increase in efficiency compared to current systems.

Deep Learning-Based Detection and Segmentation of Damage in Solar Panels

Renewable energy can lead to a sustainable future and solar energy is one the primary sources of renewable energy. Solar energy is harvested mainly by photovoltaic plants. Though there are a large number of solar panels, the economic efficiency of solar panels is not that high in comparison to energy production from coal or nuclear matter. The main risk involved in solar plants is the high maintenance cost involved in maintaining the plants. To help reduce this issue, automated solutions using Unmanned Aerial Vehicles (UAVs) and satellite imagery are proposed. In this research work, we propose a novel deep learning architecture for the segmentation of solar plant aerial images, which not only helps in automated solar plant maintenance, but can also be used for the area estimation and extraction of solar panels from an image. Along with this, we also propose a transfer learning-based model for the efficient classification of solar panel damage. Solar panel damage classification has a lot of applications. It can be integrated into monitoring systems, raising alerts when there is severe damage or damage of a certain type. The adaptive UNet model with Atrous Spatial Pyramid Pooling (ASPP) module that performed the dilated convolutions that we proposed achieved an overall accuracy of 98% with a Mean Intersection-Over-Union (IoU) Score of 95% and took under a second to process an image. Our classification model using Visual Geometry Group 19 (VGG19) as the backbone for feature extraction has achieved a classification accuracy of 98% with an F1 score of 99%, thus detecting the five classes of damage, including undamaged solar panels, in an efficient manner.

COVID-19 Detection from Computed Tomography Images Using Slice Processing Techniques and a Modified Xception Classifier.

This paper extends our previous method for COVID-19 diagnosis, proposing an enhanced solution for detecting COVID-19 from computed tomography (CT) images using a lean transfer learning-based model. To decrease model misclassifications, two key steps of image processing were employed. Firstly, the uppermost and lowermost slices were removed, preserving sixty percent of each patient's slices. Secondly, all slices underwent manual cropping to emphasize the lung areas. Subsequently, resized CT scans (224 × 224) were input into an Xception transfer learning model with a modified output. Both Xception's architecture and pretrained weights were leveraged in the method. A big and rigorously annotated database of CT images was used to verify the method. The number of patients/subjects in the dataset is more than 5000, and the number and shape of the slices in each CT scan varies greatly. Verification was made both on the validation partition and on the test partition of unseen images. Results on the COV19-CT database showcased not only improvement from our previous solution and the baseline but also comparable performance to the highest-achieving methods on the same dataset. Further validation studies could explore the scalability and adaptability of the developed methodologies across diverse healthcare settings and patient populations. Additionally, investigating the integration of advanced image processing techniques, such as automated region of interest detection and segmentation algorithms, could enhance the efficiency and accuracy of COVID-19 diagnosis.

Transfer learning-based confinement strength prediction of concrete confined by FRP transverse reinforcements

Although several confinement strength models have been proposed for concrete confined by fiber-reinforced polymer (FRP) transverse reinforcements, these models show considerable scatter and discrepancies in the estimation of experimental data. Machine learning (ML) techniques may present an alternative prediction approach, but challenges arise due to insufficient experimental data. This study, therefore, develops a transfer learning-based model for predicting the confinement strength of concrete confined by FRP transverse reinforcements. Firstly, a literature review was conducted to collect a target dataset of FRP-confined concrete columns and a source dataset of steel-confined concrete columns used for knowledge transfer. Subsequently, a transfer learning algorithm was proposed to construct an ML confinement strength model for FRP-confined concrete. Finally, the performance of the proposed model was compared to that of six ML models and seven physics-based models. The model evaluation based on one-time random split indicated that the proposed model provided more accurate predictions for the confinement strength than other models considered in this study, achieving an R2 of 0.9089 on the test dataset. Shuffle split evaluation demonstrated that the proposed model exhibited superior stability and robustness compared to other models considered. Based on the proposed transfer learning-based model, the importance of the input parameters was obtained, further confirming the robustness of the proposed model.

Transfer Learning-Based Models for Comparative Evaluation for the Detection of AI-Generated Images

As the pace of artificial intelligence (AI) evolution accelerates, the line separating authentic from AI-produced imagery becomes increasingly indistinct. This shift carries profound consequences for sectors such as content verification and digital investigation, underscoring the need for proficient AI-generated image identification systems. Our study utilizes established architectures like AlexNet, Convolutional Neural Networks (CNNs), and VGG16 to explore and evaluate the effectiveness of models based on transfer learning for spotting AI-crafted images. Transfer learning, which applies models pre-trained on large datasets, has proven beneficial in numerous computer vision tasks. In this research, we modify the intricate patterns recognized by AlexNet, CNNs, and VGG16 from extensive datasets to specifically target the detection of AI-generated content. We introduce models that are trained, validated, and tested on a comprehensive dataset that includes both real and AI-generated images. Our experimental findings demonstrate the utility of transfer learning methods in discerning between real and synthetic visuals. By conducting a comparative analysis, we highlight the comparative advantages and limitations of each model in terms of metrics such as precision, recall, accuracy, and the F1-score. Further, we investigate the distinct features identified by each model to elucidate their contribution to accurate classification.

Multi-variants vision transformer-based malware image classification model using multi-criteria decision-making

Visualization-based malware detection gets more and more attention for detecting sophisticated malware that traditional antivirus software may miss. The approach involves creating a visual representation of the memory or portable executable files (PEs). However, most current visualization-based malware classification models focus on convolution neural networks instead of Vision transformers (ViT) even though ViT has a higher performance and captures the spatial representation of malware. Therefore, more research should be performed on malware classification using vision transformers. This paper proposes a multi-variants vision transformer-based malware image classification model using multi-criteria decision-making. The proposed method employs Multi-variants transformer encoders to show different visual representation embeddings sets of one malware image. The proposed architecture contains five steps: (1) patch extraction and embeddings, (2) positional encoding, (3) multi-variants transformer encoders, (4) classification, and (5) decision-making. The variants of transformer encoders are transfer learning-based models i.e., it was originally trained on ImageNet dataset. Moreover, the proposed malware classifier employs MEREC-VIKOR, a hybrid standard evaluation approach, which combines multi-inconsistent performance metrics. The performance of the transformer encoder variants is assessed both on individual malware families and across the entire set of malware families within two datasets i.e., MalImg and Microsoft BIG datasets achieving overall accuracy 97.64 and 98.92 respectively. Although the proposed method achieves high performance, the metrics exhibit inconsistency across some malware families. The results of standard evaluation metrics i.e., Q, R, and U show that TE3 outperform the TE1, TE2, and TE4 variants achieving minimal values equal to 0. Finally, the proposed architecture demonstrates a comparable performance to the state-of-the-art that use CNNs.

A Semi-Supervised Learning Framework for Classifying Colorectal Neoplasia Based on the NICE Classification

Labelling medical images is an arduous and costly task that necessitates clinical expertise and large numbers of qualified images. Insufficient samples can lead to underfitting during training and poor performance of supervised learning models. In this study, we aim to develop a SimCLR-based semi-supervised learning framework to classify colorectal neoplasia based on the NICE classification. First, the proposed framework was trained under self-supervised learning using a large unlabelled dataset; subsequently, it was fine-tuned on a limited labelled dataset based on the NICE classification. The model was evaluated on an independent dataset and compared with models based on supervised transfer learning and endoscopists using accuracy, Matthew’s correlation coefficient (MCC), and Cohen’s kappa. Finally, Grad-CAM and t-SNE were applied to visualize the models’ interpretations. A ResNet-backboned SimCLR model (accuracy of 0.908, MCC of 0.862, and Cohen’s kappa of 0.896) outperformed supervised transfer learning-based models (means: 0.803, 0.698, and 0.742) and junior endoscopists (0.816, 0.724, and 0.863), while performing only slightly worse than senior endoscopists (0.916, 0.875, and 0.944). Moreover, t-SNE showed a better clustering of ternary samples through self-supervised learning in SimCLR than through supervised transfer learning. Compared with traditional supervised learning, semi-supervised learning enables deep learning models to achieve improved performance with limited labelled endoscopic images.

Smart grading of diabetic retinopathy: an intelligent recommendation-based fine-tuned EfficientNetB0 framework.

Diabetic retinopathy is a condition that affects the retina and causes vision loss due to blood vessel destruction. The retina is the layer of the eye responsible for visual processing and nerve signaling. Diabetic retinopathy causes vision loss, floaters, and sometimes blindness; however, it often shows no warning signals in the early stages. Deep learning-based techniques have emerged as viable options for automated illness classification as large-scale medical imaging datasets have become more widely available. To adapt to medical image analysis tasks, transfer learning makes use of pre-trained models to extract high-level characteristics from natural images. In this research, an intelligent recommendation-based fine-tuned EfficientNetB0 model has been proposed for quick and precise assessment for the diagnosis of diabetic retinopathy from fundus images, which will help ophthalmologists in early diagnosis and detection. The proposed EfficientNetB0 model is compared with three transfer learning-based models, namely, ResNet152, VGG16, and DenseNet169. The experimental work is carried out using publicly available datasets from Kaggle consisting of 3,200 fundus images. Out of all the transfer learning models, the EfficientNetB0 model has outperformed with an accuracy of 0.91, followed by DenseNet169 with an accuracy of 0.90. In comparison to other approaches, the proposed intelligent recommendation-based fine-tuned EfficientNetB0 approach delivers state-of-the-art performance on the accuracy, recall, precision, and F1-score criteria. The system aims to assist ophthalmologists in early detection, potentially alleviating the burden on healthcare units.

Leaf diseases detection empowered with transfer learning model

<p>The detection of leaf diseases using modern technology has significant importance in agriculture and artificial intelligence. Deep learning, specifically, plays a crucial role in this field, as it enables accurate and efficient disease classification. Early detection of leaf diseases is vital to implementing timely treatments and preventing widespread damage to leaves. Leaf diseases can be caused by various factors, including bacteria, fungi, viruses, and other pathogens. Among them, bacteria and viruses are the most invasive and can lead to substantial yield losses if not identified and treated promptly. Bacterial and viral infections are common in agricultural settings, affecting leaves of all types and ages. Our research aims to propose a transfer learning-based model for predicting leaf diseases using a dataset of leaf images. The images will be classified into healthy or diseased leaves based on extracted features. The proposed model, named Leaf Disease Transfer Learning Algorithm (LDTLA), demonstrates promising results with an average accuracy of 97.37% on the dataset. Utilizing convolutional neural networks (CNN) and deep learning techniques, our LDTLA model outperforms previous quantitative and qualitative research studies in leaf disease detection. This advanced approach to leaf disease identification holds the potential to revolutionize agriculture by enabling farmers to make informed decisions, implement targeted treatments, and minimize leaf losses caused by diseases.<strong></strong></p>

Deep transfer learning model for brain tumor segmentation and classification using UNet and chopped VGGNet

Brain tumors (BT) are a leading cause of cancer-related mortality worldwide, underscoring the critical need for early and precise detection to improve patient survival rates. Computer-aided diagnosis (CAD) plays a pivotal role in early BT detection by providing medical experts with valuable information image analysis. Various researchers have developed distinct methodologies, drawing from both machine and deep learning approaches. ML relies on manual feature analysis, which entails a time-intensive procedure of selecting an optimal feature extractor and necessitates domain experts with a deep understanding of feature selection. Conversely, deep learning methods exhibit superior performance compared to ML owing to their end-to-end, automated, high-level, and robust attribute mining capabilities. In this study introduced an innovative two-stage framework designed for the automatic classification of BT. In the initial stage, utilize U-Net models to conduct BT segmentation as part of the pre-processing step. Subsequently, in the second stage, utilize the improved BT images as input for a transfer learning-based model known as visual geometry group neural network (VGGNet), which excels in BT classification. The experimental analysis shows that the proposed approach has reported the average classification accuracy as 98.6%, 98.76%, and 99.45% for Meningioma, Glioma, and Pituitary BTs, respectively.

New unfreezing strategy of transfer learning in satellite imagery for mapping the diversity of slum areas: A case study in Kenitra city—Morocco

The purpose behind this paper research is to localize and detect, for the first time, three types of shantytowns that can exist in both urban and rural areas in Morocco. The reason why we have conducted this study is the absence of diversity slum mapping in the form of dynamic GIS data, which can be a part of national development strategies to tackle the risk of further proliferation of shantytowns. Therefore, we first create a new database integration from five countries whose content contains 1366 high-resolution patches of 224 × 224 pixels divided into five classes: two types of “Urban Slum”, one type of “Rural Slum”, “Formal Buildings”, and non-built-up area. Second, we suggest employing a variety of performance metrics to come up with the best transfer learning-based models for the unfreezing stage. The study reveals that by handling the unfreezing of the front layers, we can produce a reliable new model where one condition is fulfilled, namely, where high-frequency dissimilarities have arisen between the target and the source datasets.Quantitative results of these methodologies show that our dataset and our unfreezing strategy for the mobilenetv2 model are more accurate compared to other competing models. This new model can localize all possible changes in morphology and shape among the three-slum types with state-of-the-art performance that reaches an overall accuracy of 98.17%, a loss of 0.062, and a kappa score of 97.71%. Our dataset and the code will be publicly available at the github11https://github.com/mouddentarik/New_Unfreezing_Strategy. to share our results.

Cancer Diseases Prediction Using Multiple Transfer Learning based on CNN Algorithm

For many years, the most common types of cancers that causes death has been lung and brain cancer. In addition, they are very hard to treat once they have been spread in the late stages. Early cancer detection and diagnosis have become crucial for providing immediate and efficient care to those who are afflicted with the disease. To predict cancer, this process needs cancer image classification which is a difficult task in the recent improvement of computer-based diagnostics. The main objective of this research is to classify Computed-Tomography (CT) images of the lungs and brain as cancerous or not. Therefore, this research shows the possibility of using a convolutional-neural-network (CNN) for lung and brain cancer detection through transfer learning (TL) without the difficulty of specifying features for image-classification. The proposed TCNN is trained and tested from scratch using two public and one private dataset using the TL technique. The suggested transfer learning-based model attained an accuracy of 92.81%, 97.21%, and 99.40% for Scratch TCNN Model, Pre-Trained TCNN Model, and Transfer Pre-Pre-Trained Model in that order. Hence, the proposed method gives high accuracy and decreases the time of diagnosis and treatment.

Transfer Learning Empowered Bone Fracture Detection

Detection of bone fractures using modern technology has significant implications in medical analysis and artificial intelligence. This importance is especially pronounced in the realm of deep learning. Deep learning techniques find extensive application in the field of medicine and disease classification. The early identification of bone fractures is crucial for efficient treatment planning and patient care. Our research proposes a transfer learning-based model for predicting bone fractures using a dataset of bone X-ray images. These images will be classified into two categories: normal and bone fracture, based on extracted features. Our proposed model, the Bone Fracture Detection Transfer Learning Algorithm (BFDTLA), achieved an average accuracy of 97% on the dataset. The BFDTLA model demonstrated superior performance when compared to previous quantitative and qualitative research studies. This research focuses on the early detection of bone fractures using transfer learning algorithms, emphasizing the significance of accurate and timely diagnosis.

Contradiction in text review and apps rating: prediction using textual features and transfer learning.

Mobile app stores, such as Google Play, have become famous platforms for practically all types of software and services for mobile phone users. Users may browse and download apps via app stores, which also help developers monitor their apps by allowing users to rate and review them. App reviews may contain the user's experience, bug details, requests for additional features, or a textual rating of the app. These ratings can be frequently biased due to inadequate votes. However, there are significant discrepancies between the numerical ratings and the user reviews. This study uses a transfer learning approach to predict the numerical ratings of Google apps. It benefits from user-provided numeric ratings of apps as the training data and provides authentic ratings of mobile apps by analyzing users' reviews. A transfer learning-based model ELMo is proposed for this purpose which is based on the word vector feature representation technique. The performance of the proposed model is compared with three other transfer learning and five machine learning models. The dataset is scrapped from the Google Play store which extracts the data from 14 different categories of apps. First, biased and unbiased user rating is segregated using TextBlob analysis to formulate the ground truth, and then classifiers prediction accuracy is evaluated. Results demonstrate that the ELMo classifier has a high potential to predict authentic numeric ratings with user actual reviews.

Classification System for Predicting Emergent Epilepsy Phenotype in the Intra-amygdala Kainic Acid Mouse Model of Epilepsy.

Animal models of drug-resistant epilepsy represent an important resource for discovering new drug targets and testing experimental medicines. Intra-amygdala microinjection of kainic acid in mice is one of the most widely regarded models of drug-resistant epilepsy. Mice develop acute status epilepticus, which diminishes after a few hours and then, within a few days, mice display spontaneous seizures (epilepsy). The frequency of spontaneous seizures varies between mice, with some developing low or high seizure rates. The ability to predict soon after status epilepticus, which mice will go on to develop a normal frequency of seizures, would enable a significant reduction in resources and EEG reviewing time and lead to humane early end-points for the mice with low or high seizure rates. In this study, we developed two machine learning models, a feature-based and transfer learning-based approach, for predicting the emergent spontaneous seizure rates in the intra-amygdala kainic acid model based on the acute EEGs recorded in mice during status epilepticus lasting 40 minutes. The method was trained on data from 28 mice and subsequently tested on data from 16 mice. The feature-based and transfer learning-based models achieved accuracies of 69% and 75%, respectively on the test set in classifying emergent epilepsy as normal or outlier (i.e. low-frequency or high-frequency seizure rate). A limitation of the intra-amygdala kainic acid model has been the loss of time and resources from generating mice with low or high rates of spontaneous seizures. To date, no other research has attempted to predict emergent spontaneous seizure rates. The feature-based and transfer learning-based models will assist researchers in identifying mice with a normal frequency of seizures before the onset of spontaneous seizures. We have implemented this approach as a web server, which can potentially reduce the time and resources spent analysing the EEGs of mice who develop low-frequency or high-frequency seizure rates. This will enable the early humane endpoint of outlier mice, which aligns with the principles of the responsible use of animals in research and simultaneously speeds up preclinical anti-epilepsy drug discovery.

Retinal Disease Classification Using Custom CNN Model From OCT Images

Retinal diseases affect the eye’s retina and are the leading cause of vision loss. Timely detection and diagnosis can provide more treatment options and preserve vision. Retinal imaging, such as Optical Coherence Tomography (OCT), is used for screening patients and enables clinicians to visualize the retinal layers in detail, helping in early diagnosis and tailoring appropriate treatment plans. This study uses OCT images to detect diseases related to macular disorders common in old age. A custom convolution Neural Network (CNN) model is proposed in this study to classify OCT images of normal, choroidal neovascularization (CNV), diabetic macular edema (DME), and Drusen from a public dataset. Experiments were conducted using conventional machine learning (ML) and transfer learning-based models other than the proposed one. The proposed model performed favorably, attaining the training and validation accuracy of 97% and 93%, respectively. The proposed model achieves a testing accuracy of 98% with a loss of 0.051 and outperforms the existing models compared to this study.