Search

This project aims to mitigate the critical decline in bee populations, essential for crop pollination and food security. With a shortage of taxonomic specialists to identify the vast array of bee species, the project's goal is to enhance the monitoring of population changes through an automated classification system. Utilizing a dataset of bee wing images, the project aims to develop a computational pipeline to identify species based on their unique wing vein patterns. This approach not only supports bee conservation efforts but also expands our understanding of complex geometric variations in nature, offering wider applications in biological research. This poster was presented at the UCSB Data Science Capstone showcase in 2024.

Breast cancer continues to be an important health issue around the world, with timely screening being important in improving survival and therapy. Here is a presentation of PolyBreastVit, a novel hybrid deep learning (DL) model for the automatic detection and classification of breast cancer in ultrasound images that combines PolyNet with Vision Transformer (ViT). The above model is trained and validated on a dataset of 880 high‐definition images collected from 500 female subjects aged between 25 and 75 years on three classes: benign, malignant, and normal. For the enhancement of the proposed model's accuracy, thorough data augmentation and preprocessing have been performed. The performance of PolyBreastVit is evaluated against several well‐known DL models such as VGG‐16, Inception V3, and ResNet‐50 using accuracy, precision, recall, F1, AUC, and other standard metrics. These findings support the evidence that PolyBreastVit manages to outperform those classical models in the task of breast cancer classification in every aspect. This paper presents the latest development of breast cancer diagnostic tools through medical imaging incorporating convolutional neural networks (CNNs) and transformer models for radiologists. [ABSTRACT FROM AUTHOR]

Agriculture stands as the cornerstone of Africa's economy, supporting over 60% of the continent's labor force. Despite its significance, the quality assessment of agricultural products remains a challenging task, particularly at a large scale, consuming valuable time and resources. The African plum is an agricultural fruit that is widely consumed across West and Central Africa but remains underrepresented in AI research. In this paper, we collected a dataset of 2892 African plum samples from fields in Cameroon representing the first dataset of its kind for training AI models. The dataset contains images of plums annotated with quality grades. We then trained and evaluated various state-of-the-art object detection and image classification models, including YOLOv5, YOLOv8, YOLOv9, Fast R-CNN, Mask R-CNN, VGG-16, DenseNet-121, MobileNet, and ResNet, on this African plum dataset. Our experimentation resulted in mean average precision scores ranging from 88.2% to 89.9% and accuracies between 86% and 91% for the object detection models and the classification models, respectively. We then performed model pruning to reduce model sizes while preserving performance, achieving up to 93.6% mean average precision and 99.09% accuracy after pruning YOLOv5, YOLOv8 and ResNet by 10–30%. We deployed the high-performing YOLOv8 system in a web application, offering an accessible AI-based quality assessment tool tailored for African plums. To the best of our knowledge, this represents the first such solution for assessing this underrepresented fruit, empowering farmers with efficient tools. Our approach integrates agriculture and AI to fill a key gap. [ABSTRACT FROM AUTHOR]

The recent increase in the prevalence of skin cancer, along with its significant impact on individuals' lives, has garnered the attention of many researchers in the field of deep learning models, especially following the promising results observed using these models in the medical field. This study aimed to develop a system that can accurately diagnose one of three types of skin cancer: basal cell carcinoma (BCC), melanoma (MEL), and nevi (NV). Additionally, it emphasizes the importance of image quality, as many studies focus on the quantity of images used in deep learning. In this study, transfer learning was employed using the pre-trained VGG-16 model alongside a dataset sourced from Kaggle. Three models were trained while maintaining the same hyperparameters and script to ensure a fair comparison. However, the quantity of data used to train each model was varied to observe specific effects and to hypothesize about the importance of image quality in deep learning models within the medical field. The model with the highest validation score was selected for further testing using a separate test dataset, which the model had not seen before, to evaluate the model's performance accurately. This work contributes to the existing body of research by demonstrating the critical role of image quality in enhancing diagnostic accuracy, providing a comprehensive evaluation of the VGG-16 model's performance in skin cancer detection and offering insights that can guide future improvements in the field. [ABSTRACT FROM AUTHOR]

Abstract Hotspots in electrical power equipment or installations are a major issue whenever it occurs within the power system. Factors responsible for this phenomenon are many, sometimes inter-related and other times they are isolated. Electrical hotspots caused by poor connections are common. Deep learning models have become popular for diagnosing anomalies in physical and biological systems, by the instrumentality of feature extraction of images in convolutional neural networks. In this work, a VGG-16 deep neural network model is applied for identifying electrical hotspots by means of transfer learning. This model was achieved by first augmenting the acquired infrared thermographic images, using the pre-trained ImageNet weights of the VGG-16 algorithm with additional global average pooling in place of conventional fully connected layers and a softmax layer at the output. With the categorical cross-entropy loss function, the model was implemented using the Adam optimizer at learning rate of 0.0001 as well as some variants of the Adam optimization algorithm. On evaluation, with a test IRT image dataset, and a comparison with similar works, the research showed that a better accuracy of 99.98% in identification of electrical hotspots was achieved. The model shows good score in performance metrics like accuracy, precision, recall, and F 1-score. The obtained results proved the potential of deep learning using computer vision parameters for infrared thermographic identification of electrical hotspots in power system installations. Also, there is need for careful selection of the IR sensor’s thermal range during image acquisition, and suitable choice of color palette would make for easy hotspot isolation, reduce the pixel to pixel temperature differential across any of the images, and easily highlight the critical region of interest with high pixel values. However, it makes edge detection difficult for human visual perception which computer vision-based deep learning model could overcome.

Hotspots in electrical power equipment or installations are a major issue whenever it occurs within the power system. Factors responsible for this phenomenon are many, sometimes inter-related and other times they are isolated. Electrical hotspots caused by poor connections are common. Deep learning models have become popular for diagnosing anomalies in physical and biological systems, by the instrumentality of feature extraction of images in convolutional neural networks. In this work, a VGG-16 deep neural network model is applied for identifying electrical hotspots by means of transfer learning. This model was achieved by first augmenting the acquired infrared thermographic images, using the pre-trained ImageNet weights of the VGG-16 algorithm with additional global average pooling in place of conventional fully connected layers and a softmax layer at the output. With the categorical cross-entropy loss function, the model was implemented using the Adam optimizer at learning rate of 0.0001 as well as some variants of the Adam optimization algorithm. On evaluation, with a test IRT image dataset, and a comparison with similar works, the research showed that a better accuracy of 99.98% in identification of electrical hotspots was achieved. The model shows good score in performance metrics like accuracy, precision, recall, and F1-score. The obtained results proved the potential of deep learning using computer vision parameters for infrared thermographic identification of electrical hotspots in power system installations. Also, there is need for careful selection of the IR sensor's thermal range during image acquisition, and suitable choice of color palette would make for easy hotspot isolation, reduce the pixel to pixel temperature differential across any of the images, and easily highlight the critical region of interest with high pixel values. However, it makes edge detection difficult for human visual perception which computer vision-based deep learning model could overcome. [ABSTRACT FROM AUTHOR]

The COVID-19 pandemic proved how face masks became necessary to stop the spread of infection. Due to this, effective identification of people wearing face mask became challenging. Masked facial recognition has significantly increased in accuracy because of developments in convolutional neural networks (CNNs). Small size of the dataset of masked facial images has been a problem in earlier research. As would be expected, this results in poorer accuracy when the model tries to identify faces. In this study, a novel model is proposed with textural feature extraction using greylevel co-occurrence matrix (GLCM) and an ensemble of two pre-trained CNNs DenseNet-121 and VGG-16. Using the minimum redundancy and maximum relevance, the model has improved accuracy by choosing the most important features of the image. The model was trained using in-house dataset that included 38,290 photos of 2,500 people with approximately equal distribution of properly masked, partially masked, and unmasked images. In this, we evaluated the performance of the model on different classifiers multi-class logistic regression (LR) and support vector machine (SVM) with one-vs-rest (OvR) classification and artificial neural network (ANN) and applied a soft voting scheme. The model achieved the highest accuracy of 98.56% at a learning rate of 0.001 on the ANN classifier. [ABSTRACT FROM AUTHOR]

The COVID-19 pandemic, which originated in 2019, has caused a significant global number of fatalities. The economic and healthcare impacts of COVID-19 infection in survivors have become evident during this period. An important first step towards the effective management of COVID-19 is an effective screening of patients, which includes radiology examinations using chest radiography as one of the primary screening modalities. Early research has shown that patients with pneumonia and COVID-19 infection show different anomalies in chest radiography images. Classifying images of COVID-19 and pneumonia diseases has proven to be a challenging task for computers. Several classification systems were developed using different databases in order to determine the category to which the detected image belongs. The accuracy percentage was assessed using these systems. However, there are instances where the imaging techniques may produce distorted images, low contrast images, or fail to accurately depict the edges of the internal organs. These challenges can have an impact on the accuracy of a classification model's design. In this study, a new robust model called FPD-VGG-16 is introduced. This model combines the Visual Geometry Group (VGG-16) deep learning technique with the Fractional Partial Differential (FrPDA) mathematical method. The idea of using FrPDA is to improve edges, increase the visibility of texture details, and retain smooth areas in comparison to using only deep algorithms. The proposed model demonstrates accurate pneumonia detection and COVID-19 classification from chest X-ray images; the model recorded an impressive accuracy of 98.1%, along with equally remarkable precision and recall values 0.982 and 0.980 respectively, as well as and f1-score score of 0.981. While 96.2% as an accuracy measure is achieved in this study without using the FrPDA algorithm. [ABSTRACT FROM AUTHOR]

The fabric quality in textile industry is characterized by the texture (weave pattern) as it plays a vital role for the production and design of best quality fabric. The earlier proposed automated weave identification methods based on image processing techniques are highly dependent on the lighting conditions. The machine learning methods have been reported to show better accuracy. However, they require very large training datasets, very high processing power and computation time. This study proposes improved accuracy with smaller dataset and reduced computation time by proposing a modification of VGG- 16 model by adding two additional pooling layers. Using evaluation metrics of both models, the modified model results were analysed according to accuracy, balanced accuracy, and F1-score. On the basis of investigational outcomes, a comparison has been performed with earlier work. The results show that the proposed VGG-16 model is capable to achieve state-of-the-art accuracy and avoid unnecessary activation features by freezing the main convolutional base layers. Ultimately, as evidenced by the performance of the modified VGG-16 deep learning model, the proposed method demonstrated improved accuracy. The study results show that the proposed modified VGG- 16 algorithm is able to recognize the features of provided database with 90% accuracy and F1-Score ranging from 0.8 to1. [ABSTRACT FROM AUTHOR]

To increase the survival rates for lung cancer, early identification and diagnosis are essential. The detection becomes crucial for a number of reasons, including visual similarity, heterogeneity, and low contrast variation. The several varieties of lung cancer that can be categorised histologically are determined by the kind of cells a pathologist can detect under a microscope. 15% of lung cancer cases are caused by small cell lung cancer (SCLC), while 85% of cases are caused by non-small cell lung cancer (NSCLC). The three main types of NSCLC are lung adenocarcinoma, big cell carcinoma, and squamous cell carcinoma (SQCC). Deep learning models provides high level services to the healthcare domain. The proposed research focuses on applying deep learning models to segment and classify images of lung cancer histopathology. Images are segmented using the U-Net model. In order to categorise the different forms of lung cancer histopathology images, classification models like ResNet-50, VGG-16, and EfficientNet-B5 and Ensemble models of these three models were utilised. For the purpose of evaluating all the classifiers, performance metrics like accuracy, precision, recall, and F1 Score were computed. The U-Net model achieves 81% accuracy. ResNet-50 achieved an accuracy of 91%, VGG-16 94%, EfficientNet-B5 97%, and Ensemble model 99%, respectively. Among all models, an ensemble model is the most accurate. [ABSTRACT FROM AUTHOR]

In Bangladesh, where fish is a staple food, ensuring its safety from formalin contamination poses a critical challenge due to its perishable nature. This study introduces an intelligent application employing digital image processing for the rapid and non-intrusive detection of formalin in fish. Leveraging image analysis of fish eyes, the system distinguishes between formalin and non-formalin treated fish. The proposed architecture, utilizing EfficientNet-B3 and VGG-16 models, achieved a 98.05% and 98% accuracy rate in training and validation on the dataset. This method offers a swift and accurate means of examination without damaging sample preparation, particularly beneficial in large-scale operations where manual inspection is impractical. Unlike human senses, digital image processing algorithms remain impartial, overcoming human biases and subjective judgments. Challenges persist, such as the diverse appearance of fish and external factors like varying illumination, which may impact the reliability and effectiveness of image processing programs for formalin detection. Nonetheless, this technology holds promise in addressing the pressing need for dependable and automated formalin detection in the fish supply chain, ensuring food safety and public health.

In the realm of medical imaging, the precise segmentation and classification of gliomas represent fundamental challenges with profound clinical implications. Leveraging the BraTS 2018 dataset as a standard benchmark, this study delves into the potential of advanced deep learning models for addressing these challenges. We propose a novel approach that integrates a customized U-Net for segmentation and VGG-16 for classification. The U-Net, with its tailored encoder-decoder pathways, accurately identifies glioma regions, thus improving tumor localization. The fine-tuned VGG-16, featuring a customized output layer, precisely differentiates between low-grade and high-grade gliomas. To ensure consistency in data pre-processing, a standardized methodology involving gamma correction, data augmentation, and normalization is introduced. This novel integration surpasses existing methods, offering significantly improved glioma diagnosis, validated by high segmentation dice scores (WT: 0.96, TC: 0.92, ET: 0.89), and a remarkable overall classification accuracy of 97.89%. The experimental findings underscore the potential of integrating deep learning-based methodologies for tumor segmentation and classification in enhancing glioma diagnosis and formulating subsequent treatment strategies.

Abstract Background and aims Control of dialysate fluid quality is critical to secure the safety of dialysis treatment. The number of colonies is manually counted when determining viable cell count in dialysis fluid, but errors and subjective interpretation on the part of the measurer can be problematic. This prompted us to examine the potential for using deep learning to detect viable cells and count their numbers. Methods In this study we prepared 5360 images for detecting viable cell count and classified them into four categories using the VGG-16 model. These images were resized to 224 × 224 px; 90% of them were used for learning, and 10% were used for validation. In an alternative approach, we also created 110 annotated images from images to detect viable cell count in dialysis fluid and subjected them to learning using the YOLOv5 model. Results VGG-model had a detection accuracy using the test data was 43%. YOLOv5 model had a mAP (Mean Average Precision) was 0.842. The detection accuracy using the test data was 90%. Conclusions The method using the VGG-16 model had problems with overfitting, suggesting that the model was not sufficiently expressive. The detection of viable cells using the YOLOv5 model showed high accuracy.

Brain tumors, a significant health concern, are a leading cause of mortality globally, with an annual projected increase of 5% by the World Health Organization. This work aims to comprehensively analyze the performance of transfer learning methods in identifying the types of brain tumors, with a particular emphasis on the necessity of prompt identification. The study demonstrates how useful it is to use pre-trained models, including models VGG-16, VGG-19, Inception-v3, ResNet-50, DenseNet, and MobileNet—on MRI datasets and used to obtain a precise classification. Using these methods model accuracy and efficiency have been enhanced. The research aims to contribute to improved treatment planning and patient outcomes by implementing optimal methodologies for precise and automated brain tumor analysis, evaluation framework encompasses vital metrics such as confusion matrices, ROC curves, and the achieved Area Under the Curve (AUC) for each approach. The comprehensive methodology outlined in this paper serves as a systematic guide for the implementation and evaluation of brain tumor classification models utilizing deep learning techniques. The integration of visual representations, code snippets, and performance metrics significantly enhances the clarity and understanding of the proposed approach. Among our proposed algorithms, VGG-16 attains the highest accuracy at 97% and consumes only 22% of time as compared to our previous proposed methodology.

Fake face identity is a serious, potentially fatal issue that affects every industry from the banking and finance industry to the military and mission-critical applications. This is where the proposed system offers artificial intelligence (AI)-based supported fake face detection. The models were trained on an extensive dataset of real and fake face images, incorporating steps like sampling, preprocessing, pooling, normalization, vectorization, batch processing and model training, testing-, and classification via output activation. The proposed work performs the comparative analysis of the three fusion models, which can be integrated with Generative Adversarial Networks (GAN) based on the performance evaluation. The Model-3, which contains the combination of DenseNet-201+ResNet-102+Xception, offers the highest accuracy of 0.9797, and the Model-2 with the combination of DenseNet-201+ResNet-50+Inception V3 offers the lowest loss value of 0.1146; both are suitable for the GAN integration. Additionally, the Model-1 performs admirably, with an accuracy of 0.9542 and a loss value of 0.1416. A second dataset was also tested where the proposed Model-3 provided maximum accuracy of 86.42% with a minimum loss of 0.4054.

The diagnosis of lung disease is a challenging process that frequently combines clinical information, such as patient symptoms, medical history and test findings, with medical imaging, like X-rays or CT scans. The classification of lung diseases is very important in healthcare since it helps with diagnosis and treatment of many different lung diseases. A precise classification of lung conditions can aid doctors in choosing the best course of action and enhancing patient outcomes. Additionally, accurate classification can aid in evaluating the effectiveness of therapies, forecasting results and tracking the development of diseases. It is extremely important to accurately classify lung conditions. A comparison of a novel model for lung disease classification from chest CT and CXR images was presented in this paper. A modified VGG-16 model was used as the classification model. To improve the performance, a fine-tuning mechanism was added to the proposed model. The effectiveness of the suggested method is analyzed and compared on two distinct datasets in terms of performance metrics. The experimental outcomes showed that the suggested model performs better on the CXR image dataset.

Skin disease is a common health problem in Islamic boarding school environments. This disease can spread quickly among students due to close contact and sharing the same facilities. Preventing the spread of skin diseases is a top priority in efforts to maintain the health and welfare of students in Islamic boarding schools. In this research, we propose the use of machine learning techniques to predict skin diseases in Islamic boarding school students. The main goal of this research is to develop a predictive model that can help identify skin diseases quickly and accurately. It is hoped that this will enable the prevention of the spread of skin diseases in the Islamic boarding school environment. The method used in this research involves the following steps: skin disease image data collection, data processing and cleaning, feature extraction from patient data, and machine learning model training and evaluation. We will use a Convolutional Neural Network (CNN) machine learning algorithm to build a predictive model. The dataset used in this research consists of images of melanoma, acne and acne skin diseases. In addition, validation will be carried out using data that has never been seen before to test the performance of the predictive model. It is hoped that the results of this research can make a significant contribution in preventing the spread of skin diseases in the Islamic boarding school environment. With accurate predictive models, health workers in Islamic boarding schools can take appropriate preventive measures to control skin diseases effectively. Apart from that, this research can also be a basis for developing a health information system that supports preventive measures for skin diseases in Islamic boarding schools more widely.

The frequency of liver cancer is rising worldwide, and it is a common, deadly condition. For successful treatment and patient survival, early and precise diagnosis is essential. The automated classification of liver cancer using medical imaging data has shown potential outcome when employing machine and deep learning (DL) approaches. To train deep neural networks, it is still quite difficult to obtain a large and diverse dataset, especially in the medical field.

Skin cancer is a severe and potentially lethal disease, and early detection is critical for successful treatment. Traditional procedures for diagnosing skin cancer are expensive, time-intensive, and necessitate the expertise of a medical practitioner. In recent years, many researchers have developed artificial intelligence (AI) tools, including shallow and deep machine learning-based approaches, to diagnose skin cancer. However, AI-based skin cancer diagnosis faces challenges in complexity, low reproducibility, and explainability. To address these problems, we propose a novel Grid-Based Structural and Dimensional Explainable Deep Convolutional Neural Network for accurate and interpretable skin cancer classification. This model employs adaptive thresholding for extracting the region of interest (ROI), using its dynamic capabilities to enhance the accuracy of identifying cancerous regions. The VGG-16 architecture extracts the hierarchical characteristics of skin lesion images, leveraging its recognized capabilities for deep feature extraction. Our proposed model leverages a grid structure to capture spatial relationships within lesions, while the dimensional features extract relevant information from various image channels. An Adaptive Intelligent Coney Optimization (AICO) algorithm is employed for self-feature selected optimization and fine-tuning the hyperparameters, which dynamically adapts the model architecture to optimize feature extraction and classification. The model was trained and tested using the ISIC dataset of 10,015 dermascope images and the MNIST dataset of 2357 images of malignant and benign oncological diseases. The experimental results demonstrated that the model achieved accuracy and CSI values of 0.96 and 0.97 for TP 80 using the ISIC dataset, which is 17.70% and 16.49% more than lightweight CNN, 20.83% and 19.59% more than DenseNet, 18.75% and 17.53% more than CNN, 6.25% and 6.18% more than Efficient Net-B0, 5.21% and 5.15% over ECNN, 2.08% and 2.06% over COA-CAN, and 5.21% and 5.15% more than ARO-ECNN. Additionally, the AICO self-feature selected ECNN model exhibited minimal FPR and FNR of 0.03 and 0.02, respectively. The model attained a loss of 0.09 for ISIC and 0.18 for the MNIST dataset, indicating that the model proposed in this research outperforms existing techniques. The proposed model improves accuracy, interpretability, and robustness for skin cancer classification, ultimately aiding clinicians in early diagnosis and treatment. [ABSTRACT FROM AUTHOR]

The diagnosis of lung disease is a challenging process that frequently combines clinical information, such as patient symptoms, medical history and test findings, with medical imaging, like X-rays or CT scans. The classification of lung diseases is very important in healthcare since it helps with diagnosis and treatment of many different lung diseases. A precise classification of lung conditions can aid doctors in choosing the best course of action and enhancing patient outcomes. Additionally, accurate classification can aid in evaluating the effectiveness of therapies, forecasting results and tracking the development of diseases. It is extremely important to accurately classify lung conditions. A comparison of a novel model for lung disease classification from chest CT and CXR images was presented in this paper. A modified VGG-16 model was used as the classification model. To improve the performance, a fine-tuning mechanism was added to the proposed model. The effectiveness of the suggested method is analyzed and compared on two distinct datasets in terms of performance metrics. The experimental outcomes showed that the suggested model performs better on the CXR image dataset. [ABSTRACT FROM AUTHOR]

This study presents a comprehensive exploration of deep learning models for precise brain ischemic stroke classification using medical data from Morocco. Following the OSEMN approach, our methodology leverages transfer learning with the VGG-16 architecture and employs data augmentation techniques to enhance model performance. Our developed model achieved a remarkable validation accuracy of 90%, surpassing alternative state-of-theart models (ResNet50: 87.0%, InceptionV3: 82.0%, VGG-19: 81.0%). Notably, all models were rigorously evaluated on the same meticulously curated dataset, ensuring fair and consistent comparisons. The investigation underscores VGG-16’s superior performance in distinguishing stroke cases, highlighting its potential as a robust tool for accurate diagnosis. Comparative analyses among popular deep learning architectures not only demonstrate our model’s efficacy but also emphasize the importance of selecting the right architecture for medical image classification tasks. These findings contribute to the growing evidence supporting advanced deep learning techniques in medical imaging. Achieving a validation accuracy of 90%, our model holds significant promise for real-world healthcare applications, showcasing the critical role of cutting-edge technologies in advancing diagnostic accuracy and the transformative potential of deep learning in the medical field. [ABSTRACT FROM AUTHOR]

The agriculture sector plays a very important role in the increasing population, year by year, to fulfill requirements and contributes significantly to the economy of the country. One of the main challenges in agriculture is the prevention and early detection of pest attack on crops. Farmers spend a significant amount of time and money in detecting pests and diseases, often by looking at plant leaves and analyzing the presence of diseases and pests. Late detection of pest attacks and improper use of pesticide application can cause damage to plants and compromise food quality. This problem can be solved through artificial intelligence, machine learning, and accurate image classification systems. In recent years, machine learning has made improvements in image recognition and classification. Hence, in this research article, we used convolutional neural network (CNN)-based models, such as the Cov2D library and VGG-16, to identify pest attacks. Our experiments involved a personal dataset consisting of 7000 images of pest-attacked leaf samples of different positions on maize plants, categorized into two classes. The Google Colab environment was used for experimentation and implementation, specially designed for cloud computing and machine learning. [ABSTRACT FROM AUTHOR]

The COVID-19 disease outbreak resulted in a worldwide pandemic. Currently, the reverse transcription-polymerase chain reaction (RT-PCR), which relies on nasopharyngeal swabs to examine the existence of the ribonucleic acid (RNA) of SARS-CoV-27, is still a popular approach to testing for the disease. Despite the high level of specificity of testing with RT-PCR, the sensitivity of the method could be relatively low, and there is significant variability in efficacy depending on different sampling methods and the time of occurrence of symptoms. It is therefore essential for us to develop a machine-learning algorithm that can analyze computerized tomography images to detect the presence of COVID-19. Besides COVID-19, lung computerized tomography (CT) scan images can detect many other diseases, such as lung cancer, pneumonia, etc. This paper deals with the implementation of an algorithm that takes lung CT scans and lung X-ray images as input and predicts a list of probable diseases and possible diagnoses that infect the lungs. Machine learning algorithms will be able to predict disease by scanning the tiniest of regions easily missed by the human eye. This paper presents a survey of various machine learning algorithms that aid in detecting multiple diseases in lung CT scan images. Apart from the study of standard algorithms best suited for COVID-19 detection, this paper also includes recent trends. One of the major recent trends that can be incorporated into COVID-19 detection is TinyML. Tiny ML is an emerging area in machine learning algorithms that can be used to detect multiple diseases in lung CT scan images with better accuracy and in less time. This tool can aid doctors in their diagnosis and treatment of patients and help increase the efficiency of the treatment process. While understanding the features and mapping them using a hidden layer, there is a probability of compressing the dataset, as well as the model to process and classify the low-bit images in real-time using TinyML. [ABSTRACT FROM AUTHOR]

Agriculture is the backbone of the country’s economy. Sugarcane is a globally important crop and a major source of sugar, ethanol and jaggery. One of the problems faced by the sugar cane industry is the diseases that attack the crops. If these diseases are not identified early, they may result in exterminating the whole crops surrounding them. Manually checking each and every corner of a large farm is physically impossible. Machine learning is the contemporary solution to the problem, which can be resolved using the Convolution Neural Network (CNN) techniques. The drone images of all corners of the farm can be fed into the trained model for distinguishing the health status. For training the model the secondary data is taken from Kaggle, which includes both healthy and unhealthy sugarcane plant images, with various diseases in the unhealthy class. Machine learning models effectively identify early-stage crop diseases. This helps the farmer to treat that part of the affected farm quickly in order to avoid the spread of the disease to the remaining parts of the farm. This study deals with sugarcane disease prediction using the CNN model. Two different layered CNN models (VGG-16 and VGG-19) that were tested. The models were trained based on the images of 2165 containing both healthy and unhealthy leaves. The whole dataset is divided into three parts, validating data, testing data, and training data. The selected model – VGG-19 performed better and was found to be analysing the image up to an accuracy of 92% with 90% precision. [ABSTRACT FROM AUTHOR]

Pneumonia, tuberculosis, and Covid-19 are different lung diseases but have similar characteristics. One of the reasons for the worsening of disease in lung sufferers is a diagnosis that takes a long time. Another factor, the results of the X-ray photos look blurry and lack contracture, causing different diagnostic results of X-ray photos. This research classifies lung images into four categories: normal lungs, tuberculosis, pneumonia, and Covid-19 using the Convolutional Neural Network method and VGG-16 architecture. The results of the research with models and scenarios without pre-trained use data with a ratio of 9:1 at epoch 50, an accuracy of 94%, while the lowest results are in scenarios using data with a ratio of 8:2 at epoch 50, non-pre-trained models, accuracy by 87%.

The recent increase in the prevalence of skin cancer, along with its significant impact on individuals’ lives, has garnered the attention of many researchers in the field of deep learning models, especially following the promising results observed using these models in the medical field. This study aimed to develop a system that can accurately diagnose one of three types of skin cancer: basal cell carcinoma (BCC), melanoma (MEL), and nevi (NV). Additionally, it emphasizes the importance of image quality, as many studies focus on the quantity of images used in deep learning. In this study, transfer learning was employed using the pre-trained VGG-16 model alongside a dataset sourced from Kaggle. Three models were trained while maintaining the same hyperparameters and script to ensure a fair comparison. However, the quantity of data used to train each model was varied to observe specific effects and to hypothesize about the importance of image quality in deep learning models within the medical field. The model with the highest validation score was selected for further testing using a separate test dataset, which the model had not seen before, to evaluate the model’s performance accurately. This work contributes to the existing body of research by demonstrating the critical role of image quality in enhancing diagnostic accuracy, providing a comprehensive evaluation of the VGG-16 model’s performance in skin cancer detection and offering insights that can guide future improvements in the field.

En la búsqueda de soluciones sin contacto físico en espacios cerrados para la verificación de identidad en el contexto de la pandemia por el SARS-CoV-2, el reconocimiento facial ha tomado relevancia. Uno de los retos en este ámbito es la oclusión por mascarilla, ya que oculta más del 50 % del rostro. La presente investigación evaluó cuatro modelos preentrenados por aprendizaje por transferencia: VGG-16, RESNET-50, Vision Transformer (ViT) y Swin Transformer, los cuales se entrenaron en sus capas superiores con un conjunto de datos propio. Para el entrenamiento sin mascarilla, se obtuvo un accuracy de 24 % (RESNET-50), 25 % (VGG-16), 96 % (ViT) y 91 % (Swin). En cambio, con mascarilla se obtuvo un accuracy de 32 % (RESNET-50), 53 % (VGG-16), 87 % (ViT) y 61 % (Swin). Estos porcentajes de testing accuracy indican que las arquitecturas más modernas como los transformers arrojan mejores resultados en el reconocimiento con mascarilla que las CNN (VGG-16 y RESNET-50). El aporte de la investigación recae en la experimentación con dos tipos de arquitecturas: CNN y transformers, así como en la creación del conjunto de datos público que se comparte a la comunidad científica. Este trabajo robustece el estado del arte de la visión computacional en el reconocimiento facial por oclusión de una mascarilla, ya que ilustra con experimentos la variación del accuracy con distintos escenarios y arquitecturas.

Malware is intentionally designed to damage computers, servers, clients or computer networks. Malware is a general term used to describe any program designed to harm a computer or server. The goal is to commit a crime, such as gaining unauthorized access to a particular system, so as to compromise user security. Most malware still uses the same code to produce another different form of malware variants. Therefore, the ability to classify similar malware variant characteristics into malware families is a good strategy to stop malware. The research is useful for classifying malware on malware samples presented as bytemap grayscale images. The malware classification research focused on 25 malware classes with a total of 9,029 images from the Malimg dataset. This research implements the VGG-16 and InceptionResNet-V2 architectures by running 2 different scenarios, scenario 1 uses the original dataset and the other scenario uses the undersampled dataset. After building the model, each scenario will get an evaluation form such as accuracy, precision, recall, and f1-score. The highest score was obtained in scenario 2 on the VGG-16 method with a score of 94.8% and the lowest in scenario 2 on the InceptionResNet-V2 method with a score of 85.1%.

Corn is one of the substitute staple foods in Indonesia after rice. Maize crops grown in Indonesia often experience considerable losses due to maize plant diseases. Generally, plant diseases are initially caused by morphological changes in the leaves. Accurate detection and classification of diseases that appear on the leaves will prevent the widespread spread of the disease. This study will compare classification algorithms, namely Support Vector Machine, K-Nearest Neighbors, and Multilayer Perceptron to find the best algorithm in the classification of leaf disease in corn plants, namely, cercospora leaf spot gray, common rust, and northern leaf blight using the VGG-16 deep learning model used as image feature extraction. The results showed that the Multilayer Perceptron algorithm produced the best values with accuracy, precision, and recall of 97.4% each.

Background and Objective: Bone tumors present significant challenges in orthopedic medicine due to variations in clinical treatment approaches for different tumor types, which includes benign, malignant, and intermediate cases. Convolutional Neural Networks (CNNs) have emerged as prominent models for tumor classification. However, their limited perception ability hinders the acquisition of global structural information, potentially affecting classification accuracy. To address this limitation, we propose an optimized deep learning algorithm for precise classification of diverse bone tumors. Materials and Methods: Our dataset comprises 786 computed tomography (CT) images of bone tumors, featuring sections from two distinct bone species, namely the tibia and femur. Sourced from The Second Affiliated Hospital of Fujian Medical University, the dataset was meticulously preprocessed with noise reduction techniques. We introduce a novel fusion model, VGG16-ViT, leveraging the advantages of the VGG-16 network and the Vision Transformer (ViT) model. Specifically, we select 27 features from the third layer of VGG-16 and input them into the Vision Transformer encoder for comprehensive training. Furthermore, we evaluate the impact of secondary migration using CT images from Xiangya Hospital for validation. Results: The proposed fusion model demonstrates notable improvements in classification performance. It effectively reduces the training time while achieving an impressive classification accuracy rate of 97.6%, marking a significant enhancement of 8% in sensitivity and specificity optimization. Furthermore, the investigation into secondary migration's effects on experimental outcomes across the three models reveals its potential to enhance system performance. Conclusion: Our novel VGG-16 and Vision Transformer joint network exhibits robust classification performance on bone tumor datasets. The integration of these models enables precise and efficient classification, accommodating the diverse characteristics of different bone tumor types. This advancement holds great significance for the early detection and prognosis of bone tumor patients in the future.

The use of the internet is increasing all over theworld on a daily basis in the last two decades. The increase in the internet causes many sexual crimes, such as sexual misuse, domestic violence, and child pornography. Various research has been done for pornographic image detection and classification. Most of the used models used machine learning techniques and deep learning models which show less accuracy, while the deep learning model ware used for classification and detection performed better as compared to machine learning. Therefore, this research evaluates the performance analysis of intelligent neural-based deep learning models which are based on Convolution neural network (CNN), Visual geometry group (VGG-16), VGG-14, and Residual Network (ResNet-50) with the expanded dataset, trained using transfer learning approaches applied in the fully connected layer for datasets to classify rank (Pornographic vs. Nonpornographic) classification in images. The simulation result shows that VGG-16 performed better than the used model in this study without augmented data. The VGG-16 model with augmented data reached a training and validation accuracy of 0.97, 0.94 with a loss of 0.070, 0.16. The precision, recall, and f-measure values for explicit and non-explicit images are (0.94, 0.94, 0.94) and (0.94, 0.94, 0.94). Similarly, The VGG-14 model with augmented data reached a training and validation accuracy of 0.98, 0.96 with a loss of 0.059, 0.11. The f-measure, recall, and precision values for explicit and non-explicit images are (0.98, 0.98, 0.98) and (0.98, 0.98, 0.98). The CNN model with augmented data reached a training and validation accuracy of 0.776 & 0.78 with losses of 0.48 & 0.46. The f-measure, recall, and precision values for explicit and non-explicit images are (0.80, 0.80, 0.80) and (0.78, 0.79, 0.78). The ResNet-50 model with expanded data reached with training accuracy of 0.89 with a loss of 0.389 and 0.86 of validation accuracy and a loss of 0.47. The f-measure, recall, and precision values for explicit and non-explicit images are (0.86, 0.97, 0.91) and (0.86, 0.93, 0.89). Where else without augmented data the VGG-16 model reached a training and validation accuracy of 0.997, 0.986 with a loss of 0.008, 0.056. The f-measure, recall, and precision values for explicit and non-explicit images are (0.94, 0.99, 0.97) and (0.99, 0.93, 0.96) which outperforms the used models with the augmented dataset in this study. [ABSTRACT FROM AUTHOR]

Flat foot is a postural deformity in which the plantar part of the foot is either completely or partially contacted with the ground. In recent clinical practices, X-ray radiographs have been introduced to detect flat feet because they are more affordable to many clinics than using specialized devices. This research aims to develop an automated model that detects flat foot cases and their severity levels from lateral foot X-ray images by measuring three different foot angles: the Arch Angle, Meary's Angle, and the Calcaneal Inclination Angle. Since these angles are formed by connecting a set of points on the image, Template Matching is used to allocate a set of potential points for each angle, and then a classifier is used to select the points with the highest predicted likelihood to be the correct point. Inspired by literature, this research constructed and compared two models: a Convolutional Neural Network-based model and a Random Forest-based model. These models were trained on 8000 images and tested on 240 unseen cases. As a result, the highest overall accuracy rate was 93.13% achieved by the Random Forest model, with mean values for all foot types (normal foot, mild flat foot, and moderate flat foot) being: 93.38 precision, 92.56 recall, 96.46 specificity, 95.42 accuracy, and 92.90 F-Score. The main conclusions that were deduced from this research are: (1) Using transfer learning (VGG-16) as a feature-extractor-only, in addition to image augmentation, has greatly increased the overall accuracy rate. (2) Relying on three different foot angles shows more accurate estimations than measuring a single foot angle. [ABSTRACT FROM AUTHOR]

Copyright of Baghdad Science Journal is the property of Republic of Iraq Ministry of Higher Education & Scientific Research (MOHESR) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Kanker kulit benign (jinak) dan malignant (ganas) merupakan jenis kanker kulit yang sering dijumpai. Tanda-tanda kanker kulit penting untuk diketahui dengan diagnosis dini agar dapat diberikan penanganan yang tepat, sehingga dapat mengurangi tingkat kematian penderitanya. Citra dermoskopi menjadi salah satu media diagnosis yang telah banyak dikembangkan oleh peneliti. Analisis citra dermoskopi memberikan hasil lebih optimal dalam diagnosis berbasis komputasi dibandingkan deteksi visual. Model yang berhasil diterapkan dalam diagnosis berbasis komputasi tersebut di antaranya deep learning dan transfer learning, tetapi masih diperlukan optimalisasi. Pada penelitian ini, dilakukan klasifikasi citra dermoskopi kanker kulit ke dalam dua kelas (benign dan malignant) dengan memanfaatkan transfer learning. Untuk meningkatkan akurasi penelitian yang telah dilakukan sebelumnya pada dataset publik dari Kaggle dengan jumlah 3.297 citra, penelitian ini menggunakan 2.000 citra. Penelitian ini membandingkan dua pre-trained model, yaitu VGG-16 dan residual network (ResNet)-50 yang digunakan sebagai feature extractor. Selanjutnya dilakukan fine-tuning dengan menambahkan flatten layer, dua dense layer dengan fungsi aktivasi ReLU, dan satu dense layer dengan fungsi aktivasi Softmax untuk melakukan klasifikasi ke dalam dua kelas. Hyper parameter tuning pada optimizer, batch size, learning rate, dan epoch dilakukan untuk mendapatkan kombinasi parameter dengan kinerja terbaik pada masing-masing model. Sebelum dilakukan hyper parameter tuning, model diuji dengan resize citra masukan menggunakan ukuran yang berbeda-beda. Hasil pengujian model menggunakan citra uji pada model VGG-16 memberikan kinerja terbaiknya pada ukuran citra 128 × 128 piksel dengan kombinasi parameter Adam sebagai optimizer, batch size 64, learning rate 0,001, dan epoch 10 dengan nilai akurasi 91% dan loss 0,2712. Model ResNet-50 memberikan akurasi yang lebih baik, yaitu 94%, dan loss 0,2198 dengan parameter optimizer RMSprop, batch size 64, learning rate 0,0001, dan epoch 100. Hasil pengujian ini menunjukkan bahwa metode yang diusulkan memberikan akurasi yang baik dan dapat membantu dermatologi dalam deteksi dini kanker kulit.

Early diagnosis and treatment of tomato leaf diseases increase a plant's production volume, efficiency, and quality. Misdiagnosis of disease by farmers can lead to an inadequate treatment strategy that hurts the tomato plants and agroecosystem. Therefore, it is crucial to detect the disease precisely. Finding a rapid, accurate approach to take care of the issue of misdiagnosis and early disease identification will be advantageous to the farmers. This study proposed a lightweight custom convolutional neural network (CNN) model and utilized transfer learning (TL)-based models VGG-16 and VGG-19 to classify tomato leaf diseases. In this study, eleven classes, one of which is healthy, are used to simulate various tomato leaf diseases. In addition, an ablation study has been performed in order to find the optimal parameters for the proposed model. Furthermore, evaluation metrics have been used to analyze and compare the performance of the proposed model with the TL-based model. The proposed model, by applying data augmentation techniques, has achieved the highest accuracy and recall of 95.00% among all the models. Finally, the best-performing model has been utilized in order to construct a Web-based and Android-based end-to-end (E2E) system for tomato cultivators to classify tomato leaf disease.

Indoor localization methods can help many sectors, such as healthcare centers, smart homes, museums, warehouses, and retail malls, improve their service areas. As a result, it is crucial to look for low-cost methods that can provide exact localization in indoor locations. In this context, imagebased localization methods can play an important role in estimating both the position and the orientation of cameras regarding an object. Image-based localization faces many issues, such as image scale and rotation variance. Also, image-based localization's accuracy and speed (latency) are two critical factors. This paper proposes an efficient 6-DoF deep-learning model for image-based localization. This model incorporates the channel attention module and the Scale PyramidModule (SPM). It not only enhances accuracy but also ensures the model's real-time performance. In complex scenes, a channel attention module is employed to distinguish between the textures of the foregrounds and backgrounds. Our model adapted an SPM, a feature pyramid module for dealing with image scale and rotation variance issues. Furthermore, the proposed model employs two regressions (two fully connected layers), one for position and the other for orientation, which increases outcome accuracy. Experiments on standard indoor and outdoor datasets show that the proposed model has a significantly lower Mean Squared Error (MSE) for both position and orientation. On the indoor 7-Scenes dataset, the MSE for the position is reduced to 0.19 m and 6.25° for the orientation. Furthermore, on the outdoor Cambridge landmarks dataset, the MSE for the position is reduced to 0.63 m and 2.03° for the orientation. According to the findings, the proposed approach is superior and more successful than the baseline methods. [ABSTRACT FROM AUTHOR]

Malignant brain tumours are extremely frequent and deadly, and if they are not found in their early stages, they can shorten a person’s lifespan. After the tumour has been detected, it is essential to classify the tumour in order to develop a successful treatment strategy. This study aims to investigate the three deep learning tools, VGG-16 ResNet50 and AlexNet in order to detect brain tumor using MRI images. The results performance are then evaluated and compared using accuracy, precision and recall criteria. The dataset used contained 155 MRI images which are images with tumors, and 98 of them are nontumors. The AlexNet model perform extremely well on the dataset with 96.10% accuracy, while VGG-16 achieved 94.16% and ResNet-50 achieved 91.56%. The early diagnosis of cancers before they develop physical side effects like paralysis and other problems is positively impacted by these accuracy. [ABSTRACT FROM AUTHOR]

Identifying events using surveillance videos is a major source that reduces crimes and illegal activities. Specifically, abnormal event detection gains more attention so that immediate responses can be provided. Video processing using conventional techniques identifies the events but fails to categorize them. Recently deep learning-based video processing applications provide excellent performances however the architecture considers either spatial or temporal features for event detection. To enhance the detection rate and classification accuracy in abnormal event detection from video keyframes, it is essential to consider both spatial and temporal features. Earlier approaches consider any one of the features from keyframes to detect the anomalies from video frames. However, the results are not accurate and prone to errors sometimes due to video environmental and other factors. Thus, two-stream hybrid deep learning architecture is presented to handle spatial and temporal features in the video anomaly detection process to attain enhanced detection performances. The proposed hybrid models extract spatial features using YOLO-V4 with VGG-16, and temporal features using optical FlowNet with VGG-16. The extracted features are fused and classified using hybrid CNN-LSTM model. Experimentation using benchmark UCF crime dataset validates the proposed model performances over existing anomaly detection methods. The proposed model attains maximum accuracy of 95.6% which indicates better performance compared to state-of-the-art techniques. [ABSTRACT FROM AUTHOR]

Innovation and rapid increased functionality in user friendly smartphones has encouraged shutterbugs to have picturesque image macros while in work environment or during travel. Formal signboards are placed with marketing objectives and are enriched with text for attracting people. Extracting and recognition of the text from natural images is an emerging research issue and needs consideration. When compared to conventional optical character recognition (OCR), the complex background, implicit noise, lighting, and orientation of these scenic text photos make this problem more difficult. Arabic language text scene extraction and recognition adds a number of complications and difficulties. The method described in this paper uses a two-phase methodology to extract Arabic text and word boundaries awareness from scenic images with varying text orientations. The first stage uses a convolution autoencoder, and the second uses Arabic Character Segmentation (ACS), which is followed by traditional two-layer neural networks for recognition. This study presents the way that how can an Arabic training and synthetic dataset be created for exemplify the superimposed text in different scene images. For this purpose a dataset of size 10K of cropped images has been created in the detection phase wherein Arabic text was found and 127k Arabic character dataset for the recognition phase. The phase-1 labels were generated from an Arabic corpus of quotes and sentences, which consists of 15kquotes and sentences. This study ensures that Arabic Word Awareness Region Detection (AWARD) approach with high flexibility in identifying complex Arabic text scene images, such as texts that are arbitrarily oriented, curved, or deformed, is used to detect these texts. Our research after experimentations shows that the system has a 91.8% word segmentation accuracy and a 94.2% character recognition accuracy. We believe in the future that the researchers will excel in the field of image processing while treating text images to improve or reduce noise by processing scene images in any language by enhancing the functionality of VGG-16 based model using Neural Networks. [ABSTRACT FROM AUTHOR]

Pneumonia, tuberculosis, and Covid-19 are different lung diseases but have similar characteristics. One of the reasons for the worsening of disease in lung sufferers is a diagnosis that takes a long time. Another factor, the results of the X-ray photos look blurry and lack contracture, causing different diagnostic results of X-ray photos. This research classifies lung images into four categories: normal lungs, tuberculosis, pneumonia, and Covid-19 using the Convolutional Neural Network method and VGG-16 architecture. The results of the research with models and scenarios without pre-trained use data with a ratio of 9:1 at epoch 50, an accuracy of 94%, while the lowest results are in scenarios using data with a ratio of 8:2 at epoch 50, non-pre-trained models, accuracy by 87%. [ABSTRACT FROM AUTHOR]

This comparative study evaluates the performance of three popular deep learning architectures, AlexNet, VGG-16, and VGG-19, on a custom-made dataset of GPR C-scans collected from several archaeological sites. The introduced dataset has 15,000 training images and 3750 test images assigned to three classes: Anomaly, Noise, and Structure. The aim is to assess the performance of the selected architectures applied to the custom dataset and examine the potential gains of using deeper and more complex architectures. Further, this study aims to improve the training dataset using augmentation techniques. For the comparisons, learning curves, confusion matrices, precision, recall, and f1-score metrics are employed. The Grad-CAM technique is also used to gain insights into the models' learning. The results suggest that using more convolutional layers improves overall performance. Further, augmentation techniques can also be used to increase the dataset volume without causing overfitting. In more detail, the best-obtained model was trained using VGG-19 architecture and the modified dataset, where the training samples were raised to 60,000 images through augmentation techniques. This model reached a classification accuracy of 94.12% on an evaluation set with 170 unseen data. [ABSTRACT FROM AUTHOR]

About 1.5 million women are diagnosed with breast cancer every year, making it the most frequent disease among women. In Pakistan, one woman in every nine has a lifetime chance of being diagnosed with breast cancer, making it the country with the highest incidence rate of breast cancer in Asia. The mortality rate from breast cancer in Pakistan was 22.7% in 2020. A lack of resources, such as competent pathologists, causes a delay in diagnosis and inadequate therapy planning, all of which contribute to a dismal survival rate. End-to-end solutions that may be implemented into computer-aided diagnostic (CAD) systems have been developed by medical professionals and researchers using domain-specific artificial intelligence (AI) technologies, most notably deep learning models, to address this critical issue. By increasing the amount of work for pathologists, these AI models may help in breast cancer detection and diagnosis. The goal of this research was to compare and contrast the effectiveness of many recent convolutional neural network (CNN) designs. Five pre-trained and fine-tuned deep CNN architectures, InceptionV3, ResNet152V2, MobileNetV2, VGG-16, and DenseNet-121, are tested to determine the best-performing model. The goal is to discover which models are preferable in terms of accuracy and effectiveness. Notably, the pre-trained InceptionV3 model outperforms the basic CNN model by 9%, with a high accuracy level of 94%. ResNet152V2 got 95% accuracy, and MobileNetV2 got 97% accuracy. The VGG-16 model outperforms the competition with a remarkable 98% accuracy rate. Following suit, the DenseNet-121 model achieves a remarkable 99% accuracy. These findings highlight the utility of deep learning models in the diagnosis of breast cancer as well as the range of model precision.

Brain tumors are serious conditions caused by uncontrolled and abnormal cell division. Tumors can have devastating implications if not accurately and promptly detected. Magnetic resonance imaging (MRI) is one of the methods frequently used to detect brain tumors owing to its excellent resolution. In the past few decades, substantial research has been conducted in the field of classifying brain images, ranging from traditional methods to deep-learning techniques such as convolutional neural networks (CNN). To accomplish classification, machine-learning methods require manually created features. In contrast, CNN achieves classification by extracting visual features from unprocessed images. The size of the training dataset had a significant impact on the features that CNN extracts. The CNN tends to overfit when its size is small. Deep CNNs (DCNN) with transfer learning have therefore been developed. The aim of this work was to investigate the brain MR image categorization potential of pre-trained DCNN VGG-19, VGG-16, ResNet50, and Inception V3 models using data augmentation and transfer learning techniques. Validation of the test set utilizing accuracy, recall, Precision, and F1 score showed that the pre-trained VGG-19 model with transfer learning exhibited the best performance. In addition, these methods offer an end-to-end classification of raw images without the need for manual attribute extraction. [ABSTRACT FROM AUTHOR]

Knee osteoarthritis is a challenging problem affecting many adults around the world. There are currently no medications that cure knee osteoarthritis. The only way to control the progression of knee osteoarthritis is early detection. Currently, X-ray imaging is a central technique used for the prediction of osteoarthritis. However, the manual X-ray technique is prone to errors due to the lack of expertise of radiologists. Recent studies have described the use of automated systems based on machine learning for the effective prediction of osteoarthritis from X-ray images. However, most of these techniques still need to achieve higher predictive accuracy to detect osteoarthritis at an early stage. This paper suggests a method with higher predictive accuracy that can be employed in the real world for the early detection of knee osteoarthritis. In this paper, we suggest the use of transfer learning models based on sequential convolutional neural networks (CNNs), Visual Geometry Group 16 (VGG-16), and Residual Neural Network 50 (ResNet-50) for the early detection of osteoarthritis from knee X-ray images. In our analysis, we found that all the suggested models achieved a higher level of predictive accuracy, greater than 90%, in detecting osteoarthritis. However, the best-performing model was the pretrained VGG-16 model, which achieved a training accuracy of 99% and a testing accuracy of 92%. [ABSTRACT FROM AUTHOR]

Alzheimer Disease (AD) is the ordinary type of dementia which does not have any proper and efficient medication. Accurate classification and detection of AD helps to diagnose AD in an earlier stage, for that purpose machine learning and deep learning techniques are used in AD detection which observers both normal and abnormal brain and accurately detect AD in an early. For accurate detection of AD, we proposed a novel approach for detecting AD using MRI images. The proposed work includes three processes such as trilevel pre-processing, swin transfer based segmentation, and multi-scale feature pyramid fusion module-based AD detection. In pre-processing, noises are removed from the MRI images using Hybrid KuanFilter and Improved Frost Filter (HKIF) algorithm, the skull stripping is performed by Geodesic Active Contour (GAC) algorithm which removes the non-brain tissues that increases detection accuracy. Here, bias field correction is performed by Expectation-Maximization (EM) algorithm which removes the intensity non-uniformity. After completed pre-processing, we initiate segmentation process using Swin Transformer based Segmentation using Modified U-Net and Generative Adversarial Network (ST-MUNet) algorithm which segments the gray matter, white matter, and cerebrospinal fluid from the brain images by considering cortical thickness, color, texture, and boundary information which increases segmentation accuracy. The simulation of this research is conducted by Matlab R2020a simulation tool, and the performance of this research is evaluated by ADNI dataset in terms of accuracy, specificity, sensitivity, confusion matrix, and positive predictive value. [ABSTRACT FROM AUTHOR]

Tyre pressure monitoring systems (TPMS) are electronic devices that monitor tyre pressure in vehicles. Existing systems rely on wheel speed sensors or pressure sensors. They rely on batteries and radio transmitters, which add to the expense and complexity. There are two types of basic tyres: non-pneumatic and pneumatic tyres. Non-pneumatic tyres lack air and combine the tyre and wheel into a single unit. When it comes to noise reduction, durability, and shock absorption, pneumatic tyres are more valuable than non-pneumatic tyres. In this study, nitrogen-filled pneumatic tyres were considered due to the uniform pressure management property. Additionally, nitrogen has less of an effect on thermal expansion than regular air-filled tyres. This work aimed to offer a deep learning approach for TPMS. An accelerometer captured vertical vibrations from a moving vehicle's wheel hub, which were then converted in the form of vibration plots and categorized using pretrained networks. The most popular pretrained networks such as AlexNet, GoogLeNet, ResNet-50 and VGG-16 were employed in this study. From these pretrained networks, the best-performing pretrained network was determined and suggested for TPMS by varying the hyperparameters such as learning rate (LR), batch size (BS), train-test split ratio (TR), and solver (SR). Findings: A higher classification accuracy of 97.20% was obtained while using ResNet-50. [ABSTRACT FROM AUTHOR]

The deep dream is one of the most recent techniques in deep learning. It is used in many applications, such as decorating and modifying images with motifs and simulating the patients' hallucinations. This study presents a deep dream model that generates deep dream images using a convolutional neural network (CNN). Firstly, we survey the layers of each block in the network, then choose the required layers, and extract their features to maximize it. This process repeats several iterations as needed, computes the total loss, and extracts the final deep dream images. We apply this operation on different layers two times; the former is on the low-level layers, and the latter is on the high-level layers. The results of applying this operation are different, where the resulting image from applying deep dream on the high-level layers are clearer than those resulting from low-level layers. Also, the loss of the images of low-level layers ranges between 31.1435 and 31.1435, while the loss of the images of upper layers ranges between 20.0704 and 32.1625. [ABSTRACT FROM AUTHOR]

Convolutional neural networks (CNNs) are widely implemented in modern facial recognition systems for image recognition applications. Runtime speed is a critical parameter for real-time systems. Traditional FPGA-based accelerations require either large on-chip memory or high bandwidth and high memory access time that slow down the network. The proposed work uses an algorithm and its subsequent hardware design for a quick CNN computation using an overlap-and-add-based technique in the time domain. In the algorithm, the input images are broken into tiles that can be processed independently without computing overhead in the frequency domain. This also allows for efficient concurrency of the convolution process, resulting in higher throughput and lower power consumption. At the same time, we maintain low on-chip memory requirements necessary for faster and cheaper processor designs. We implemented CNN VGG-16 and AlexNet models with our design on Xilinx Virtex-7 and Zynq boards. The performance analysis of our design provides 48% better throughput than the state-of-the-art AlexNet and uses 68.85% lesser multipliers and other resources than the state-of-the-art VGG-16.

Skin cancer is a severe and potentially lethal disease, and early detection is critical for successful treatment. Traditional procedures for diagnosing skin cancer are expensive, time-intensive, and necessitate the expertise of a medical practitioner. In recent years, many researchers have developed artificial intelligence (AI) tools, including shallow and deep machine learning-based approaches, to diagnose skin cancer. However, AI-based skin cancer diagnosis faces challenges in complexity, low reproducibility, and explainability. To address these problems, we propose a novel Grid-Based Structural and Dimensional Explainable Deep Convolutional Neural Network for accurate and interpretable skin cancer classification. This model employs adaptive thresholding for extracting the region of interest (ROI), using its dynamic capabilities to enhance the accuracy of identifying cancerous regions. The VGG-16 architecture extracts the hierarchical characteristics of skin lesion images, leveraging its recognized capabilities for deep feature extraction. Our proposed model leverages a grid structure to capture spatial relationships within lesions, while the dimensional features extract relevant information from various image channels. An Adaptive Intelligent Coney Optimization (AICO) algorithm is employed for self-feature selected optimization and fine-tuning the hyperparameters, which dynamically adapts the model architecture to optimize feature extraction and classification. The model was trained and tested using the ISIC dataset of 10,015 dermascope images and the MNIST dataset of 2357 images of malignant and benign oncological diseases. The experimental results demonstrated that the model achieved accuracy and CSI values of 0.96 and 0.97 for TP 80 using the ISIC dataset, which is 17.70% and 16.49% more than lightweight CNN, 20.83% and 19.59% more than DenseNet, 18.75% and 17.53% more than CNN, 6.25% and 6.18% more than Efficient Net-B0, 5.21% and 5.15% over ECNN, 2.08% and 2.06% over COA-CAN, and 5.21% and 5.15% more than ARO-ECNN. Additionally, the AICO self-feature selected ECNN model exhibited minimal FPR and FNR of 0.03 and 0.02, respectively. The model attained a loss of 0.09 for ISIC and 0.18 for the MNIST dataset, indicating that the model proposed in this research outperforms existing techniques. The proposed model improves accuracy, interpretability, and robustness for skin cancer classification, ultimately aiding clinicians in early diagnosis and treatment.