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.

Farming has many moving parts, including planting, watering, harvesting, and more. One of their most complex and time-consuming is keeping an eye out for and controlling weeds that might ruin a harvest. Unwanted weeds cause decreased crop productivity by competing with desired agricultural plants for water, sunshine, and soil nutrients. This research aims to use Region-Based Convolutional Neural Networks (RCNNs) to detect weeds in photographs of sesame crops and then classify them into their respective weed families. Object detection is a promising use of deep learning, and the suggested method takes advantage of RCNNs, a prominent method. By applying RCNNs to sesame crop images, we could accurately identify the presence of weeds, achieving an impressive detection accuracy of 96.84%. This high accuracy can significantly aid farmers in pinpointing areas of their fields that require immediate attention and weed management strategies. Furthermore, after successfully detecting weeds, we classified them into different types. This classification step is crucial as different weed species require specific control measures. Our proposed methodology achieved an outstanding weed classification accuracy of 97.79%. By correctly categorizing weeds, farmers better understand the weed composition in their fields, making it easier to use targeted control methods and lessen the use of possibly dangerous chemicals with a wide range of effects. [ABSTRACT FROM AUTHOR]

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]

To solve the problem of how to obtain important information from fuzzy distorted images, an intelligent method for extracting salient objects from fuzzy distorted images based on multi-scale convolution is proposed. A multi-scale deformation feature convolution network is established to extract the salient features of fuzzy distorted images. Among them, the multi-scale convolution network VGG-16 extracts the shallow features of the fuzzy distortion image through the convolution layer operation, uses the multi-scale convolution kernel to extract the fuzzy distortion image in parallel, and introduces the self-attention mechanism to make the extracted features more relevant, Input the fused features into the proposed area extraction network, Through the target area detection network, the proposed target area of the fuzzy distortion image is classified and position regression is performed to obtain the final salient target of the fuzzy distortion image. The experimental results show that this method can accurately recognize the contour of salient objects, and extract salient objects from fuzzy distorted images; The extracted salient objects have high accuracy, low mean square error and similarity of 92.9% with the original image; For the salient target extraction in various scenarios, it shows high advantages. [ABSTRACT FROM AUTHOR]

One of the most common life-threatening diseases, the brain tumor is a condition characterized by the rapid proliferation of abnormal cells that leads to the destruction of healthy brain cells. Its aggressive nature can result in a patient succumbing to the disease before an accurate diagnosis is achieved. Timely detection is crucial to effective treatment and patient survival. Similarly, early detection plays a pivotal role in the case of brain tumors, where swift identification is vital to providing optimal care and increasing the chances of patient recovery. Streamlining the complex process of brain tumor detection is a significant undertaking that aims to simplify and expedite the procedure, ultimately contributing to saving valuable time and enhancing patient outcomes. The proposed model, a modified VGG-16, facilitates faster and more accurate identification of abnormal brain cells, leading to early detection of brain tumors. A novel multihead self-attention mechanism is used in the modified VGG-16 architecture to improve tumor detection performance. The proposed model performs better than other state-of-the-art models, such as normal VGG-16, ResNet-50, and EfficientNet. [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.

Hyperspectral imaging is a crucial technology of remote sensing that captures hundreds of continuous spectral bands. In hyperspectral image (HSI) classification, pixels of HSI are classified into a particular class. HSI classification methods face challenges due to high dimensional data and the small number of labeled samples available. Recent years have witnessed impressive advancements in HSI classification using deep learning models. This research proposes an innovative method that uses a pretrained convolutional neural network (CNN) to extract robust spatial features from the HSI to assist in classification. Our strategy begins with the principal component analysis for spectral dimensionality reduction, then moves on to the pretrained CNN model for spatial feature extraction, and finally, utilizes a support vector machine (SVM) as the classifier. We conducted tests using three widely-used pretrained CNNs, namely AlexNet, VGG-16, and GoogLeNet, on three different HSI datasets (Indian Pines, University of Pavia, and Salinas) to assess the effectiveness of our approach. The results reveal that the proposed model achieves better performance. Specifically, when utilizing the VGG-16 model for feature extraction on the Salinas dataset, our model achieves an overall accuracy of 99.12%, an average accuracy of 99.40%, and a Kappa coefficient of 0.9901. Furthermore, we compare our results with other commonly used HSI classification methods, highlighting the superior performance of our proposed model. [ABSTRACT FROM AUTHOR]

Cucumber (Cucumis sativus) is a significant horticultural crop worldwide, highly valued for both fresh consumption and processing. However, cucumber cultivation faces challenges due to diseases that can substantially reduce yield and quality. Diseases like leaf spots, stem wilt, and fruit rot are caused by pathogens including viruses, bacteria, and fungi. Traditionally, disease detection in cucumbers is performed manually, which is time-consuming and inefficient. Therefore, developing machine vision-based models using Deep Learning (DL) and Machine Learning (ML) for early disease detection through image analysis is crucial for assisting farmers. While many studies on plant disease classification using various DL and ML models show optimal results, research on cucumbers has mostly focused on leaf diseases. This study aims to optimize cucumber disease image classification by developing a model that combines Local Binary Pattern (LBP) texture features and VGG-16 convolutional features. The dataset used, Cucumber Disease Recognition Dataset consists of 8 classes of cucumber plant disease images covering leaves, stems, and fruits. This study classifies cucumber plant disease images using Random Forest (RF) combined with LBP texture features and VGG-16 visual features and compares its performance with models using VGG-16, LBP+RF, and VGG-16+RF on the same dataset. The results show that the proposed model achieved a precision of 84.7%, recall of 84%, F1-Score of 83.8%, and accuracy of 84%. These results outperform the comparative models, demonstrating the effectiveness of the combined approach in classifying cucumber plant diseases. [ABSTRACT FROM AUTHOR]

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]

In recent years, numerous deep learning architectures have used publicly available/author-generated datasets to classify plant diseases. This study suggested a four-stage process for classifying plant diseases using a comparative evaluation method based on deep learning. First, the ideal CNN was found by comparing basic CNN designs with adapted and hybrid versions of contemporary DL models. Second, we tried to train the best acquired model through Adam deep learning optimizers to increase its performance. Xception and VGG-16 architecture were compared using a number of different performance criteria. These metrics included validation accuracy/loss, F1-score, precision, recall, AuC and RoC. All of the chosen DL architectures were trained on three leaf species such as tomato, potato and bell pepper of the PlantVillage dataset, which includes information about 26 unique diseases that have been seen in 14 distinct plant species. To train deep learning architectures, we used Keras with TensorFlow as the backend. Overall, the Adam optimizer-trained VGG-16 architecture performed best in terms of training and validation accuracy of (98.42%, 100%, 99.75%) and (91.85%, 97.21% and 98.18%) for dataset-1, dataset-2 and dataset-3 respectively, demonstrating its superiority over prior methods and establishing its unique contribution to the field. This study's proposed method can, therefore, be used in other agricultural applications for detection and categorization in a more open and accurate manner. [ABSTRACT FROM AUTHOR]

Coffee is a widely consumed beverage, and sorting coffee beans is a critical process that ensures high-quality graded coffee products. Coffee beans were graded into nine grades in robusta types. To automate the grading process, a deep learning-based approach was developed using a large dataset of highresolution images and data augmentation techniques. In contrast to previous studies focusing on robusta type graded into six coffee bean grads, our research extends this framework by employing robusta type into nine grades with an outperformed accuracy. The proposed work uses four deep learning models, namely residual network 34(ResNet34), inception version 3 (Inception v3), efficient network Bayesian optimization (EfficientNet-B0), and visual geometry group-16 (VGG-16), where trained and evaluated for coffee bean classification into nine grades. The EfficientNet-B0 model exhibited outperformed accuracy, achieving 100% in distinguishing good and bad coffee beans, even in challenging lighting and background conditions. [ABSTRACT FROM AUTHOR]

The world of technology has dramatically benefited from artificial intelligence's rapid development. Deep learning and machine learning algorithms have attained remarkable success in various applications, including recommendation system, pattern recognition, classification system, etc., where traditional algorithms have failed to fulfill the requirements of humans in real time. A person's thoughts, conduct, and feelings are greatly influenced by their emotions. In this work proposed method for FER is based on existing VGG16 and concatenates additional layers. The model consists of the preprocessing stage based on the median filter and data augmentation, and classification based on pertained VGG16 with transfer learning added four layers to the existing vgg16 that already trained on the ImageNet dataset. The model proposed attained an accuracy of 90% on FER2013 test set. It is observed that the proposed method outperformed the previous works. [ABSTRACT FROM AUTHOR]

Tailoring a deep convolutional neural network (DCNN) is a tedious and time-consuming task in the field of medical image analysis. In this research paper, Deep-generative adversial neural network (Deep-GAN) based model is proposed using grid search optimization (GSO) technique for identification and classification of thyroid nodule. The main objective of this work is to propose a deep learning (DL) model for the identification and classification of thyroid nodules without user or specialist intervention. The proposed model has gone through four phases namely (i) data acquisition, (ii) pre-processing (iii) data augmentation using GAN technique and (iv) optimization and classification using Deep-GAN model. Two pre-trained architectures namely Alex-Net and Visual Geometry Group (VGG-16) are considered for the identification and classification of thyroid nodule in ultrasonography (USG) images. From the experiment, it is found that Alex-GAN model has shown an improvement of 2 to 4 percentage points in comparison with VGG-GAN model and reported literature on Thyroid digital image database (TDID) public and collected dataset. [ABSTRACT FROM AUTHOR]

During this digital era, substantial visual data is being generated by various multimedia sources. A technique is urgently required to provide a clear and accurate summary of the original video to highlight the most informative segments of the video content. However, the varying video resolution, multi-dimensional feature representation, and massive storage create difficulties in key frame extraction techniques. As a result, many unnecessary features of the videos must be dropped to count their unique qualities. Therefore, a novel deep learning-based approach is proposed where frames are first retrieved using 25 frames per second; then, objects are detected on extracted frames using YOLOv5, and the frames with the target object only are processed further to overcome time consumption and high-speed computing hardware limitations. Further features are obtained using VGG-16 and object of Interest (OoI) based ResNet-50, respectively, and comparisons are performed to find the best solution. The extracted features are compressed using Principal Component Analysis (PCA) based on unsupervised Learning, which may efficiently minimize information loss, and potentially reduce dimension. By performing a comprehensive evaluation to obtain the best value of K using the Silhouette score, Candidate frames are extracted with the maximum mean and standard deviation from each K-means algorithm-based cluster. Pearson Correlation Coefficient (PCC) is used as a post- processing step to remove the redundant frames from the candidate frames and final keyframes extraction. The experiment was performed on the benchmark office dataset from industrial surveillance, which outperforms the state-of-the-art models in terms of recall score. [ABSTRACT FROM AUTHOR]

Cardiovascular disease is the leading cause of death globally. This disease causes loss of heart muscles and is also responsible for the death of heart cells, sometimes damaging their functionality. A person's life may depend on receiving timely assistance as soon as possible. Thus,minimizing the death ratio can be achieved by early detection of heart attack (HA) symptoms. In the United States alone, an estimated 610,000 people die fromheart attacks each year, accounting for one in every four fatalities. However, by identifying and reporting heart attack symptoms early on, it is possible to reduce damage and save many lives significantly. Our objective is to devise an algorithm aimed at helping individuals, particularly elderly individuals living independently, to safeguard their lives. To address these challenges, we employ deep learning techniques.We have utilized a vision transformer (ViT) to address this problem.However, it has a significant overhead cost due to its memory consumption and computational complexity because of scaling dot-product attention. Also, since transformer performance typically relies on large-scale or adequate data, adapting ViT for smaller datasets is more challenging. In response, we propose a three-in-one steam model, theMulti-Head Attention Vision Hybrid (MHAVH). Thismodel integrates a real-time posture recognition framework to identify chest pain postures indicative of heart attacks using transfer learning techniques, such as ResNet-50 and VGG-16, renowned for their robust feature extraction capabilities. By incorporatingmultiple heads into the vision transformer to generate additional metrics and enhance heart-detection capabilities, we leverage a 2019 posture-based dataset comprising RGB images, a novel creation by the author that marks the first dataset tailored for posture-based heart attack detection. Given the limited online data availability, we segmented this dataset into gender categories (male and female) and conducted testing on both segmented and original datasets. The training accuracy of our model reached an impressive 99.77%. Upon testing, the accuracy for male and female datasets was recorded at 92.87% and 75.47%, respectively. The combined dataset accuracy is 93.96%, showcasing a commendable performance overall. Our proposed approach demonstrates versatility in accommodating small and large datasets, offering promising prospects for real-world applications. [ABSTRACT FROM AUTHOR]

India is one of the world's leading tea producers, yet more than 70% of the country's tea is consumed domestically. Tea leaf diseases have a significant impact on the quality and yield of tea. So, it is very important to find a more accurate method to identify tea leaf diseases correctly. Due to very limited number of tea leaf images, classification is very difficult. Very frequently overfitting of model occurs. To cope up with this, we applied images augmentation process, that increased dataset nearly fourteen times. But still this number of datasets is not adequate for DL based classification. So, we used here deep learning for feature extraction and machine learning based classifier for classification. In this work, we have proposed a hybrid technique that combines deep learning-based features of augmented dataset with machine learning based classifier for getting better classification result. In proposed work, VGG-16 is used for colour feature extraction from the tea leaf dataset. Based on this feature, model is built and several machine learning-based classifiers like KNN, XGB, Random Forest, and kernelized SVM are employed for classification task. Our proposed model achieved highest classification accuracy with Sigmoid and Linear kernel based SVM and VGG-16 features. The accuracy of proposed model is 96.67%. We compared our proposed work with existing work on tea leaf dataset and found that our model is performing comparatively better. [ABSTRACT FROM AUTHOR]

Several deep learning algorithms have shown amazing performance for existing object detection tasks, but recognizing darker objects is the largest challenge. Moreover, those techniques struggled to detect or had a slow recognition rate, resulting in significant performance losses. As a result, an improved and accurate detection approach is required to address the above difficulty. The whole study proposes a combination of spiked and normal convolution layers as an energy-efficient and reliable object detector model. The proposed model is split into two sections. The first section is developed as a feature extractor, which utilizes pre-trained VGG16, and the second section of the proposal structure is the combination of spiked and normal Convolutional layers to detect the bounding boxes of images. We drew a pre-trained model for classifying detected objects. With state of the art Python libraries, spike layers can be trained efficiently. The proposed spike convolutional object detector (SCOD) has been evaluated on VOC and Ex-Dark datasets. SCOD reached 66.01% and 41.25% mAP for detecting 20 different objects in the VOC-12 and 12 objects in the Ex-Dark dataset. SCOD uses 14 Giga FLOPS for its forward path calculations. Experimental results indicated superior performance compared to Tiny YOLO, Spike YOLO, YOLO-LITE, Tinier YOLO and Center of loc + Xception based on mAP for the VOC dataset. [ABSTRACT FROM AUTHOR]

In recent years, breast cancer is observed to be more prevalent among women. Timely and accurate prediction of the disease enables health care professionals to adopt a strong decision-making system in treatment optimization. Thus, this study employed a deep learning-based strategy for efficient breast cancer diagnosis. In this study, the feature extraction is efficiently performed with the Deep CNN and VGG-16 and the classification process has been processed that intends to classify appropriate features by using the newly introduced CBGAT (CNN-Bi-LSTM-GRU-AM) technique that helps to enhance the accuracy of image recognition and to predict the breast cancer without any human intervention. The complete approach uses MIAS and the CBIS-DDSM dataset for the process of training and for the evaluations. The proposed study aims in minimising the cases of human intervention of breast cancer diagnosis. The approach DL architectures comprising both the Deep CNN and VCG-16, for the process of feature extraction from the breast cancer diagnosis. Further, the proposed approach is embedded with the PCA in enhancing the procedures of feature extraction. This PCA is used in the proposed study as a fusion technique. PCA is used as one of a dimensionality reduction technique, used in capturing the more of exact information from the features. The combination of CNN-Bi-LSTM-GRU-AM classification approach used in the study is considered in analysing the sequential information and in capturing the long-term dependencies also used in focusing the salient features. The Deep-CNN and VCG-16 are incorporated for leveraging the strengths of each of the network, and are used in capturing the range of features. This integration aids in enhancing the representation and the discriminative power of the extracted features. Influencing the use of AM in the classification process is one more an added advantage of the proposed approach. This AM allows the model to be focused on the vita regions of features within the images provided as input.The experimental implementation and performance analysis of the proposed system is undertaken. The accuracy of each proposed classification technique is discussed with respect to their dataset. The analytical outcomes explore that the proposed model is more effective than the traditional methods as the proposed model highlights a higher accuracy rate, F1 score, sensitivity, specificity, and Area under the curve (AUC). The proposed also determined the importance of breast cancer prediction. [ABSTRACT FROM AUTHOR]

The successful implementation of deep learning nets opens up possibilities for various applications in viticulture, including disease detection, plant health monitoring, and grapevine variety identification. With the progressive advancements in the domain of deep learning, further advancements and refinements in the models and datasets can be expected, potentially leading to even more accurate and efficient classification systems for grapevine leaves and beyond. Overall, this research provides valuable insights into the potential of deep learning for agricultural applications and paves the way for future studies in this domain. This work employs a convolutional neural network (CNN)-based architecture to perform grapevine leaf image classification by adapting VGG-16 net and VGG-19 net models and subsequently identifying the optimal performer between the two nets during the classification process. A publicly available dataset comprising 500 images categorized into 5 distinct classes (100 images per class), was utilized in this work. The obtained empirical outcomes demonstrate a remarkable accuracy rate of 99.6% for the VGG-16 net model, while VGG-19 net achieves a 100% accuracy rate. Based on these findings, it can be inferred that VGG-19 net exhibits superior performance in classifying images of grapevine leaves compared to the VGG-16 net. [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]

Early detection of Lung tumors, which is lethal and equally affects men and women, is challenging. In order to decrease mortality rates and raise survival rates, early detection and classification of Lung tumors is essential. However, at the start of 2020, the entire planet would be afflicted with a coronavirus that causes a fatal sickness (COVID-19). CT imaging is a good tool to detect illness among the various COVID-19 screening techniques available. On the other hand, alternative methods of disease detection take a lot of time. Deep learning, a type of machine learning, opens up a wealth of opportunities for investigating and assessing tumor features using CT scans, allowing for improved disease prediction, diagnosis, and classification. Using CNN, DNN, and VGG-16 models, the suggested approach in this research gives unambiguous and accurate categorization. [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]

This study focuses on recognizing and categorizing South Indian Sign Language gestures based on different age groups through transfer learning models. Sign language serves as a natural and expressive communication method for individuals with hearing impairments. The intention of this study is to develop deep transfer learning models, namely Inception-V3, VGG-16, and ResNet-50, to accurately identify and classify double-handed gestures in South Indian languages, like Kannada, Tamil, and Telugu. A dataset comprising 30,000 images of double-handed gestures, with 10,000 images for each considered age group (1-7, 8-25, and 25 and above), is utilized to enhance and modify the models for improved classification performance. Amongst the tested models, Inception-V3 achieves best performance with test precision of 95.20% and validation accuracy of 92.45%, demonstrating its effectiveness in accurately categorizing images of double-handed gestures into ten different classes. [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]

Face image generation plays an important role in generating innovative and unique multimedia content using the GAN model. With these qualities of the GAN model, they have numerous challenges in the human face image generation. The problems encountered in the generation of facial images are like blurriness in images, incomplete details in the generated facial images, high computational power requirements, and so forth. In this manuscript, we proposed a GAN model that utilizes the composite strength of VGG‐16 and ResNet‐50's models to overcome those difficulties. It uses VGG‐16 to build a discriminator model to discriminate between real and fake images. The generator model utilizes a combination of components from the ResNet‐50 and VGG‐16 models to enhance the image generation process at each iteration, resulting in the creation of realistic face images. The proposed DRFI GAN (Diversified and Realistic Face Image Generation GAN) model's generator achieves an impressive low FID score of 20.50, which is less than existing state‐of‐the‐art approaches. Furthermore, our findings indicate that the images generated by the DRFI GAN model exhibit 10%–15% greater efficiency and realism with reduced training time compared to existing state‐of‐the‐art methods with lower FID scores. [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 amount of video data is growing exponentially on a daily basis. Easily available software or mobile applications offer simple tools to perform the forgery in the video. So, before sending these videos from one place to another, it is important to verify them. In this paper, a forgery detection system is proposed to detect the multiple forgeries in the video using the VGG-16 deep neural model and KPCA (Kernel Principal Component Analysis). The proposed system works in four stages. The preprocessing approach is initially employed to extract and resize video frames. Then, a pre-trained VGG-16 model is tuned to extract the visual features from each input frame. A feature selection methodology, such as KPCA, is applied to minimize the dimensions of extracted features. Finally, correlations distribution among the selected features is analyzed to expose the forgeries. The performance of the proposed system is tested on a forged video dataset. The simulation result reveals that it gives better performance in identifying forgeries in the video, with accuracy and precision of 97.24% and 96.86%, respectively. In addition, the significance of the proposed system is that it yields superior results in post-processing operations like noise addition and adjustments to brightness, contrast, and hue. [ABSTRACT FROM AUTHOR]

The head and neck squamous cell carcinoma (HNSCC) is a group of malignant tumors that typically originates in squamous cells lining mucous membranes of head and neck regions. This paper proposed a hidden markov random field model (HMRFM) and VGG-16 for effective segmentation and classification of head and neck cancer. The preprocessing is done by using the min-max normalization method which improves the model performance and feeds into the segmentation process. In segmentation, the HMRFM is utilized to effectively identify and isolate segments in sequential data which makes it easier to analyze the accurate data from input sequence. The VGG-16 model is fine-tuned by certain convolutional layers which is utilized due to less image dataset and overcome the overfitting issues. This method is evaluated on the HNSCC-3DCT-RT dataset and attains better results with regards to AUC, accuracy, sensitivity, specificity, and F1-score values about 95.2%, 98.7%, 91.4%, 97.5% and 91.5% correspondingly. The obtained result shows that the HMRFM with VGG-16 is better compared to other techniques like Deep CNN with data augmentation, 3D-unet convolutional neural network (CNN), and voted ensemble machine learning (VEML). [ABSTRACT FROM AUTHOR]

Brain tumor presents a complex challenge in modern medical treatment. During the initial stages of tumor growth, radiologists prioritize accurate and efficient analysis for which deep learning has emerged as a valuable tool. In particular, the deep residual network (ResNet), incorporating convolutional neural networks (CNNs) and VGG16, has demonstrated significant success in detecting and categorizing images of tumors. This advancement in deep learning holds the potential to aid radiologists in diagnosing tumors noninvasively. By enhancing comprehension of MRI images and improving training speed and accuracy, deep learning could revolutionize medical research. This study focuses on employing transfer learning with pretrained ResNet50 and VGG16 models to investigate multiclass brain tumor classification. The achieved accuracy rates are noteworthy: 78.32% for VGG16 and 80.10% for ResNet on brain tumor dataset. [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]

Magnetic Resonance Imaging (MRI) is a critical tool in the detection and characterization of brain tumors, offering precise information on tumor location, size, and properties. This information is vital for healthcare professionals to devise personalized treatment plans and select suitable therapeutic approaches while preserving neurological functions. Presented here is an innovative AI-based MRI tumor diagnosis system, accessible to a wide range of medical professionals including radiologists, specialists, and registrars. The system integrates advanced web service applications, providing an improved user experience. The diagnosis system is built utilizindg a Y-Net architecture with transfer learning, demonstrating a classification loss of 0.2152 and an accuracy rate of 0.9075. Remarkably, for segmentation tasks, the system achieves an accuracy of 0.9983, a dice coefficient of 0.9036, and an Intersection over Union (IoU) of 0.8225. Hosted on Amazon's cloud servers, the system is readily available to medical center personnel, ensuring widespread accessibility. For deployment on the Amazon cloud, a virtual machine running the Ubuntu Linux distribution was established, and the training model was successfully deployed online. To bolster the reliability of interactions among various users, the deployment of HTTP/2 for internet connections is recommended. This protocol significantly enhances the handling of substantial MRI data, fostering improved transfer speeds and effective collaboration in the diagnosis and treatment of brain tumors. This implementation culminates in a sophisticated Picture Archiving and Communication System (PACS) with cloud-based functionalities for the storage, retrieval, management, and distribution of medical images and associated patient data. The MRI PACS system guarantees precise and error-minimized interactions among users, excelling in data interchange speed and accuracy. Simultaneously, the system's core AI functionalities, including segmentation, classification, localization, and tumor area calculation, are executed flawlessly, ensuring integrity and no data loss or corruption. [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.