The Coronavirus (COVID-19) has become a critical and extreme epidemic because of its international dissemination. COVID-19 is the world's most serious health, economic, and survival danger. This disease affects not only a single country but the entire planet due to this infectious disease. Illnesses of Covid-19 spread at a much faster rate than usual influenza cases. Because of its high transmissibility and early diagnosis, it isn't easy to manage COVID-19. The popularly used RT-PCR method for COVID-19 disease diagnosis may provide false negatives. COVID-19 can be detected non-invasively using medical imaging procedures such as chest CT and chest x-ray. Deep learning is the most effective machine learning approach for examining a considerable quantity of chest computed tomography (CT) pictures that can significantly affect Covid-19 screening. Convolutional neural network (CNN) is one of the most popular deep learning techniques right now, and its gaining traction due to its potential to transform several spheres of human life. This research aims to develop conceptual transfer learning enhanced CNN framework models for detecting COVID-19 with CT scan images. Though with minimal datasets, these techniques were demonstrated to be effective in detecting the presence of COVID-19. This proposed research looks into several deep transfer learning-based CNN approaches for detecting the presence of COVID-19 in chest CT images.VGG16, VGG19, Densenet121, InceptionV3, Xception, and Resnet50 are the foundation models used in this work. Each model's performance was evaluated using a confusion matrix and various performance measures such as accuracy, recall, precision, f1-score, loss, and ROC. The VGG16 model performed much better than the other models in this study (98.00 % accuracy). Promising outcomes from experiments have revealed the merits of the proposed model for detecting and monitoring COVID-19 patients. This could help practitioners and academics create a tool to help minimal health professionals decide on the best course of therapy. 

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9595382

A deep transfer learning-based convolution neural network model for COVID-19 detection using computed tomography scan images for medical applications

Agriculture is the backbone of many economies throughout the world including Pakistan. Similarly, tomatoes are the most widely cultivated vegetables in the agricultural field. In addition, the tropical weather increases the throughput yield of tomato crops. However, various climatic conditions and other factors affect the growth of the tomato plant. Rather than such climate conditions and natural disasters, plant diseases are the primary reason for the production crisis resulting in less tomato yield and financial disaster. Traditional methods for detecting diseases in tomato leaves failed to produce the expected outcomes, and disease detection seemed static. However, making the vegetable plants healthy with time is becoming very significant. Identifying diseases in vegetable plants is essential before they cause too severe harm to the vegetables. This research proposes three CNN-based models VGG-16, ResNet-152, and EfficientNet-B4, to classify tomato leaf diseases into normal of disease affected. The proposed research is conducted to find the best possible solution for detecting tomato leaf disease using these deep learning approaches. Employing the Plant-Village dataset with 5524 leaf images, ResNet-152 and EfficientNet-B4 achieved 93.75% and 97.27% accuracy respectively, while VGG-16 achieved 98% accuracy. The efficiency of the system makes it capable of becoming a preference in the agricultural field for real-time tomato leave disease detection applications.

Detection of Tomato Leaf Disease Using Deep Convolutional Neural Networks

Agriculture is the backbone of many economies throughout the world including Pakistan. Similarly, tomatoes are the most widely cultivated vegetables in the agricultural field. In addition, the tropical weather increases the throughput yield of tomato crops. However, various climatic conditions and other factors affect the growth of the tomato plant. Rather than such climate conditions and natural disasters, plant diseases are the primary reason for the production crisis resulting in less tomato yield and financial disaster. Traditional methods for detecting diseases in tomato leaves failed to produce the expected outcomes, and disease detection seemed static. However, making the vegetable plants healthy with time is becoming very significant. Identifying diseases in vegetable plants is essential before they cause too severe harm to the vegetables. This research proposes three CNN-based models VGG-16, ResNet-152, and EfficientNet-B4, to classify tomato leaf diseases into normal of disease affected. The proposed research is conducted to find the best possible solution for detecting tomato leaf disease using these deep learning approaches. Employing the Plant-Village dataset with 5524 leaf images, ResNet-152 and EfficientNet-B4 achieved 93.75% and 97.27% accuracy respectively, while VGG-16 achieved 98% accuracy. The efficiency of the system makes it capable of becoming a preference in the agricultural field for real-time tomato leave disease detection applications. 

A pneumothorax is the accumulation of air in the pleural space between the chest and lungs. Air that is in the lungs during breathing can leak out of the lungs and become trapped between the chest and lungs in the thoracic cavity, causing chest pain, difficulty breathing, and ultimately the complete collapse of the taut lungs. pneumothorax. Therefore, early diagnosis and treatment should be started. Neural networks have proven effective in image classification tasks, and many researchers believe that training neural network models can detect radiologist-diagnosed chest abnormalities such as pneumonia and pneumothorax. is proving. Moreover, we utilize various techniques, including Stochastic Weight Averaging (SWA), aggressive data augmentation, and learning rate schedule. We use the chest x-ray dataset provided by the 2019 SIIM-ACR In this study, a ResNet-34 neural network is trained on a data set of chest x-rays containing over 10,675 images to create a model that predicts the presence of pneumothorax from chest x-rays.our suggested system receives a Dice Similarity Coefficient (DSC) of 0.8410 

A Novel Method for Pneumothorax Diagnosis and Segmentation Using Deep Convolution Neural Network

Today’s marketing strategies place a high priority on comprehending customer sentiments. It will not only give businesses a better understanding of how their clients view their goods and/or services, but it will also give them suggestions on how to enhance their offerings. We make an effort to comprehend the relationship between various factors in customer reviews on an online store for women’s clothing. The proposed system also classifies each review, according to, whether it recommends the product in question or not, and whether it has a positive, negative, or neutral sentiment. With the exception of review titles and review texts, we used univariate and multivariate analyses on datasets features to accomplish these goals. Additionally, we have implemented a bidirectional recurrent neural network (RNN) with a long-short term memory unit (LSTM) for sentiment and recommendation.

Product Recommendation System using Deep Learning based Recurrent Neural Network

Investigation and comparison of different CNN architectures on tomato leaf disease prediction using deep learning

Rapid growth in technological development, the use of the internet has grown many folds. Along with it, the sharing of privacy information in networks creates ownership issues. In order to create a high level of security for sharing private information, the concept of steganography is introduced along with encryption based invisible watermarking techniques. The proposed system hides the encrypted private messages by using onetime pad which follows the concept LSB algorithm in spatial domain. The system combines steganography and encryption for enhancing the confidentiality of the intended messages. At first, the private information of the user is encrypted by using the onetime pad algorithm. Then the encrypted text is hidden the Least Significant Bit (LSB) of the different components of the color image in such a way that as to minimize the perceived loss of quality of the cover image. The beneficiary of the message is able to retrieve the hidden back and from the stego-image and extract the cipher text and find the plaintext from using the onetime pad algorithm. The proposed algorithm will be tested and analysed against three different hiding positions of color image components.

N. Karthikeyan

Papers

Investigation and comparison of different CNN architectures on tomato leaf disease prediction using deep learning

Enhancing the confidentiality of text embedding using image steganography in spatial domain