Search

This research addresses the challenge of automating skin disease diagnosis using dermatoscopic images. The primary issue lies in accurately classifying pigmented skin lesions, which traditionally rely on manual assessment by dermatologists and are prone to subjectivity and time consumption. By integrating a hybrid CNN-DenseNet model, this study aimed to overcome the complexities of differentiating various skin diseases and automating the diagnostic process effectively. Our methodology involved rigorous data preprocessing, exploratory data analysis, normalization, and label encoding. Techniques such as model hybridization, batch normalization and data fitting were employed to optimize the model architecture and data fitting. Initial iterations of our convolutional neural network (CNN) model achieved an accuracy of 76.22% on the test data and 75.69% on the validation data. Recognizing the need for improvement, the model was hybridized with DenseNet architecture and ResNet architecture was implemented for feature extraction and then further trained on the HAM10000 and PAD-UFES-20 datasets. Overall, our efforts resulted in a hybrid model that demonstrated an impressive accuracy of 95.7% on the HAM10000 dataset and 91.07% on the PAD-UFES-20 dataset. In comparison to recently published works, our model stands out because of its potential to effectively diagnose skin diseases such as melanocytic nevi, melanoma, benign keratosis-like lesions, basal cell carcinoma, actinic keratoses, vascular lesions, and dermatofibroma, all of which rival the diagnostic accuracy of real-world clinical specialists but also offer customization potential for more nuanced clinical uses. [ABSTRACT FROM AUTHOR]

It's observed that in recent years, cyber-attacks are becoming a regular threat. In conventional phishing attacks, targeted users are redirected to visit a fake or counterfeit website, for taking out personal information and credentials like banking information, credentials, and even UPI wallets. Usually, phishing attacks happens using email, text messages, and voice calls by forwarding fake website URL. This attack is not only referring to users who have very little information about this fraud but also those who have good and sound knowledge of this type of attack. Detection of a Social engineering attack such as phishing is a challenging task due to its nature of affecting. In this research, the System uses the approach of detecting this sophisticated attack using ML, NLP, WDM, and MCAM which is the best suitable approach to identify the phishing attack. Machine Learning is the most advanced way of detecting targeted phishing attacks from URL, Email, or SMS. a Detection is done with NLP and Machine learning with attack vectors as a dataset with help of simulators performing data visualization work. [ABSTRACT FROM AUTHOR]

Keeping patient records with diagnostics details is the main aim of digitalized healthcare but health data in traditional storage systems will always attract a risk to data security. There is a high risk of data leak if adequate measurement is not obtained, intruders can modify or delete any of the records. Blockchain is a stable technology that will be helpful in the development of a secure yet tamper-resistant system for the management of data. However, setting up an all-new system based on blockchain that will replace the existing system is quite expensive and sometimes time-consuming. But to get an ultimate and temper-proof system in the proposed architecture, introduce a smart contract with a layered approached integration mechanism, named the blockchain PHR (Patient Health Recorder), Migrating the existing cloud-basis system of health records to a public yet secure blockchain infrastructure to develop a tamper-resistant managing system of the health record. [ABSTRACT FROM AUTHOR]

In systemic lupus erythematosus (SLE), T helper cells exhibit increased and prolonged expression of cell-surface CD40 ligand (CD154), spontaneously overproduce interleukin-10 (IL-10), but underproduce interferon-gamma (IFN-[Gamma]). We tested the hypothesis that the imbalance of these gene products reflects skewed expression of CD154, IL-10, and IFN-[Gamma] genes. Here, we demonstrate that the histone deacetylase inhibitor, trichostatin A, significantly down-regulated CD154 and IL-10 and up-regulated IFN-[Gamma] gene expression in SLE T cells. This reversal corrected the aberrant expression of these gene products, thereby enhancing IFN-[Gamma] production and inhibiting IL-10 and CD154 expression. That trichostatin A can simultaneously reverse the skewed expression of multiple genes implicated in the immunopathogenesis of SLE suggests that this pharmacologic agent may be a candidate for the treatment of this autoimmune disease.