Enhancing Optical Coherence Tomography Image Classification Via Swarm Optimization-Based Feature Selection and Machine Learning Models

Optical Coherence Tomography (OCT) greatly facilitates the diagnosis of retinal diseases. However, traditional models based on Convolutional Neural Networks (CNNs) suffer from challenges, most notably high computational cost, sensitivity to noise, and data imbalance. This study aims to compare three hybrid deep learning frameworks, all of which rely on feature extraction using a pre-trained CNN model and then selecting the most important features using intelligent swarm algorithms: the Dolphin Swarm Optimization (DSO), the Particle Swarm Optimization (PSO), and the Ant Swarm Optimization (ACO). The selected features were evaluated using four classifiers: SVM, random forest, XGBoost, and k-NN. Experiments were conducted on a standard dataset from the University of California, San Diego (UCSD) and a local dataset. The comparison results showed that the hybrid framework, which combines the dolphin swarm algorithm and SVM, outperformed the other combinations, achieving a classification accuracy of 93% on local data and 95% on standard data, while also outperforming them in terms of accuracy and computational efficiency.

Proposed Model for Credit Card Fraud Detection Model Using Machine Learning Technique

The online payment system is at high risk due to the increasing rates of credit card theft. The primary objective is to identify cases of credit card theft by analysing the purchase history of cardholders and categorising them accordingly. These include an increase in the slope of logistics, steep slope, and scattered woodlands. The proposed model utilises tools such as logistic regression and random forest as machine learning techniques. Additionally, a set of preprocessing techniques is employed, including data balancing using SMOTE. After being trained on a large dataset of credit card transactions, the model is used to detect trends and anomalies that may indicate fraudulent activity, taking into account factors such as transaction amount, location, and time of day. We have used artificial minority oversampling to put the data set into proper perspective. The two algorithms were applied, yielding 97.34% accuracy for Logistic Regression and 99.99% accuracy for Random Forest. The accuracy metric is used for performance evaluation. The results indicate a promising performance that can enhance credit card security, potentially helping to reduce financial losses to victims of fraud.

Smart Homes Network Security Issues and Solutions IOT

There has been a consistent uptick in both the number of connected devices in use and the number of smart homes being built in recent years (IDATE, 20160. Smart locks, HVAC systems, and networking technologies like Zigbee and Z-Wave have all entered the market in recent years, and the number of available options has increased dramatically. This thesis serves a dual function. For starters, it provides a concise overview of the dangers facing smart homes in the near and far future from a security standpoint. Second, using this data as a starting point helps with the overall smart home security management. The contribution is a prototype of a security module designed to monitor for and alert users to any suspicious activity. In this thesis, we'll look into whether or not the smart hub is an adequate environment for this kind of mechanism in terms of its impact on system resources and the frequency with which it may be detected. Our research for this thesis has centered on creating and assessing a security system for the Internet of Things (IoT) that can reduce the risk of cyber attacks on individuals and communities.