Chaotic Water Wave Optimization and Support Vector Machine of Role-Based Access Control Policies in Enterprise IAM

The access control state of a system is complex, and Machine Learning (ML) based access control decision engines have demonstrated advantages of policies. However, struggle to effectively implement Role-Based Access Control (RBAC) policies because require large enterprises Identity and Access Management (IAM) system with a high volume of users and access logs. This paper, proposed Chaotic Water Wave Optimization (CWWO) algorithm combined with a Support Vector Machine (SVM) to classify users based on selected features, leading to more accurate and secure role to assignment. The dataset used is obtained from amazon and pre-processing is done using Min-max normalization, which scales the feature to a specific range, ensuring that different features are on same scale. Feature selection is performed using the CWWO algorithm, which helps in selecting relevant feature and reduce dimensionality. The classification using SVM for binary classification, which assigns relevant feature and handle large amounts of data, achieving better accuracy. The proposed ensemble model technique for ship motion detection is achieving better outcomes such as high accuracy of 0.98, precision of 0.97, F1-score of 0.96 and recall of 0.98 and respectively. The existing technique such Random Forest (RF) and Decision Tree (DT) are evaluated of proposed method.