Paper Title

MACHINE LEARNING–GENETIC ALGORITHM BASED OPTIMIZATION OF NETWORK BEHAVIOUR

Abstract

Machine learning (ML) promises advances in automation and threat detection for the future generations of communication networks. However, new threats are introduced, as adversaries target ML systems with malicious data. Adversarial attacks on tree-based ML models involve crafting input perturbations that exploit non-smooth decision boundaries, causing misclassifications. These so-called evasion attacks are imperceptible, as they do not significantly alter the input data distribution and have been shown to degrade the performance of tree-based models across various tasks. Adversarial training and genetic algorithms have been proposed as potential defenses against these attacks. This study evaluates an optimization approach inspired by genetic algorithms to generate adversarial samples and studies the impact of adversarial training on the accuracy of attack detection. AI is useful in many different disciplines. One type of AI application is a neural network; task specific AI consists of many different architecture types. Genetic algorithm optimization, a population-based evolutionary algorithm, is proposed to help find the most efficient neural network architecture for a specific task.
KEYWORDS : Machine learning (ML), genetic algorithms, neural network, Genetic algorithm optimization, neural network architecture, AI application.

Paper Title

HYBRID CLOUD DATABASE FRAMEWORK FOR MODERNIZING LEGACY DATA SYSTEMS

Abstract

Modernizing legacy systems is critical for organizations striving to enhance operational efficiency, scalability, and security in an increasingly data-driven and digital landscape. Traditional infrastructures, burdened by technical debt, security vulnerabilities, and operational inefficiencies, pose significant challenges to innovation and long-term sustainability. This paper explores a scalable approach to legacy system modernization, emphasizing next-generation data architectures and seamless integration strategies. It examines the limitations of outdated systems, the benefits of cloud-native and distributed architectures, and the role of micro services and event-driven frameworks in improving system agility It also discusses data integration strategies, compares ETL and ELT processes, and highlights the significance of middleware solutions, API-driven ecosystems, and hybrid cloud environments in ensuring interoperability. The paper concludes with recommendations for organizations seeking to transform legacy systems, advocating for structured modernization roadmaps, security-centric designs, and future-proof architectural strategies. The modernization of legacy systems through migration to cloud-based platforms has become a cornerstone of enterprise IT transformation. In particular, the transition of Unix-based infrastructures long regarded as the foundation of mission-critical operations into hybrid cloud environments underscores the growing need for scalability, agility, and operational efficiency. Architecting hybrid Unix environments involves harmonizing the reliability and proven capabilities of Unix with the dynamic features of cloud computing.
KEYWORDS : Legacy System Modernization, Scalable Data Architectures, Hybrid Cloud Environments, Data Migration Strategies

Paper Title

COMPUTATIONAL MODELING AND ANALYSIS OF NANOFIBER COMPOSITES FOR MARITIME APPLICATIONS

Abstract

This study investigates the drug release performance of electrospun composite nanofiber mats, which hold significant promise as drug carriers for site-specific delivery in therapeutic applications such as cancer therapy. Predicting drug release rates from poly nanofibers produced via emulsion electrospinning is challenging due to the system\'s inherent complexity. Computational modeling was employed to evaluate the continuous drug release from these nanofibers. The carbon nanotubes/nanofibers reinforced composites show great mechanical properties. There are several methods to simulate the mechanical properties of composites. In the last few decades nanofibers have been developed and introduced in a vast number of industrial and research applications. One of their most effective use is as interleaved reinforcement for composite laminate materials against delamination. Nanofibrous mats have the ideal morphology to be embedded between two plies of a laminate, and a vast and deep research has been carried out investigating their effect on the global behaviour of a composite laminate. This review is the first of its kind to date which presents a detailed state-of the-art on the effect of nanofibrous interleaves into composite laminates with focus on the mechanical performances and behaviours of nano modified materials. A detailed description of the working mechanisms of the nano interleave under different load cases is presented, and a comparative analysis between papers in literature will provide readers with a powerful tool to understand and use nanofibers for reinforcing purposes.
KEYWORDS : Nanofibers, Composite Materials, Nano composite, carbon nanofibers, Computational modeling