Alkadhim Journal for Computer Science

The exponential growth of internet usage has led to a significant rise in
network attacks, posing critical cybersecurity challenges. Fog computing, an
extension of cloud computing, offers low-latency services but is highly
susceptible to such attacks due to its decentralized architecture and resource
constraints. Traditional Intrusion Detection Systems (IDS) designed for
centralized networks are often ineffective in fog environments, necessitating
the development of specialized detection methods. This paper proposes a
novel hybrid approach for network anomaly detection tailored for fog
computing environments. The method integrates Particle Swarm Optimization
(PSO)-based wrapper feature selection with the Bagging technique to address
computational and accuracy challenges. Using the NSL-KDD dataset, the
proposed system achieves an impressive accuracy of 98.3% while maintaining
a low false positive rate of 1.5%. These results demonstrate the effectiveness
of the PSO-Bagging framework in enhancing the security of fog computing
systems, making it a robust solution to the growing problem of network
intrusions in distributed computing environments

This research proposes a rigorous Quality assurance (QA) framework for AIgenerated text to evaluate and ensure content quality. Multiple dimensions are
assessed, including grammar, spelling, prompt relevance, and linguistic
diversity. Python-based language models are used to find grammatical errors,
TF-IDF vectorization with cosine similarity to judge relevance, and natural
language processing (NLP) to look at lexical variety. This methodology
incorporates these criteria into a unified and consistent evaluation process to
assure high-quality text output, unlike many other QA methods. The framework
tackles major industry issues. It enhances the accuracy and readability of
medical reports, guaranteeing the effective communication of crucial
information. It helps lawyers write clear, unambiguous documents. It helps
educators create contextually relevant, engaging learning materials that
promote understanding and interaction. Flexibility and scalability allow the
framework to meet different user demands across disciplines. An actual
implementation shows that the framework improves AI-generated content over
previous methods. Higher relevance, grammatical identification, and lexical
diversity are key benefits. Actionable feedback allows generative AI systems to
be refined and model performance improved. Possible inclusions include realtime QA systems, domain-specific relevance models for specialized domains,
and multimodal QA that evaluates text, pictures, and audio. This method is
reliable, morally sound, and useful because it takes into account all the
important quality factors. It makes it possible for new and advanced generative
AI applications in many areas.

In the field of incipient fault protection, various sources can cause failures, such as lightning, switching transients, mechanical imperfections, and chemical breakdown. To guard against these errors, Buchholz relays and pressure relief devices have been utilized. However, in recent years, preventive health measures have gained more attention. One popular approach is the implementation of the Dissolved Gas Analysis (DGA) system, which detects incipient faults by analyzing the gases dissolved in the transformer oil. In this context, the use of artificial neural networks (ANN) and artificial neural networks combined with expert systems (ANNEPS) has shown promise for power transformer protection against incipient faults using DGA. Power transformers, especially large oil-filled ones, are commonly subjected to DGA for identifying and diagnosing early-stage faults. By analyzing the dissolved gases and employing interpretation systems, such as (ANNEPS), unexpected failures can be prevented. The objective of this research is to identify internal problems within transformers, and an (ANN) structure has been specifically developed for this purpose. The ANNEPS approach combines the outputs of ANN and expert systems to ensure rapid and accurate identification of various types of transformer failures. By comparing the results of both computational methods, a reliable assessment can be made, enhancing the effectiveness of incipient fault protection strategies. Overall, the combination of (DGA) and advanced techniques like (ANN) and (ANNEPS) provides a robust approach to detect and prevent incipient faults in power transformers. These methods offer improved accuracy and promptness in identifying transformer failures, ultimately contributing to the reliability and efficiency of power systems.