×
The submission system is temporarily under maintenance. Please send your manuscripts to
Go to Editorial ManagerFederated learning (FL) offers a robust and privacy-preserving approach for developing collaborative intrusion detection systems (IDS). However, statistical variance severely hinders its practical application. Although privacy-preserving federated learning models have been used to develop intrusion detection systems for cyberattacks, problems arise when statistical variance is present. In practice, the performance of the FedAvg algorithm is significantly affected by the heterogeneous distribution of customer data in a real-world network. This distribution causes skewness among customer data, resulting in poor detection accuracy, delayed convergence, and model instability. In this paper, presents conduct a comprehensive comparison of the Scaffold algorithm with the FedAvg baseline using the CICIDS2017 datasets. Because the Scaffold algorithm addresses the client skew problem using control variables, it is considered a state-of-the-art federated optimization technique under the heterogeneous partitioning approach. This paper documents the importance of using the Scaffold algorithm as a reliable and essential tool for building high-performance detection systems in a variety of scientific settings. Therefore, our results demonstrate that Scaffold achieved more stable convergence and outperformed FedAvg, with a 15.1% increase in F1-score and a 13.6% higher overall accuracy under highly skewed data distributions. The present evaluation process operates through simulation testing, but physical testbed implementation remains essential for future work to evaluate real-world deployment challenges.
Autism spectrum disorder (ASD) is a neurological condition marked by impaired communication abilities, social detachment, and repetitive behaviors in individuals. Global health organization facing difficulties in establishing an effective ASD diagnostic system that facilitates precise analysis and early autism prediction. It is a scientific issue that necessitates resolution. This research presents an approach for the early prediction of children with ASD utilizing significant variables through machine learning (ML) methods. Three stages comprise the suggested technique. First, a 1250-case ASD dataset was identified and preprocessed. Five extremely effective traits with high Pearson correlation coefficient (PCC) are chosen from 10 chosen ASD feature dataset through its paces using five ML techniques: Naive Bayes (NB), K-Nearest Neighbor (kNN), Decision Tree(DT), Support Vector Machine (SVM), and AdaBoostM1 (ABM1). The proposed framework is assessed in the third phase utilizing five measurements such as accuracy, precision, predicting time ,recall, and F1-score, . The findings revealed that: NB and K-NN approaches exhibit superior accuracy rates of 99.2% and 97.2%, with minimal prediction times of approximately 0.3 and 0.45 seconds, correspondingly. Conversely, the DT and AdBM1 methods demonstrate a minor decline in accuracy, achieving 94.8% and 87.6%, respectively, along with increased prediction times. Nonetheless, the SVM approach exhibits the least performance, achieving an accuracy of 80.4% with prediction time of 0.84 seconds. This research aligns with several Sustainable Development Goals (SDGs), including ٍSDG3, which focuses on good health, SCG10, which addresses reducing inequalities, including those related to disability. and SCG9 by strengthening technological capabilities, particularly in scientific research