MSE for ILSTM algorithm in binary classification. by Asmaa Ahmed Awad (16726315)

“…The ILSTM was then used to build an efficient intrusion detection system for binary and multi-class classification cases. The proposed algorithm has two phases: phase one involves training a conventional LSTM network to get initial weights, and phase two involves using the hybrid swarm algorithms, CBOA and PSO, to optimize the weights of LSTM to improve the accuracy. …”

Comparison between ILSTM and machine learning-based algorithms in binary classification. by Asmaa Ahmed Awad (16726315)

Comparison between ILSTM and deep learning-based algorithms in binary classification. by Asmaa Ahmed Awad (16726315)

Confusion matrices for KDDTest+ in binary classification. by Asmaa Ahmed Awad (16726315)

Shap analysis for NSL-KDD in binary classification. by Asmaa Ahmed Awad (16726315)

Confusion matrices for KDDTest-21 in binary classification. by Asmaa Ahmed Awad (16726315)

Confusion matrices for LITNET-2020 dataset in binary classification. by Asmaa Ahmed Awad (16726315)

LSTM vs ILSTM for LITNET-2020 in binary classification. by Asmaa Ahmed Awad (16726315)

LSTM vs ILSTM for KDDTest-21 for binary classification. by Asmaa Ahmed Awad (16726315)

Statistic Test for KDDTest+ and KDDTest-21 in binary classification. by Asmaa Ahmed Awad (16726315)

Accuracy and number of iterations for LSTM and ILSTM using KDDTest+ in binary classifications. by Asmaa Ahmed Awad (16726315)

Comparison between LSTM and ILSTM using LITNET-2020 in binary classification. by Asmaa Ahmed Awad (16726315)

Comparison between other methods in literature using KDDTest+ for binary classification. by Asmaa Ahmed Awad (16726315)

Comparison between LSTM, LSTM-BOA, LSTM-CBOA and ILSTM using KDDTest+ and KDDTest-21 in binary classification with average 10 runs. by Asmaa Ahmed Awad (16726315)

Classification performance after optimization. by Amal H. Alharbi (21755906)

“…We applied this hybrid strategy to a Radial Basis Function Network (RBFN), and validated its performance improvements through extensive experiments, including ANOVA and Wilcoxon tests for both feature selection and optimization phases. The optimized model achieved a classification accuracy of 99.46%, significantly outperforming classical machine learning and unoptimized deep learning models. …”

ANOVA test for optimization results. by Amal H. Alharbi (21755906)

“…We applied this hybrid strategy to a Radial Basis Function Network (RBFN), and validated its performance improvements through extensive experiments, including ANOVA and Wilcoxon tests for both feature selection and optimization phases. The optimized model achieved a classification accuracy of 99.46%, significantly outperforming classical machine learning and unoptimized deep learning models. …”

Wilcoxon test results for optimization. by Amal H. Alharbi (21755906)

“…We applied this hybrid strategy to a Radial Basis Function Network (RBFN), and validated its performance improvements through extensive experiments, including ANOVA and Wilcoxon tests for both feature selection and optimization phases. The optimized model achieved a classification accuracy of 99.46%, significantly outperforming classical machine learning and unoptimized deep learning models. …”

Wilcoxon test results for feature selection. by Amal H. Alharbi (21755906)

“…We applied this hybrid strategy to a Radial Basis Function Network (RBFN), and validated its performance improvements through extensive experiments, including ANOVA and Wilcoxon tests for both feature selection and optimization phases. The optimized model achieved a classification accuracy of 99.46%, significantly outperforming classical machine learning and unoptimized deep learning models. …”

Feature selection metrics and their definitions. by Amal H. Alharbi (21755906)

“…We applied this hybrid strategy to a Radial Basis Function Network (RBFN), and validated its performance improvements through extensive experiments, including ANOVA and Wilcoxon tests for both feature selection and optimization phases. The optimized model achieved a classification accuracy of 99.46%, significantly outperforming classical machine learning and unoptimized deep learning models. …”

Statistical summary of all models. by Amal H. Alharbi (21755906)

“…We applied this hybrid strategy to a Radial Basis Function Network (RBFN), and validated its performance improvements through extensive experiments, including ANOVA and Wilcoxon tests for both feature selection and optimization phases. The optimized model achieved a classification accuracy of 99.46%, significantly outperforming classical machine learning and unoptimized deep learning models. …”