Search alternatives:
network optimization » swarm optimization (Expand Search), wolf optimization (Expand Search)
while optimization » whale optimization (Expand Search), wolf optimization (Expand Search), phase optimization (Expand Search)
binary based » library based (Expand Search), linac based (Expand Search), binary mask (Expand Search)
binary a » binary _ (Expand Search), binary b (Expand Search), hilary a (Expand Search)
a while » a whole (Expand Search), a white (Expand Search)
network optimization » swarm optimization (Expand Search), wolf optimization (Expand Search)
while optimization » whale optimization (Expand Search), wolf optimization (Expand Search), phase optimization (Expand Search)
binary based » library based (Expand Search), linac based (Expand Search), binary mask (Expand Search)
binary a » binary _ (Expand Search), binary b (Expand Search), hilary a (Expand Search)
a while » a whole (Expand Search), a white (Expand Search)
-
1
MSE for ILSTM algorithm in binary classification.
Published 2023“…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. …”
-
2
Datasets and their properties.
Published 2023“…In addition, we designed nested transfer (NT) functions and investigated the influence of the function on the level-1 optimizer. The binary Ebola optimization search algorithm (BEOSA) is applied for the level-1 mutation, while the simulated annealing (SA) and firefly (FFA) algorithms are investigated for the level-2 optimizer. …”
-
3
Parameter settings.
Published 2023“…In addition, we designed nested transfer (NT) functions and investigated the influence of the function on the level-1 optimizer. The binary Ebola optimization search algorithm (BEOSA) is applied for the level-1 mutation, while the simulated annealing (SA) and firefly (FFA) algorithms are investigated for the level-2 optimizer. …”
-
4
Summary of LITNET-2020 dataset.
Published 2023“…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. …”
-
5
SHAP analysis for LITNET-2020 dataset.
Published 2023“…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. …”
-
6
Comparison of intrusion detection systems.
Published 2023“…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. …”
-
7
Parameter setting for CBOA and PSO.
Published 2023“…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. …”
-
8
NSL-KDD dataset description.
Published 2023“…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. …”
-
9
The architecture of LSTM cell.
Published 2023“…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. …”
-
10
The architecture of ILSTM.
Published 2023“…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. …”
-
11
Parameter setting for LSTM.
Published 2023“…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. …”
-
12
LITNET-2020 data splitting approach.
Published 2023“…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. …”
-
13
Transformation of symbolic features in NSL-KDD.
Published 2023“…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. …”
-
14
Table_1_An efficient decision support system for leukemia identification utilizing nature-inspired deep feature optimization.pdf
Published 2024“…To optimize feature selection, a customized binary Grey Wolf Algorithm is utilized, achieving an impressive 80% reduction in feature size while preserving key discriminative information. …”
-
15