Acceso abierto

Development of Hybrid Intrusion Detection Systems for IoT Enabled Devices Utilizing Resource Constraint Learning Frameworks

P. Rachana

P. Rachana

Department of Computer Science and Engineering, Alvas Institute of Engineering and TechnologyMangalore, India
Buscar este autor en
Sciendo|Google Scholar
Rachana, P.
, 
Mamatha Talakoti

Mamatha Talakoti

Department of Computer Science and Engineering, Sreenidhi Institute Of Science and TechnologyHyderabad, India
Buscar este autor en
Sciendo|Google Scholar
Talakoti, Mamatha
 y 
V. Surya Narayana Reddy

V. Surya Narayana Reddy

Department of Computer Science and Engineering, Bvrit Hyderabad College of Engineering for WomenHyderabad, India
Buscar este autor en
Sciendo|Google Scholar
Surya Narayana Reddy, V.
  
15 jun 2024
Development of Hybrid Intrusion Detection Systems for IoT Enabled Devices Utilizing Resource Constraint Learning Frameworks's Cover Image
Acerca de este artículo
Artículo anterior
Artículo siguiente
Cite
Descargar portada
Categoría del artículo: Article
Publicado en línea: 15 jun 2024
Páginas: 60 - 76
Recibido: 11 feb 2024
Aceptado: 01 may 2021
DOI: https://doi.org/10.2478/jsiot-2024-0005
Palabras clave
© 2023 Rachana P et al., published by Sciendo
This work is licensed under the Creative Commons Attribution 4.0 International License.

Figure 1:

Hybrid LSTM-GRU Intrusion Detection Framework
Hybrid LSTM-GRU Intrusion Detection Framework

Figure 2:

Long Short Term Memory Network
Long Short Term Memory Network

Figure 3:

Gated Recurrent Unit Network
Gated Recurrent Unit Network

Figure 4:

Hyperparameter tuning Grid Search Architecture
Hyperparameter tuning Grid Search Architecture

Figure 5:

Comparative Analysis of Different Deep Learning Models Based on Evaluating the Accuracy
Comparative Analysis of Different Deep Learning Models Based on Evaluating the Accuracy

Figure 6:

ROC Curve for different models in intrusion detection
ROC Curve for different models in intrusion detection

Comparitive Analysis between different models for intrusion detection

Algorithm Accuracy Precision Recall F1-Score Specificity
CNN 0.75 0.78 0.78 0.79 0.78
RNN 0.77 0.8 0.79 0.8 0.8
LSTM 0.85 0.86 0.86 0.87 0.88
GRU 0.89 0.9 0.9 0.89 0.9
Proposed Model 0.95 0.96 0.95 0.96 0.95

Hyperparameter Tuning for proposed Model

Learning Rate No. of units Dropout Rate Optimizer
0.001 16 0.2 Adam
0.01 32 0.3 SGD
0.1 64 0.5 RMSProp

Evaluation of Performance Metrics

Performance Measures Expression
Accuracy TP+TNTP+TN+FP+FN ${{TP + TN} \over {TP + TN + FP + FN}}$
Precision TNTP+FP ${{TN} \over {TP + FP}}$
Recall TPTP+FN×100 ${{{\rm{TP}}} \over {{\rm{TP}} + {\rm{FN}}}} \times 100$
F1-Score Precison ∗ RecallPrecison + Recall ${{Precison\, * \,{Recall}} \over {Precision\, + \, {Recall}}}$
Specificity TNTN+FP ${{TN} \over {TN + FP}}$
Idioma:
Inglés
Calendario de la edición:
2 veces al año
Temas de la revista:
Ingeniería, Introducciones y reseñas, Historia de la Ingeniería, Ingeniería eléctrica, Fundamentos de ingeniería eléctrica, Electrónica, Tecnologías de la información
RSS Feed de revista