Uneingeschränkter Zugang

Predictive IoT-AI Model for Cyber Threat Detection in Smart Healthcare Environments

 und   
15. Juni 2024

Zitieren
COVER HERUNTERLADEN

Figure 1:

Hybrid Architecture for the Recommended Approach
Hybrid Architecture for the Recommended Approach

Figure 2:

Visualization of the Protocol types of the Dataset
Visualization of the Protocol types of the Dataset

Figure 3:

Visualization of the Normal and attacked flags
Visualization of the Normal and attacked flags

Figure 4:

CNN Architecture
CNN Architecture

Figure 5:

Architecture for GRU
Architecture for GRU

Figure 6:

Performance Metrics Visualization
Performance Metrics Visualization

Comparative Analysis between the Different Models

Algorithms / Performance Metrics ACCURACY PRECISION RECALL F1 SCORE
RNN 93.3 90.1 89.4 91
CNN 94.3 92.1 91.4 91.7
GRU 92.8 91.3 90.6 90.9
LSTM 93 92.4 92 90.5
CNN+LSTM 96.2 94.8 94.1 94.4
PROPOSED 98.2 98.1 96 96.8

Performance measures utilized for assessment

SL.NO Evaluation Metrics Mathematical Expression
01 Accuracy TP+TNTP+TN+FP+FN {{TP + TN} \over {TP + TN + FP + FN}}
02 Recall TPTP+FN×100 {{{\rm{TP}}} \over {{\rm{TP}} + {\rm{FN}}}} \times 100
03 Specificity TNTN+FP {{TN} \over {TN + FP}}
04 Precision TNTP+FP {{TN} \over {TP + FP}}
05 F1-Score 2.PrecisonRecallPrecison+Recall 2.{{Precison\, * \,{Recall}} \over {Precision\, + \, {Recall}}}
Sprache:
Englisch