CHICKEN SWARM OPTIMIZATION BASED ENSEMBLED LEARNING CLASSIFIER FOR BLACK HOLE ATTACK IN WIRELESS SENSOR NETWORK
Journal Title: International Journal of Data Science and Artificial Intelligence - Year 2024, Vol 2, Issue 04
Abstract
Wireless Sensor Networks (WSNs) are an inevitable technology prevalently used in various critical and remote monitoring applications. The security of WSNs is compromised by various attacks in wireless mediums. Even though, various attacks are present, the black hole attack degrades the network performance and resource utilization, resulting in poor network lifetime. Therefore, the proposed research suggests an effective Intrusion Detection System for WSN to detect and classify black hole attacks based on ensemble ML classifiers. The BDD dataset is used for the analysis which is subjected to Chicken Swarm Optimization based feature selection. The selected features are balanced through SMOTE and TOMEK based STL data balancing module. An ensemble of five baseline ML classifiers such as SMO, NB, J48, KNN and RF utilizing voting ensemble approach is suggested to classify the attacks in the dataset. The performance of the algorithm is analyzed through evaluation metrics such as accuracy, precision, recall and F1-score. The comparison of proposed model with six ML and DL classifiers exposes the superiority of the proposed model’s classification performance.
Authors and Affiliations
K. Vijayan, S. V. Harish and R. A. Mabel Rose
Keywords
Related Articles
- EP ID EP744941
- DOI -
- Views 25
- Downloads 0
HYBRIDIZATION OF DILATED CNN WITH ATTENTION LINK NET FOR BRAIN CANCER CLASSIFICATION
Brain tumours (BT) are highly prevalent and dangerous disease, have extremely short prognoses at the most malignant grade. Merging the MRI modes results in hybrid images with information that is used to classify tumours....
IOT BASED AIR QUALITY MONITORING USING DENSENET IN URBAN AREAS
– Internet of Things is being used more and more in the control and monitoring of air quality. Real-time data regarding air pollutants and other environmental parameters can be gathered by deploying IoT devices with sens...
DEEP LEARNING BASED LSTM-GAN APPROACH FOR INTRUSION DETECTION IN CLOUD ENVIRONMENT
Cloud computing is a rapidly growing technology paradigm with enormous potential. While cloud computing has many advantages, it also poses new security risks. Cloud computing security vulnerabilities have been identified...
DETECTION OF VIOLENCE IN FOOTBALL STADIUM THROUGH BIG DATA FRAMEWORK AND DEEP LEARNING APPROACH
Football is the most famous game in the world, with over 4 billion supporters worldwide. Football hooliganism refers to the aggressive or destructive actions of a supporter or player in a stadium while watching or partic...
CLASSIFICATION OF LIVER CANCER VIA DEEP LEARNING BASED DILATED ATTENTION CONVOLUTIONAL NEURAL NETWORK
Liver cancer occur when normal cells develop aberrant DNA alterations and reproduce uncontrollably. Patients with cirrhosis, hepatitis B or C, or both have an increased risk of developing the progressing stage of cancer....