| Title | Intrusion Detection System Using Optimal Support Vector Machine for Wireless Sensor Networks |
| Publication Type | Conference Paper |
| Year of Publication | 2021 |
| Authors | Amaran, Sibi, Mohan, R. Madhan |
| Conference Name | 2021 International Conference on Artificial Intelligence and Smart Systems (ICAIS) |
| Date Published | mar |
| Keywords | Benchmark testing, composability, Intrusion detection, Kernel, kernel selection, machine learning, Metrics, network intrusion detection, Optimization, Predictive Metrics, pubcrawl, resilience, Resiliency, Support vector machines, SVM, Transforms, Wireless sensor networks, WSN |
| Abstract | Wireless sensor networks (WSN) hold numerous battery operated, compact sized, and inexpensive sensor nodes, which are commonly employed to observe the physical parameters in the target environment. As the sensor nodes undergo arbitrary placement in the open areas, there is a higher possibility of affected by distinct kinds of attacks. For resolving the issue, intrusion detection system (IDS) is developed. This paper presents a new optimal Support Vector Machine (OSVM) based IDS in WSN. The presented OSVM model involves the proficient selection of optimal kernels in the SVM model using whale optimization algorithm (WOA) for intrusion detection. Since the SVM kernel gets altered using WOA, the application of OSVM model can be used for the detection of intrusions with proficient results. The performance of the OSVM model has been investigated on the benchmark NSL KDDCup 99 dataset. The resultant simulation values portrayed the effectual results of the OSVM model by obtaining a superior accuracy of 94.09% and detection rate of 95.02%. |
| DOI | 10.1109/ICAIS50930.2021.9395919 |
| Citation Key | amaran_intrusion_2021 |
Intrusion Detection System Using Optimal Support Vector Machine for Wireless Sensor Networks