Revolutionizing Perimeter Intrusion Detection: A Machine Learning-Driven Approach with Curated Dataset Generation for Enhanced Security
Issued Date
2023-01-01
Resource Type
eISSN
21693536
Scopus ID
2-s2.0-85172998631
Journal Title
IEEE Access
Rights Holder(s)
SCOPUS
Bibliographic Citation
IEEE Access (2023)
Suggested Citation
Pitafi S., Anwar T., Widia I.D.M., Yimwadsana B., Pitafi S. Revolutionizing Perimeter Intrusion Detection: A Machine Learning-Driven Approach with Curated Dataset Generation for Enhanced Security. IEEE Access (2023). doi:10.1109/ACCESS.2023.3318600 Retrieved from: https://repository.li.mahidol.ac.th/handle/20.500.14594/90368
Title
Revolutionizing Perimeter Intrusion Detection: A Machine Learning-Driven Approach with Curated Dataset Generation for Enhanced Security
Author(s)
Author's Affiliation
Other Contributor(s)
Abstract
Perimeter intrusion detection systems (PIDS) play a crucial role in safeguarding critical infrastructures from unauthorized access and potential security breaches. Security is the main concern everywhere in the world. There are already many PIDS available, but the PID systems are still lacking in terms of probability of detection, false intrusion, and the activity recognition of intrusion. To solve the above problem, we designed a prototype for PIDS using a DHT22 temperature and humidity sensor, vibration sensor SW- 420 Module Pinout, Mini PIR motion sensor, and Arduino UNO. After collecting the data from above mentioned sensors we applied machine learning algorithms DBSCAN to cluster the data points and K-NN classification to classify those clusters in one-dimensional data, but the results were not much satisfying. From there we got the motivation to improve the algorithm and applied it to two-dimensional data. The existing DBSCAN is not efficient due to its high complexity and the varying densities. To overcome these issues in this algorithm, we have improved the existing DBSCAN to ST-DBSCAN where we have used the estimation for the epsilon value and used the Manatton distance formula to find out the distance between points which produces 94.9853% accuracy on our dataset. Another contribution of the proposed work is that we have developed our own dataset named STPID-dataset, captured from security cameras installed in various locations which can be used by future researchers.