ICTACT Journal on Communication Technology

Open Access Open Access  Restricted Access Subscription Access

DEEP PACKET INSPECTION USING HYBRID CLASSIFIER FOR UNKNOWN TRAFFIC FLOWS IN THE INTERNET


Affiliations
1 Sona College of Technology, India
2 Madanapalle Institute of Technology and Science, India
 

   Subscribe/Renew Journal


In this era of Internet every electronic device being manufactured comes with built-ins to connect itself with the Internet. Such electronic gadgets create a massive amount of traffic flows every second. Managing this immense Internet traffic has become an exhausting job. Classifying these massive flows of data and interpreting them has attained considerable importance in the sight of researchers and Internet Service Providers. Many methods have been presented by various researchers to address this classification issue. This paper presents a Hybrid Classifier algorithm, which is a combination of the well-known machine learning types; the supervised learning and unsupervised learning to solve this classification issue. Accurate and Efficient recognition of flows is the key to manage flows in real-time. This algorithm classifies the traffic flows into real time flows and non-real time flows. It uses the built decision support model for classifying the flows based on the target class. To further validate the classification, it applies the k-means model. A significant improvement in the classification accuracy has been obtained.

Keywords

Voltage Stability, Voltage Collapse, Voltage Stability Indices, Radial Distribution Network.
Subscription Login to verify subscription
User
Notifications
Font Size

  • T. Karthikeyan and K. Praghash, “An Improved Task Allocation Scheme in Serverless Computing using Gray Wolf Optimization (GWO) based Reinforcement Learning (RIL) Approach”, Wireless Personal Communications, Vol. 117, No. 3, pp. 1-19, 2020.

  • S. Kannan, G. Dhiman, and M. Gheisari, “Ubiquitous Vehicular Ad-Hoc Network Computing using Deep Neural Network with IoT-Based Bat Agents for Traffic Management”, Electronics, Vol. 10, no. 7, pp. 785-796, 2021.

  • N.V. Kousik, “Analyses on Artificial Intelligence Framework to Detect Crime Pattern”, Intelligent Data Analytics for Terror Threat Prediction: Architectures, Methodologies, Techniques and Applications, pp. 119-132, 2021.

  • A.S. Nandhini and P. Vivekanandan, “A Survey on Energy Efficient Routing Protocols for MANET”, International Journal of Advances in Engineering and Technology, Vol. 6, No. 1, pp. 370-381, 2013.

  • N.G. Veerappan Kousik, K. Suresh, R. Patan and A.H. Gandomi, “Improving Power and Resource Management in Heterogeneous Downlink OFDMA Networks”, Information, Vol. 11, No. 4, pp. 203-216, 2020.

  • K.W. Kim, Y.H. Han and S.G. Min, “An Authentication and Key Management Mechanism for Resource Constrained Devices in IEEE 802.11-based IoT Access Networks”, Sensors, Vol. 17, No. 10, pp. 1-20, 2017.

  • G. Dhiman, K. Somasundaram and K. Sharma, “NatureInspired-Based Approach for Automated Cyberbullying Classification on Multimedia Social Networking”, Mathematical Problems in Engineering, Vol. 2021, pp. 1- 21, 2021.

  • P.K. Dhillon and S. Kalra, “Multi-Factor User Authentication Scheme for IoT-Based Healthcare Services”, Journal of Reliable Intelligent Environments, Vol. 4, No. 3, pp. 141-160, 2018.

  • A.K. Das, P. Sharma, S. Chatterjee and J.K. Sing, “A Dynamic Password-Based User Authentication Scheme for Hierarchical Wireless Sensor Networks”, Journal of Network and Computer Applications, Vol. 35, No. 5, pp. 1646-1656, 2012.

  • N.V. Kousik, P. Johri and M.J. Divan, “Analysis on the Prediction of Central Line-Associated Bloodstream Infections (CLABSI) using Deep Neural Network Classification”, Proceedings of International Conference on Computational Intelligence and Its Applications in Healthcare, pp. 229-244, 2020.

  • P. Johri, “Improved Energy Efficient Wireless Sensor Networks using Multicast Particle Swarm Optimization”, Proceedings of International Conference on Innovative Advancement in Engineering and Technology, pp. 1-6, 2020.

  • S. Kannan and S.N. Mohanty, “Survey of Various Statistical Numerical and Machine Learning Ontological Models on Infectious Disease Ontology”, Proceedings of International Conference on Data Analytics in Bioinformatics: A Machine Learning Perspective, pp. 431-442, 2021.

  • D.S.K. Tiruvakadu and V. Pallapa, “Confirmation of Wormhole Attack in MANETs using Honeypot”, Computers and Security, Vol. 76, No. 2, pp. 32-49, 2018.

  • S. Jayasri, A. Daniel and P. Rajakumar, “A Survey on Various Load Balancing Algorithm to Improve the Task Scheduling in Cloud Computing Environment”, Journal of Advance Research in Dynamic Control Systems, Vol. 11, No. 8, pp. 2397-2406, 2019.

  • M.N. Ahmed, A.H. Abdullah, H. Chizari and O. Kaiwartya, “F3TM: Flooding Factor based Trust Management Framework for Secure Data Transmission in MANETs”, Journal of King Saud University-Computer and Information Sciences, Vol. 29, No. 3, pp. 269-280, 2017.


Abstract Views: 158

PDF Views: 95




  • DEEP PACKET INSPECTION USING HYBRID CLASSIFIER FOR UNKNOWN TRAFFIC FLOWS IN THE INTERNET

Abstract Views: 158  |  PDF Views: 95

Authors

P Shanmugaraja
Sona College of Technology, India
K Chokkanathan
Madanapalle Institute of Technology and Science, India
K Thangaraj
Sona College of Technology, India
P Ilanchezhian
Sona College of Technology, India

Abstract


In this era of Internet every electronic device being manufactured comes with built-ins to connect itself with the Internet. Such electronic gadgets create a massive amount of traffic flows every second. Managing this immense Internet traffic has become an exhausting job. Classifying these massive flows of data and interpreting them has attained considerable importance in the sight of researchers and Internet Service Providers. Many methods have been presented by various researchers to address this classification issue. This paper presents a Hybrid Classifier algorithm, which is a combination of the well-known machine learning types; the supervised learning and unsupervised learning to solve this classification issue. Accurate and Efficient recognition of flows is the key to manage flows in real-time. This algorithm classifies the traffic flows into real time flows and non-real time flows. It uses the built decision support model for classifying the flows based on the target class. To further validate the classification, it applies the k-means model. A significant improvement in the classification accuracy has been obtained.

Keywords


Voltage Stability, Voltage Collapse, Voltage Stability Indices, Radial Distribution Network.

References