Research

MS Thesis Title: Machine learning-based attack detection in Internet of Things network

🔑 Key Features:

📌 Proposed a machine learning-based methodology to detect cyber-attacks on the Internet of Things (IoT) network systems.

📌 Executed k-nearest neighbors (KNN), logistic regression (LR), and random forest (RF) models during research.

📌 Applied the UNSW-NB15 dataset to train the model and obtained 98.03% of prediction accuracy as an outcome.

📌 The dataset contains 210,000 data points, including 61,987 attack data and 148,013 benign data.

📌 The types of attacks, such as backdoor, denial of service, shellcode, reconnaissance, and exploits, were studied.

📌 The dataset includes 39 features and 1 class label.

🕒 The research outcomes were presented at the Louisiana Academy of Sciences (LAS) 95th Annual Conference, Louisiana Tech University, Ruston, LA, on March 12, 2021, and obtained the best paper award.

Fig. ROC Curve for KNN Model from [Article-MS]

Fig. ROC Curve for Logistic Regression Model from [Article-MS]

Fig. ROC Curve for Random Forest Model from [Article-MS]

BS Thesis Title: Reduction of Latency in LTE Using Additional Control Region for Downlink Transmission and Prior Generation of Packets for Uplink Transmission

🔑 Key Points:

📌 Proposed a random forest model-based prediction algorithm to generate transport blocks (TBs) before signaling in LTE.

📌 Executed new transmissions in uplink as well as Hybrid Automatic Repeat Request (HARQ) retransmissions in any direction.

📌 Reduced latency by 2 ms for the transfer of a TB during software simulation validation.

📌 Saved 8 ms during three retransmissions, considering the uplink data transfer of a TB.

🕒 The project results were presented at the IEEE 5th International Conference on Computer and Communications (ICCC), Chengdu, China, on 06-09 December 2019.

Fig. State-of-the-Art Uplink Data Transfer with HARQ from [Article-BS]

Fig. Proposed Uplink Data Transfer with HARQ from [Article-BS]

Fig. State-of-the-Art Downlink Data Transfer with HARQ from [Article-BS]

Fig. Proposed Downlink Data Transfer with HARQ from [Article-BS]

Article-MS: M. R. Rafi, M. A. Salam, and O. Kandara, “Machine Learning Based Attack Detection in Internet of Things Network,” International Journal of Computer Science and Information Security, vol. 19, no. 8, August 2021

🔗 Article

Article-BS: M. T. Kawser, M. R. Rafi, F. M. Faijus Salehin Rifat, M. F. Rahman, N. Zaki, and S. Z. Rahman, “Prior Generation of Transport Blocks to Expedite HARQ Retransmissions and Uplink Transmissions Improving Latency in LTE,” 2019 IEEE 5th International Conference on Computer and Communications (ICCC), 2020

🔗 Article

Page updated

Google Sites

Report abuse