Maheshi B. Dissanayake

Work place: Department of Electrical and Electronic Engineering, Faculty of Engineering, University of Peradeniya, Sri Lanka



Research Interests: Image Processing, Image Manipulation, Image Compression, Computational Learning Theory, Computer systems and computational processes, Wireless Communication, Computational Science and Engineering, Medical Image Computing


Maheshi Buddhinee Dissanayake received the B.Sc. Engineering degree with First Class Honors in electrical and electronic engineering from the University of Peradeniya, Sri Lanka, in 2006, and the Ph.D. in electronic engineering from the University of Surrey, U.K., in 2010. Since 2013, she has been a Senior Lecturer with the Department of Electrical and Electronic Engineering, Faculty of Engineering, University of Peradeniya. She has been a visiting research fellow at King's College London from 2015-2017. Her research interests include error correction codes, robust video communication, molecular communication, machine learning, and biomedical image analysis. She has co-authored nearly 75 conference and journal articles and has a citation record of more than 200. Dr. Dissanayake is a Senior Member of Institute of Electrical and Electronics Engineers (IEEE) and Associate member of Institution of Engineers, Sri Lanka (IESL). She has served as an organizing committee member and TPC Member of many IEEE conferences, and as a reviewer in IEEE journals in the area of Molecular communication and image processing. At present she is the Chairperson of IEEE Sri Lanka Section, and the founder as well as the immediate past Chair of IEEE Women in Engineering Sri Lanka section.

Author Articles
Deep Learning Based Autonomous Real-Time Traffic Sign Recognition System for Advanced Driver Assistance

By Sithmini Gunasekara Dilshan Gunarathna Maheshi B. Dissanayake Supavadee Aramith Wazir Muhammad

DOI:, Pub. Date: 8 Dec. 2022

Deep learning (DL) architectures are becoming increasingly popular in modern traffic systems and self-driven vehicles owing to their high efficiency and accuracy. Emerging technological advancements and the availability of large databases have made a favorable impact on such improvements. In this study, we present a traffic sign recognition system based on novel DL architectures, trained and tested on a locally collected traffic sign database. Our approach includes two stages; traffic sign identification from live video feed, and classification of each sign. The sign identification model was implemented with YOLO architecture and the classification model was implemented with Xception architecture. The input video feed for these models were collected using dashboard camera recordings. The classification model has been trained with the German Traffic Sign Recognition Benchmark dataset as well for comparison. Final accuracy of classification for the local dataset was 96.05% while the standard dataset has given an accuracy of 92.11%. The final model is a combination of the detection and classification algorithms and it is able to successfully detect and classify traffic signs from an input video feed within an average detection time of 4.5fps

[...] Read more.
Feature Engineering for Cyber-attack detection in Internet of Things

By Maheshi B. Dissanayake

DOI:, Pub. Date: 8 Dec. 2021

Internet of Things (IoT) consists of group of devices which communicates information over private networks. One of the key challenges faced by IoT networks is the security breaches.  With the objective of automating the detection of possible security breaches in five categories, IoT traffic created with Message Queue Telemetry Transport (MQTT) protocol is analyzed. The five categories of cyber-attacks considered are brute force, denial of service (DoS), flooding, malformed data, and SlowITe attacks along with legitimate traffic.  The popular five machine learning (ML) models, LightGBM, Random Forest, MLP, AdaBoost, and Decision Tree Classifiers are trained to predict cyber-attacks. In traditional traffic analysis all the available features of MQTT traffic were utilized for the ML modeling and in this work, we challenge the practice by showing that automated feature selection improves the performance of the overall ML models. The average accuracy, precision, recall and the F1 score are used as performance evaluation metrics. It is observed that all models in average are able to achieve 90% of accuracy in classification, while MLP model is trained 10 times faster than the other models.  Further the optimal number of features for correct classification is identified as 10 features through Monte Carlo analysis. With the reduced features, it is possible to detect DoS, flooding, and  SlowITe attacks with more than 90% accuracy and precision. Yet, it is difficult to tell apart brute force and malformed data attacks.

[...] Read more.
Other Articles