Research Papers - Dept of Computer Systems Engineering
Permanent URI for this collection https://rda.sliit.lk/handle/123456789/1253
Browse
18 results
Filters
Advanced Search
Filter by
Settings
Search Results
Publication Open Access A cost effective machine learning based network intrusion detection system using Raspberry Pi for real time analysis(PLOS ONE, 2025-12-29) Wijethilaka R.W.K.S; Yapa, K; Siriwardena, DIn an increasingly interconnected world, the security of sensitive data and critical operations is paramount. This study presents the development of a Network Intrusion Detection System (NIDS) that analyzes both inbound and outbound network traffic to detect and classify various cyber attacks. The research begins with an extensive review of existing intrusion detection techniques, highlighting the limitations of traditional methods when addressing the unique security challenges posed by distributed networks. To overcome these limitations, advanced machine learning algorithms, including Random Forest, Long Short Term Memory (LSTM) networks, Artificial Neural Networks (ANN), XGBoost, and Naive Bayes, are employed to create a robust and adaptive intrusion detection system. The practical implementation utilizes a Raspberry Pi as the central processing unit for real time traffic analysis, supported by hardware components such as Ethernet cables, LEDs, and buzzers for continuous monitoring and immediate threat response. A comprehensive alert system is developed, sending email notifications to administrators and activating physical indicators to signify detected threats. Our proposed NIDS achieves 96.5 detection accuracy on the NF-UQ-NIDS dataset, with a significantly reduced false positive rate after applying SMOTE. The system processes real time network traffic with an average response time of 50 milliseconds, outperforming traditional IDS solutions in accuracy and efficiency. Evaluation using the NF-UQ-NIDS dataset demonstrates a significant improvement in detection accuracy and response time, establishing the system as an effective tool for safeguarding networks against emerging cyber threats.Publication Embargo IDairy: Intelligence and Secure E-Commerce Platform for Dairy Production and Distribution Using Block Chain and Machine Learning(IEEE, 2022-07-18) Liyanage, I; Madhuwantha, N; Perera, M; Ruhunage, S; Mahaadikara, M. D. J. T. H; Rupasinghe, LThe dairy industry plays an essential role in the Sri Lanka economy. The purpose of this study is to reduce the cost of import dairy products and increase the profit of the dairy industry. IDairy: Intelligence and secure e-commerce platform for dairy production and distribution using blockchain and machine learning has been suggested as a mobile application. As a first step, this research suggested four factors. Develop a business intelligence dashboard using predictive analysis and provide business solutions to dairy companies described the revenue for the coming month using machine learning and the earning data charts for years to come to display in the dashboard. Design IOT device to maintain the temperature of fresh milk cargo while transporting to productions and design smart contract to maintain the optimum temperature for the fresh milk harvest. Develop a system to identify the cows’ diseases using image processing the primary objective was identified cows’ Foot and Mouth diseases and provide notifications to milk farms about existing illnesses. Cows’ disease directly affects dairy productions. Develop a mobile application for farmers to store animal data, do profit calculation, including giving business solutions through the application with location tracking service. With this IDairy application, both farmers and production companies will be able to get an idea about their future profit and will be suggesting the business solutions.Publication Open Access Machine Learning Modelling of the Relationship between Weather and Paddy Yield in Sri Lanka(Hindawi, 2021-05) Ekanayake, P; Rankothge, W; Weliwatta, R; Jayasinghe, J. M. J. WThis paper presents the development of crop-weather models for the paddy yield in Sri Lanka based on nine weather indices, namely, rainfall, relative humidity (minimum and maximum), temperature (minimum and maximum), wind speed (morning and evening), evaporation, and sunshine hours. The statistics of seven geographical regions, which contribute to about two-thirds of the country’s total paddy production, were used for this study. The significance of the weather indices on the paddy yield was explored by employing Random Forest (RF) and the variable importance of each of them was determined. Pearson’s correlation and Spearman’s correlation were used to identify the behavior of correlation in a positive or negative direction. Further, the pairwise correlation among the weather indices was examined. The results indicate that the minimum relative humidity and the maximum temperature during the paddy cultivation period are the most influential weather indices. Moreover, RF was used to develop a paddy yield prediction model and four more techniques, namely, Power Regression (PR), Multiple Linear Regression (MLR) with stepwise selection, forward (step-up) selection, and backward (step-down) elimination, were used to benchmark the performance of the machine learning technique. Their performances were compared in terms of the Root Mean Squared Error (RMSE), Correlation Coefficient (R), Mean Absolute Error (MAE), and the Mean Absolute Percentage Error (MAPE). As per the results, RF is a reliable and accurate model for the prediction of paddy yield in Sri Lanka, demonstrating a very high R of 0.99 and the least MAPE of 1.4%.Publication Embargo EasyTalk: A Translator for Sri Lankan Sign Language using Machine Learning and Artificial Intelligence(IEEE, 2020-12-10) Manoj Kumar, D; Bavanraj, k; Thavananthan, S; Bastiansz, G. M. A. S; Harshanath, S. M. B; Alosious, JSign language is used by the hearing-impaired and inarticulate community to communicate with each other. But not all Sri Lankans are aware of the sign language or verbal languages and a translation is required. The Sri Lankan Sign Language is tightly bound to the hearing-impaired and inarticulate. The paper presents EasyTalk, a sign language translator which can translate Sri Lankan Sign Language into text and audio formats as well as translate verbal language into Sri Lankan Sign Language which would benefit them to express their ideas. This is handled in four separate components. The first component, Hand Gesture Detector captures hand signs using pre-trained models. Image Classifier component classifies and translates the detected hand signs. The Text and Voice Generator component produces a text or an audio formatted output for identified hand signs. Finally, Text to Sign Converter works on converting an entered English text back into the sign language based animated images. By using these techniques, EasyTalk can detect, translate and produce relevant outputs with superior accuracy. This can result in effective and efficient communication between the community with differently-abled people and the community with normal people.Publication Embargo Performance evaluation on machine learning classification techniques for disease classification and forecasting through data analytics for chronic kidney disease (CKD)(IEEE, 2017-10-23) Gunarathne, W. H. S. D; Perera, K. D. M; Kahandawaarachchi, K. A. D. C. PChronic Kidney Disease (CKD) is considered as kidney damage which lasts longer than three months. In Sri Lanka, CKD has become a severe problem in the present days due to CKD of unknown aetiology (CKDu) that can be seen popularly in North Central Province. Identifying CKD in the initial stage is important to provide necessary treatments to prevent or cure the disease. In this work main focus is on predicting the patient's status of CKD or non CKD. To predict the value in machine learning classification algorithms have been used. Classification models have been built with different classification algorithms will predict the CKD and non CKD status of the patient. These models have applied on recently collected CKD dataset downloaded from the UCI repository with 400 data records and 25 attributes. Results of different models are compared. From the comparison it has been observed that the model with Multiclass Decision forest algorithm performed best with an accuracy of 99.1% for the reduced dataset with the 14 attributes.Publication Embargo Real-time credit card fraud detection using machine learning(IEEE, 2019-01-10) Thennakoon, A; Bhagyani, C; Premadasa, S; Mihiranga, S; Kuruwitaarachchi, NCredit card fraud events take place frequently and then result in huge financial losses [1]. The number of online transactions has grown in large quantities and online credit card transactions holds a huge share of these transactions. Therefore, banks and financial institutions offer credit card fraud detection applications much value and demand. Fraudulent transactions can occur in various ways and can be put into different categories. This paper focuses on four main fraud occasions in real-world transactions. Each fraud is addressed using a series of machine learning models and the best method is selected via an evaluation. This evaluation provides a comprehensive guide to selecting an optimal algorithm with respect to the type of the frauds and we illustrate the evaluation with an appropriate performance measure. Another major key area that we address in our project is real-time credit card fraud detection. For this, we take the use of predictive analytics done by the implemented machine learning models and an API module to decide if a particular transaction is genuine or fraudulent. We also assess a novel strategy that effectively addresses the skewed distribution of data. The data used in our experiments come from a financial institution according to a confidential disclosure agreement.Publication Embargo WANHEDA: A Machine Learning Based DDoS Detection System(IEEE, 2020-12-10) Sudugala, A. U; Chanuka, W. H; Eshan, A. M. N; Bandara, U. C. S; Abeywardena, K. YIn today's world computer communication is used almost everywhere and majority of them are connected to the world's largest network, the Internet. There is danger in using internet due to numerous cyber-attacks which are designed to attack Confidentiality, Integrity and Availability of systems connected to the internet. One of the most prominent threats to computer networking is Distributed Denial of Service (DDoS) Attack. They are designed to attack availability of the systems. Many users and ISPs are targeted and affected regularly by these attacks. Even though new protection technologies are continuously proposed, this immense threat continues to grow rapidly. Most of the DDoS attacks are undetectable because they act as legitimate traffic. This situation can be partially overcome by using Intrusion Detection Systems (IDSs). There are advanced attacks where there is no proper documented way to detect. In this paper authors present a Machine Learning (ML) based DDoS detection mechanism with improved accuracy and low false positive rates. The proposed approach gives inductions based on signatures previously extracted from samples of network traffic. Authors perform the experiments using four distinct benchmark datasets, four machine learning algorithms to address four of the most harmful DDoS attack vectors. Authors achieved maximum accuracy and compared the results with other applicable machine learning algorithms.Publication Embargo Performance evaluation on machine learning classification techniques for disease classification and forecasting through data analytics for Chronic Kidney Disease (CKD)(IEEE, 2017-10-23) Gunarathne, W. H. S. D; Perera, K. D. M; Kahandawaarachchi, K. A. D. C. PChronic Kidney Disease (CKD) is considered as kidney damage which lasts longer than three months. In Sri Lanka, CKD has become a severe problem in the present days due to CKD of unknown aetiology (CKDu) that can be seen popularly in North Central Province. Identifying CKD in the initial stage is important to provide necessary treatments to prevent or cure the disease. In this work main focus is on predicting the patient's status of CKD or non CKD. To predict the value in machine learning classification algorithms have been used. Classification models have been built with different classification algorithms will predict the CKD and non CKD status of the patient. These models have applied on recently collected CKD dataset downloaded from the UCI repository with 400 data records and 25 attributes. Results of different models are compared. From the comparison it has been observed that the model with Multiclass Decision forest algorithm performed best with an accuracy of 99.1% for the reduced dataset with the 14 attributes.Publication Embargo HemoSmart: A Non-invasive, Machine Learning Based Device and Mobile App for Anemia Detection(IEEE, 2020-12-22) Jayakody, A; Edirisinghe, E. A. G. A.This paper presents a non-invasive method to detect Anemia (a low level of Hemoglobin) easily. The Hemoglobin concentration in human blood is an important substance to health condition determination. With the results which are obtained from Hemoglobin test, a condition which is called as Anemia can be revealed. Traditionally the Hemoglobin test is done using blood samples which are taken using needles. The non-invasive Hemoglobin measurement system, discussed in this paper, describes a better idea about the hemoglobin concentration in the human blood. The images of the finger- tip of the different hemoglobin level patients which are taken using a camera is used to develop the neural network-based algorithm. The pre-mentioned algorithm is used in the developed noninvasive device to display the Hemoglobin level. Before doing the above procedure, an account is created in the mobile app and a questionnaire is given to answer by the patient. Finally, both the results which are obtained from the mobile app and the device are run through a machine learning algorithm to get the final output. According to the result patient would be able to detect anemia at an early stage.Publication Embargo An Integrated Framework for Predicting Health Based on Sensor Data Using Machine Learning(IEEE, 2020-12-10) Jayaweera, K. N; Kallora, K. M. C; Subasinghe, N. A. C. K; Rupasinghe, L; Liyanapathirana, CAccording to recent studies, the majority of the world's population shows a lack of concern in their health. As a consequence, the non-communicable disease rate has increased dramatically. Amongst these diseases, heart diseases have caused the most catastrophic situations. Apart from the busy lifestyle, studies also show that stress is another factor that causes these diseases. Therefore, the focus of our research is to provide a user-friendly health monitoring system that causes minimum disturbance to its users. However, many studies have focused on predicting health; very few have focused on its usability. The objective of our research is to predict the possibility of cardiac arrests and the presence of stress in real-time using a wearable device prototype. The system uses biometric signals obtained from the photoplethysmogram sensor embedded in the wearable device to perform real-time predictions. We trained three models using random forest, k-nearest neighbor, and logistic regression classification algorithms to predict sudden cardiac arrests with accuracies 99.93%, 99.10%, and 94.47%, respectively. Further, we trained three additional models to predict stress using the same algorithms with accuracies 99.87%, 96.83%, and 65.00%, respectively. Thus, the results of this study show that an integrated framework, capable of predicting different health-related conditions, through sensor data collected from wearable sensors, is feasible.