Smart Computing and Systems Engineering (SCSE)
Permanent URI for this communityhttp://repository.kln.ac.lk/handle/123456789/18936
Browse
9 results
Search Results
Item Defaulter Prediction in the Fixed-line Telecommunication Sector Using Machine Learning(Department of Industrial Management, Faculty of Science, University of Kelaniya Sri Lanka, 2023) Ginige, Sachini; Rajapakse, Chathura; Asanka, Dinesh; Mahanama, ThiliniIn the modern connected era, the telecommunications sector plays a critical role in enabling efficient business operations across all industries. However, defaulting customers who fail to pay their dues after consuming services remain a significant challenge in the industry. Defaulters pose a risk to service providers, calling for measures to lessen both the probability of occurrence as well as its impact. Early identification of defaulters through prediction is a possible solution that enables proactive measures to mitigate the risk. However, the nature of the fixed-line product segment poses additional constraints in identifying defaulters, highlighting an existing knowledge gap. The research aims to evaluate the effectiveness of machine learning as a technique for the prediction of defaulters in the fixed-line telecommunication sector, and to develop an effective predictive model for the purpose. The success of machine learning techniques in analysis and prediction over traditional methods prompted its use in this study. The study followed the design science research methodology. An analysis was conducted based on past transaction data. Special consideration was given to the scenario of customers with little to no transaction history. Based on the analysis, a feature list for identifying defaulters was compiled, and multiple predictive models were developed and evaluated in comparison. The resulting predictive model, which uses the Random Forest technique, shows high performance in all considered aspects. The findings of the study demonstrate that machine learning techniques can effectively predict defaulters in the fixed-line telecommunication sector, with significant implications for mitigating the risk associated.Item Evaluating the Factors that Affect the Adoption of Blockchain Technology in the Pharmaceutical Supply Chain - A Case Study from Sri Lanka(Department of Industrial Management, Faculty of Science, University of Kelaniya Sri Lanka, 2022) Paththinige, Pavani; Rajapakse, ChathuraOne of the significant causes of medicine counterfeiting is the pharmaceutical industry's inadequate supply chain system, which makes it hard to keep track of it. This study aims to identify the factors affecting the adoption of Blockchain in the pharmaceutical supply chain in Sri Lanka. The study's conceptual framework is developed through a thorough literature review and structured interviews. Sample data is acquired from supply chain practitioners, pharmaceutical manufacturers, Medical Supply Division, and National Medicine Regulatory Authority to validate the conceptual model. The Partial Least Squares, Structural Equation Modelling (PLS-SEM) technique was used to investigate the effect of factors on the adoption of Blockchain. Based on a thorough examination of the literature, the suggested conceptual model incorporates the complex relationships between eight significant factors, namely1) Relative advantage, 2) Upper management support, 3) Human resources, 4) Compatibility, 5) Cost, 6) Complexity, and 7) Technological Infrastructure and 8) Architecture. Academics can use the proposed framework to design and review blockchain-based research as a starting point for implementing blockchain applications in the pharmaceutical supply chain.Item Personalized Classification of Non-Spam Emails Using Machine Learning Techniques(Department of Industrial Management, Faculty of Science, University of Kelaniya Sri Lanka, 2022) Dinendra, Harsha; Rajapakse, Chathura; Asanka, P. P. G. DineshWith the advent of computer networks and communications, emails have become one of the most widely accepted communication means, which is faster, more reliable, cheaper, and accessible from anywhere. Due to the increased use of email communications, day-to-day computer users; particularly corporate users, find it cumbersome to filter the most important and urgent emails out of the large number of emails they receive on a given business day. Enterprise email systems are able to automatically identify spam emails but still, there are many non-urgent and unimportant emails among such non-spam emails which cannot be filtered by conventional spam filter programs. Though it may be feasible to set up some static rules and categorize some of the e-mails, the practicality and sustainability of such rules are questionable due to the magnitude of such rules, and the validity period as such rules may become redundant after some time. Thus, it is desired to have an email filtering system for non-spam emails to filter unimportant emails, based on the user’s past behaviour. Despite the availability of research on identifying spam e-mails in the area of further classifying the non-spam e-mails, is lacking. The purpose of this research is to provide a machine learning-based solution to classify non-spam e-mails considering the importance of such e-mails. As part of the research, several machine learning models have been developed and trained using non-spam e-mails, based on the personal mailbox of the first author of this research. The results showed a significant accuracy, particularly with a decision tree, random forests and deep neural network algorithms. This paper presents the modelling details and the results obtained accordingly.Item Detection of IoT Malware Based on Forensic Analysis of Network Traffic Features(Department of Industrial Management, Faculty of Science, University of Kelaniya Sri Lanka, 2022) Nimalasingam, Nisais; Senanayake, Janaka; Rajapakse, ChathuraThe usage of Internet of Things (IoT) devices is getting unavoidable lately, from handheld devices to factory automated machines and even IoT embedded automotive vehicles. On average, 100+ devices are connected to the IoT world per second, and the volume of data generated by these devices and added to the space is just too enormous. The value of the data costs more, and sometimes it is invaluable, and it may pull over the cybercriminals and eventually increases the number of cybercrimes. Therefore, the need to identify malware in IoT is a timely requirement. This research work applies Machine Learning (ML) models and yields an efficient lead to identifying the IoT malware using forensic analysis of their network traffic features by selecting the foremost unique features and combining them with the binary features of the malware families. An outsized dataset with many network traffic collections used various network traffic features. Thus, the proposed model's detection accuracy of almost 100% was achieved from the model during the experimental phase of the study, which was a result of the feature extraction process for each malware type. This model can be further improved by considering the fog level implementation of the IoT layer, where the learning will help identify a malicious packet transfer to the network at level zero.Item A community-based hybrid blockchain architecture for the organic food supply chain(Department of Industrial Management, Faculty of Science, University of Kelaniya Sri Lanka, 2021) Thanujan, Thanushya; Rajapakse, Chathura; Wickramaarachchi, DilaniThis paper presents a novel blockchain architecture to incorporate community-level trust into the organic food supply chain by hybridizing Proof of Authority (PoA) and Federated Byzantine Agreement (FBA) consensus protocols. Community-level trust is an important aspect in the organic agriculture industry. Organic farming, in most parts of the world, happens in small scale farms where the farmers represent rural and less-privileged communities. Even though third-party certification systems exist for quality assurance in organic farming, due to many socio-economic reasons, participatory guarantee systems (PGS) have become a popular alternative among organic farmers and consumers. However, such participatory guarantee systems are still prone to frauds and have limitations in scalability as well. With the recent rise of blockchain technology, there is an emerging trend to adopt blockchain technology to enhance the credibility of organic food supply chains and mitigate the risk of fraudulent transactions. However, despite the popularity of participatory guarantee systems among organic farmer communities, the blockchain researchers have paid little attention to develop blockchain architectures by adopting the community-level trust into their consensus protocols. The hybrid consensus mechanism presented in this paper addresses that gap in existing blockchain research. Apart from discussing the details of the proposed blockchain architecture and the underlying consensus protocol, this paper also presents a qualitative analysis on the proposed architecture based on expert opinions.Item Predicting examination performance using machine learning approach: A case study of the Grade 5 scholarship examination in Sri Lanka(Department of Industrial Management, Faculty of Science, University of Kelaniya, Sri Lanka, 2020) Ranawaka, U.M.; Rajapakse, ChathuraUniversal primary school education is a must requirement and one of the criteria that should be fulfilled by the developing countries according to the International development goals which are also recognized as “Eight Millennium Development Goals”. In the context of Sri Lanka, Government is mostly involved in primary education through government-controlled schools. The success of primary education is measured by conducting a scholarship examination. Those who are getting higher results are given opportunities to attend well-facilitated schools for secondary education. Due to that case, there is a massive competition for passing the examination. Limitless pressure for examination provides lots of issues to students. This paper uses data to investigate a model of academic performance as measured by past results of school tests of Grade 4 and Grade 5. 500 students from eight primary schools in the Gampaha district have been selected for collecting data. The Data on the above-mentioned students have been collected by conducting questionnaires to the teachers who incharged the classes. Then the Logistic Regression model and Multiple Linear Regression model have been applied to predict students’ performances at the examination. The model depicts the likelihood of a student passing or failing the grade 5 scholarship examination and predicts the range of results that students will obtain in the examination. The accuracy of predictive models is measured using the results of students who have already faced the Grade 5 examination. Revealing the potential of students at the grade 5 examination is heavily benefited by teachers because they can provide personalized education for talented students and provide opportunities to other students to improve their talents. The initial architecture of the Grade 5 examination results’ predictive model is being discussed in this paper.Item A microtransaction model based on blockchain technology to improve service levels in public transport sector in Sri Lanka(Department of Industrial Management, Faculty of Science, University of Kelaniya, Sri Lanka, 2020) Jayalath, S.A.; Rajapakse, Chathura; Senanayake, J. M. D.Ticketing mechanism in a public transportation system is a major factor which defines the service quality of the system. Current online payment systems (credit/debit cards, PayPal, etc.) are not compatible with micropayments because transaction processing companies need a minimum transaction amount to make the transaction profitable for them. Therefore, an acceptable micro-transaction model is required in the micropayments domain. In blockchain systems, a third-party intermediary is not facilitating the transactions. Therefore, transaction fees decrease drastically. Using consortium blockchain concept, these fees can be further minimized when proof of work is also handled by a set of approved entities. In this study, an Ethereum based micro-transaction model is proposed to be implemented within the ticketing system in Sri Lankan public transport sector. Bus tickets are programmed as Ethereum smart contracts to handle the payment distribution. Consortium blockchain concept is used in the blockchain-based model where there are regulated bodies as nodes such as the national transport commission to handle the proof of work. Digital currency and Quick Response (QR) codes are incorporated to identify and complete the transaction process. The methodology of this development-oriented research can be described under three major phases. In the first phase, interviews were carried out with relevant stakeholders to identify the process of the current system and its limitations. Also, a broad and extensive study of literature was done parallel to this. During the second phase, identified issues, limitations and downfalls were addressed by designing a novel architecture. In the final phase a prototype is being developed to demonstrate the architecture, In the final phase a prototype is being developed to demonstrate the architecture, then prototype validation and testing were done with simulated data and several key use cases in the domain. The preliminary results of the prototype model show signs of considerable improvement in the service level of the public transport ticketing process and a significant reduction of transaction fees.Item Minimization of fraudulent activities in land authentication through Blockchain-based system(Department of Industrial Management, Faculty of Science, University of Kelaniya, Sri Lanka, 2020) Jayabodhi, L.W.D.C.; Rajapakse, Chathura; Senanayake, J.M.D.In Sri Lanka, the land administration process has not been digitized, which has led to plenty of conflicts in determining the real ownership of lands and drastically increasing the land transaction processing time, which has resulted in many fraudulent activities concerning land management. The existing system is majorly paper-based and centralized. Administrators who have the powers to alter the system according to their wishes hold a huge threat for information security and is a centralized system that bears the risk of a single point of failure. Hence, transitioning into another system that could mitigate the drawbacks in the current land authentication system has become a vital need and currently, the knowledge regard this area is very much limited. The decentralized nature of the blockchain-based system has the potential of diluting major limitations in the current system. The overall objective of this research is to mitigate fraudulent activities in land authentication systems through the blockchainbased technological approach. A prototype of a smart contractbased model has been created and verified with the involvement of the actual users. Since the smart contract-based land authentication model verifies the land ownership within a short period, the transaction processing time narrows down from a few months to a couple of minutes. The results show signs of considerable improvements in the efficiency and the security of the land authentication process, the users who interacted with the prototype and presented positive comments.Item Blockchain-based distributed reputation model for ensuring trust in mobile adhoc networks(Department of Industrial Management, Faculty of Science, University of Kelaniya, Sri Lanka, 2020) Peiris, P.P.C.; Rajapakse, Chathura; Jayawardena, B.Mobile ad-hoc networks also known as MANETs have been in global use for numerous applications which are not possible with fixed network topologies. The distributed operation and dynamic topology have encouraged MANETs to be applied for establishing communication in unstable environments. MANET's dynamic topology and mobility have been very advantageous in the fields of military and disaster management. These dynamic characteristics of a MANET also create a major challenge in managing trust between the mobile nodes. Managing the trustworthiness of information that a node provides to the rest of the MANET is very crucial as misinformation spread can lead to erroneous decision making. Although previous studies have been carried out on trust management in MANETs using price-based and reputation systems, the potential of a globally distributed system has not been utilized practically. Therefore, these systems address the trust management issue within a boundary of a single MANET. Above mentioned systems should be re-evaluated when a node from another MANET joins a new MANET as the reputations of the node in the previous MANET cannot be imported to the new MANET. Lack of a possible solution for this gap may result in misinformation spreading by a malicious node before other nodes determine its reputation, which could be very dangerous in sensitive environments. Therefore, a globally distributed reputation model is a timely need in mobile ad-hoc networking. Blockchain technology is one of the most suitable technologies in present for its immutable and distributed properties to build robust systems. Blockchain is a distributed ledger, that has the ability to store feedback from mobile nodes about the accuracy of information provided by other nodes. A trust factor for each node can be calculated using these feedbacks. A mobile node can then decide whether to trust information, based on nodes’ trust factors. Adopting a development-oriented research methodology, a blockchain based reputation model prototype has been implemented and validated within the study.