ICACT–2021

Permanent URI for this collectionhttp://repository.kln.ac.lk/handle/123456789/24483

Browse

Now showing 1 - 20 of 35

M-LMS Adoption Intention; Empirical Evidence from Postgraduates in Developing Context
(Faculty of Computing and Technology (FCT), University of Kelaniya, Sri Lanka, 2021) Chandradasa, Isuru
Mobile learning is a widely used teaching and learning method and a Mobile learning management system is a part of the mobile learning process. During the pandemic period, the demand for mobile learning raised rapidly and is continuing to rise. After the pandemic if academic institutions hope to continue this trend, it is important to know about students’ intention to use this Mobile learning management system in the future. Without knowing this continuing this application in the future is a risk for the organization as well as a negative factor for users’ satisfaction. The evidence from past literature in this regard is lacking. Therefore, the objective of this study is to examine the continued intention of Sri Lankan postgraduate's mobile learning management system use in the future. The variables that might influence their continued intention of using this Mobile learning management system are identified from previous literature and based on that conceptual framework and hypothesis of the study developed. This study used quantitative techniques and data collected from 119 postgraduate students of one of the reputed state university in Sri Lanka by employing a convenience sampling technique. The data was analyzed using SPSS 25 statistical software package. The results of the study showed that direct utilization, ease of use, mobility value, academic relevance, and university management support will have a significant impact on the post-graduates' intent on the mobile learning management system in their future academic pursuits. This study provides theoretical and practical insights for researchers and practitioners about M-LMS usage and future implications. The data included postgraduates only from one state university which is the major limitation of this study.
Hybrid Movie Recommendation System
(Faculty of Computing and Technology (FCT), University of Kelaniya, Sri Lanka, 2021) Punitharasa, Sinthujan; Selvanajagam, Kirisanthi; Ramakrishnan, Thamilini; Chelvarajah, Amalraj; Weerasinghe, W.M.R.M.
Movie recommendations play a great part in the aspects of our social life. Such a system allows users to recommend a group of films based on their interests or the popularity of the movies. This research was conducted to study different approaches to movie recommendation and discusses a hybrid approach that combines a content-based filter, a collaborative-memory-based filter, and a collaborative-model-based filter. The proposed system aims to reduce the issues with existing movie recommendation systems by enhancing performance. The content-based filter is based on a TF-IDF classifier with cosine similarity. The collaborative-memory-based filter is based on truncated SVD with Pearson correlation. A collaborative model-based filter is based on improved SVD matrix factorization.
A Consortium Blockchain Model to Overcome Issues in the Global Patent Authentication and Management Process
(Faculty of Computing and Technology (FCT), University of Kelaniya, Sri Lanka, 2021) Gunasekara, Prageeth Thilina; Rajapakse, Chathura
Patent authentication and management is an important activity to protect the intellectual property rights of individuals and organizations globally. As the patents are territorial and the data management related to patent applications mostly happens with local intellectual property (IP) offices, the patent authentication and management (PAM) process is significantly inefficient and time-consuming on the global scale. Moreover, the data management issues in the patent process often lead to conflicts and legal actions among competing parties. Blockchain technology is widely recognized for its potential use in creating decentralized, secure, and transparent systems with immutable records. It hence seems to be a useful technology to overcome the issues in the patent domain. This paper explores the adaptability of blockchain technology in the patent domain. It presents the design of a consortium blockchain system, which is proposed as a solution to numerous issues stemming from inefficient data management. The proposed consortium blockchain design is based on the Ethereum architecture and is equipped with smart contracts to ensure the reliability of patent data as well as the real-time update of records. This paper further discusses the potential testing and validation strategies for the proposed model.
Use of Early Semester Student Feedback for Enhancing Effectivness of Teaching and Learning
(Faculty of Computing and Technology (FCT), University of Kelaniya, Sri Lanka, 2021) Nissanka, Indrajith D.; Nandasiri, Gayani K.
Student feedback in basic engineering modules is important, as the module involves the application of theory into practice. The feedback is used to assess the teaching and learning process at the end of the semester, which is the current practice. This mainly focuses on summative assessment through quantitative scores, where feedback is addressed in subsequent academic years. The early semester feedback can be used to improve the teaching and learning process within the semester itself. It can be designed as formative feedback, focusing on meaningful improvement of the teaching and learning. Hence, it is explored whether early semester feedback can be applied for enhancing the effectiveness of teaching and learning process. In this study, early semester feedback was obtained for the Basic Thermal Sciences module from a selected sample size of 122 students representing two engineering disciplines of the same semester of study. The feedback was collected in two stages of the semester using both paper and Moodle based online questioners. The feedback survey was designed in two sections: the first section provided for quantitative evaluation using rating questions while the second included open-ended questions to obtain qualitative feedback. Survey results depicted students’ selfassessments on their learning and the suggestions for improving the teaching and learning process. The feedback provided diagnostic information on the key changes to be adopted in teaching, that resulted in improved student engagement and performance. Almost 90% of the students responded that their interest was valued, and they felt inclusive in the class while 80% of students were of the impression that class materials are relevant to their professional practice. Also, the subsequent assessment has shown a 10% increase in the average marks for group assignments. It was evident that the students were appreciative of taking the early semester feedback, and it helped to improve the inclusiveness of the student’s requirements into the module.
Advancements in Environmental Technologies for Sustainable Urban Regeneration: A Comparative Assessment
(Faculty of Computing and Technology (FCT), University of Kelaniya, Sri Lanka, 2021) Edirisinghe, Ruwan Danuka
The present study aims to appraise advancements in environmental technologies applicable to urban regeneration, with a special focus on urban brownfield redevelopment. The rapid literature review technique was employed as the research strategy, in the mixed method research design. Technological solutions proposed in the selected articles were comparatively assessed their practicality in an urban setting, in terms of cost, efficacy, physical space required and potential harm to the neighboring environment, by using a five-point scale scoring system. In this study, nanoremediation, thermal remediation methods (i.e. electrical resistance heating, thermal conduction heating and steam enhanced extraction), non-thermal physical remediation methods (electrokinetic remediation, non-thermal plasma technologies, air sparging, soil washing and replacement and passive treatment technologies such as permeable reactive barriers), chemical oxidation (advanced chemical oxidation and Fenton process), and naturebased solutions or bioremediation or gentle remediation technologies (biodegradation processes methods such as bioaugmentation, bioventing, bioprecipitation, biostimulation, landfarming, and phytoremediation methods such as phytostabilization, phytovolatilization and phytoextraction or phytomining and monitored natural attenuation) are presented. Each environmental restoration strategies provided has its own set of limitations, application possibilities and future development potential, as evidenced by this study. Nanoremediation, bioremediation and radio frequency heating in the current state of the art are found to be feasible for an urban area. Property developers and urban authorities could consider the application potential of these technologies in urban brownfield redevelopment in urban regeneration. An integrated approach for addressing the limitations of these technologies may be worth considering in research and developments in the urban sector.
Challenges of Adopting Blockchain Technology to Pharmaceutical Supply Chain – A Case Study from Sri Lankan Health Sector
(Faculty of Computing and Technology (FCT), University of Kelaniya, Sri Lanka, 2021) Paththinige, Pavani Wasana; Rajapakse, Chathura
Ensuring the transparency of pharmaceutical supply chains is an important task to control the adverse health effects of counterfeit drugs. Blockchain technology has been widely recognized among supply chain researchers as a useful emerging technology to enhance transparency and security of various supply chains. However, the adoption of the blockchain technology in pharmaceutical supply chains is still in its infancy with only a handful of research reported to date. This paper presents the details of a conceptual model developed to explore the challenges of adopting blockchain technology to manage pharmaceutical supply chain while combatting against the flow of counterfeit drugs. The proposed conceptual model, which is based on a comprehensive review of literature, encapsulates the complex linkages between seven influencing factors namely 1) Relative advantage 2) Upper management support 3) Human Resource 4) Compatibility 5) Cost 6) Complexity, and 7) Technological Infrastructure and Architecture. The factors evaluated in the framework interact and impact one another. The proposed framework can be utilized as a starting point for implementing blockchain applications in the pharmaceutical supply chain as well as by academics to develop, refine, and assess blockchain based research. As factors have been identified, practitioners will be able to develop a strategy for implementing blockchain in the pharmaceutical supply chain
Solar Power as a Sustainable Energy Source and Readiness Level in Sri Lanka: A Review
(Faculty of Computing and Technology (FCT), University of Kelaniya, Sri Lanka, 2021) Manjitha, Lasny; Munasinghe, Amila
Rapid demand for energy has influenced engineers and scientists' investigation on renewable sustainable energy solutions. Although a wide variety of sustainable natural energy resources are available, usableness depends on technical feasibility and government intervention. Solar energy is a widely accepted solution for electricity generation due to its unique availability. With promotion of the solar power as a means for Sustainable Development Goal (SDG7) of the United Nations, this study is motivated to review information on solar power as a renewable energy source and to examine how Sri Lanka is ready for such move to relieve the economic burden from imported energy. The paper reveals government interventions in solar power initiatives and challenges towards energy sustainability and provides a future outlook.
Convolutional Neural Network for Classification and Value Estimation of Selected Gemstones in Sri Lanka
(Faculty of Computing and Technology (FCT), University of Kelaniya, Sri Lanka, 2021) Amarasekara, Samali; Meegama, Ravinda
Gemstone classification and value estimation are considered to be tedious tasks encountered in the gem industry all over the world. This happens due to colour variations found in the same gem type which is often difficult to detect with the naked eye. This paper presents a machine learning approach to automatically classify the gem type by using an image and also to estimate the value of the stone using a few measurements. The proposed technique uses a microscopic image of a gemstone which is taken using a gemological microscope. A Convolutional Neural Network (CNN) is trained to classify gem type while features such as type, colour palette, shape and weight are used to estimate the value of the. This work creates a system that is capable of classifying and estimating the value of four types of gemstones, namely, Blue Sapphire, Yellow Sapphire, Amethyst and Cat’s eye. The results indicate that the proposed technique managed to classify the gemstones with the highest accuracy of 87% for yellow sapphires and 77% for blue sapphires. The yellow sapphires produced the highest accuracy in colour categorization which can be attributed to the high contrast of the images vailable. As such, it can be concluded that the quality of the original image is important in correctly identifying the exact colour of a gemstone.
Road Accident Severity Prediction in Mauritius using Supervised Machine Learning Algorithms
(Faculty of Computing and Technology (FCT), University of Kelaniya, Sri Lanka, 2021) Sowdagur, Jameel Ahmad; Rozbully-Sowdagur, B. Tawheeda B; Suddul, Geerish
Road accidents with high severities are a major concern worldwide, imposing serious problems to the socio-economic development. Several techniques exist to analyse road traffic accidents to improve road safety performance. Machine learning and data mining which are novel approaches are proposed in this study to predict accident severity. Support Vector Machine (SVM), Gradient Boosting (GB), Logistic Regression (LR), Random Forest (RF) and Naïve Bayes (NB) were applied to perform effective data analysis for informed decisions using Python programming language. The gradient boosting outperformed all the other models in predicting the severity outcomes, yielding an overall accuracy of 83.2% and an AUC of 83.9%
Database Management System Deployment on Docker Containerization for Distributed Systems
(Faculty of Computing and Technology (FCT), University of Kelaniya, Sri Lanka, 2021) Kithulwatta, W.M.C.J.T.; Jayasena, K.P.N.; Kumara, B.T.G.S.; Rathnayaka, R.M.K.T.
Containerization is a novel technology that brings an alternative for virtualization. Due to the most infrastructure-based features, most computer system administration engineers use Docker as the infrastructure level platform. On the Docker containers, any such kind of software service can be deployed. This study aims to evaluate Docker container based relational database management system container behavior. Currently, most scholarly research articles are existing for the database engine performance evaluation under different metrics and measurements of the database management systems. Therefore, without repeating them: this study evaluated the data storage mechanisms, security approaches, container resource usages and container features on the launching mechanism. According to the observed features and factors on the containerized database management systems, containerized database management systems are presenting more value-added features. Hence containerized database management system Docker containers can be recommended for the distributed computer systems for getting the benefit of effectiveness and efficiency.
Review on Decision Support Systems used for Resource Allocation in Health Crises
(Faculty of Computing and Technology (FCT), University of Kelaniya, Sri Lanka, 2021) Diyasena, Deshanjali; Arambepola, Nimasha; Munasinghe, Lankeshwara
A disaster or crisis can be stated as a serious disruption occurring for a certain period of time, which could cause loss of human lives, properties, and disrupt the day-to-day life of people. Managing such situations is always a challenge due to various reasons. Especially, allocating and providing resources to manage disaster situations to restore the normal life of people is the main challenge in a disaster situation. Having a proper mechanism for resource allocation could save thousands of human lives as well as properties. Modern smart technologies play a vital role in designing and developing solutions for efficient and effective resource allocation mechanisms. For example, the COVID-19 pandemic has forced people to work from home using digital platforms. Those digital platforms have been able to support people to do their routine work while maintaining social distancing which minimizes the spread of Covid-19. On the other hand, those digital platforms provide an easy and fast way for healthcare officials to reach infected patients to provide necessary treatments and care. Present research critically reviews the past research on managing resources in health crises particularly falls under pandemics and epidemics.
Audio Steganography using LSB Technique to Embedding Data
(Faculty of Computing and Technology (FCT), University of Kelaniya, Sri Lanka, 2021) Shanmugaradnam, Dayanantha; Weerasinghe, Hesiri Dhammika
Data protection is a major concern on the internet medium. Data needs to be protected from intrusion, penetration, and data theft. Audio steganography is used to hide secret messages in an audio file. This method was intended to secure the secret message. The secret message was protected using the hashing and encryption technique and the Least Significant Bit substitution was performed to hide the data. The Stego audio files were analyzed by Signal-to- Noise Ratio and Mean Opinion Score. The Stego audio files had an 80dB average Signal-to-Noise Ratio and the overall Mean Opinion Score was 4.4 out of 5. It proves that this method helped to improve the robustness and imperceptibility. Using the proposed method higher security can be achieved.
Regularization Risk Factors of Suicide in Sri Lanka for Machine Learning
(Faculty of Computing and Technology (FCT), University of Kelaniya, Sri Lanka, 2021) Delpitiya., D. M. A. U.; Kumarage, Prabha M.; Yogarajah, B.; Ratnarajah, Nagulan
Indication to World Health Organization, suicide is a major world public health concern that is in the top twenty leading causes of death worldwide. Sri Lanka is a country that has the highest suicidal rates in the globe. The comprehensive study about risk factors for suicide is important because we can prevent or treat the recognized most risky categories of people. The emergence of big data concepts with machine learning techniques introduced a resurgence in predicting models using risk factors for suicide. Regularization is one of the most decisive components in the statistical machine learning process and this technique is used to reduce the error on the training dataset and prevent over-fitting. Comprehensive regularization approaches are presented here to select significant risk factors for age-specific suicide in Sri Lanka and build unique predictive models. The Least Absolute Shrinkage and Selection Operator (LASSO) approach presents regularization along with the feature selection to improve the prediction precision. The dataset collected for the study is rooted in the Sri Lankan people and the factors used for the analysis are, suicide person’s gender, lived place, education level, mode of suicide, job, reason, suicide time, previous attempts, and marital status. Further, the riskiest age category of the people, who has exposure to suicide, is identified. Multiple linear regression and Ridge regression were used to evaluate the performance of LASSO. The selected most relevant factors with regularization to predict age-specific suicide prove the effectiveness of the proposed regularization approaches.
Modeling the Relationship between Profitability and Market Share of Licensed Commercial Banks in Sri Lanka
(Faculty of Computing and Technology (FCT), University of Kelaniya, Sri Lanka, 2021) Hettiarachchi, Imesha; Ekanayake, Piyal; Aponsu, Lakshan
Sri Lankan banking industry comprises of two major types of establishments viz. Licensed Commercial Banks (LCB) and Licensed Specialized Banks of which the profitability of the former being determined by the size of the firm, indicated by total assets held by the bank. In this study, the relationship between market share and profitability of LCBs was investigated using Multiple Linear Regression (MLR) analysis and considering the variables unique to the Sri Lankan banking industry. Quarterly data were obtained from the Central Bank of Sri Lanka from 2008 to 2020. In addition to MLR, analysis of variance and time-series analysis was also carried out to ensure the reliance of the results and conclusions. It was found that the market share represented by Deposit Customers and Loan Customers have a positive relationship with the profitability measured by Profit After Tax (PAT). Further, market share explained a substantial 96.5% of the variability in profitability. The model predicted that a unit increase in deposits and loans lead to an increase in profitability by 6.1% and 10.7% respectively. Finally, it could be concluded that the loans granted to bank customers accounted for increasing the profitability of LCBs in Sri Lanka than the deposits made by the customers. Accordingly, the LCBs can review their strategies to optimize profitability based on the loans granted to and deposits received from the customers.
Model for Integration of Technology in Authentic Education-An interpretation of a literature Review
(Faculty of Computing and Technology (FCT), University of Kelaniya, Sri Lanka, 2021) Manjaree, Bhagya; Liyanage, Laalitha S.I.; Rupasinghe, Thilini P.; Tillekaratne, Aashani; de Silva, K.M.N.
This literature review is conducted to identify, appraise and synthesize empirical evidence of a filtered list of recent literature regarding methods in which technology could be integrated to facilitate authentic learning pedagogy. A protocol was developed to carry out a search for screening[1]. iDiscover search engine of University of Cambridge library was used for selection and filtering of the articles for their appropriateness. Critical appraisal was performed and data was extracted to map, conceptualize and synthesize the proposed tripod model for integration of technology in authentic education. This model depicts the findings in three zones namely, foundational layer, operational layer and the stage which is the platform for authentic education. Understanding the landscape of the tripod model for integration of technology in authentic education could be quite decisive in selecting the best-fit technological tool. This article argues about how technological interventions could enhance the outcomes of authentic education and the need of an appropriate pedagogical strategy to align such interventions to the elements of authentic education.
Open Educational Resources (OER) usage in learning: Perspectives of undergraduate students, University of Vocational Technology, Sri Lanka
(Faculty of Computing and Technology (FCT), University of Kelaniya, Sri Lanka, 2021) Thenabadu, M.; Seneviratne, H.A.
Open Educational Resources has gained momentum during the past decade as a way of sharing educational resources with the learning community. This initiative has been very influential in changing the learning culture of higher education worldwide. However, there is a dearth of literature on OER usage, particularly among higher education students in developing countries, despite the fact that, higher education students in developing countries are portrayed as the primary beneficiaries of such initiatives. The aim of this study was to examine the awareness and perceived barriers of using OERs at the University of Vocational Technology. Data were gathered using a survey questionnaire from undergraduate students representing ICT and Food Technology degree programs (n=150). The findings revealed that a significant proportion of students were having less awareness of OER. It was observed that students face many barriers in using OER such as search techniques, content and environmental issues. According to the study, university and faculty members should take the lead in practice and dissemination of the concept of OER among students in order to encourage adoption of this valuable initiative.
UML System Model to Implement Authentic Learning in the 21st Century
(Faculty of Computing and Technology (FCT), University of Kelaniya, Sri Lanka, 2021) Wickramasinghe, Manuja; Wijayarathna, Gamini; Ferenando, Kasun
The Pandemic situation demanded all universities to transform towards online teaching and learning as an alternative to face-to-face study through Technology Enabled Learning (TEL). In most developing countries, universities use Learning Management Systems (LMS) such as Moodle and Blackboard to facilitate online education. The LMS is used mainly to facilitate staff, administration, and students sharing module outlines, specifications, lecture schedules, lesson plans, assignment generation and submission, announcements, and generating assessment reports. However, it has been observed that many inefficiencies exist in the teaching and learning approaches as there is less focus on learner autonomy. Dynamic changes in the world and drastic transformations demand continuous learning and innovative thinking. Authentic learning is an approach that focuses on real-world situations to gain new knowledge and skills in a context rather than listening to lectures and memorizing information. In authentication learning, enabling collaborative learning has been observed as a practical approach to developing critical thinking, reflective thinking, and enhancing creativity. Sri Lankan culture is inherited with authentic learning as our cultural events, traditions, and values encourage living in harmony and learning from each other. This paper proposes a new system as a web portal to ensure that the learner can effectively gain the required knowledge, skills, and attitudes to face complex realworld situations, thus arriving at practical solutions to overcome contemporary issues. The proposed system focuses particularly on distance learning programs, as those could be advanced by the adoption of a model that can be used to guide the design of online learning environments focused on elements of authentic learning. In addition to presenting the authentic task model and its theoretical functionalities, the authors have implanted Bloom's Taxonomy Theory to ensure the quality and effectiveness of the system model. Researchers have incorporated use case diagrams and activity diagrams to exemplify the UML model.
Heart Disease Prediction Using Machine Learning Techniques: A Comparative Analysis
(Faculty of Computing and Technology (FCT), University of Kelaniya, Sri Lanka, 2021) Gamage, L.
In today's world, heart disease is one of the leading causes of death. In clinical data analysis, predicting heart disease is a difficult task. Machine Learning (ML) helps assist with the decision-making and prediction of large volumes of data generated by the healthcare industry. The main goal of this study is to find the best performance model and compare machine learning algorithms for predicting heart disease. This work applies supervised machine learning algorithms, namely Logistic Regression, Support Vector Machine, KNearest Neighbor, and Random Forest, to the Cleveland Heart Disease dataset to predict heart disease. Our experimental analysis using preprocessing steps and model hyperparameter tuning, Logistic Regression, Support Vector Machine, K- Nearest Neighbor and Random Forest achieved 90.16%, 86.89%,86.89%, and 85.25%, accuracies respectively. As a result, Logistic Regression classification outperforms other machine learning algorithms in predicting heart disease.
Field Testing of Highway Bridges Enhanced by Assumptions of Composite Action
(Faculty of Computing and Technology (FCT), University of Kelaniya, Sri Lanka, 2021) Lu, Renxiang; Judd, Johnn
A load rating procedure that involves field testing and composite action considerations for girders affected by external effects is presented in this paper. In the proposed procedure, the critical vehicle sequence for the bridge is determined and the actual response of the bridge is measured using a series of runs by driving a vehicle of calibrated weight. To replace the data readings affected by external effects, the position of the neutral axis corresponding to a fully composite action is assumed. After applying this correction, the actual load rating is discretized and compared with the analytical load rating so that different contributions to the loading capacity are quantified. A three-span non-composite steel girder highway bridge was used to illustrate the procedure. Results indicate that although the unintended composite action was the dominant contribution, the contribution was unreliable for loads beyond the linear elastic regime. It was observed that corrections made based on composite action assumptions improve the understanding of the case study because the contributions due to additional stiffness lateral and longitudinal distribution would have been unrealistic otherwise.
A Systematic Approach to Identify the Breast Cancer Grades in Histopathological Images Using Deep Neural Networks
(Faculty of Computing and Technology (FCT), University of Kelaniya, Sri Lanka, 2021) Silva, S.H.S.; Jinesena, T. M. K. K.
Breast cancer can be recognized as one of the most well-known and life-threatening cancers impacting women and this has been identified as the second most common cancer across the world. According to registered data, there were over 2 million newly reported cases in 2020. The Deep Convolutional Neural Network has been identified as one of the most dominant and powerful deep learning approaches involved in the analysis of visual imagination. There are many shreds of evidence that indicate the appropriateness of this in medical imaging including breast cancer detection, lassification, and segmentation with higher accuracy rates. The main intent of the research is to develop an automated application that can determine the Nottingham Histologic Score of a given input histopathological image obtained from breast cancer or healthy tissues with DenseNet based architecture. Healthy or benign tissues are categorized as zero and cancerous tissues are categorized based on the grade obtained as one, two, or three. In this study, we were able to obtain more than 94% accuracy rates for each trained model including 2-predict, 3-predict, and 4-predict networks. Further, a desktop-based inference tool that allows us to perform breast cancer grading was also developed as a result of this study.