DRC 2024

Permanent URI for this collectionhttp://repository.kln.ac.lk/handle/123456789/29875

Browse

Now showing 1 - 20 of 25

A SYSTEMATIC REVIEW OF AI-BASED IMAGE PROCESSING MODELS FOR PERSONALIZED DIAGNOSIS AND SEVERITY ASSESSMENT OF SKIN DISEASES
(The Library, University of Kelaniya, Sri Lanka., 2024) Wijerama, N. S.; Asanka, P. P. G. D.; Mahanama, T.
This systematic review provides a thorough analysis of the current state of AI-based image-processing models used in diagnosing and assessing the severity of skin diseases. The review synthesizes recent advancements in deep learning models, exploring various methodologies employed in dermatological image analysis. While significant progress has been made in developing AI tools for skin disease diagnosis, the review identifies critical challenges that hinder the clinical adoption of these technologies. Among the most pressing issues are the lack of data diversity, insufficient integration of patient-specific information, and limited generalizability of models across different skin types and conditions. The review also highlights a major gap in current research: the frequent omission of demographic and clinical data, which are essential for creating personalized diagnostic tools. Furthermore, there is a notable absence of models that can accurately assess disease severity—a crucial component for effective treatment planning and management. These shortcomings underline the necessity for more comprehensive data collection strategies, including the incorporation of multi-modal datasets that encompass diverse patient populations. In addition to data improvements, the review emphasizes the need for the development of more robust and generalizable AI frameworks. Such frameworks would enhance the accuracy and reliability of AI diagnostics in dermatology, making them more applicable in real-world clinical settings. By addressing these gaps, the review offers valuable insights and practical recommendations for future research. Ultimately, this work aims to contribute to the advancement of equitable, personalized, and effective dermatological care through the integration of cutting-edge AI technologies.
ADVANCES IN FLEXIBLE ORGANIC FIELD-EFFECT TRANSISTORS IN THE APPLICATION OF ARTIFICIAL SKIN
(The Library, University of Kelaniya, Sri Lanka., 2024) Madampage, M. S. V.; Keshan, K. D. H.; Kodithuwakku, T.; Karunarathna, M. G. N. S.; Liyanapathirana, B. C.; Seneviratne, J. A.; Kumarage, W. G. C.
Flexible organic field-effect transistors (FOFETs) represent a breakthrough in the domain of flexible electronics, encompassing roll able displays, bendable smart cards, flexible sensors, and influencing the development of artificial skin. In the realm of artificial skin, flexible electronic systems have achieved remarkable advancements for instance in stretch ability, from 30% up to 300%, through rational structural designs involving rigid inorganic matter. Recent studies highlight the practical applications of these technologies in prosthetics, robotics, and wearable health monitoring devices, particularly in the form of pressure sensors, temperature sensors, and bioelectronic interfaces. OFET can work inside a human body because of their mechanical resilience. The skin-like sensing, skin-biothermal, and self-healing properties endow them with broadband applications. Integration of machine learning and soft robotics has further improved their performance, making them more reliable and efficient in such a way that leading the path to exciting advancements in artificial skin, but it is also important to recognize that many challenges remain including long-term stability and biocompatibility. This review article provides a comprehensive overview of the state-of-the-art advancements in flexible OFETs, underscoring their transformative potential in artificial skin applications. It also addresses the current challenges in the field, including issues related to long-term stability, biocompatibility, and the need for seamless integration with biological tissues. Additionally, the article discusses the potential for future research and development, highlighting the interdisciplinary nature of this domain that bridges material science, electronic engineering, and biomedical technology. The insights provided in this review pave the way for continued innovation, fostering advancements that could revolutionize the fields of prosthetics, robotics, and wearable health technologies.
ASSESS THE ROLE OF ARTIFICIAL INTELLIGENCE IN SUPPORTING AND ENHANCING DECISION-MAKING PROCESSES WITHIN ORGANIZATIONS: A SYSTEMATIC LITERATURE REVIEW
(The Library, University of Kelaniya, Sri Lanka., 2024) Perera, K. A. V. U
This study aims to assess the role of Artificial Intelligence (AI) in supporting and enhancing decision-making processes within organizations. The research objectives include understanding how AI influences decision-making, identifying AI tools and applications used in this context, and exploring the challenges associated with AI-driven decision-making. A systematic literature review was employed while reviewing articles from Google Scholar database. Key findings indicate that AI significantly enhances decision-making by providing data-driven insights, automating routine tasks, and enabling predictive analytics. AI tools such as machine learning algorithms, natural language processing, and expert systems were identified as critical enablers of improved decision-making processes. However, the study also highlights several challenges, including data quality issues, algorithmic bias, lack of transparency, ethical considerations, and the need for robust integration with existing organizational processes. The conclusion emphasizes that while AI holds considerable potential for transforming decision-making in organizations, addressing these challenges is crucial for its effective implementation. Recommendations include establishing robust data governance frameworks, investing in explainable AI techniques, implementing ethical guidelines, and fostering a culture of continuous learning and innovation. By navigating these challenges, organizations can fully leverage AI to make more informed, ethical, and effective decisions. The findings contribute to the existing body of knowledge on AI in organizational decision-making and provide practical insights for practitioners aiming to integrate AI into their decision-making processes.
BARRIERS FOR MANUFACTURING SMES: A SYSTEMATIC EMPIRICAL RE-VIEW AND FUTURE RESEARCH AGENDA
(The Library, University of Kelaniya, Sri Lanka., 2024) Hettiarachchi, H. N.; Abeysekera, R.; Divakara, S.
Small and Medium-sector enterprises play an important role in creating employment opportunities, poverty reduction, GDP growth and economic improvement in any country. Thus it is considered as the backbone of the economy. The objective of this paper is to examine the entrepreneurship literature that discusses the barriers for small and medium-sector manufacturing organizations and set future research directions through a systematic literature review. To do this systematic literature review, a number of researches that investigated the barriers for manufacturing SMEs have been taken into consideration. To conduct the review, the PRISMA Method (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) has been followed. This study is based on journal articles published in databases such as Emerald Insight, Sage, Research Gate Net, Taylor & Francis, Science Direct and Google Scholar. After setting inclusion & exclusion criteria, 60 journal articles were selected. Economic issues, financial barriers, political barriers, lean manufacturing barriers, internationalization barriers, e-commerce adoption barriers, lack of resources and management issues have been identified as the prominent barriers for manufacturing SMEs. However, there is no adequate evidence to support that institutions and human capital are strong determinants for SME development. In line with the systematic literature review, most of the research to investigate SME barriers had been done in developing countries. However, research is scarce in South Asian countries like Sri Lanka, Nepal, Maldives and Bhutan. At the same time, the majority of the studies utilized the quantitative methodology to investigate the SME barriers. Qualitative researches are comparatively less. Therefore, more attention is needed to fill these gaps in existing literature to get a full understanding of the matter. Thus, this literature-based study calls for a new research agenda to investigate such issues as it directly and indirectly results in to improvement of the entire SME sector.
BEYOND BORDERS: ORCHESTRATING UNITY IN DIVERSITY AND NURTURING A CULTURE OF INCLUSIVITY IN THE WORKPLACE
(The Library, University of Kelaniya, Sri Lanka., 2024) Illangarathne, S. M. R.
This research paper review explores the pivotal role of Human Resources (HR) professionals in promoting diversity and inclusion (D&I) within the workplace. In today's interconnected global landscape, organizations are increasingly acknowledging the importance of diversity and inclusion not only as a moral obligation but also as a strategic advantage. The paper commences by clarifying the conceptual framework of diversity and inclusion, emphasizing their significance in fostering creativity, innovation, and overall organizational performance. Subsequently, the study conducts an extensive analysis of optimal strategies for HR professionals to effectively advance D&I within their organizations. These strategies encompass diverse elements, including recruitment and hiring approaches, employee training and development initiatives, leadership commitment, and the establishment of inclusive workplace policies and practices. Additionally, the paper deep dives into the role of HR technology and data analytics in facilitating D&I initiatives, underscoring the importance of utilizing data-driven insights to identify disparities and implement targeted interventions. Furthermore, the paper addresses the challenges and obstacles that HR professionals may confront in their efforts to promote D&I, such as unconscious bias, resistance to change, and inadequate resources. It outlines strategies for overcoming these challenges, emphasizing the significance of leadership support, cultural competence training, and fostering a culture of accountability. Through a thorough review of existing literature and case studies, this paper offers valuable perspectives and actionable recommendations for HR professionals aiming to cultivate diverse and inclusive workplaces.
BIOETHICS TEACHING AND ITS’ EFFECTIVENESS IN UNDERGRADUATE MEDICAL PROGRAMMES: A NARRATIVE REVIEW
(The Library, University of Kelaniya, Sri Lanka., 2024) Godamunne, P. K. S.; Kodikara, K.
Medicine is an art as much as it is a science. Patients wish to consult professional and compassionate doctors, though they rarely meet such. To cultivate professionalism in medical students, bioethics teaching have been incorporated into medical programmes in varying degrees across the world. This reports findings from a narrative synthesis of previously published literature that evaluates the evidence regarding implementation of bioethics in undergraduate medical curricula, with special attention to the Asia, Pacific region. For this purpose, Google Scholar and MEDLINE/PubMed databases were searched for articles on bioethics published between January 2000 to April 2024. Reviews or studies that were published in languages other than English were excluded from the search. The focus was placed on the development of moral competence as the intention of this review was to inform bioethics teaching. The results reveal a high degree of diversity of the curricular structure of bioethics courses and the lack of formalization of bioethics in the curricula specially in the Asia-Pacific region. Bioethics teaching resulted on lowering student indecision when faced with moral dilemmas. The call for use of local cases to enhance bioethics education is prominent, enabling more opportunities for reflection and discussion, to stimulate critical judgment of future clinicians.
COMPARATIVE ANALYSIS OF REGIONAL NATIONAL RESEARCH AND EDUCATION NETWORK (NREN) CONSORTIUMS: COMPARING MEMBERSHIP, GOVERNANCE, FINANCING, AND REGIONAL CONTEXTS IN THE GLOBAL SCENARIO
(The Library, University of Kelaniya, Sri Lanka., 2024) Withanage, S. D.; Ragel, R. G.; Gunasekera, K.
This research undertakes a comprehensive comparative analysis of regional National Research and Education Network (NREN) consortiums, examining critical elements such as membership criteria, governance models, financing mechanisms, and the influence of regional contexts. The objective is to delineate best practices and provide recommendations to enhance the effectiveness, inclusivity, and sustainability of NREN consortiums globally. The analysis reveals that NREN consortiums vary significantly in their membership criteria, with some offering multiple membership categories beyond the core NREN members. Governance models predominantly feature a Board of Directors, although community governance models are also practiced. Financing mechanisms primarily rely on membership and service fees, with some consortiums in lower-income regions benefiting from grant funding. Regional contexts play a crucial role in the formation and operation of NREN consortiums. Political stability and economic strength are notably higher in American and European regions compared to African and Asian regions, where conditions vary widely. Technological advancement and digital connectivity are also more developed in American and European regions, while cultural and social factors exhibit significant diversity across all regions. Based on these findings, the study recommends enhancing membership criteria to be more inclusive, adopting effective governance models, diversifying financing mechanisms, and tailoring strategies to regional contexts.
DIFFERENT ENTOMOLOGICAL TECHNIQUES USED FOR SURVEILLANCE OF LEISHMANIASIS VECTOR SAND FLIES (DIPTERA; PSYCHODIDAE); A REVIEW ON THE APPLICABLITY FOR SURVEILLANCE PROGRAMME
(The Library, University of Kelaniya, Sri Lanka., 2024) Kumari, J. Y.; Gunathilaka, N.; Amarasinghe, L. D.; Dalpadado, C. P. R. D.
Sand flies (Diptera; Psychodidae) are vectors of Leishmania, a protozoan parasite that causes the disease leishmaniasis. Since the disease leishmaniasis is prevalent among people in some parts of the world, it is necessary to apply possible control measures to prevent further transmission of the disease. For that, effective vector surveillance plays a vital role. Depending on sand fly species, their resting and breeding habitats, and environmental characteristics, the suitability of an effective trapping method could vary. Therefore, this comparative review was conducted to examine the effectiveness of various entomological techniques for sampling sand fly immature and adults, focusing on their suitability in vector surveillance programs in different environmental habitats. Different field traps including hand operated aspirators, light traps, baited traps, and sticky traps, have been employed in different studies from various geographical areas. This review provides the pros and cons of different techniques, their applicability in different ecological settings, and their productivity in trapping sand flies, highlighting emerging advances of each technique, challenges, and possibilities for improvement of trapping strategies in respect to designing and implementing more productive sand fly surveillance which will ultimately affect the control and possible elimination of leishmaniasis.
EFFECT OF BISPHENOL-A ON THE GROWTH, DEVELOPMENT, AND SURVIVAL OF EARLY STAGES OF ANURANS; A SYSTEMATIC REVIEW
(The Library, University of Kelaniya, Sri Lanka., 2024) Rajapaksha, N.; Rajapaksa, G.
Bisphenol – A is a popular industrial chemical used in the production of polycarbonate plastics and epoxy resins. Bisphenol – A is a xenoestrogen and type-I endocrine disruptor that interferes with natural hormone signaling pathways, leading to physiological and developmental adversities in living organisms. Owing to high industrial usage and poor plastic waste management practices, bisphenol – A has become a ubiquitous contaminant in urban aquatic ecosystems around the world. Aquatic larval stages of frogs and toads of Order Anura are vulnerable for aquatic pollutants including bisphenol-A. However, research findings on the effects of bisphenol – A on Anurans are not comprehensive and inconclusive. Therefore, existing literature on growth-related effects of bisphenol – A on early life stages of Anurans were systematically reviewed. Literature search was carried out using keywords such as “bisphenol A”, “tadpoles”, “amphibians”, “xenoestrogens” across several data bases. Collected literature was screened according to inclusion and exclusion criteria of Preferred Reporting Items of Systematic Review and Meta-Analysisn (PRISMA) approach. Twelve articles were recruited for the systematic review. Systematic review revealed that survival rate of tadpoles decreases with increasing concentration of bisphenol – A under exposure concentrations of 110-10– 110-4 M. However, significant lower survival rates were observed only under non – environmentally relevant concentrations and prolonged exposures. Bisphenol – A induced morphological malformations such as oedema, flexures, short body length, and scoliosis were observed in concentrations higher than 210-5 M. Female – biased sex ratios were observed even under low concentrations such as 110-8 M and 1*10-7 M of bisphenol - A. According to the systematic review, bisphenol - A significantly affects Anuran larvae at non – environmentally concentrations leading to morphological abnormalities and increased morphology. However, female – biased sex ratios were evident even under low concentrations.
EXPLORING INDUSTRY 4.0 DRIVERS AND THEIR IMPACT ON LOGISTIC SECTOR: A SYSTEMATIC REVIEW
(The Library, University of Kelaniya, Sri Lanka., 2024) Samarathunga, D.; Withanaarachchi, A.
Industry 4.0 marks the fourth industrial revolution, characterized by the integration of advanced digital technologies such as the Internet of Things (IoT), artificial intelligence (AI), robotics, big data analytics, and cloud computing into manufacturing and production processes. This evolution aims to create intelligent and efficient manufacturing environments by enhancing computerization, application, and information exchange throughout the value chain. In the logistics sector, a crucial component of global value chains, the adoption of Industry 4.0 technologies is expected to revolutionize operations by offering real-time information, advanced analytics, and self-sustaining processes, which can lead to increased efficiency, reduced costs, and improved customer satisfaction. However, the adoption of Industry 4.0 in Sri Lanka's logistics industry has been slow due to several challenges, including inadequate infrastructure, high implementation costs, and a shortage of skilled personnel. Regulatory and economic factors further complicate the adoption process. This study aims to address these challenges by exploring key factors that affect the performance of logistics firms in Sri Lanka in the context of Industry 4.0. Through a systematic literature review of 45 empirical publications, the study identifies critical components for successful adoption, including technological readiness, organizational culture, and workforce skills. It also examines how economic fluctuations impact the adoption and effectiveness of Industry 4.0 technologies. The findings offer valuable insights for overcoming adoption barriers and optimizing logistics performance, contributing to the broader understanding of Industry 4.0 in logistics and providing a foundation for future research and practice.
FORMATIVE AND SUMMATIVE ASSESSMENT AND ITS IMPACT ON COURSE UNIT PERFORMANCE: EVIDENCE FROM MANAGEMENT UNDERGRADUATES OF UNIVERSITY
(The Library, University of Kelaniya, Sri Lanka., 2024) Weligamage, S. S.; Karunarathne, W. V. A. D.; Karunarathne, R. A. I. C.
Assessment plays a fundamental role in education. The primary purpose of this study is to examine the effect of formative and summative assessment on students’ performance in the course units. To achieve this objective, we designed this study as a multi-stage study, and this paper presented the data collected in stage one of the study. First, we examined the existing practices of formative and summative assessment in evaluating students’ performance; then, we examined the relationship between formative and summative assessment and the students’ performance of different course units. Furthermore, we examined the impact of formative and summative assessments on the performance of different course units. We collected secondary data from two selected departments of the Faculty of Commerce and Management Studies, University of Kelaniya, which aimed to see the effect of changing the composition of each assessment method on the final evaluation. We choose the course units which represent the main course units offered by the faculty. This study's findings revealed that the student's final performance of the course unit is highly related to the summative assessment, and the formative assessment score varies according to the type of assessment, i.e., individual vs group. Individual assessments have a more impact on final course unit performance. The outcomes of this study, theoretically as well as practically is very vital and important for policy design in higher education.
IMPACT OF CLOUD ENTERPRISE SYSTEMS ON BUSINESS SECURITY AND BUSINESS CONTINUITY IN SMES IN SRI LANKA: A SYSTEMATIC LITERATURE REVIEW
(The Library, University of Kelaniya, Sri Lanka., 2024) Malshan, W. P. P.; Wijayanayake, W. M. J. I.
The adoption of cloud enterprise systems presents a transformative opportunity for small and medium enterprises (SMEs) in Sri Lanka, particularly in enhancing business security and continuity. This research investigates how these systems can effectively address critical challenges faced by SMEs, including cybersecurity threats, regulatory compliance, and infrastructural constraints. Utilizing a mixed-methods approach, the study integrates a systematic literature review with qualitative data from interviews and focus groups, as well as quantitative data from structured surveys. The findings reveal that while cloud technologies provide significant benefits in terms of data security, operational efficiency, and disaster recovery, the adoption process is hindered by unique local challenges. Key barriers identified include inadequate technological infrastructure, limited awareness among stakeholders, and regulatory hurdles that complicate implementation. To tackle these issues, the research proposes a tailored cybersecurity framework designed to offer practical guidelines for SMEs, enhancing their security posture. Moreover, strategic recommendations are presented to assist policymakers and technology providers in creating a supportive environment for cloud adoption. This research contributes to a deeper understanding of the role of cloud enterprise systems in improving business security and continuity for SMEs in Sri Lanka. It offers actionable insights for stakeholders aiming to cultivate a resilient and secure business ecosystem. By addressing the specific needs and challenges of SMEs, the study aims to promote a more robust adoption of cloud technologies, ultimately supporting the growth and sustainability of these enterprises in the evolving digital landscape. Overall, this research underscores the importance of cloud solutions in fostering a secure and efficient operational framework for SMEs in Sri Lanka.
IMPROVING CARDIOVASCULAR RISK PREDICTION OF SRI LANKANS USING ARTIFICIAL INTELLIGENCE
(The Library, University of Kelaniya, Sri Lanka., 2024) Mettananda, C.; Solangaarachchige, M. B.; Haddela, P. S.; Dassanayake, A. S.; Kasturiratne, A.; Wickramasinghe, A. R.; Kato, N.; De Silva, H. J.
There are no CV risk prediction models derived from Sri Lankan cohorts. Therefore, the World Health Organization(WHO) risk charts developed for the Southeast Asia Region are being used to risk stratify Sri Lankans. However, Sri Lankans are quite different to some Southeast Asian countries and may not agree with Sri Lankans. Therefore, we aimed to develop a CV risk prediction model specific to a cohort of Sri Lankans. Using supervised machine learning of 10-year follow-up data of a randomly selected, population-based cohort of Sri Lankans, we developed a model to predict the 10-year risk of developing a cardiovascular event. We compared predictions of the new model at baseline in 2007 with the observed events in 2017 following a 10-year follow-up using receiver operating characteristic curves(ROC) to find the predictive performance. We compared the predictions of the new model and the currently used WHO risk charts. We selected 2596 Sri Lankans between 40 and 65 years old with no history of previous CV diseases (CVD) at recruitment and who had completed 10-year follow-ups. There were 179 hard CVDs recorded over the ten years. CVD included all cardiovascular deaths confirmed or presumed cases as mentioned in death certificates, non-fatal strokes, and physician-diagnosed non-fatal acute coronary syndromes, including elective percutaneous coronary interventions and coronary artery bypass grafts done on patients with symptomatic unstable angina. Any cardiac presentation except those mentioned here was excluded. Of 179 events, the ML-based model predicted 124; only 33 were predicted by the new model, while only 33 were predicted by 2019 WHO risk charts. The new ML-based model had 0.93 accuracy with an AUC-ROC of 0.74 ± 0.06. Machine learning of individual data of a Sri Lankan cohort improved CV risk prediction of Sri Lankans than using risk charts developed for an epidemiological region using a modelling approach.
INDIGENOUS MANAGEMENT FOR SUSTAINABILTY: A SYSTEMATIC REVIEW
(The Library, University of Kelaniya, Sri Lanka., 2024) Rajapaksha, S.
Meeting sustainable practices is a worldwide necessity in order to address the present issues encountered by the contemporary world. The involvement of indigenous management is essential for ensuring the long-term sustainability. Indigenous management and sustainability are closely linked ideas that emphasize the significance of indigenous knowledge, practices, and values in fostering the enduring welfare of ecosystems and communities. Indigenous management practices are founded on a profound comprehension of local ecosystems. Given the present global circumstances, it is crucial to examine and investigate the potential of indigenous management and knowledge systems in order to understand their role in promoting sustainability. This review study was conducted using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) technique, which involved doing a systematic literature review (SLR). The VOSviewer program was utilized to conduct keyword co-occurrence analysis, which unveiled the specific research areas requiring concentration. The Scopus database was utilized to download articles in order to assure the high quality of the information included in this conceptual paper. The keywords that are least studied in relation to indigenous management and sustainability are social and ecological resilience, as well as traditional medicine. Approximately 70% of the publications published pertain to the topic areas of agriculture, social sciences, and environmental studies. Based on the cluster analysis, two themes were developed, Indigenous Management in Natural Environment and Sustainability and Indigenous Management in Traditional Medicine and Sustainability. There is a significant void in various sectors when it comes to investigating the influence of indigenous management practices on sustainability. Moreover, it is imperative to examine the influence of indigenous knowledge on contemporary management education and the interconnectedness between the two.
LEVERAGING LARGE LANGUAGE MODELS IN CYBERSECURITY: A SYSTEMATIC REVIEW OF EMERGING METHODS AND TECHNIQUES
(The Library, University of Kelaniya, Sri Lanka., 2024) Sandaruwan, T.; Wijayanayake, J.; Senanayake, J.
This systematic literature review examined how Large Language Models (LLMs) can be incorporated with vulnerability scanning and other cybersecurity tools and explored and assessed ways to improve cybersecurity practices. The PRISMA model was used, and the search was conducted using specific search terms in the leading databases such as the ACM Digital Library, IEEE Xplore Digital Library, and ScienceDirect from 2018 to July 2024. Initially, 313 records were gathered and reduced the count was reduced to 48 articles after applying the inclusion criteria. The findings were structured to answer the research questions regarding the approaches applied to incorporate LLMs with cybersecurity tools and the strengths and limitations of these tools based on the identified methodologies. The methods were reviewed and classified into Training and Adaptation Methods, Integration and Deployment Methods, and Inference and Utilization Techniques. After that, the accuracies of these methods were presented. The results show that fine-tuning and domain adaptation improves LLMs’ performance in cybersecurity tasks. In addition, fine-tuning, prompt engineering, and few-shot learning enhance models for specific tasks, making them more efficient in practical applications.
OUTLIER DETECTION IN DATA WAREHOUSES TO IMPROVE DESCRIPTIVE AND DIAGNOSTIC ANALYTICS
(The Library, University of Kelaniya, Sri Lanka., 2024) Fernando, W. W. A. D. R.; Asanka, P. P. G. D.
This paper reviews the literature on outlier detection(OD) technologies to improve descriptive and diagnostic analytics in data warehouses. This will ensure higher-quality and more reliable data, increasing decision-making and operational efficiency. The major research objectives are a systematic review of existing OD techniques; identification and discussion of the key challenges and limitations in applying the OD methods to data warehouse environments and synthesis of methodologies for integrating OD with descriptive and diagnostic analytics. The study collects data from both traditional and AI-based literature review tools. Traditional review tools are Google Scholar, Research Gate, and IEEE Xplore. AI-based review tools are Semantic Scholar, Research Rabbit, and SciSpace. To present the insights, the study objectively selected 57 papers that were published between 2010 and 2024 were considered. The literature review here elaborates on the OD in a data warehouse which uses different data warehousing techniques and data analytics to enhance the quality and reliability of data to correct. This systematic review goes from the evaluation of statistical-based to distance-based, density-based, clustering-based, learning-based, and ensemble-based. The OD methods of unsupervised learning have been found to outperform those of supervised learning in special settings that are massive and heterogeneous in information like data warehouses. Isolation Forest, Local Outlier Factor (LOF), One-Class SVM, and Autoencoders are identified as highly accurate and efficient at detecting anomalies. Moreover, hybrid models combining several OD methods have been demonstrated to perform better than individual techniques. The results may be useful in offering important new insights and practical guidelines for developing more effective.
POTENTIAL CRITICAL FACTORS INFLUENCING THE MATURITY OF BUSINESS ANALYTICS IN SRI LANKA – A SYSTEMATIC LITERATURE REVIEW
(The Library, University of Kelaniya, Sri Lanka., 2024) De Silva, T. N.; Jayasinghe, S.; Wijayanayake., W. M. J. I.
In the rapidly evolving, data-driven business landscape, organizations leverage vast amounts of data from various sources to enhance efficiency, decision-making, and financial performance. Business Analytics (BA), defined as the use of data, IT, statistical analysis, quantitative methods, and computer-based models, plays a crucial role in this context. The maturity of business analytics, which measures an organization's analytics competency, is pivotal for making informed, data-driven decisions. This systematic literature review investigates the potential critical factors influencing business analytics maturity in Sri Lanka's apparel and software industries. This review utilized the PRISMA framework to identify and screen relevant literature, resulting in the selection of 43 papers that met the inclusion criteria, focusing on business analytics maturity and its influencing factors, using the Technology-Organization-Environment (TOE) framework. The review identifies and categorizes key factors such as compatibility, data management, data infrastructure, technology-supporting infrastructure, trust-in-technology, top management support, organizational culture, organizational readiness, and environmental factors including regulations and competition pressure as the potential factors that could affect the BA maturity of Sri Lankan apparel and software industry. The analysis reveals that top management support, organizational culture, data management, and robust technology infrastructure are the most significant determinants of BA maturity. The findings suggest that while these factors are widely recognized in broader contexts, their applicability and impact within Sri Lanka's unique business environment require empirical validation. Consequently, this review highlights the necessity for future research to test these factors specifically in Sri Lanka's software and apparel industries.
REVIEW OF EFFECTIVE CANDIDATE EVALUATION USING KSA PARAMETERS
(The Library, University of Kelaniya, Sri Lanka., 2024) Asanka, P. P. G. D.; Dilshan, B. A. T.
This literature study has the goal of reviewing the significance of Knowledge, Skills, and Abilities in resume analysis in the case of software engineering applicants. The period of study is from 2015 to 2024, and the emphasis is on the use of Natural Language Processing (NLP) and Machine Learning (ML) in the automation of the recruitment process. The purpose of the study is to assess KSA(Knowledge, Skills, Abilities) factors in their relationship to resume analysis and evaluate successful approaches in the application of NLP and ML. Research data was obtained through academic databases. Inclusion criteria included information on KSA, peer-reviewed studies, and data on the NLP and ML application in resume analysis. The result is that 58 records were selected and submitted to risk of bias evaluation. The findings state that the employment of the combined NLP and ML significantly assists in the process of KSA evaluation of submitted resumes. Recommendations include further studies of the analysis and information extraction skills of the two technologies. The implications of KSA factors are that they significantly improve the resume analysis and candidate assessment. The results present important stakeholders, most influential researchers and authors, most reliable journals, and major trends in the field of resume evaluation. This study constitutes a new basis for the following research and applications. The emphasis can be made on the utilization of standardized concepts for KSA evaluation and further innovation in this sphere.
SYSTEMATIC LITERATURE REVIEW ON AI CHATBOT SOLUTION FOR MEDICAL PRACTITIONER ADOPTION AND ENGAGEMENT WITH THE HEALTHCARE SYSTEM IN SRI LANKA
(The Library, University of Kelaniya, Sri Lanka., 2024) Adhikari, T.; Wijenayake, J.; Vidanage, K.
This study examines the impact of adopting digital health technologies, specifically AI-driven solution chatbots, on healthcare systems in Sri Lanka. Despite the global proliferation of digital health tools, Sri Lanka faces unique challenges and opportunities in integrating these technologies. This research addresses key barriers, facilitators, and the potential role of AI chatbots in transforming healthcare delivery in the region. A systematic literature review was conducted, analyzing 52 relevant studies from 2016 to 2023, sourced from Google Scholar, ResearchGate, arXiv, and Sci-Hub. The review focused on global trends in health technology adoption, barriers specific to Sri Lanka, and strategies for the successful implementation of AI-driven healthcare solutions. The findings indicate that inadequate infrastructure, socio-economic factors, and cultural resistance are significant barriers to the adoption of digital health technologies in Sri Lanka. However, lessons from global best practices and case studies from similar contexts highlight the potential strategies to overcome these challenges. AI chatbots, in particular, demonstrate significant potential in improving healthcare efficiency and patient engagement but require robust infrastructure and supportive policies for successful implementation. Effective strategies such as improving infrastructure, providing financial incentives, and comprehensive training programs are crucial for overcoming the identified barriers. The role of AI chatbots is underscored as a transformative tool in healthcare, capable of reducing workload for healthcare professionals and enhancing patient management. However, challenges related to data privacy, accuracy, and reliability necessitate continuous human oversight and adaptive regulatory frameworks. Integrating AI-driven solutions like chatbots into Sri Lanka's healthcare system could lead to more efficient healthcare delivery, reduced workload for medical practitioners, and ultimately, better patient care and management across the country. While these technologies offer promising improvements, addressing their limitations through better infrastructure, supportive policies, and ongoing human involvement is essential. Future research should focus on practical applications and the long-term impact of these technologies in healthcare settings.
SYSTEMATIC REVIEW OF DEEP LEARNING TECHNIQUES FOR REAL-TIME DEFECT DETECTION IN FABRIC MATERIALS
(2024) Harith, W.A.S.; Rajapakse. C.
This systematic review delves into the significant advancements of deep learning techniques in realtime defect detection for fabric materials, a critical component of improving quality control in textile manufacturing. By providing an in-depth analysis of key methods, including Convolutional Neural Networks (CNNs), Generative Adversarial Networks (GANs), Autoencoders (AEs), and Active Continual Learning (ACL) frameworks, the review highlights how these technologies have dramatically enhanced the accuracy, efficiency, and adaptability of defect detection processes. The integration of these techniques has led to more precise identification of defects, reducing the reliance on manual inspection and significantly improving production speeds and quality. However, the review also identifies several persistent challenges, such as the need for more realistic and diverse synthetic data to better train models, the complexities in maintaining model adaptability to evolving and unforeseen defect types, and the difficulties associated with seamlessly integrating these sophisticated systems into existing industrial workflows without disrupting current operations. The study underscores the importance of ongoing research to refine deep learning methods, aiming to enhance their robustness, scalability, and reliability across various industrial environments, from small-scale textile workshops to large-scale manufacturing plants. This review not only synthesizes the current progress in deep learning applications for fabric defect detection but also outlines critical areas for future exploration, offering a detailed roadmap for the continued evolution of automated quality control in the textile industry, ultimately leading to more consistent and higher-quality textile products