DRC 2024

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

Browse

Now showing 1 - 3 of 3

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.
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.
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.