Computing and Technology

Permanent URI for this communityhttp://repository.kln.ac.lk/handle/123456789/15605

Browse

Search Results

Now showing 1 - 10 of 273
  • No Thumbnail Available
    Item
    Temporal cross-validation in forecasting: A case study of COVID-19 incidence using wastewater data
    (Quality and Reliability Engineering International, 2024-11) Lai, M.; Wulff, S. S.; Cao, Y.; Robinson, T. J.; Rajapaksha, R.
    Two predominant methodologies in forecasting temporal processes include traditional time series models and machine learning methods. This paper investigates the impact of time series cross-validation (TSCV) on both approaches in the context of a case study predicting the incidence of COVID-19 based on wastewater data. The TSCV framework outlined in the paper begins by engineering interpretable features hypothesized as potential predictors of COVID-19 incidence. Feature selection and hyperparameter tuning are then utilized with TSCV to identify the best features and hyperparameters for optimal model performance given a specific forecast horizon. While evidence supporting the utility of TSCV for auto-regressive integrated moving average model with exogenous variables (TS-ARIMAX) forecasts is lacking in this study, such an approach proves advantageous for gradient boosting machine forecasts (TS-GBM). In Wyoming, for instance, TS-GBM had a 34.9% improvement compared to naïve predictions, whereas GBM without TSCV only had a 15.6% improvement. However, TSCV also enhances interpretability for both TS-ARIMAX and TS-GBM models as this approach selects specific features, such as lagged values of COVID-19 cases, based on forecast performance and forecast length. Future research should work to explore the influence of stationarity and model averaging on the performance of TSCV in forecasting applications.
  • No Thumbnail Available
    Item
    Advancements and Challenges in Real-Time Electronic Vision Technologies for Canned Fish Quality Inspection: A Comprehensive Review
    (2024) Sharmilan, Tharaga; Mahatheesan, Anis Jeluxsha
    The global demand for high-quality canned fish products has driven the adoption of advanced inspection technologies to ensure consistency, safety, and compliance with industry standards. This paper provides a comprehensive review of real-time electronic vision technologies employed in the inspection of canned fish quality. It traces the evolution of the canned fish industry from manual inspection methods to sophisticated automated systems, emphasizing the role of technologies such as hyperspectral imaging, machine learning algorithms, and electronic vision systems. The effectiveness of these technologies in detecting defects, assessing quality parameters, and maintaining product integrity is critically analyzed. Despite their benefits, challenges such as high costs, the need for specialized skills, and integration complexities with existing production processes are significant barriers. This review addresses these challenges and proposes solutions, including cost-reduction strategies, workforce training, and the development of adaptable systems. The paper concludes by outlining future research directions, particularly in validating these technologies in real-world scenarios and enhancing their accessibility to the industry. The findings offer valuable insights for researchers and industry stakeholders aiming to advance the quality control of canned fish products through innovative technological solutions.
  • No Thumbnail Available
    Item
    Advancements and Challenges in Real-Time Electronic Vision Technologies for Canned Fish Quality Inspection: A Comprehensive Review
    (European Modern Studies Journal, 2024-09) Mahatheesan, A. J.; Sharmilan, T.
    The global demand for high-quality canned fish products has driven the adoption of advanced inspection technologies to ensure consistency, safety, and compliance with industry standards. This paper provides a comprehensive review of real-time electronic vision technologies employed in the inspection of canned fish quality. It traces the evolution of the canned fish industry from manual inspection methods to sophisticated automated systems, emphasizing the role of technologies such as hyperspectral imaging, machine learning algorithms, and electronic vision systems. The effectiveness of these technologies in detecting defects, assessing quality parameters, and maintaining product integrity is critically analyzed. Despite their benefits, challenges such as high costs, the need for specialized skills, and integration complexities with existing production processes are significant barriers. This review addresses these challenges and proposes solutions, including cost-reduction strategies, workforce training, and the development of adaptable systems. The paper concludes by outlining future research directions, particularly in validating these technologies in real-world scenarios and enhancing their accessibility to the industry. The findings offer valuable insights for researchers and industry stakeholders aiming to advance the quality control of canned fish products through innovative technological solutions.
  • No Thumbnail Available
    Item
    Electronic Technologies for Quality Control in the Biscuit Manufacturing Process
    (Lomaka & Romina Publisher, 2024) Lakshani, K.W.I.; Tharaga, Sharmilan
    By 2030, the biscuit industry may go global due to advancements in electronic tools like eNose, eTongue, and eVision. This shift is governed by precision, productiveness, and regulatory compliance. Ultimately, the automation increase is driven by this consequence. This article will critically look at the issues and benefits arising within the biscuit production field after the shift towards the use of electronic control systems. It analyses the present situation and figures out the ineffectiveness on the part of conventional tools in solving the problem as it currently exists and shows how electronic instruments can be better in aiding visual and sensory inspections. While there have been remarkable achievements, these are persisting, of course, and they include high investment costs, specific skills requirements, and less flexibility when adapting to different production conditions. Without thorough research and development, the challenges in the production of the electronic control systems will still stand and no technology will be created to resolve the problems of the system. This study further reaffirms the need for the invention of modern and improved quality control processes for biscuit manufacturing plants. Through identifying previous methods and approaches and, the advantageous features of each, as well as highlighting shortcomings of current quality control strategies, this paper serves as an effective driving force for the future evolution and further improvement of quality control practices during biscuit production. Comprehensive product evaluation is attended to by employed approaches that analyse future benefits and opportunities as well as drawbacks and risks of the application of electronic quality control systems in the biscuit industry.
  • No Thumbnail Available
    Item
    Microbial Remediation Technologies for Mining Waste Management
    (Springer, Singapore, 2024) Samarasekere, P.W.
    Mining activities have significantly contributed to pollution and environmental degradation, generating vast amounts of waste that pose substantial risks to ecosystems. Conventional remediation methods often fail to address the complex nature of pollutants in mining wastes. Alternative approaches, such as microbial remediation, have emerged as promising solutions for sustainable remediation of contaminated sites. This chapter provides a detailed overview of microbial remediation technologies specifically tailored to mining and industrial waste. It explores the diversity of microorganisms capable of degrading various pollutants commonly found in these waste, including heavy metals, organic pollutants, and toxic chemicals. Additionally, it examines factors that affect microbial activity and the optimization of remediation processes. Furthermore, it highlights the advantages, limitations, and applicability of microbial remediation techniques for different types of mining and industrial waste. The chapter also discusses the challenges and considerations regarding the real-world implementation of microbial remediation. Additionally, it reviews the synergistic effects of combining different antimicrobial approaches to enhance overall efficacy and efficiency. Overall, this chapter presents a valuable resource for interested parties seeking to understand and apply microbial remediation technologies for mining and industrial waste. By harnessing the power of microbes, these techniques offer promising prospects for restoring contaminated sites, reducing environmental impacts, and promoting sustainable development.
  • No Thumbnail Available
    Item
    Use of a ChatBot-Based Advising System for the Higher-Education System
    (Faculty of Computing and Technology, University of Kelaniya Sri Lanka., 2023) Radhakrishnan, Hansi K; Dias, N. G. J.
    The educational advising process most often consists of repeated queries related to institutional policies, academic progression, career pathways, and industry placements. In the higher education system, this procedure is usually initiated by various learners directing the same questions toward a limited number of advisors, which results in the advising process being reliant on the availability of the individuals and their hectic work schedules. Hence, this study introduces a feasible mechanism of a chatbot-based advising system to bridge this identified gap between learner requirements and resource availability by automating the prescriptive advising process beyond the traditionally available methods. Most existing systems provide a rule-based approach with limited pre-defined intent-response structures, resulting in several identified usability shortcomings. In response, this study utilizes an opensource Large Language Model (LLM) combined with a custom knowledge base to address critical aspects needed for a chatbot-based advising system, such as personalization, conversational memory, and ease of maintenance. The system is built around three major components: an admin panel for advisors, a conversational user interface (CUI) for learners, and an easy-to-maintain custom knowledge base. It uses the traditional form of information distributed to students through handbooks, guidelines, and course outlines to create a custom knowledge base which is then utilized to answer the user's queries through a semantic similarity algorithm. This work contributes (1) a prototype of a chatbot-based advising system for higher educational institutes in Sri Lanka, (2) the application of Large Language Models, vector databases, and semantic similarity in the design of the system, and (3) the results of evaluating the system's functionality and performance metrics through comprehensive test cases and a comparative analysis against the existing approaches. As identified, the proposed system showcased a response accuracy rate of 89% proving that this novel approach of a component-based architecture excels in performance when compared to similar approaches.
  • No Thumbnail Available
    Item
    Usability of the Fuzzy Logic-based Visual Impairment Level Identification System for Preschoolers and Toddlers
    (Faculty of Computing and Technology, University of Kelaniya Sri Lanka., 2023) Sammani, MHK; Perera, MPL; Vidanagama, DU
    Nearsightedness, or myopia, and Colorblindness, the two common eye diseases, can affect preschoolers and toddlers. This research is to provide parents with a method for testing the two eye impairments listed above in children who are illiterate in both letters and numbers. Using the knowledge offered by ophthalmologists, comments from parents with young children of survey findings, and pertinent literature, this is to create a mobile gaming application based on Fuzzy Logic, that could evaluate the level of children's Colorblindness and Nearsightedness. The "Ishihara test" and "Hue test," which are still widely used today, can be used to identify color blindness by selecting hues from a color palette that have a similar color intensity, and by allowing children to choose images that range in size from large to small (follow the Snellen Chart), and Preferential Looking Test concept that parents can determine whether their child has nearsightedness based on the child's outward behavior. Also, a usability test has also been done at the current level of development of this app. This mobile gaming application roughly identifies the level of the above two eye defects in young children and refers to medical advice if there is a certain risk level. This research paper mainly considers the current development of this mobile gaming app and its usability.
  • No Thumbnail Available
    Item
    Review of Uncommon Power Generation Methods
    (Faculty of Computing and Technology, University of Kelaniya Sri Lanka, 2023) Perera, Poornima L; Edirisinghe, Nishad M; Hettige, Budditha
    Fossil fuel shortage is a common problem in every country. Day by day it going to discreet also fuel prices going to increase. When burning fossil fuels have made a few problems. The main problem is environmental pollution. Considering the current rate of usage of fossil fuels will let its life up to the next five decades only. Most countries referred to the use of renewable energy. Wind power, Solar power, sea wave power, Hydropower, and Geothermal heat are a few of the renewable energy they have used. Also, few countries have used nuclear power plants, charcoal power plants, and diesel power plants. But when using charcoal or diesel power plants, it has to spend a lot of money on one unit of electricity. Nuclear power plants are not suitable for small countries like Sri Lanka. In history, the most powerful kingdoms had used uncommon and hidden power for their living area. The main objective is this review paper is to identify uncommon power generation methods and weaknesses of the existing renewable power generation system and To what extent are these suitable for Sri Lanka. Performance analysis has been carried out in this study along with the literature review.
  • No Thumbnail Available
    Item
    Predictive Analysis on Social Media Content to Become Viral
    (Faculty of Computing and Technology, University of Kelaniya Sri Lanka., 2023) Silva, Singhe; Rajapaksha, Rasika
    In the continuously changing world of social media, Instagram has taken a prominent place by becoming one of the most popular social media platforms. Instagram has not only the biggest organic reach but also the highest organic engagement rate. Above all, understanding and predicting what makes posts go viral is an uneasy yet significant challenge. This study focuses on Instagram and presents a fresh approach to discovering the key factors contributing to post virality, specifically on image posts. In this study, a metric named ‘Virality Rate’ is defined to predict the likelihood of going viral. It is calculated by dividing the sum of number of likes and comments by the number of followers. There were studies on Instagram post popularity prediction based on various features and datasets. But with a focus on public image-based posts from influencers worldwide, this research delves into sentiment analysis, image processing for technical features and content, hashtag assessment, user history and user features to forecast the potential virality of a post. This research trained and compared several regression models to predict the Viral Rate and employed Faster R-CNN and OpenCV to detect objects and help extract essential technical details. Through rigorous model training and evaluation, our results highlight the Random Forest Regression model as the most effective predictor. It boasts an impressive Mean Absolute Percentage Error (MAPE) of 0.15, which implies an accuracy of 85% and a notable R-squared (R2) value of 0.924 which is significant compared to previous studies. It was found that the User History Features, sentiment score, technical features and posting time have a high impact on Virality Rate. In conclusion, this research aims to advance social media analytics by offering actionable insights for content creators, influencers, marketers and regular users.
  • No Thumbnail Available
    Item
    Peenamu.lk - A Swimming Web Portal for Sri Lanka with Advanced Water Quality Monitoring System
    (Faculty of Computing and Technology, University of Kelaniya Sri Lanka., 2023) Perera, Poornima L; Rupasinghe, Induwara; Wanniarachchi, Ashen
    Swimming is a world-popular physical activity that integrates arm and leg actions with natural flotation of the body. This is an excellent stress reliever because it releases endorphins, which give a sense of well-being and happiness. In Sri Lanka, the majority of the people are doing swimming as a sport, and some are willing to do this as a hobby. Most people don't know how to swim, where they can learn swimming and how to find a certified coach. The objective of this research paper is to identify the problems that occur when swimmers finding certified coaches, the nearest pool and maintain the water quality of the swimming pool. This research was conducted using both qualitative and quantitative data. This mainly focuses on the survey that was conducted to the swimmers via a google form using social media platforms and identified the problems that the responders faced. And interviewed some of the leading swimming coaches in Sri Lanka to get their experience and qualifications and also interviewed pool managers to know how the maintain process of water quality of the pool. To overcome these issues, this research paper proposed a web-based swimming portal with advanced water quality Monitoring system for Sri Lankans who are doing swimming. This includes the previous techniques used for the web portals and the main strategies that can be added to the swimming portal. In the future, this portal can be implemented for diving, lifesaving, surfing, synchronized swimming, underwater diving, and water polo.