ICATC 2023

Permanent URI for this collectionhttp://repository.kln.ac.lk/handle/123456789/27835

Browse

Now showing 1 - 17 of 17

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.
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.
Adaptive Academic Guidance System via Student Activity Performance Analysis and Profiling
(Faculty of Computing and Technology, University of Kelaniya Sri Lanka., 2023) Balasooriya, Saumya K.; Abeysinghe, D.V.D.S.; Sathsara, D.M.S.
In the ever-evolving landscape of education driven by rapid technological advancements, e-learning has emerged as a transformative force. However, it faces challenges, notably the difficulty of personalizing education in a digital environment. This paper introduces an innovative adaptive academic guidance system called "StudyMate." The system analyzes student activity, performance, and profiles to enhance the e-learning experience. The objectives encompass extensive research, surveys for primary and secondary data collection, algorithm development for student analysis, foundational database creation, source code development, and online system hosting. StudyMate leverages learning management system (LMS) functionalities to offer tailored learning experiences and demonstrates its efficacy in the digital realm. The literature review explores adaptive e-learning systems, highlighting the need for personalized education and referencing related research projects. The methodology outlines planning, design, implementation, testing, and critical evaluation phases, including sample code snippets and test cases. The findings confirm the successful implementation of adaptive concepts in StudyMate, addressing the academic question effectively. The limitations lie in the system's scope, primarily focusing on student views, leaving room for future enhancements such as lecturer and admin functionalities. The paper concludes with the potential for expanding StudyMate's features and improving its usability, making it a valuable solution for personalized e-learning.
Development of a Green Tea Emulsion Infused Hydrogel
(Faculty of Computing and Technology, University of Kelaniya Sri Lanka., 2023) Sakayaxavior, Jensiya; Siriwardane, Induni W.
The study focused on the development of a hydrogel based herbal eye patch. This study aims to evaluate the benefits of green tea, coconut oil, and the surfactant in creating an emulsion based eye patch. A complete literature analysis was carried out to understand the present research related to nanoemulsions and preparation methods, herbal components, hydrogels, surfactants, and their uses in skincare. The experiment utilizes the water-in-oil emulsion method to prepare the emulsion formulation. The basic materials, green tea, coconut oil, and surfactant were carefully selected based on their antioxidant, anti-inflammatory, and moisturizing qualities for addressing under-eye issues. The emulsions were examined using Malvern Zetasizer (nano-ZS) and optical microscope analysis. The participants' subjective input was also obtained through a questionnaire. Then the prepared emulsion was used to make a hydrogel of carcoxymethyl cellulose (CMC). As future work, improvement of emulsion droplet sizes to nanosizes, comparison of anti-oxidant activities of encapsulated and neat green tea infusions in hydrogel and conducting the user trials after ethical clearance is required.
Enhanced Violence Detection Using Deep Learning
(Faculty of Computing and Technology, University of Kelaniya Sri Lanka, 2023) Bhawantha, Praveen; Arachchi, S. P. Kasthuri
Global violence needs to be stopped to increase public safety. With the increasing number of surveillance cameras, manual monitoring of all surveillance feeds is less practical. Because of that, the development of technology-driven solutions to detect real-time violence and inform authorities to prevent it has become necessary. This study focuses on finding a novel deep learning approach to enhance violence detection, specifically addressing the limitations and complexities of previous studies. Notably, the research utilizes proposed models and techniques to evaluate real-life violence scenarios captured in Closed-Circuit Television (CCTV) footage, overcoming the challenges identified and improving the accuracy of violence detection. Two models were proposed in this research paper. The model architecture consists of a multimodal approach, integrating two deep learning techniques, Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM). The proposed model utilizing VGG-16 with CNN layers and LSTM, achieved 89% accuracy on the real life violence situations dataset. This emphasizes the effectiveness of applying multimodal deep learning technique in detecting violence, outperforming similar research in accuracy.
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.
Modeling and Feasibility Study on Pumped Hydro Storage System for Sri Lanka
(Faculty of Computing and Technology, University of Kelaniya Sri Lanka., 2023) Moraes, Nimshan Avishka De; Fernando, Kasun
Due to Sri Lanka's reliance on imported fossil fuel for a large portion of its energy needs, the cost of energy has significantly increased. Sri Lanka has agreed to zero carbon emissions in energy generation by the year 2050, and the country’s future energy generation must depend on renewable energy sources. In the future, sustainable energy generation in Sri Lanka will be more favorable if water, wind, and solar energy are combined to generate energy. But since there are some limitations in the generation of that energy, measures should also be taken to store that energy for use within the required period. Pumped hydroelectric storage power plants are regarded as a reliable and effectively used energy storage technology. The thesis has mentioned the economic and environmental benefits of this pumped hydro storage system over existing non-renewable energy power plants by implementing this system using two existing reservoirs in Sri Lanka
Fog Computing based Heart Disease Prediction System using Deep Learning for Medical IoT
(Faculty of Computing and Technology, University of Kelaniya Sri Lanka, 2023) Welhenge, Anuradhi; Welhenge, Chiranthi; Subodhani, Shanika
Internet of Things (IoT) is used in all areas because of the benefits it is offering. All most anything can be connected to the internet and data created by these devices can be analyzed to predict results. IoT is helpful in the medical field because it can connect the patients with the healthcare professionals, and the healthcare professionals can monitor their patients remotely and analyze their data and take necessary actions. Because of the huge amount of data in IoT systems, cloud services are utilized to store the data. But this is not a feasible option in medical IoT, because the predictions should be available as quickly as possible, since patients’ lives are at risk. Therefore, edge-fog- cloud architecture is used. Fog nodes can be used to analyze data closer to the edge devices, resulting in much faster predictions and the cloud can be used for storage. This paper proposes a novel fog based architecture for medical IoT based on deep learning. Deep learning is used on the fog nodes to make accurate predictions. This study used data collected from heart patients to predict the heart disease to evaluate the system and yielded a good accuracy.
Automated Face Recognition based Attendance Monitoring Approach for the Sustainable Economic Recovery in Sri Lanka
(Faculty of Computing and Technology, University of Kelaniya Sri Lanka., 2023) Gamlath, Yugani; Pathiraja, Ashan
These days, biometric authentication methods, begin growing rapidly as one of promising authentication methods, besides the conventional authentication method. Almost all biometrics techniques require some actions by user, which are the user needs to place funds on the scanner to set the fingers. The user shall stand still in a fixed position in front of the camera for iris or retina identification process. The face recognition method has several external advantages compared to other biometric methods. Because this method can be done without action since the face image can be obtained by the camera. The new system can recognize the faces captured automatically by the camera accurately. And also this automated attendance monitoring method can use for the sustainable economic recovery in this economic crisis period in various phases.
Carbothermally Synthesized, Lignin-Based, Embedded And Surface Deposited Nano Zero- Valent Iron for Water Purification: Characteristics and Applications
(Faculty of Computing and Technology, University of Kelaniya Sri Lanka., 2023) Alahakoon, Yasmitha A; Wilson, Shine; Ranasinghe, Yohara K; Peiris, Chathuri; Mlsna, Todd; Gunatilake, Sameera
Synthesizing tailor-made materials for remediating wastewater polluted with contaminants of emerging concerns, has become a major concern of the scientific community. Nanoscale zero valent iron (nZVI) together with a biochar (BC) support provide advantageous materials for wastewater purification via adsorption, reduction, complexation and advanced oxidation mechanisms. Two approaches to nZVI-composite engineering have been reported: embedding in support matrix and surface depositing, where the latter being more common. Nonetheless, the behavior of embedded material towards contaminant remediation has not yet been sufficiently studied. Furthermore, the remediation capability of these two materials has not been comparatively evaluated. The present study focuses on preparing and extensively characterizing two materials; nZVI embedded in (Lig-e-nZVI) and surface deposited (Lig-s-nZVI) on lignin BC with subsequent comparative analysis of remedial action of the two materials. SEM, SEM/EDX, XRD, FTIR, proximate and ultimate analysis, point of zero charge, iron leaching and regeneration studies were carried out using pristine lignin BC as the control material. Porous and non-porous structures of the carbothermally prepared materials where crystalline iron was embedded or surface coated were compared along with their surface and bulk elemental compositions. It was evident that although the surface iron content is high in Lig-s-nZVI, the total iron content in both the materials were same. Loaded iron was confirmed to be in the zero valent state as per the observed XRD peak patterns. Surface functional groups and overall surface charge of the materials and iron leaching and depletion of remediation capacity were also analyzed. Pharmaceutical precursors p-nitroaniline (pNA) and p-nitrophenol (pNP) were used as sample molecules in this study due to their toxicity and health effects owing to persistence and bioaccumulation. Synergistic adsorptive and degradative behavior of the materials towards pNA and pNP showed an optimum pH of 3.0 and an optimum contact time of 60 minutes. Higher initial adsorption capacity was observed for Lig-s-nZVI and high sustainability and stability was portrayed by Lig-e-nZVI over the regeneration cycles. Both materials showed comparatively increased adsorption capacities in a simulated wastewater matrix. Therefore, it is conclusive that Lig-s-nZVI is of improved remedial capacity towards organic contaminants whereas, Lig-e-nZVI is a better candidate in action over time. Providing a thorough comparison of the properties and remediation performance of nZVI-BC composites synthesized using two commonly employed methods is expected to offer fresh insights to the scientific community.
Auto-Guided Smart Forklift
(Faculty of Computing and Technology, University of Kelaniya Sri Lanka., 2023) Thiruchelvam, Stephenraj; Pathirana, Thisara
Combination of automation and cognitive ability offers a creative way to change conventional warehouse and logistics processes through the concept of Auto guided smart forklift. The project focused on developing a prototype of a forklift capable of autonomous navigation, obstacle recognition, and adaptive decision-making by using modern technologies and sophisticated sensor systems. The initiative aims to increase operational effectiveness, eliminate human error, and promote workplace safety by automating routine materials handling operations. The project highlights the value of multidisciplinary cooperation in promoting innovation in industrial automation while also showcasing the potential of modern engineering. Through the establishment of new criteria for effectiveness, security, and productivity in warehouse and logistics management, the outcomes of this project have the potential to significantly impact the materials handling environment.
Park Smart and Ride
(Faculty of Computing and Technology, University of Kelaniya Sri Lanka., 2023) Abeywardhane, KG Kaushalya; Ratnayake, Bhagya; Abeywardhane, KG Hasara; Mayooran, P; Rankothge, Windhya
The traffic congestion in metropolitan areas is exacerbated by the recent increase in vehicles. Parking has also become a major problem in metropolitan cities. Traffic congestion was a big issue in the suburbs around Colombo in Sri Lanka. vehicles coming from the south to Colombo via the expressway exit through Makumbura and use public transport to avoid the Capital traffic crisis. This smart parking system helps them to park their vehicles safely and efficiently. This further reduces the time it takes for the user to park the vehicle and allows him to know if there is space in the parking lot. Here solutions have been developed for these with the help of IoT and cloud technology. IoT allows you to connect through the network and access it remotely. In this paper, we propose an IoT solution for this. Park Smart and Ride in real-time, accurately forecast and sense spot/vehicle occupancy, and direct vehicles to available parking. Allows for more accurate and real-time monitoring and management of vehicles in a parking lot. Use Parking Spaces More Efficiently. Relevant solutions are explored in this Paper.
Effect of Finite Impulse Response Filters on Activities of Daily Living Classification Algorithms
(Faculty of Computing and Technology, University of Kelaniya Sri Lanka., 2023) Welhenge, Anuradhi; Welhenge, Chiranthi
With the increasing aging population, improving the healthcare system is an important task in every country. The largest number of hospitalizations of the elderly people is due to falls. Therefore, many researchers have come up with different fall detection mechanisms. Improving the accuracy of these algorithms is an important task. This paper focuses on the use of Finite Impulse Response filters to improve the accuracy.
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.
Lignin Based Embedded and Surface Deposited Nanoscale Zero Valent Iron for Cd(II) Remediation
(Faculty of Computing and Technology, University of Kelaniya Sri Lanka., 2023) Arachchi, Uthsara Malaweera; Hettige, Ayesha L; Alahakoon, Yasmitha A; Peiris, Chathuri; Mlsna, Todd; Gunatilake, Sameera
Vast industrialization occurring throughout the world has led to a drastic increase in water pollution by heavy metals. Cd is a heavy metal that has garnered significant concern due to its toxicity and adverse health effects on humans and other living organisms. Recent studies have focused on the application of Biochar (BC) supported carbothermally produced Nanoscale Zero Valent Iron (nZVI) for the remediation of a variety of contaminants. However, only limited research has been carried out to assess and compare the mechanisms of Cd removal and remediation efficiency by different types of carbothermally prepared nZVI. To address this issue, the present study investigated the application of two nanocomposites, Lig-eG@nZVI and Lig-sG@nZVI, produced through two carbothermal reduction routes at 1000 °C. In Lig-eG@nZVI, nZVI was embedded in the Lignin Biochar (Lig-BC) matrix while in Lig-sG@nZVI, nZVI was deposited on the Lig-BC surface. In this study, enhanced uptake of Cd(II) was observed with increasing pH with maximum uptake at pH 6. Cd sorption at 30 °C was evaluated using the Langmuir, Freundlich, Temkin, Redlich-Peterson, Sips, Toth and Jossens adsorption isotherm models. The experimental data was best fitted to Sips isotherm model, with a maximum Sips capacity of 9.688, 8.102 and 6.665 mg g-1 at 30 °C and pH 6 for Lig-eG@nZVI, Lig-sG@nZVI and Lig-BC, respectively. The two composites showed enhanced remediation due to the synergistic effect of remedial mechanisms of both nZVI and Lig-BC components. Possible adsorption mechanisms for BC include cation-π interactions, electrostatic attractions and surface complexation precipitation with minerals. Owing to the nearly identical standard redox potential of Cd with zero valent iron, the feasibility of Cd(II) remediation through reduction is very low and the only viable removal mechanism is sorption or surface complex formation. Fast remediation kinetics were observed for the three materials. According to thermodynamic studies conducted, the overall adsorption processes of all three materials were confirmed to be physisorptive, endothermic and spontaneous in nature. This study bridges the existing knowledge gap by conducting a comprehensive evaluation on the application of Lig-eG@nZVI, Lig-sG@nZVI and Lig-BC for the remediation of Cd(II) in aqueous media.
Online Assessment Technologies and Future Trends: A Systematic Review
(Faculty of Computing and Technology, University of Kelaniya Sri Lanka., 2023) Nafrees, Abdul Cader Mohamed; Liyanage, S. R.; Dias, N. G. J.
A rapidly expanding method of continuing education in times of epidemic or conflict is online assessment (OA). Numerous tools are now available to perform OA more effectively and maintain the quality of e-learning (EL) as a result of the fast growth of new technologies. In order to analyse OA technologies and their future prospects, this study has conducted a systematic literature review (SLR). These publications were evaluated in light of the study issue, recent developments and future trends. It was shown that while few studies took into account automated feedback providing, the majority of studies concentrated on eradicating OA cheating. Few studies also concentrated on creating software for OA. Additionally, the bulk of studies have taken AI-based research into account. This research has downloaded articles only from 8 publishers and only open access articles. Future researches can be done about identifying techniques, how OA helps for the fair access to the quality education, and implications and considerations of implementing OA technologies.
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.