International Research Conference 2024

Permanent URI for this collectionhttp://localhost:4000/handle/123456789/446

Browse

Now showing 1 - 8 of 8

Sentiment Analysis for Amazon Reviews to Identify Customer Interests.
(Sri Lanka Technology Campus, 2024-11-06) Abeysirigunawardana,K. Aloka; Rajapaksha,Dr. Rasika
In the twenty-first century, consumers now frequently buy online and use reviews to judge the quality of the products they purchase. These reviews are also examined by businesses to enhance their offerings. In order to glean business insights from massive datasets, this study uses sentiment analysis on Amazon product reviews. To determine the specific subjects upon which the entire collection of reviews is predicated, an LDA model is created for the Amazon review dataset. Word frequencies for each topic are visualised by us. After determining which machine learning model is most appropriate for sentiment analysis, the analysis is carried out on a topic-by-topic basis. Using logistic regression, the themes derived from the LDA model are categorised as either positive or negative product review subjects. Analysis is done on both the positive and negative subjects.
DreamyMirror A Machine Learning-Based Personalized Outfit Recommendation System Integrating Skin Tone Classification and Size
(Sri Lanka Technology Campus, 2024-11-06) Serasinghe,S. J. A. S. K.; Jayarathne,P. V. C. G.
Due to the increasing popularity of e-commerce, buying has undergone a tremendous shift and belongs to a different world. ” But there is still some difficulties with personalization when it comes to the proposed size and the choice of the color taking into consideration the skin color of the person. In this paper, the authors introduce DreamyMirror, a novel system for recommending outfits based on the individual user’s skin tone and size, along with allowing for virtual fitting. Based on a skin tone classifier CNN model built from CelebA database and a pre-trained Pose_iter_440000 of OpenPose. size prediction caffemodel, DreamyMirror provides unique suggestions of outfits according to the appearance of the person. The system also contains the Virtual Try on system wherein users can anticipate what the selected apparels look like at a glance. The proposed system can automatically recognize skin tone with an overall classification accuracy of 92% and the size prediction accuracy is found to be 95%. Moreover, the user engagement metrics also show an 85% level of satisfaction with the features – this is about the virtual try-on. This work shows how the application of AI in fashion retail can help better engage the customer through a truly individualized shopping experience and, at the same time, minimize the return rate because of the wrong size or color choice.
Intelligent Road Safety Navigation in Sri Lanka: A Review of Machine Learning Techniques and Proposal of a Model for Predicting Accident Hotspots and Severity
(Sri Lanka Technology Campus, 2024-11-06) Jayamanna,JMCT; Kalansooriya,Pradeep
Both public safety and the stability of the economy are seriously threatened by traffic accidents. Like many other regions, Sri Lanka is faced with the challenge of road accidents, which hinder the path to safer roads. One of the reasons that accidents occur is that people are unaware of common accident locations. The government has already enforced other tactics, like traffic signals and fines, to reduce these incidents, but they have been ineffective. In order to decrease road accidents, people must change their driving patterns. While looking for a solution to that problem, existing studies around the world have proposed predictive machine learning models for accident-prone locations known as hotspots and severity levels. But there were not any existing studies that proposed a solution that was suitable for Sri Lanka. This research seeks to address these challenges by conducting an in-depth review of existing machine learning techniques and proposing the most suitable model approaches for prediction of accident hotspots and severity in Sri Lanka based on the availability of the accident data. One of the main objectives is to identify the correct machine learning techniques. According to studies, 81% used the 'Random Forest' algorithm, which is a supervised machine learning algorithm for the prediction. And Random Forest performed better in approximately 69% of the studies. And this research is not just proposing suitable model approaches for predictions. It provides the foundation to revolutionize road safety through the development of an intelligent road safety mobile navigation application
THE IMPACT OF DIFFERENT CORPORATE EVENT ANNOUNCEMENTS ON SHORT-RUN STOCK RETURNS; EVIDENCE FROM COLOMBO STOCK EXCHANGE
(Sri Lanka Technology Campus, 2024-11-06) Abeyrathna,Lakshmika.; Sudasinghe,Sandali.
Publicly traded markets function as the base of our economic system. Efficiently valued financial markets power up national development according to Malkiel (2010). Market effectiveness shows precise security assessment results. When information travels rapidly into stock prices in an efficient market it won't help investors earn more than the market or find ways to get abnormal returns from what they already know. This paper examines the efficiency of the market in relation to four prominent corporate events: We examine the information event impact of stock dividend announcements alongside bonus issues, rights issues, and stock splits under Sri Lanka's conditions. A sample of 13 stock dividend and 9 bonus issue releases formed the base data alongside 31 rights issue and 29 stock split announcements. This research uses market model event studies to track price reactions through Average Abnormal Returns and Cumulative Average Abnormal Returns calculations. The research discoveries question what current market efficiency stories tell us. Investors in Sri Lanka currently lack complete data about stock price reactions to corporate news. Our study examines market reactions to corporate event announcements in CSE using 82 unique events across 14 economic zones between 2019 and 2021.
A Novel Factorization Method Using Continued Fractions
(Sri Lanka Technology Campus, 2024-11-06) Vinodya,Malshi; Ranasinghe,Rajitha
The study of continued fractions is a significant area of mathematics with diverse applications, particularly in the field of factorization. Continued fractions can be used to approximate irrational numbers and are integral to algorithms for factoring integers. In this study, we present a novel method for factoring large integers that utilize generalized continued fractions to improve efficient factorization. Additionally, we introduce several theoretical statements about generalized continued fractions and demonstrate their application within the proposed factorization algorithm. Using this algorithm, we successfully factor a large integer into two prime numbers, whose product constitutes the original large number. Our findings suggest that this method is a highly effective tool in number theory, cryptography, and computational mathematics.
Comparative Analysis of BER Performance in UAV-assisted THz Communication Systems with Different Modulation Schemes
(Sri Lanka Technology Campus, 2024-11-06) Mohamed,Safran; Rajahrajasingh,Hanojhan
—This paper presents a detailed comparison of bit error rate (BER) performance for three modulation schemes—Pulse Amplitude Modulation (PAM), Quadrature Am plitude Modulation (QAM), and Chirp Spread Spectrum Mod ulation (CSSM)—in the context of UAV-assisted terahertz (THz) communication systems. As THz communication gains traction for its potential to support ultra-high data rates, understanding the error performance of various modulation techniques is essential for optimizing system design. This study simulates and analyzes the BER performance of PAM, QAM, and CSSM under various signal-to-noise ratio (SNR) conditions, aiming to identify the trade-offs in reliability and efficiency for each scheme. The results indicate that CSSM exhibits superior resilience under noisy and fluctuating conditions, making it the most robust choice for UAV-assisted THz communication. In contrast, QAM performs moderately well at high SNR levels but is less effective in low-SNR environments, while PAM requires high SNR for reliable performance. These findings offer valuable guidance for selecting suitable modulation schemes in THz communication systems, especially for UAV applications.
The tourist’s perception and uniqueness of the Sri Lankan tea tourism experiences with reference to Nuwara Eliya District in Sri Lanka
(Sri Lanka Technology Campus, 2024-11-06) Sankalpana, H.Y.M.; Pathirana,Ramitha
Sri Lanka is a famous tourist destination around the world. The scenic beauty, cultural heritage, abundant wildlife, substantial wildlife, and toasty climate provide enormous value to "The Pearl of the Indian Ocean," making it a world-famous tourist destination (Jolliffe et al., 2022). With that, even though there were lots of ups and downs in the Sri Lankan tourism industry in recent years, Sri Lankan tourism recorded a remarkable over 1.9 million tourist arrivals in 2019. According to DailyFT, (2023), Sri Lanka is ranked as one of the top places to visit in the Europe and Asia region for 2023 DailyFT (2023). The tourism industry is one of the fastest-growing economic sectors. In Sri Lanka, this has contributed directly and indirectly to economic development (Punchihewa, 2020). As a result of British colonial growth, the tea industry emerged in Sri Lanka, with historical places in scenic hill country tea estate surroundings (Aslam and Jolliffe, 2015). When developing teabased tourism, it brings double economic benefits to Sri Lankan tourism, and this industry will be strengthened by more promotion and the consumption of tea and authentic tea culture experiences in Sri Lanka (Jolliffe and Aslam, 2009). Tea tourism experiences have been identified as one niche tourism segment under the emerging novel concept of nature based tourism (Fernando et al., 2017). Tea tourism in Sri Lanka is one of the niche markets to support economic development, and it has attracted different market segments. Instead of only being consumed, the tea product is presented as a unique opportunity for tourists to be engaged in an authentic, immersive experience, where the journey from leaf to cup is showcased within the factories where it is produced. By combining tea-producing and tourism, tourists create a stronger connection to the destination and enhancing the area's attractiveness and reputation.
Enhancing Stock Price Forecasting on the Colombo Stock Exchange with Cluster-Based Gated Recurrent Unit Architectures
(Sri Lanka Technology Campus, 2024-11-06) Fernando,W. M. K. T. M. P.; D. M. R. B. N. Dissanayake

Browse

Recent Submissions