Research Publications
Permanent URI for this communityhttps://rda.sliit.lk/handle/123456789/4194
This main community comprises five sub-communities, each representing the academic contribution made by SLIIT-affiliated personnel.
Browse
4 results
Filters
Advanced Search
Filter by
Settings
Search Results
Publication Embargo AppGuider: Feature Comparison System using Neural Network with FastText and Aspect-based Sentiment Analysis on Play Store User Reviews(Institute of Electrical and Electronics Engineers, 2022-10-22) Thelijjagoda, S; Oshadi, D.M.KNowadays, there's a rapid growth in the number of apps downloaded from the app stores. People nowadays use apps for even the most simple daily tasks. In this situation, people always tend to search for new apps for the new tasks they come across in daily life. User reviews have a high impact on the app downloads. When analysing user reviews, it's important to consider the aspect that has been discussed in reviews. In mobile app reviews, the discussed aspect is mostly a functionality or feature of the mobile app. Therefore, it's crucial to make use of this important data in a way that helps app seekers to easily find the best-suited app for their requirements and also helps app developers to identify their weak features that need to be improved. This research was conducted to provide a strategy that visualizes user review summaries in a form that is relevant to the end user with the intention of achieving a model that is not only lightweight but also highly accurate and effective in terms of its performance. The AppGuider system was implemented, mainly with two models for sentiment analysis and aspect extraction. The sentiment classification model was developed with a deep learning approach that included a two-layer neural network, while the aspect extraction model was built with an unsupervised machine learning approach using the LdaMulticore algorithm. FastApi was used for data visualization in Frontend. User reviews were vectorized with FastText prior to input into the model. The accuracy of the sentiment classification model is 91%, with an 85.97% f1 score, an 85.93% recall, and an 86.05% precision. The FastText model outperformed the Stanford CoreNLP library in the performance test. The integrated system was evaluated by 25 user reviews that were entered manually and sentiment classification model scored 92% while the aspect extraction model scored of 76% accuracy.Publication Embargo A Gamified Approach for Screening and Intervention of Dyslexia, Dysgraphia and Dyscalculia(2019 International Conference on Advancements in Computing (ICAC) -SLIIT, 2019-12-05) Kariyawasam, R.; Nadeeshani, M.; Hamid, T.; Subasinghe, I.; Ratnayake, P.This paper aims to diagnose children with specific learning disabilities and provide treatments via a mobile game. Learning disabilities are neurological disorders that affect the brain. Children with learning disabilities have trouble with learning compared to their fellow peers and quite often fall back academically since a majority of them go undiagnosed. The specific learning disabilities for which this paper provides screening are dyslexia a reading disability, dyscalculia a mathematical disability, letter dysgraphia and numeric dysgraphia are both writing disabilities. Deep learning and machine learning techniques are used in the screening process of these specific learning disabilities. Trained convolutional neural networks are used to detect the spoken letter/word, detect the written letter/word and detect the written number on the mobile application. Outputs from the convolutional neural network are fed into the models used for screening learning disabilities. The machine learning algorithms used in building the models include k-nearest neighbors, random forest and support vector machine. Screening results from the models built in this research provided an accuracy of 89%, 90%, 92%, 92% for dyslexia, letter dysgraphia, dyscalculia and numeric dysgraphia respectively. This is the first game based screening and intervention tool for dyslexia, letter dysgraphia, dyscalculia and numeric dysgraphia.Publication Embargo Predictive Analytics Platform for Airline Industry(2020 2nd International Conference on Advancements in Computing (ICAC), SLIIT, 2020-12-10) Tissera, P. H. K.; llwana, A.N.M.R.S.P.; Waduge, K.T.; Perera, M.A.l.; Nawinna, D.P.; Kasthurirathna, D.The research is to develop accurate demand forecasting model to control the availability in Airline industry. The primary outcome of the model is that the Airline organization can maximize the revenue by controlling the availability. The product in airline industry is the seat, which is an expensive, unstock able product. The demand for the seats is almost uncertain, the capacity is constraint and difficult to increase and the variable costs are very high. Hence the priority of the expected demand forecast is very high for airline industry. An accurate mechanism to predict the revenue for future months of ODs (Origin destinations) is done using fare and passenger data. The revenue is derived by the number of passengers and the fares they pay which vary for each flight. Airline travel is very susceptible to the social, political and economic changes. Therefore, passenger buying patterns change quite dynamically. Hence, it is challenging to develop an accurate method to project the revenue for each route. To overcome this, we are going to use semi-supervised learning mechanism. We have the current ticketed revenue plus we have the current booked passengers. We also have the ticketed passenger details of previous flights. Hence most of the information is available, however changing market conditions is an unknown variable which can have a significant impact on passenger travel patterns. Through this research We are going to design and develop the best fit model to forecast flight OD level passenger demand based on the historical data.Publication Embargo Vehicle Recommendation System using Hybrid Recommender Algorithm and Natural Language Processing Approach(2020 2nd International Conference on Advancements in Computing (ICAC), SLIIT, 2020-12-10) Boteju, P.; Munasinghe, L.Owning a vehicle has become a mandatory requirement in the modern world. Automobile industry investing a lot on producing different car models to cater the needs of their customers with different social and economic backgrounds. Thus, Auto makers constantly produce similar car models with different features. In Sri lanka, total number of new vehicles registered at Sri Lanka Registry of Motor Vehicles(RMV) during the period of seven years (from 2008 to 2015) has been increased from 265,199 to 668,907 which is nearly 2.5 times growth. This figure shows the rapid growth of the domestic vehicle market. For a new customer, choosing the most appropriate vehicle requires an extra effort/time and has become a challenging task. For example, matching personal interests and economy with number of available options is a quite complex task. Thus, most of the customers seek support from experts who provide consultancy services. However, customers frequently making complains about the existing services which offers consultancy for new vehicle buyers. The key issues are the people involved in the consultancy are not technically sound and pay minimal attention to customer requirements. Their main focus is to sell the vehicle. Thus, the customers face numerous difficulties before and after buying their vehicle. To address this problem, this research presents a novel vehicle recommender system which guides and gives suggestions to the customers using machine learning technologies. Here, we trained a neural network model using data collected from vehicle users and vehicle sellers. Other than the neural network model, the proposed recommendation system uses natural language processing (NLP) to produce more personalized recommendations. The results shows that the recommendations made by the proposed vehicle recommendation system achieves 96% accuracy in recommending vehicles.