Browsing by Author "De Silva, H"

Now showing 1 - 10 of 10

Embargo
Assisting Wheelchair: Assist W
(IEEE, 2021-12-07) Ranaweera, D; Athalage, C; Sri Virajamana, M; Kaveesha, C; De Silva, D. I; De Silva, H
Traditional wheelchairs used by disabled people are required to be controlled manually. Hence, continuous monitoring and assistance of a caretaker is a mandatory requirement. This paper introduces an autonomous assisting wheelchair - Assist W, which would facilitate disabled people to do their day-to-day activities independently in a very safe manner, thereby managing their mental and physical health. Assist W can scan the location and design a 2D map of the house using SLAM algorithm and LIDAR sensor. After generating the map, Assist W is able to move automatically according to the commands (Voice and touch) given by the user, with the help of the map data. There is an AR (Augmented Reality) chat-bot that acts as a good companion to manage the mental health of the disabled person. Assist W is also able to manage the security and physical health of the disabled person by providing a fall detection system and automatic lifting system, and sending emergency alerts to the caretakers. This system was tested using simulation.
Embargo
Automated Spelling Checker And Grammatical Error Detection And Correction Model for Sinhala Language
(IEEE, 2022-10-04) Goonawardena, M; Kulatunga, A; Wickramasinghe, R; Weerasekara, T; De Silva, H; Thelijjagoda, S
Sinhala is a native language spoken by the Sinhalese people, the largest ethnic group in Sri Lanka. It is a morphologically rich language, which is a derivation of Pali and Sanskrit. The Sinhala language creates a diglossia situation, as the language’s written form differs from its spoken form. With this difference, the written form requires more complex rules to be followed when in use. Manually proofreading the content of Sinhala material takes up much time and labor, and it can be a tedious task. Hence, a system is necessary which can be used by different industries such as journalism and even students. At present, there are a handful of systems and research that have automated Sinhala spelling analysis and grammar analysis. In addition, the existing systems are mainly focused on either spelling analysis or grammar analysis. However, the proposed system will cover both aspects and improve upon existing work by either optimizing or re-building the process to provide accurate outputs. The proposed system consists of a suffix list built for verbs and subjects, which helps the system stand out from the current proposed solutions. This research intends to implement a service for spell checking and grammar correctness of formal context in Sinhala. The research follows a rule-based approach with some components adopting a hybrid approach. As per the literature survey, many papers were analyzed, related to different aspects of the proposed system and complete systems. The proposed system would be able to overcome most barriers faced by previous papers whilst it takes a fresh take on providing a solution.
Embargo
BlindAid - Android-based Mobile Application Guide for Visually Challenged People
(IEEE, 2021-12-06) Senarathne, G; Punchihewa, D; Liyanage, D. I; Wimalaratne, G; De Silva, H
Millions of people across the world are affected by visual impairments. The proposed application is designed for visually impaired people consists of three components which are face recognition with emotion, obstacle identification through distance measurement, extract and convey critical information like text, labels, and currency details. Most works reported in the literature depends on the availability of specific hardware. The proposed proof of concept prototype aims to make visually impaired people more independent and carry out tasks conveniently and safely.
Embargo
BlindAid-Android-based Mobile Application Guide for Visually Challenged People
(IEEE, 2021-10-27) Senarathne, G; Punchihewa, D; Liyanage, D. I; Wimalaratne, G; De Silva, H
Millions of people across the world are affected by visual impairments. The proposed application is designed for visually impaired people consists of three components which are face recognition with emotion, obstacle identification through distance measurement, extract and convey critical information like text, labels, and currency details. Most works reported in the literature depends on the availability of specific hardware. The proposed proof of concept prototype aims to make visually impaired people more independent and carry out tasks conveniently and safely.
Embargo
Classification of Documents and Images Using an Enhanced Genetic Algorithm
(IEEE, 2022-12-09) Athuraliya, N; De Silva, H; Dasanayake, D; Fernando, K; Haddela, P.S; Gunarathne, A
In 1975, John Holland proposed the Genetic Algorithm (GA). The algorithm is widely used to provide superior solutions for optimization and search problems by relying on biologically inspired operators including mutation, crossover, and selection. The fittest individuals are chosen for reproduction in this algorithm to generate the next generation’s offspring. Classification is a technique used in data mining to analyze the collected data and to divide them into different classes. The relationship between a known class assignment and the properties of the entity to be classed may serve as the foundation for the classification procedure. Through this research, it has mainly consider classification for documents and images using GA. In order to enhance the accuracy and to reduce the error rate of traditional models, a new approach is proposed which is based on GA. The primary benefit of using GA in conjunction with classification is the efficiency in which it can address optimization issues. The experiment results are used to verify the suggested algorithm using benchmark data sets gathered from the UCI machine learning repository.
Embargo
Escort - Natural Language Processing Based University Students Guidance System
(IEEE, 2022-12-26) Srinivasan, D; Uthayakumar, A; Thiyagalingam, P; Ravindran, S; De Silva, H; Kasthururarthna, D
Universities play a significant role in students’ lives and aim to provide the best education, knowledge, and experience. However, university students face many difficulties during their university life including language, communication issues, and the inability to get proper guidance for education and career improvement. This paper proposes an approach to overcome these issues. With the help of Natural Language Processing (NLP), in this paper, several solutions are recommended for the mentioned issues. First, a chatbot helps to communicate with the university administration, where students can ask relevant administrative-related questions. A recommendation system is developed to provide solutions for their psychological issues. Another recommendation system is built for career guidance which will help students to identify the future career of their interest, and the provided mentors will be able to guide them. Another recommendation system identifies the performance of students in each module according to their performance level. The system recommends learning materials to improve their level. With these components, ESCORT – A university students’ guidance system, will make students’ life easier and more efficient.
Embargo
Genetic Algorithm Based Hybrid Clustering Technique for the Retinal Blood Vessels Segmentation
(IEEE, 2022-12-09) Dasanayake, D; Athuraliya, N; De Silva, H; Fernando, K; Haddela ., P.S
Important details about the visual anomaly can be found in the retinal fundus imaging. The segmentation of the blood vessels is crucial and necessary for diagnosing different ocular fundus. The primary and most common causes of blindness are diabetic retinopathy and its effects on the retinal vascular structures. The study suggested a genetic algorithm combined with the K-means clustering technique for unsupervised retinal segmentation. An essential pre-processing step for vessel identification applications is vessel enhancement. The CLAHE filtering method is employed in this work as a preprocessing step for vessel improvement. The improved vessels were grouped together using a genetic approach, and K-means clustering was applied for superior clustering outcomes. DRIVE and IOSTAR databases that are accessible to the public are used to evaluate the suggested strategy. According to the experimental findings, the proposed algorithm successfully separates clusters that are more dense and well-separated than those of other previous findings. Both the Calinski-Harabasz I ndex S core and the Silhouette Index Score are used to validate the proposed algorithm.
Open Access
A Singlish Supported Post Recommendation Approach for Social Media
(SCITEPRESS – Science and Technology Publications, 2022-01) Sandamini, U; Rathnakumara, K; Pramuditha, p; Dissanayake, M; Sriyaratna, D; De Silva, H; Kasthurirathna, D
Social media is an attractive means of communication which people used to exchange information. Post recommendation eliminates the overflooding of information in social media to the users’ news feed by suggesting the best matching information based on users’ preference that in return increase the usability. Social media users use different languages and their variations where most of the Sri Lankan users are accustomed to use Sinhala and Romanized Sinhala. However, post recommendation approaches used in current social media applications do not cater to code-mixed text. Therefore, this paper proposes a novel post recommendation approach that supports Singlish. The study is separated into two major components as language identification and transliteration, and post recommendation. In this study, script identification was performed using regular expressions while a Naïve Bayes classification model that accomplished 97% of accuracy was employed for language identification of Romanized text. Transliteration of Singlish to Sinhala was conducted using a character level seq2seq BLSTM model with a BLEU score of 0.94. Furthermore, Google translation API and YAKE were used for Sinhala-English translation and keyword extraction respectively. Post recommendation model utilized a combination of rule-based and CF techniques that accomplished the RMSE of 0.2971 and MAE of 0.2304.
Embargo
Smart Device and Tracer to Overcome COVID-19 Using Digital Technology for Better Protection
(IEEE, 2022-12-09) Avinash, K; Dithmal, C; Wijerathne, P; Kaushan, N; De Silva, H; Kasthurirathna, D
A number of nations have experienced challenging circumstances as a result of the coronavirus disease (COVID-19), which has turned into a global pandemic. As a result of the social changes it has caused, this crisis will also have an impact on future generations. With the help of this technology, health organizations can quickly locate individuals who are infected with COVID-19 and provide them with medical care. The objective of this work is to develop a COVID-19 Tracer that is capable of COVID-19 detection and mitigation. The goal of this research is to reduce the number of COVID-19-related fatalities in Sri Lanka while also enabling users who are infected with the disease to access appropriate care and hospitalization. This software uses digital technologies to acquire accurate data and provide precise interpretations based on that data. Through the proposed method, patients can be treated using the application to get a precise diagnosis of their disease, maintaining social distance, stabilizing the mental level of the patient through AI, predicting the epidemic, providing COVID-19 vaccinations, as well as ambulance services through this application. Using every preventative measure available, this mobile application has now been developed to safeguard against COVID-19.
Embargo
Social media based personalized advertisement engine
(IEEE, 2018-02-19) De Silva, H; Jayasinghe, P; Perera, A; Pramudith, S; Kasthurirathna, D
Online advertising has become a global phenomenon that affects the retail market substantially. Advertisements engines are an effective solution to the mobile application market to push advertisements. This paper reports evidence that AdSeeker, User Preference Based Advertisement Engine Based on Social Media is an effective solution to improve the business value of the marketing and advertising. Since the internet is used by vast number of people, it essentially needs a comprehensive method to push personalized advertisements to the right people. Adseeker is a system built using ontological mapping and social media content based semantic analysis to direct personalized. Identifying personal relationship hierarchy, and ontological approach for advertisement classification helps to identify the most appropriate advertisement for each user. AdSeeker uses the tweets posted by users to capture the preference of each and every user. Each user pushed advertisements based on their individual preferences. Based on the social experiments done using Adseeker, we could demonstrate that the social media profile based advertising is effective in providing highly relevant advertisements.