Browsing by Author "Warnajith, N."

Now showing 1 - 7 of 7

Contextual assistant framework for the Sinhala language
(Department of Industrial Management, Faculty of Science, University of Kelaniya, Sri Lanka, 2020) Dasanayaka, D.D.S.S.; Warnajith, N.
Continuous customer relationship plays an important role in the success of any business milieus in today’s world. Nonetheless, it can be harder to achieve consistent engagement with the customers round the clock and therefore many businesses have paved their focus in using a variety of solutions in overcoming this scenario. Contextual assistants that can have both linear and non-linear conversations with humans implicitly plays a prominent role in such situations. In contrast to resource-rich languages, creating a contextual assistant for resource-poor languages like Sinhala has been difficult mainly due to the unavailability of a rich digital footprint and the complexity of the language. Hence, this research was conducted to propose and implement a novel and common architecture of a contextual assistant framework for the Sinhala language. Here we have used a deep learning Intent Mapping (IM) model to map the consumer response to a predefined “Intent” and a Feature Extraction Mechanism (FEM) to extract related information from the input text. A set of data types for this framework were defined and FEM was trained to identify them efficiently. The IM model gave an accuracy output of 89.67 percent. The results depicted that the implemented system performs with higher accuracy in linear conversations.
Development of E-learning community in Asia Pacific countries
(Faculty of Social Sciences, University of Kelaniya, 2009) Dasanayake, G.; Vaise, P.; Minato, A.; Warnajith, N.; Wijayanayake, J.; Ozawa, S.
Factors Influencing Mobile App User Experience: An Analysis of Education App User Reviews
(Institute of Electrical and Electronics Engineers (IEEE), 2024) Arambepola, N.; Munasinghe, L.; Warnajith, N.
In the competitive digital world, user reviews considered as the most vital source of user feedback, provide valuable insights that reflect the success of software applications in terms of user experience (UX). As user-generated content grows exponentially, extracting meaningful information from user reviews has become an immensely challenging task. Though existing approaches can identify UX factors from mobile app reviews with a certain accuracy, prioritizing these factors poses a significant challenge. This research proposes a method to identify influential UX factors for mobile app reviews. Specifically, we did an in-depth analysis on educational app reviews of the Google Play Store. Notably, it was revealed that, although short reviews are pivotal for sentiment analysis, short reviews (word count < 3) do not significantly contribute to the generation of well-defined and meaningful topics in topic modeling. The quality of the generated topics for UX factor identification was quantitatively evaluated using coherence scores. Scores of 0.56 and 0.49 were obtained for positive and negative topics, respectively, indicating the effectiveness of the topic generation process. In addition, word embedding was utilized to prioritize the topics generated from topic modeling. There, the thumbs-up count of the reviews playsa significant role in identifying the most influencing UX factorsof educational mobile apps. The proposed method serves as a guide for researchers and practitioners to extract and prioritize UX factors from mobile app reviews in various domains.
ICT for Sustainable Growth in the World
(Department of Zoology, University of Kelaniya, Kelaniya, Sri Lanka, 2014-06) Dassanayake, G.; Warnajith, N.; Minato, A.; Itaba, M.; Ozawa, S.
Information and Communication Technologies (ICTs), including satellites, mobile phones or the Internet, play a key role in addressing the major challenges related with climate change and sustainable development. ICTs can play a significant role to improve the carbon footprint of cities by moving to a more intelligent use of energy. Climate change has risen rapidly up the agenda of international organizations, governments, communities, universities and industry sectors in the past decade, reflecting the growing impact of climatic manifestations at multiple levels with the potential to become a major disruptive factor in the achievement of economic growth and development over the next fifty years, climate change is playing an increasing role in processes of policy design, strategy implementation, livelihood maintenance and business practices around the world. This paper aims to raise awareness of the need to design and implement strategies for the ICT sector to better prepare for, respond and adjust to the impacts of short-term and long-term climatic manifestations. It gives an overview of the importance of adaptation for the ICT sector and of the challenges and opportunities resulting from this adaptation. It also describes the ICT sector's current response to climate change and gives a list of suggested adaptation actions. ICTs are fundamental for monitoring climate change, mitigating and adapting to its effects and assisting in the transition towards a green economy. By raising awareness of the role of ICTs, it is promoting transformative solutions that can ensure a sustainable future for all.
Image Processing Approach for Ancient Brahmi Script Analysis
(University of Kelaniya, 2015) Warnajith, N.; Bandara, D.; Bandara, N.; Minato, A.; Ozawa, S.
Writing is one of the most important inventions of Humankind. There are few main languages in the ancient world. Among these ancient languages Sanskrit was used in Indo region. Brahmi script is one of the most important ancient letters in South Asia. It became the matrix of Debanagaricharacter used for Sanskrit and Hindi. And, it produced Burmese script, Khmer script, Thai alphabet, Laotian alphabet, Tibetan alphabet, etc., during the last two thousand years. The people of Sri Lanka are fortunate that some of the writing of their ancestors is preserved on various inscriptions found throughout the country. These inscriptions have been discovered under the drip ledges of caves, rocks, pillars and slabs. Inscribed gold, silver and copper plates have been discovered as well. On the decipherment of these inscriptions, historical, linguistic and paleographical conclusions could be arrived at. The source data of this study is already published grayscale images of early Brahmi script. These images are taken from the paper copies of inscriptions called as estampages (rubbed copy). Up to the present, reading and analyzing these inscriptions are done by manually. The aim of this study is to develop algorithms based on image data of these estampages and implement a digital data repository. The process of this study can be divided into few stages. Such as: (1). Producing precise alphabet fonts of early Brahmi scripts has been produced from photographic data, (2). Precise method of identification of ancient letters with the aid of the alphabet fonts, which leads to automatic reading of ancient inscriptions by computers, (3). Database implementation for the analysis, (4). Develop web based interface for scholars over KISSEL network to share the knowledge and experience among the KISSEL users.
Novel Approach for Analyzing Brahmi Scripts
(Department of Zoology, University of Kelaniya, Kelaniya, Sri Lanka, 2014-06) Bandara, D.; Warnajith, N.; Minato, A.; Ozawa, S.
Writing is one of the most important inventions of humankind. There are few main languages in the ancient world. Among these ancient languages Sanskrit was used in the Indo region. Brahmi script is one of the most important ancient letters in South Asia. It became the matrix of Debanagari character used for Sanskrit and Hindi. The people of Sri Lanka are fortunate that some of the writing of their ancestors is preserved on various inscriptions found throughout the country. These inscriptions have been discovered under the drip ledges of caves, rocks, pillars and slabs. Inscribed gold, silver and copper plates have been discovered as well. On the decipherment of these inscriptions, historical, linguistic and paleographical conclusions could be arrived at. The source data of this study is already published as gray scale images of early Brahmi script. These images are taken from the paper copies of inscriptions called as estampages (rubbed copy). Up to the present, reading and analyzing these inscriptions are done manually. The aim of this study was to develop algorithms based on image data of these estampages and implement a digital data repository. The process of this study can be divided into several stages as follows: (1). Producing precise alphabet fonts of early Brahmi scripts from photographic data, (2). Development of a precise method of identification of ancient letters with the aid of the alphabet fonts, which leads to automatic reading of ancient inscriptions by computers, (3). Database implementation for the analysis, (4). Development of web based interface for scholars over KISSEL network to share the knowledge and experience among the KISSEL users.
Using KISSEL as a new direction of education and research on Humanities studies
(University of Kelaniya, 2015) Warnajith, N.; Minato, A.; Ozawa, S.
Internet technologies are changing our lives and educational systems in many ways. The term e-Learning was widely used in the 1990's with the rapid developments in the use of the Internet. Although it has a relatively short history of about two decades, it is becoming an important issue in the learning environments such as universities, research organizations and high schools. An important characteristic of e-learning is its interactivity with the learners. Multimedia is an integral part of the educational environment through online distance learning. Interactive multimedia technologies are engrossing because it provides the opportunity for deep involvement, which captures and holds learner interest. However, e-Learning approaches of Asia-Pacific countries, still lag behind when compared with developed countries. The KISSEL project established by a research group of Ibaraki University, Japan, is a new approach for the improvement of e-Learning in these countries. The term KISSEL which stands for "Knowledge Integration Servers System for E-Learning" is a knowledge sharing system that is designed to cater to teachers’ communities in Asian Pacific countries. KISSEL is developed to provide resources, particularly in multimedia, and tools and techniques essential for student-teacher communication and self-learning. Recently, a new research category named "Studies on Humanities" was introduced to this system. The aim of this paper is to report how researchers in this field of research benefit and contribute to enhance research knowledge among the member countries.