Research Papers - Dept of Information Technology
Permanent URI for this collectionhttps://rda.sliit.lk/handle/123456789/593
Browse
180 results
Filters
Advanced Search
Filter by
Settings
Search Results
Publication Open Access Hashtag Generator and Content Authenticator(researchgate.net, 2018-01) Yapa Abeywardena, K; Ginige, A. R; Herath, N; Somarathne, H; Thennakoon, T. M. N. SIn the recent past, Online Marketing applications have been a focus of research. But still there are enormous challenges on the accuracy and authenticity of the content posted through social media. And if the social media business platforms are considered, majority of the users who try to add a market value to their own product face the problem of not getting enough attention from their target audience. The purpose of this research is to develop a safe and efficient trending hashtag generating application solution for social media business users which generates trending and relevant hashtags for user content in order to get a broad reach of target audience, automatically generates a meaningful caption to their relevant posts and guarantees the authenticity of the product at the same time. The user content is analyzed and filters the important keywords, generates a meaningful caption, suggest related trending keywords and generates trending hashtags to get the required reach for online marketers. Additionally, the marketing products’ content authentication is ensured. The application uses Natural Language Processing, Machine Learning, API technologies, Java and Python technologies. A unique database is assigned to users which contains rankings for each user. The target audience who engages in buying products get to know about the status of the sellers with respect to authenticity of the content. It is believed that the application provides a promising solution to existing audience reach problems of online marketers and buyers. The significance of this system is to help marketers and buyers to engage in online buying and selling with much effective, reliable and safer ways. This mitigate the vulnerability of bad social media marketing influences and helps to establish a safe and reliable online marketing practice to make both sellers and buyers happy. This paper provides a brief description on how to perform an organized online marketing discipline via the Trending Hashtag Generator & Image Authenticator application.Publication Open Access Recommending a Model to Forecast Sri Lanka Wholesale Price Index Using Big Data Analytics(IEEE, 2018-02-22) Thakshila, P. M. C; Asanka, P. P. G. DThe Whole Sale Price Index (WPI) is a main index, which is used to measure price variance before a product or service release to a consumer. WPI represents the basket of wholesale goods and services on market basket. Sri Lanka WPI is accumulated using Laspeyre's formula considering based year as 1974 and up till now not seasonally adjusted. Data collection, compilation, and Dissemination of WPI are done by Prices, Wedges, and Employment division of the Statistics Department of Central bank of Sri Lanka (CBSL) and releasing to public every month. Forecasting of WPI is necessary to understand the aid primary level economic impact of the country. Big data analysis and Data mining are using for data where it is hard to handle using traditional tools and techniques. Decision makers able to gain valuable insights analyzing that varied and rapidly changing data. Time series analysis compromise method for analyzing time series data in order to extract meaningful statistics and other characteristics of data. This review discusses the way to utilize big data analysis technology to systematically analyze time series based WPI data in Sri Lanka. The time series based forecast technologies ARIMA, ANN, VAR, Moving Average, AFARIMA etc. are reviewed based on previous findings. Based on the result will present the effective model to forecast WPIs in Sri Lanka and will critically evaluate selected WPIs. That selection will coordinate based on the weight and relationship to all items based WPI. WPI will compare with existing Sri Lankan Price Indices based on the relational factors.Publication Embargo Impact Analysis of US Dollar Index Volatility on Imports and Import Categories of Sri Lanka(IEEE, 2018-07-31) Sahabandu, R. V; Asanka, P. P. G. DThe economic liberation in 1977 resulted in drastic changes in many aspects of Sri Lanka. Considering about 1978-2015, the country yearly import demand represents over 30% share of the gross domestic product (GDP) except 1984, 2009, 2010, 2013-2015. Investigations and the studies on a countries' imports are surprisingly overlooked as there are several studies being carried out focusing only the aggregated export volume concerning the exchange rate volatility. The monthly data of Sri Lanka imports, import categories and monthly US Dollar (USD) volatility from January 2007-December 2016 were used for the analysis. This study tries to learn the impact of US Dollar Index (USDX) volatility on import demand of Sri Lanka. The Autoregressive Distributed Lag (ARDL) Approach is employed to learn long-term and short-term cointegration among the underlying variables. There exists a 95% statistically significant short-run relationship and it is identified that the import categories, Consumer Goods (CG), Intermediate Goods (IG), Investment Goods (INV), Unclassified Items (UI), None-Oil Imports (NO) have a speed of adjustment to the equilibrium (SAE) in the long-run of 17%, 36%, 23%, 23%, 25% respectively. The total imports reveal that the disequilibrium conditions will be resolved by 27% within a period of one month that is shocked due to the USDX volatility. Knowledge of the relationship between USDX fluctuation, exchange rate volatility and import volume will support to pursuit for a beneficial trade and prevent or be prepared for a much more stable situation within Sri Lanka.Publication Open Access SeizeIT: SEIZURE victims are no longer leashed(Institute of Advanced Engineering and Science, 2019-09-18) Wimalarathne, M. A. J. I; Ubeysingha, K. U. K; Imbulana, I. A. D. M; Welikala, W. A. D. R; Pulasinghe, KSeizure is considered to be one of the severe and most common type of neurological disorders. Despite the availability of numerous anti-seizure drugs, it is often difficult to control the disease completely and effectively. Lack of close supervision and failure in providing urgent medical care during and after seizure episodes, leads to serious injuries or even death. On the other hand, the use of wireless sensor networks in everyday applications have rapidly increased due to decreased technology costs and improved product reliability. Therefore, developing a wearable device to monitor seizure may complete the anamnesis, help medical staff in diagnosing and acute treatment while preventing seizure related accidents. There are number of seizure detection systems available in the market. Still their performance is far from perfect. This paper explores an application of biomedical wireless sensor networks, which attempts to monitor patients in a completely non-invasive and non-intrusive manner. It describes a wearable device together with seizure prediction and alerting system, which is designed to address some issues with seizure detection systems in the market. Its functional block diagram and operating modes are detailed. Possible application areas of the device are also discussed.Publication Embargo Auto Generation of Gold Standard, Class Labeled Data Set and Ontology Extension Tool [QuadW](IEEE, 2019-02-25) Tissera, M; Weerasinghe, RAutomatic Knowledge Extraction (AKE) from domain independent, unstructured text sources is a challenging task in Natural Language Processing and Text analytics. Though, supervised learning mechanisms are very much result promising, application is painful due to the mandatory requirement of a class labeled training data set, as it involves expensive manual effort which is more time consuming. As a solution for this problem, this paper introduces a novel mechanism to build a self-learned classifier model that can automatically generate class labeled training data set for Knowledge/Information Extraction from domain independent unstructured text. Sri Lankan English newspapers (which comprise unstructured text in unconstrained domains) are the main data source for this study and a prototype was built to Professional Information Extraction with the semantic pattern Who holds/held What position, Where and When (Four words start with `W', hence named `QuadW'). Methodology uses advanced machine learning techniques such as, a Random Forest with Adaboost ensemble algorithm to build a composite classification model. This classifier is called as self-learned since, it generates its own training data set automatically. This composite model has improved accuracy and avoided over fitting to data as well. The rule-based feature extraction algorithm and the hand-craft ontology developed, can also be considered as novel components of this study. Self-learned classifier has been extensively improved and tested to show higher accuracy with precision and recall close to one. Therefore, the classified output from the self-learned classifier can be used as a gold-standard data set for future research in Professional Information Extraction. The constructed ontology with approximately 400 facts, also can be effectively used in future researches. Further, introduced classifier can be used as a tool to extend the existing ontology as well. A novel usage of machine learning algorithms to text classification demonstrates that, this study goes with the state-of-the-art technologies.Publication Embargo A Review of Geothermal Energy for Future Power Generation(IEEE, 2019-09-26) Kulasekara, H; Seynulabdeen, VRenewable power generation is rapidly increasing due to the depletion and unfavorable environmental impact of fossil fuels. Geothermal energy is a form of renewable energy that can be effectively used for electric power generation. Besides, geothermal power provides considerable advantages compared to other renewable resources such as solar and wind power. Geothermal energy provides reliable, stable and efficient power compared to the lack of inertia, lack of efficiency and the intermittent nature of solar and wind resources. Moreover, geothermal power plants must be integrated with energy storage devices to improve the stability and flexibility of the power system. Gravity-fed energy storage and flywheel energy storage systems are two reliable technologies that can be integrated with geothermal power for improved stability and flexibility. Furthermore, the disadvantages of geothermal energy such as higher initial cost and geographic dependency can be compensated using recent research and developments in the geothermal technology. These recent developments include enhanced geothermal systems, small-scale geothermal power generation and geothermal power generation using abandoned oil and gas wells. Therefore, geothermal energy has the potential to become a major power generating source in the future.Publication Embargo ATHWEL: Gamification Supportive Tool for Special Educational Centers in Sri Lanka(IEEE, 2019-12-19) Kiriwaththage, P. N; Morawaka, ALearning Disability is a neurologically-based problem which involves in learning basic skills such as reading, writing and math. Intellectual Disability is characterized by below-average intelligence. Children with Intellectual Disability can do and learn new skills, but they learn them more slowly than average children of their age. Game-based learning is an effective way of getting learners actively involved in educational activities. Educating children with Intellectual Disability is a challenging process. They usually learn and progress more slowly than average children. Such children may have issues with motivation and interest in education; the use of Gamification approach becomes important as a motivational and interested affordance. A prototype desktop Gamification Supportive Tool called “ATHWELA” is proposed which operates through Assistive Technology. Assistive technology can be a device or a service that is used to increase, maintain, or improve functional capabilities of individuals with disabilities. Children with Intellectual Disability can be less interested in Mathematics, some can be not good in reading and some can be not good in writing. ATHWELA is targeting at increasing, maintaining, or improving these three points and ATHWELA can be used in special education classrooms as a tool of gratification and extrinsic motivation. Points and rewards will be presented as the motivational technique. The main objective of our research is to help children with Intellectual Disability with their primary educational skills with less effort and in an interactive way and this prototype desktop application is developed in the Sinhala language because the Sinhala is the mother-tongue of Sri Lanka. In addition, it has used Machine Learning and Image Processing techniques to improve the educational skills of children with Intellectual Disability.Publication Embargo Methodology of knowledge representation from natural language (Onto_X)(IEEE, 2013-04-26) Koggalahewa, D. N; Amararachchi, J. L; Pilapitiya, S. U; Geegange, D. T. KInformation available in different formats cannot be understood by a computer or a machine due to lack of a proper knowledge representation mechanism. It always requires more human effort in feeding the knowledge to the computers or the knowledgebase. XML covers the basic level of knowledge representation, but is incapable of utilizing the concepts and semantics in a proper way. Onto_X is an effort made to automate the process of ontology construction from an annotated xml file or database. The annotation process is done by any natural language processing tool (apart from the system). The system requires an xml file as the input and converts it into ontology in owl format. The system is capable of generating the semantics over annotated content with owl components. XML entities will be automatically mapped into the owl components such as classes, sub classes, instances and relationships. The conversion mechanism is totally automated inside the Onto_X since it assures all the co-relationships over the annotated content. The conversion process identifies the xml properties and assigns semantics with the integration of word-net 2.1 and owl properties over the parsed content. The system uses the protege libraries for the conversion process. The most special feature in the conversion process is that it uses its own inference, without just mapping xml properties to owl. The system is capable of visualizing the mapped owl ontology and it allows the user to refine the content of the constructed ontology. The final outcome of the system is ontology in owl format, which is mapped from the xml file or a database. The research ensures a better knowledge representation mechanism and it will assure the creation of domain knowledge from the xml file. The expandability is high since it takes information from the base level.Publication Embargo Sentence based mathematical problem solving approach via ontology modeling(IEEE, 2016-09-26) Geeganage, D. T. K; Koggalahewa, D. N; Amararachchi, J. L; Karunananda, A. SMathematics includes solving a variety of problems by applying theories and formulas. Thus mathematical problem solving requires performing arithmetical operations by using analytical and problem solving skills. Sentence based mathematical problems contains real world scenarios and requires to apply both mathematical and problem analyzing knowledge to solve problems. Human beings solve sentence based mathematical problems by applying different mathematical formulas and theorems to the comprehend questions. Understanding the sentence based questions requires an additional effort to grab the content and grasped content should be mapped with known concepts in terms of variables. Organizing the variables and formulas by understanding the relationships and properties would be important to formulate the answer. Thus the content can be easily modeled using an ontological approach and the problem solving can be accomplished by querying the ontology using a multi agent approach. Sentenced based mathematical problem solving approach demonstrates a system which can solve mathematical questions by acquiring the semantics of the question and applying learnt formulas. Information extraction from the question, ontology based knowledge representation, multi agent based ontology querying and answer generation with explanations can be defined as major functions. This approach can be used to introduce effective intelligent tutoring systems in any domain.Publication Embargo Semantic Self Learning And Teaching Agent (SESLATA)(IEEE, 2013-04-26) Koggalahewa, D. N; Amararachchi, J. L; Pilapitiya, S. U; Geegange, D. T. KSemantic Self Learning And Teaching Agent (SESLATA) is a self learning software which is capable of learning from a natural language source. It identifies language complexity, ambiguity and influence of diverse writing styles to extract and decipher. The specialty herein the system is, usage of its acquired knowledge to perform teaching and explaining activities to its end users. The agent is capable of updating its own knowledge and it interacts with learner through intelligent response and using own experiences in the process of teaching according to learner's knowledge. Simply it learns somewhat like a human and teaches what it has learnt as a human does. The software is endowed with inventions involving in Natural Language Processing, machine learning, explanation and knowledge representation and ontology, which are still under research. Self learning from natural language (acquiring the domain knowledge to model ontology), automate the ontology creation from natural language, the teaching and explaining capability of an agent, updating the knowledge via ontology, knowledge representation and sharing, a new methodology of online learning, teaching according to the depth of user's knowledge are the major findings of the system.