Browsing by Author "Thelijjagoda, S"

Now showing 1 - 20 of 95

Open Access
ACADEMIC SUCCESS OF PERSONS WITH VISUAL IMPAIRMENT AND BLINDNESS IN THE TERTIARY SECTOR: EXPLANATORY MODEL
(Available on-line at: www.oapub.org/edu, 2022-01-14) Suraweera, T; Bandara, S; Wickramarachchi, C; Dewage, N; Gunawardana, T; Nanayakkara, N; Yapa, E; Thelijjagoda, S; Jayathilaka, R
Ensuring universal access to education is an effective and sustainable means of empowering people with visual impairment and blindness. Literature confirms that blindness of a person is not a barrier for learning, yet past research brings about a range of diverse obstacles for productive engagement in education due to universities being designed for the sighted persons. Given that the persons with impairment are looked after comparatively better in the western world than in the developing nations for realising their challenging academic goals. Purpose of this paper is to present the findings of a comprehensive study on the academic work of persons with visual impairment and blindness in the tertiary sector. This population included recent undergraduates and those who have completed a university degree. The two distinct outcomes presented are; (first phase) the critical factors influencing the academic performance of persons with visually impairment and blindness and, (second phase) an explanatory model that characterizes the construct ‘the academic performance’. Using a semi-structured questionnaire, purposely selected eleven key informant interviews were utilized for the first phase for the qualitative investigation. Thematic analysis was used as the main method of data analysis. The Second phase employed a sample survey. Fifty respondents who had studied in universities during the 5-year period from 2015-2020 were selected through snow-ball sampling. Exploratory factor analysis was used as the main data analysis technique. The key findings of phase one revealed that external support, physical environment, motivation to learn, instructional strategies, ICT and English literacy are major contributory factors to academic performance. The second phase of the quantitative analysis derived five composite factors. Of these, the factor labeled “Motivating influences” appears to be mostly contributing to the academic performance of persons with visual impairment and blindness. While education is a lifelong endeavor of a person, these findings can contribute to make a substantial change in the quality of life of this community in the long run.
Embargo
AI Solution to Assist Online Education Productivity via Personalizing Learning Strategies and Analyzing the Student Performance
(Institute of Electrical and Electronics Engineers, 2022-10-29) Liyanage, M.L.A.P.; Hirimuthugoda, U.J; Liyanage, N.L.T.N.; Thammita, D.H.M.M.P; Koliya Harshanath Webadu Wedanage, D; Kugathasan, A; Thelijjagoda, S
Higher productivity in online education can be attained by consistent student engagement and appropriate use of learning resources and methodologies in the form of audio, video, and text. Lower literacy rates, decreased popularity, and unsatisfactory end-user goals can result from unbalanced or inappropriate use of the aforementioned. Prior studies mainly focused on identifying and separating the elements affecting the quality of online education and pinpointing the students' preferred learning styles outside of in-person and online instruction. This has not been able to clearly show how to enhance and customize the online learning environment in order to benefit the aforementioned criteria. This case study will primarily concentrate on elements that can be personalized and optimized to improve the quality of online education. With the aid of various algorithms like logistic regression,Support Vector Machines (SVM), time series forecasting (ARIMA), deep neural networks, and Recurrent Neural Networks (RNN), which make use of machine learning and deep learning techniques, the ultimate result has been attained. To increase application and accuracy, the newly presented technique will then be presented as a web-based software application. Contrary to what is commonly believed, this applied research proposes a new all-in-one Learning Management System (LMS) for students and tutors that acts as a central hub of all the learning resources.
Embargo
ALEXZA: A mobile application for dyslexics utilizing artificial intelligence and machine learning concepts
(IEEE, 2018-12-05) Rajapakse, S; Polwattage, D; Guruge, U; Jayathilaka, I; Edirisinghe, T; Thelijjagoda, S
Dyslexia can be explained as a neurological learning disability which causes difficulties in reading, word decoding, comprehension, short-term memory, writing, spelling, and speaking. People who are diagnosed with dyslexia tend to show signs of low self-esteem and anxiety since they can't interact with the society in a way that their peers do. Many applications available in this domain help them by correcting their issues by playing games and reading some hard-coded texts or pdf books. This correcting process takes time and dyslexics become helpless when coping with their day-to-day activities. This paper describes results of an evaluation of a prototype mobile application which helps the dyslexic users to deal with their reading difficulties in real life successfully, while they are receiving proper treatments. This prototype can identify the texts around them and read it loudly so that user can understand and will be allowed to customize the chunking, scrolling and highlighting of words according to their disability levels. By integrating dictionary support with the phonic and morphological structure of the word, the user will be able to comprehend difficult and complex words easily. In addition, the study also explores the use of a machine learning approach to improve the effectiveness of the learning dyslexic complex words.
Embargo
Analyzing the Location Feasibility for Retail Businesses using Market Location Factors
(IEEE, 2018-12-21) Marasinghe, L; Rupasinghe, M; Kumarasinghe, B; Perera, M; Thelijjagoda, S
The retail industry is a fast growing and a highly revenue generating industry. The location of a retail outlet is the most influencing factor for the success of the business. Therefore selecting a location for a retail store or an outlet is a challenging process. The purpose of this study is to define a method and develop a system to analyze the feasibility of a selected location for a retail store. The factors used in this method are location and market factors of a selected area. In order to define and test the method, we selected three different areas and five different retail store types. To retrieve location data, we used Google Maps web service. Consumer surveys were conducted in selected areas to get information about consumers' shopping patterns and selections. From the web service, we were able to identify transport modes, locations of competing stores and shopping areas. The findings of this study and the method described is useful in deciding the feasibility of any given location for a retail outlet. Also the specified method and model can be modified and extended to analyze different kinds of business locations.
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.K
Nowadays, 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.
Embargo
ARROW: A web-based employee turnover analysis tool for effective human resource management in large-scale organizations
(IEEE, 2017-09-14) Weeramanthrie, T. T; Thilakumara, C. N; Wijesiri, K. N. A. C; Fernando, N. I; Thelijjagoda, S; Gamage, A
To gain the competitive advantage, organizations need to adapt to the dynamic market. Therefore, many researchers have tried to find different ways for adapting to competitive conditions. Most of these research have finally ended up focusing on the human resource, which is the major and important resource in any organization. Currently human beings are treated as assets rather than resources. The System, ARROW is a unique web application developed to satisfy the requirements of company management in employee understanding process. The main objective of the system, ARROW is to fulfil the gap between employees' past, present and future behavior and the management's ability to understand the behavior of the organization's employees at the HR practices. Natural Language Processing and Data Mining techniques were used to accomplish the main objective.
Embargo
Arunalu: Learning Ecosystem to Overcome Sinhala Reading Weakness due to Dyslexia
(IEEE, 2020-12-10) Sandathara, L; Tissera, S; Sathsarani, R; Hapuarachchi, H; Thelijjagoda, S
Dyslexia is an impairment in ability in reading. People having Dyslexia has difficulties in identifying specific letters and words and identifying speech sounds and decoding the letters which leads to difficulties in comprehension, spelling and writing. Dyslexia may severely affects language development and impacts reading and other language based improvement and functioning. “ARUNALU: Learning ecosystem to overcome reading disabilities in Sinhala language due to Dyslexia” has been proposed as a multi-sensory mobile solution, in native language of Sri Lanka (Sinhala) and with effective screening and intervention methodologies recommended by health professionals. Objective is to deliver, a phonological support to enhance reading skills of dyslexic children by providing a machine learning based automated screening and intervention mobile solution. Through these reading environments, there's a reward system in intervention process to encourage the user, and also users and respective parties can analyze user's progress. The proposed system is mainly based on Voice recognition, Natural Language Processing, Machine Learning and Deep Learning concepts collaborating with reading and gaming environments. Core Objective of the proposed system is to come up with a better and effective screening and intervention methodologies for early identification of Dyslexia and provide phonological training to overcome Sinhala reading difficulties due to Dyslexia in a user friendly manner.
Embargo
Aspect Based Sentiment Oriented Hotel Recommendation Model Exploiting User Preference Learning
(IEEE, 2020-11-26) Godakandage, M; Thelijjagoda, S
Due to the advancement of the technology, people tend to focus on the online content related to products and services available through websites and the opinions of others which are provided in the form of reviews and comments. In the tourism domain, travelers are more concerned with the place of accommodation, facilities provided by a hotel, the location or the environment that the hotel is situated and tend to find the hotels that fulfill their requirements. They have to go through each and every review or comment in order to get a clear idea about a particular hotel, according to the opinion of the previous reviewers, which is a difficult and time-consuming task. Therefore, through this research, the users are provided with a system which analyses hotel reviews and provides aspect based personalized hotel recommendations that help users to easily find the best hotel according to their preferences, without having to go through a lot of reviews. For that, the proposed system was implemented with four steps, namely data gathering, data pre-processing, aspect extraction and sentiment analysis, and visualization of the output. In the implemented system, hotel reviews were analyzed and extracted the overall opinion of the reviews as opinion units with their related aspects. Based on the sentiment of those opinion units and the preferences of the user, the best hotels were suggested enabling the users to get an insight about the hotels. For this approach, aspect-based sentiment analysis was used. In addition to that, a weighted average calculation method was used for the final recommendations of the hotels, which suit users' preferences in an accurate manner.
Embargo
Aspect-based sentiment analysis on hair care product reviews
(IEEE, 2020-09-24) Kothalawala, M; Thelijjagoda, S
Nowadays, with almost everything being shared online, people are more verbal about their consumer experiences with products via reviews. Reviews can be vital for manufacturers to get insights into consumer opinions and consumers in their purchase decisions. Sentiment analysis, referring to the extraction of subjective opinions on a particular subject within a text, is a field within Natural Language Processing, that can convert this unstructured information hidden within reviews into structured information expressing public opinion. In regards to a specific product group like hair care products, certain brands are rising in the market due to their positive public opinion on particular aspects. While ecommerce websites facilitate users to view the reviews, they do not display which reviews contain which type of opinion on which aspect at a glance. This research aims to introduce an automated process that focuses on determining the polarity of online consumer reviews on different aspects of hair care products by using Aspect-based Sentiment Analysis. The system consists of processes like data gathering, pre-processing, aspect extraction and polarity detection and follows a sequential approach to achieve the intended goal. Consequently, by deciphering the aspect-wise polarity of the reviews, the implemented system demonstrates an accuracy of 85% from the test data for overall aspects, enabling consumers to get an at a glance idea about the public opinion and manufacturers to identify their strong and weak points.
Embargo
Assistant Zone – Homeschooling Assistance System based on Natural Language Processing
(IEEE, 2022-12-09) Premendran, K; Bopearachchi, S.B.D.D.; Senevirathna, S.D.M.; Giridaran, S; Archchana, K; Ganegoda, D; Thelijjagoda, S
As a developing country, most people give their highest priority to education. When focusing on building an e-learning platform to improve the knowledge of students and teacher-student interactivity, the pandemic season can be mentioned as the main blocker which highly impacted the education field. Not only by considering the pandemic situation but also by addressing the concerns when it comes to teacher and student evaluation and psychological levels of students who are undergoing different difficulties, the “Home Schooling Assistance System” (Assistant Zone) has been introduced as a solution. The Assistant Zone has been initiated with three unique features which are valuable for both students and teachers. This system analyzes the strengths, weaknesses and evaluates the student performance, suggests study materials to improve themselves, provides solutions to the problems faced by the students, teachers, and parents and measures the performance of teachers based on their students, and recommends learning materials for the low-performing teachers. The Assistant Zone fulfills the targeted problems and introduces the above-mentioned three unique features with the use of Natural Language Processing (NLP) such as the BERT algorithm and Machine Learning models such as the Recurrent Neural Network, Forward Neural Network, and Gaussian Model.
Embargo
Automate Traditional Interviewing Process Using Natural Language Processing and Machine Learning
(IEEE, 2021-04-02) Senarathne, P; Silva, M; Methmini, A; Kavinda, D; Thelijjagoda, S
Nowadays, almost everything is equipped with technology. People can save time by using modern day technological applications in the most convenient way. Smart Interviewing System is one such software/tool which automates the traditional interviewing process using modern Natural Language Processing techniques and deep learning applications. The system will be mainly beneficial for interviewers and HR management employees working for different organizations who conduct technology related interviews. The system works with human voice and writing patterns. The system converts human language into system understandable text-based inputs, and these are used as inputs in the automated interviewing process. The system then checks the accuracy of the answers which candidates provided on the both oral interviews/ technical interviews and written tests. Later, the system automatically predicts scores for each answer using concepts of the deep learning. Interviewers can reduce the effort that they have to put in for selecting the most suitable candidates who are qualified enough to work with their organization. SIS is developed based on modern DL and NLP concepts using Python programming language alongside with ReactJS Framework. This system checking and evaluating candidate more accurately in every stage of the interview using advance evaluation parameters than human oriented evaluations. Above process lead system to find more human errors which critically can be affected to future of the organizations. Because of that, it can be led organizations to find best human resources comparing to the traditional interviewing process by sacrificing less time and effort.
Embargo
Automated Location Scouting and Production Planning for Movie Industry in Sri Lanka using scripts written in Natural Language
(IEEE, 2021-04-02) Perera, V; Lakshan, N; Hettiarachchi, A; Himantha, K; Gamage, M. P. A. W; Thelijjagoda, S
The film industry in Sri Lanka has grown into a multi-billion-dollar industry. However, it has not reached its fullest potential yet. This is due to the insufficient number of films produced locally. One of the major causes for a film to fail is the low attention given for production planning. Planning should take place with the commencement of the Preproduction state. This should include the entire process from scriptwriting to final ticket issuing. The pre-production state that determines the success or failure of the film consists of the critical processes that will be required to execute the production state. Place Scouting is one of the main processes in a production plan. Since the film industry focuses primarily on the esthetic enjoyment of people in society, scenic beauty is a must when choosing locations for a film. “Film-It” is developed to provide all-around assistance in Location Scouting and Resource Planning in the Pre-Production State of a movie. With the aid of this application, key players in the film industry will be able to save their time, effort and money spend on Preproduction preparation. Key stakeholders in the film industry have confirmed that this application would carry the Sri Lankan film industry to a whole new level.
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
Business Intelligence Assistant for Human Resource Management for IT Companies
(IEEE, 2020-11-04) Athukorala, C; Kumarasinghe, H; Dabare, K; Ujithangana, P; Thelijjagoda, S; Liyanage, P
The advancement in technology is exponential. Moore's law supports this argument, by stating that the computing power doubles every two years. In such a premise, many IT companies have risen to meet the challenges. These companies provide various solutions in various fields of enterprises, pushing the limits of technology. Human resource is considered the most important asset in any organization. In order to utilize this asset beneficially, an organization must have great Human Resource Management practices. This includes practices from recruitment until employee termination. One great employee can offset the work of several regular employees. IT companies strive to acquire and retain such talent. But this is not a simple task. It requires resources including manpower and time. There should be knowledgeable individuals to handle important human resource processes, and many organizations lack these. They do not have enough time or labor to invest in good human resource processes. This research proposes a solution to this problem by creating a Business Intelligence Assistant for Human Resource Management Targeting Information Technology companies. It delves into Human Resource Management practices revolving around employee recruitment, job placing, employee engagement and human resource decision making. The solution consists of four solutions, namely; Structured Resume Analyzer, Smart Candidate Ranker, Employee Engagement Survey Generator and Business Intelligence Processor. Each component will enable the organization to streamline certain processes helping them save both time and labor. The individual components will make use of various applications of artificial intelligence to aid in the decision-making of an organization.
Open Access
Can “Build-operate and transfer” be a gamechanger for the future of Colombo port?
(Emerald Publishing, 2022-12-01) Leuwanduwa, H. C; Katudampe, K.T.B.P; Wijewardhana, M.A.R.H; Wikramarathna, H.A; Karunarathna, K. N. P; Thelijjagoda, S
The purpose of this research is to investigate the importance of private-public partnerships in the development of container terminals. The study will thoroughly examine the necessity of Private Public Partnerships (PPP) and its impact in increasing as well as in finding investments, when developing container terminals. We gather qualitative, statistical information & facts related to the sector from primary & secondary sources to identify & analyse elements like current and past capacities, history of handling volumes, efficiency rates, productivity, revenue etc. on various terminals established within the port of Colombo. Due to major benefit of sharing capital funding responsibility and public risk with the private sector, this analysis shows that resorting to PPP-based projects is a much healthier alternative for SLPA. In addition, the PPP spectrum serves to highlight the SLPA's efforts to develop appropriate models, such as the BOT model, in response to the growing demand for shipping line services. The SAGT & CICT, which were created as contemporary container terminals under BOT conditions, have been successful. The introduction of BOT-based investments has improved the Colombo port's performance levels and enhanced the SLPA's motivation.
Open Access
Can visual impairment impact your income potential?
(PLoS ONE, 2023-04-20) Wickramaarachchi, C; Jayathilaka, R; Suraweera, T; Thelijjagoda, S; Kollure, L
People’s quality of life (QOL) has been disrupted globally in the wake of the pandemic in recent times. This was mainly due to global economic crises fuelled by the coronavirus (COVID– 19) and other related factors. Sri Lanka, too, was facing major social and economic constraints in the period 2021–2022. Thus, all communities islandwide have been economically disturbed. Among others, people with Visual Impairment and Blindness (VIB) have been pushed to severely disadvantageous positions, financially and otherwise. A sample from three geographical locations in Sri Lanka; and eleven individuals representing diverse cadres in Sri Lankan society were purposively selected for the study based on the existence of the majority of the visually impaired community using a mixed approach. Descriptive statistics were utilised to analyse the identified socio-economic characteristics. Ordered probit regression was employed to determine the mediating effect of socio-economic status on income levels. Word Cloud illustrates the factors affecting the QOL. Most severely impaired individuals are more likely to earn a lower rate of income. This situation has degraded their lives and poor QOL. Participants’ responses elucidate that facilities, resources, education, opportunities, income, employment, and government activities would enhance their QOL. The study adds value to society by recognising VIB people, helping them gain financial independence and strengthening them without marginalising the impaired community. The proposed policies in this study would be valuable for these social groups to address their wealth concerns.
Open Access
CHALLENGES & PROSPECTS FOR ECONOMIC EMPOWERMENT OF PERSONS WITH VISUAL IMPAIRMENT & BLINDNESS ENGAGED IN SELFEMPLOYED VENTURES
(y Sri Lanka Forum of University Economists (SLFUE) Uva Wellassa University of Sri Lanka, 2021-01-21) Dunuwila, V. R; Suraweera, T; Jayathilaka, R; Thelijjagoda, S
People with disabilities experience numerous barriers with regard to securing employment, thus, they are more likely to work for low wages, informally and precariously. Besides, some of them are entitled for a disability benefit which is often inadequate to cover their daily expenses (Global Disability Summit, 2018). Economic empowerment can be defined as a way of ensuring income security for people with disabilities to achieve income security, advance economically, enrich themselves through empowerment and autonomy to make economic decisions within and outside the home (Global Disability Summit, 2018). Self-employment is perceived as a viable option for empowering disabled individuals that facilitates achieving a balance between disability status and work life (Kitching, 2014; Pagán, 2009; Adams, et al., 2019). Pagán (2009) indicated the presence of a strong relationship between disability status and self-employment; thus, selfemployment rates were higher among people with disabilities compared to those who report no limitation in daily activities (Kitching, 2014; Pagán, 2009; Adams, et al., 2019). The Global Disability Summit (2018) indicates that obstacles to economic empowerment experienced by people with disabilities can vary depending on the nature of an individual’s impairment, their gender, socioeconomic status and the context in which they live. Adams, et al., (2019) further indicate that the decision to enter into self-employment for most disabled individuals were influenced by the ‘push’ factors such as lack of alternative employment opportunities, rather than the ‘pull’ factors such as passion or interest in a particular field, or the desire to work for themselves (Kitching, 2014; Adams, et al., 2019). Past research reveals that the disabled self-employed face significant problems in sustaining the business due to reasons such as consumer discrimination, inadequate training, poor access to information, absence of appropriate business support and challenges in accessing finance (Adams, et al., 2019; Kitching, 2014; Pagán, 2009; Vaziri, Schreiber, Wieching, & Wulf, 2014)
Embargo
Collabcrew—an intelligent tool for dynamic task allocation within a software development team
(IEEE, 2017-12-06) Samath, S; Udalagama, D; Kurukulasooriya, H; Premarathne, D; Thelijjagoda, S
Currently in the IT industry, the people factor has become very critical when determining the quality of a software project. It is highly important that the correct person performs the relevant task and proper human resource allocation happens within the software project team to obtain successful outcome. This often needs critical thinking, regular team meetings and discussions. Typically a software project manager needs to be highly experienced with the team for this purpose and can be really complex and time consuming with the limited project schedules. This research work introduces a task management tool - CollabCrew specially designed for the software development teams which dynamically allocate tasks based on the skills and previous work done by the team members. This uses historical data from its' own repository or from an external source to find useful information of the previous work done by the project team members to automatically allocate them for new tasks. This proposed system will be containing an Extract, Transform and Load (ETL) tool which will extract data from different data sources, a prediction model to predict the aptness of each team member for a given task and a peer review mining and summarization component to provide a viable way to extract features from peer reviews. Then based on the result, the task allocation component will do the allocations in the most optimal and the feasible way for the project. Even though there are several commercially available task management tools, none has an intelligent component to automatically delegate work within the team. The scope of this work extends beyond the IT domain and a similar procedure can be adopted to develop a task allocation framework in other fields as well.
Embargo
Conditional Random Fields based named entity recognition for sinhala
(IEEE, 2015-12-18) Senevirathne, K. U; Attanayake, N. S; Dhananjanie, A. W. M. H; Weragoda, W. A. S. U; Nugaliyadde, A; Thelijjagoda, S
Named Entity Recognition (NER) plays an important role in Natural Language Processing (NLP). Named Entities (NEs) are special atomic elements in natural languages belonging to predefined categories such as persons, organizations, locations, expressions of times, quantities, monetary values and percentages etc. These are referring to specific things and not listed in grammar or lexicons. NER is the task of identifying such NEs. This is a task entwined with number of challenges. Entities may be difficult to find at first, and once found, difficult to classify. For instance, locations and person names can be the same, and follow similar formatting. This becomes tough when it comes to South and South East Asian languages. That is mainly due to the nature of these languages. Even though Latin languages have accurate NER solutions those cannot be directly applied for Indic languages, because the features found in those languages are different from English. Therefore the research was based on producing a mathematical model which acts as the integral part of the Sinhala NER system. The researchers used Sinhala News corpus as the data set to train the Conditional Random Fields (CRFs) algorithm. 90% of the corpus was used in training the model, 10% is used in testing the resulted model. The research makes use of orthographic word-level features along with contextual information, which are helpful in predicting three different NE classes namely Persons, Locations and Organizations. The findings of the research were applied in developing the NE Annotator which identified NE classes from unstructured Sinhala text. The prominent contribution of this research for NER could benefit Sinhala NLP application developers and NLP related researchers in near future.
Open Access
Critical Analysis on Identifying the Effect of Military Training Simulations on Confidence Level of Soldiers
(2014-08-21) Fernando, S; Thelijjagoda, S
Simulations and games grow very rapidly and dynamically with technologies evolving every day. Technologies of military simulation are continuously evaluated and upgraded since it is a key factor for military training, analysis, planning, etc. The training simulations had been used to train soldiers for a long time period, but systematic analysis haven't been made to identify if the military simulations have been able to achieve increasing the confidence level of soldiers,. There have been many researches on military training simulations time to time around the world. Mainly defence research centers had done researches to identify the areas to improve in order to upgrade the quality of training. These have been used to train soldiers' way back in the World War II. In the advancement of technology these have become more and more advance and effective on achieving their goals. DARPA (Defence Advance Research Program Agency) and the US Army research institute were the major two researchers on this domain. This paper presents a research that was conducted to identify whether military training simulations make an effect on the confidence level of the soldiers when they are battling. The objective of this research was achieved through evaluating the existing background of military simulations against the confidence level of soldiers, investigating how military training is done in terms of simulations, evaluating how simulation based training are effective for soldiers, identifying the factors that affect the confidence level of soldier and introducing a model to evaluate the confidence level of soldiers. According to the conceptual model used, actual experience, experience of others, self-efficacy, mission readiness, persuasion and emotional arousal were identified as factors affecting the confidence level of a soldier. Based on the collected data, the conceptual model which was proposed to measure the confidence level of soldiers could be justified to acceptable level.