ITRU - 2013
Permanent URI for this collectionhttp://192.248.9.226/handle/123/14725
Browse
Recent Submissions
- item: Conference-Full-textVoice Disorder Recognizer to Aid Diagnosis of a Speech PathologistHettiarachchi, YK; Withanage, DKIn the field of medicine, currently a variety of methods are used to identify the pathologies in the human speech production system. The most common drawbacks of those methods are the discomfort for the patient caused during inspection, the dependency of the results on medical practitioner’s experience and the high cost of diagnosis involved if advanced systems are used. This research discusses how to overcome those drawbacks by using an ICT tool that can provide quantitative evidence of the vocal disorder of patients to medical practitioners to diagnose pathologies in deceased speech producing system of patients.
- item: Conference-Full-textSkin Wound Analysis SystemRanasinghe, CD; Igalawithana, TC; Udayanga, SMR; Hettiarachchi, SY; Chaminda, HTIn modern medical science, there is a growing trend of applying Information Technology into manual routines. Automated skin wound analysis is a novel approach in treatment of skin wounds. The system is intended to analyze different types of skin wounds/lesions by using digital image processing techniques. Diabetic ulcers, skin-grafted burn wounds and nail lesions have been chosen for analysis. Nail lesions require an identification process whereas diabetic ulcers and skin-grafted burn wounds require an analysis of the healing process. A semantic web search is performed in order to verify the identification of nail lesions. The system also generates line graphs in order to facilitate the assessment of the healing process. A 3D model of the diabetic ulcer is created based on the data captured by an IR sensor-based mechanism. This wound analysis system is expected to help the doctor’s diagnosis process immensely. The system provides quantitative and accurate results on wound healing. Moreover, it supports better comparisons and decision making.
- item: Conference-Full-textSentiment Analysis for Social MediaJayasanka, RASC; Madhushani, MDT; Marcus, ER; Aberathne, IAAU; Premaratne, SCSentiment analysis, the automated extraction of expressions of positive or negative attitudes from text has received considerable attention from researchers during the past decade. In addition, the popularity of internet users has been growing fast parallel to emerging technologies; that actively use online review sites, social networks and personal blogs to express their opinions. They harbor positive and negative attitudes about people, organizations, places, events, and ideas. The tools provided by natural language processing and machine learning along with other approaches to work with large volumes of text, makes it possible to begin extracting sentiments from social media. In this paper we discuss some of the challenges in sentiment extraction, some of the approaches that have been taken to address these challenges and our approach that analyses sentiments from Twitter social media which gives the output beyond just the polarity but use those polarities in product profiling, trend analysis and forecasting. Promising results has shown that the approach can be further developed to cater business environment needs through sentiment analysis in social media.
- item: Conference-Full-textRecognition of online learner emotions through facial expressions: online learner facilitatorChethana, BAS; Rukmal, KWJ; Rathnayake, HC; Randeni, RPKJ; Sandanayake, TCEmotions play an essential role in decision making, managing, perceiving, learning and influencing the thinking process of humans. Emotions are also important in teaching and learning and often find expression in particular ways, such as interactions with others, as well as interest and motivation in learning. However the influence of emotions on learning is still under-emphasized. Continuous and increasing exploration of the complex set of parameters surrounding online learning reveals the importance of the emotional states of learners and especially the relationship between learning and affective behavior. Automated learner facilitator is a system that has ability to capture the learners’ facial expression and comprehend that data. The system always detects a user’s facial expressions and recognized the changes in those facial expressions. The proposed actions were based on an experiment carried out among in the Sri Lankan university system regarding online learner behaviour during learning. The system focuses on investigate the current approaches in facial expression recognition and application them into the field of online learning to solve the problems related to learner facilitation. The results of the experiment have been used for new developments in e-learning courses and thereby the performance of e-learners is expected to be enhanced.
- item: Conference-Full-textPerception Transformation for Visually Impaired PeopleSamarasingha, SLLK; Sandaruwan, AMDM; Sandaruwan, AMDM; Senanayake, MDRN; Withanage, DK; Sudantha, BHBlindness is the form of absence of visual sensation due to physiological or neurological factors. With this lack of vision blind people have to face unexpected situations while travel or attend their day to day work. There are many guidance systems with a few superfluous features for visually impaired travelers to navigate quickly and safely against obstacles. Most of such systems support only one area of interest such as identifying objects and supporting navigation. The system proposed in this paper is capable of providing some essential guidance for a blind person to find the way in an in-house environment. The research focuses on exploiting the use of image processing and other sensors to provide a clear understanding of an environment with voice perception. The visual perception is captured by the camera attached to the blind person and provides preprocessed instances of these visual frames as descriptors to an artificial neural network. In addition to object recognition, sensor based hardware module is used to detect obstacles, and to provide information on other unexpected situations.
- item: Conference-Full-textNavigation System for Visually ImpairedSilva, WMAU; Kanakarathna, KMDTK; Priyankara, WAAN; Wijerathna, DMHGNN; Chaminda, HTObject recognition and navigation are highly challengeable for visually impaired even though the environment is familiar for him. There are different approaches for addressing this problem domain using technologies such as Global Positioning System (GPS) technology, Radio Frequency Identification (RFID) sensor technology etc. Although existing systems which use these different technologies for addressing this approach there are still limitations and issues due to usability and cost effectiveness of them to be addressed. The proposed system enables the blind person to directly interact with a mobile application and request the needed object as a voice command. Then it will process through image recognition and optimal path finding modules and identify the correct object and will guide the blind person to navigate to it. The system use Scale Invariant Feature Transformation (SIFT) algorithm for track each and every object in the assumed indoor environment. And then using cell based map identify the object location, user location and provide navigate information to the user for navigating to that object optimally. This solution has been evaluated using several experimental scenarios. Although the results are still not enough to provide strong conclusions, they indicate that the system is suitable for visually impaired people as object recognition and navigation system.
- item: Conference-Full-textMind Reading: A Survey and a Proof of Concept Platform for Perception AnalysisGunawardana, ASL; Pathirana, PS; Gamage, TST; Ponnamperuma, SR; Weerawarana, SMThis research paper discusses evolution of perception capturing and analytic mechanisms and presents a system for crowdsourced perception analysis. Crowdsourcing has become a buzzword in social computing which can be effectively applied for perception analysis. There are situations in recent past like Arab Spring in which crowdsourcing was heavily affected to increase the interest and motivation of the citizens through a huge crowdsourced news scoop. In mega sporting and entertainment events the members of the crowd can actively participate through handheld mobile devices to convey their perception. Crowdsourced perceptual data can be analyzed in many dimensions which creates diversified opportunities across several sectors. This paper discusses conventional survey mechanisms which have evolved towards real time emotion capturing systems with video processing and image processing. Also we present architecture and a prototype application for crowdsourced perception analysis.
- item: Conference-Full-textLexical Enrichment and Sense Disambiguation of Ontology ConceptsPremarathna, PHSR; Indrajee, KHH; Mahawithana, P; De Silva, LYSG; Wimalasuriya, DCThis paper presents a model to measure semantic similarity between custom ontology concepts and the taxonomy of WordNet and introduces a new ontology concept similarity measure. The similarity measure is based on a measure of weighted overlap of semantic cotopy of a concept in two taxonomies. The model can be applied to automatically enhance the vocabulary of terms in ontologies embedding equivalence classes of terms and other linguistic information directly in the ontology. This model is applied to the products and services domain where a Product Ontology is lexically enhanced and the effectiveness of the model is evaluated.
- item:Integrated Automobile Service PlatformDissanayaka, DMRCB; Silva, TLS; Rankothge, DGTS; Ratalakotuwa, RDGDJ; Madurasinghe, SY; Kulawansa, KADT; Fernando, SANowadays people have to face many difficulties when they are going to buy or get services for a vehicle and in storing all the information about vehicles in a one place and access whenever they want. Even companies which facilitate vehicle related services not be able to supply their services to their customers effectively and efficiently. Because of this reason people who are planning to buy a vehicle after some period, will not be able to make a better decision regarding the vehicle brands, models and prices that will be available at that time. Furthermore it is very valuable if potential customers get aware of newly released versions of vehicles which they are interested. However there is no better solution to achieve mentioned scenarios yet, so people have to search for details manually. Therefore “Autoslk: Integrated Automobile Service Platform” is a solution to overcome the issues faced by customers and companies in the automobile industry. Our approach is mainly user friendly and effective web based platform to interact with four separate users’ namely individual users, visitors, companies and administration to ensure their needs are satisfied.
- item: Conference-Full-textDecision Supportive System for Customers and Merchants with Enhanced RelevanceBandara, YMJK; Madhumalie, SHP; Madurasinghe, SY; Weerasinghe, MSC; Karunaratne, PMThe rising development of technologies caused consumers to deal with an increasingly large amount of product and service information which is far beyond the individual’s cognitive effort to process. However due to the popularity of ecommerce the number of online retailers proliferated. As a result of this, currently there are large numbers of brand names available online and this results in customer difficulty of finding the best product among alternatives. Since different customers have different perspectives and parameters about products it is better to facilitate customized information. Merchants have problems in improving their businesses due to lack of information about the customer buying pattern variations. Therefore, a system which provides accurate information and suggestions which significantly decrease users’ cognitive effort which would be beneficial for both customers and merchants when selecting and providing products and services. “Decision Supportive System for Customers and Merchants with Enhanced Relevance - EpsiShoppingBot” is a mobile and web based solution which addresses above mentioned requirements of both customers and merchants.
- item: Conference-Full-textContent based Hybrid SMS Spam Filtering SystemChaminda, T; Dayaratne, TT; Amarasinghe, HKN; Jayakody, JMRSWorld has changed. Everybody is connected. Almost each and everyone have a mobile phone. Millions of SMSs are going around the world over mobile networks in every second. But about 1/3 of them are spam. SMS spam has become a crucial problem with the increase of mobile penetration around the world. SMS spam filtering is a relatively new task which inherits many issues and solutions from email spam filtering. However it poses its own specific challenges. Server based approaches and Mobile application based approaches are accommodate content based and content less mechanism to do the SMS spam filtering. Though there are approaches, still there is a lack of a hybrid solution which can do general filtering at server level while user specific filtering can be done on mobile level. This paper presents a hybrid solution for SMS spam filtering where both feature phone users as well as smart phone users get benefited. Feature phone users can experience the general filter while smart phone users can configure and filter SMSs based on their own preferences rather than sticking in to a general filter. Server level solution consists of a neural network along with a Bayesian filter and device level filter consists of a Bayesian filter. We have evaluated the accuracy of neural network using spam huge dataset along with some randomly used personal SMSs.
- item: Conference-Full-textAn Empirical Study Of The Impact Of User Training And Attitude Towards ERP Implementation In Selected Companies In Sri LankaKumara, AS; Gunawardana, KD; Halwatura, RUImplementation of an Enterprise Resource Planning (ERP) is a radical change in an organization. Some of the staff are willing to accept new challenges whereas others are not. Therefore, there is a gap between attitudes of the staff who would involve with the ERP systems and desired objectives of the system. Conducting different types of user training programs can improve communication with employees. It makes them to change their attitudes. This study focused on user attitudes and the effectiveness of training towards the ERP implementation in Sri Lankan Companies. The data collection was done through a series of structured interviews and a questionnaire from the five top recently ERP implemented companies in Sri Lanka. One-way ANOVA result shows the users’ attitudes vary from different age groups and the education level of the employees. Further, findings reveal that attitudes have a positive impact depending on their income level and the number of years that they worked for the company. Based on the analysis it can be conclude that the way of training should change.
- item: Conference-Full-textAn Empirical Study of the Impact of User Training and Attitude Towards ERP Implementation in selected Companies in Sri LankaKumara, AS; Gunawardana, KD; Halwatura, RUImplementation of an Enterprise Resource Planning (ERP) is a radical change in an organization. Some of the staff are willing to accept new challenges whereas others are not. Therefore, there is a gap between attitudes of the staff who would involve with the ERP systems and desired objectives of the system. Conducting different types of user training programs can improve communication with employees. It makes them to change their attitudes. This study focused on user attitudes and the effectiveness of training towards the ERP implementation in Sri Lankan Companies. The data collection was done through a series of structured interviews and a questionnaire from the five top recently ERP implemented companies in Sri Lanka. One-way ANOVA result shows the users’ attitudes vary from different age groups and the education level of the employees. Further, findings reveal that attitudes have a positive impact depending on their income level and the number of years that they worked for the company. Based on the analysis it can be conclude that the way of training should change.
- item: Conference-Extended-AbstractVoice disorder recognizer to aid diagnosis of a speech pathologist(2014-01-17) Hettiarachchi, YK; Withanage, DKIn the field of medicine, currently a variety of methods are used to identify the pathologies in the human speech production system. The most common drawbacks of those methods are the discomfort for the patient caused during inspection, the dependency of the results on medical practitioner's experience and the high cost of diagnosis involved if advanced systems are used. This research discusses how to overcome those drawbacks by using an leT tool that can provide quantitative evidence of the vocal disorder of patients to medical practitioners to diagnose pathologies in deceased speech producing system of patients.
- item: Conference-Extended-AbstractSkin wound analysis system(2014-01-16) Ranasinghe, CD; lgalawithana, TC; Udayanga, SMR; Hettiarachchi, SY; Chaminda, HTIn modern medical science, there is a growing trend of applying Information Technology into manual routines. Automated skin wound analysis is a novel approach in treatment of skin wounds. The system is intended to analyze different types of skin wounds/lesions by using digital image processing techniques. Diabetic ulcers, skin-grafted burn wounds and nail lesions have been chosen for analysis. Nail lesions require an identification process whereas diabetic ulcers and skin-grafted burn wounds require an analysis of the healing process. A semantic web search is performed in order to verify the identification of nail lesions. The system also generates line graphs in order to facilitate the assessment of the healing process. A 3D model of the diabetic ulcer is created based on the data captured by an IR sensor-based mechanism. This wound analysis system is expected to help the doctor's diagnosis process immensely. The system provides quantitative and accurate results on wound healing. Moreover, it supports better comparisons and decision making.
- item: Conference-Extended-AbstractSentiment analysis for social media(2014-01-16) Jayasanka, RASC; Madhushani, MDT; Marcus, ER; Aberathne, IAAU; Premaratne, SCSentiment analysis, the automated extraction of expressions of positive or negative attitudes from text has received considerable attention from researchers during the past decade. In addition, the popularity of internet users has been growing fast parallel to emerging technologies; that actively use online review sites, social networks and personal blogs to express their opinions. They harbor positive and negative attitudes about people, organizations, places, events, and ideas. The tools provided by natural language processing and machine learning along with other approaches to work with large volumes of text, makes it possible to begin extracting sentiments from social media. In this paper we discuss some of the challenges in sentiment extraction, some of the approaches that have been taken to address these challenges and our approach that analyses sentiments from Twitter social media which gives the output beyond just the polarity but use those polarities in product profiling, trend analysis and forecasting. Promising results has shown that the approach can be further developed to cater business environment needs through sentiment analysis in social media.
- item: Conference-Extended-AbstractRecognition of online learner emotions through facial expressions: online learner facilitator(2014-01-16) Chethana, BAS; Rukmal, KWJ; Rathnayake, HC; Randeni, RPKJ; Sandanayake, TCEmotions play an essential role in decision making, managing, perceiving, learning and influencing the thinking process of humans. Emotions are also important in teaching and learning and often find expression in particular ways, such as interactions with others, as well as interest and motivation in learning. However the influence of emotions on learning is still under-emphasized. Continuous and increasing exploration of the complex set of parameters surrounding online learning reveals the importance of the emotional states of learners and especially the relationship between learning and affective behavior. Automated learner facilitator is a system that has ability to capture the learners' facial expression and comprehend that data. The system always detects a user's facial expressions and recognized the changes in those facial expressions. The proposed actions were based on an experiment carried out among in the Sri Lankan university system regarding online learner behaviour during learning. The system focuses on investigate the current approaches in facial expression recognition and application them into the field of online learning to solve the problems related to learner facilitation. The results of the experiment have been used for new developments in e-Iearning courses and thereby the performance of e-learners is expected to be enhanced.
- item: Conference-Extended-AbstractPerception transformation for visually impaired people(2014-01-16) Purnima, DMH; Samarasingha, SLLK; Sandaruwan, AMDM; Senanayake, MDRN; Withanage, DK; Sudantha, BHBlindness is the form of absence of visual sensation due to physiological or neurological factors. With this lack of vision blind people have to face unexpected situations while travel or attend their day to day work. There are many guidance systems with a few superfluous features for visually impaired travelers to navigate quickly and safely against obstacles. Most of such systems support only one area of interest such as identifying objects and supporting navigation. The system proposed in this paper is capable of providing some essential guidance for a blind person to find the way in an in-house environment. The research focuses on exploiting the use of image processing and other sensors to provide a clear understanding of an environment with voice perception. The visual perception is captured by the camera attached to the blind person and provides preprocessed instances of these visual frames as descriptors to an artificial neural network. In addition to object recognition, sensor based hardware module is used to detect obstacles, and to provide information on other unexpected situations.
- item: Conference-Extended-AbstractAn empirical study of the impact of user training and attitude towards ERP implementation in selected companies in Sri Lanka(2014-01-16) Kumara, AS; Gunawardana, KD; Halwatura, RUImplementation of an Enterprise Resource Planning (ERP) is a radical change in an organization. Some of the staff are willing to accept new challenges whereas others are not. Therefore, there is a gap between attitudes of the staff who would involve with the ERP systems and desired objectives of the system. Conducting different types of user training programs can improve communication with employees. It makes them to change their attitudes. This study focused on user attitudes and the effectiveness of training towards the ERP implementation in Sri Lankan Companies. The data collection was done through a series of structured interviews and a questionnaire from the five top recently ERP implemented companies in Sri Lanka. One-way ANOV A result shows the users' attitudes vary from different age groups and the education level of the employees. Further, findings reveal that attitudes have a positive impact depending on their income level and the number of years that they worked for the company. Based on the analysis it can be conclude that the way of training should change.
- item: Conference-Extended-AbstractNavigation system for visually impaired(2014-01-16) Silva, WMAU; Kanakarathna, KMDTK; Priyankara, AAN; Wijerathna, DMHGNN; Charninda, HTObject recognition and navigation are highly challengeable for visually impaired even though the environment is familiar for him. There are different approaches for addressing this problem domain using technologies such as Global Positioning System (GPS) technology, Radio Frequency Identification (RFID) sensor technology etc. Although existing systems which use these different technologies for addressing this approach there are still limitations and issues due to usability and cost effectiveness of them to be addressed. The proposed system enables the blind person to directly interact with a mobile application and request the needed object as a voice command. Then it will process through image recognition and optimal path finding modules and identify the correct object and will guide the blind person to navigate to it. The system use Scale Invariant Feature Transformation (SIFT) algorithm for track each and every object in the assumed indoor environment. And then using cell based map identify the object location, user location and provide navigate information to the user for navigating to that object optimally. This solution has been evaluated using several experimental scenarios. Although the results are stilI not enough to provide strong conclusions, they indicate that the system is suitable for visually impaired people as object recognition and navigation system.