http://dlib.iit.ac.lk/xmlui/handle/123456789/66 2026-04-06T22:09:28Z http://dlib.iit.ac.lk/xmlui/handle/123456789/82 Question answering through unsupervised knowledge acquisition Perera, Rivindu; Perera, M. S. U. Current question answering systems are usually based on a knowledge base which is populated with domain specific knowledge and managed through Unstructured Information Management Architecture (UIMA). But drawback in this approach is that knowledgebase may be grown with knowledge which is not relevant to the users connected with the system. In order to address this drawback we propose unsupervised knowledge accumulation algorithm which can monitor user preferences and acquire knowledge without any supervision of the system management unit. Basically, this algorithm learns domain of interest of each and every user connected with the system and extract knowledge from the web or from a given corpus. We have also adopted several Natural Language Processing algorithms to design this high-level algorithm. Knowledge modelling is done through a conceptual graph based knowledge base. This novel paradigm is evaluated with the help of several connected users and with more than 280 questions. We have achieved excellent accuracy during the evaluation phase. It shows our novel approach is effective and can be used to address the drawback decently. 2012-01-01T00:00:00Z http://dlib.iit.ac.lk/xmlui/handle/123456789/81 Intelligent emotion recognition system using electroencephalography and active shape models Wijeratne, Upani; Perera, M. S. U. Human emotion recognition has become one of the key steps towards advanced human-machine interactions. Brain waves or Electroencephalography (EEG) is one of the frequently used bio signals in emotion detection as it is found that the signal measured from the central nervous system has a relationship between physiological changes and emotions. Using facial expressions is another mode that could be used for emotion recognition using external physiological signals. This project investigates the possibility of identifying emotions using brain signals and facial expressions. EEG feature extraction is done, using Relative Wavelet Energy calculation and Discrete Wavelet Transform methods for feature extraction, and Artificial Neural Network for emotion classification. For facial feature extraction Active Shape Model is used while the facial emotion classification is done using a Support Vector Machine. The solution could be used to study about the behaviour of EEG signals as well as facial expressions in different mental states. 2012-01-01T00:00:00Z http://dlib.iit.ac.lk/xmlui/handle/123456789/80 Brain hemorrhage diagnosis using artificial neural networks Balasooriya, Ushani; Perera, M. S. U. Intelligent B Brain hemorrhage is a type of stroke which is caused by an artery in the brain bursting and causing bleeding in the surrounded tissues. Diagnosing brain hemorrhage, which is mainly through the examination of a CT scan enables the accurate prediction of disease and the extraction of reliable and robust measurement for patients in order to describe the morphological changes in the brain as the recovery progresses. Though a lot of research on medical image processing has been done, still there is opportunity for further research in the area of brain hemorrhage diagnosis due to the low accuracy level in the current methods and algorithms, coding complexity of the developed approaches, impracticability in the real environment, and lack of other enhancements which may make the system more interactive and useful. Additionally many of the existing approaches address the diagnosis of a limited no of brain hemorrhage types. This project investigates the possibility of diagnosing brain hemorrhage using an image segmentation of CT scan images using watershed method and feeding of the appropriate inputs extracted from the brain CT image to an artificial neural network for classification. The output generated as the type of brain hemorrhages, can be used to verify expert diagnosis and also as a learning tool for trainee radiologists to minimize errors in current methods. The prototype developed using Matlab can help medical students to practice the related concepts they learn using an image guide with examples for surgeries and surgical simulation. System was evaluated by the domain experts, like radiologists, intended users such as medical students as well as by technical experts. The prototype developed was successful since it was being evaluated as credible, innovative and useful software for the students in the field of radiology while 100% of the evaluators mentioned the diagnosis accuracy is acceptablerain Hemorrhage Diagnosis 2012-01-01T00:00:00Z http://dlib.iit.ac.lk/xmlui/handle/123456789/74 IPedagogy: Question answering system based on web information clustering Perera, Rivindu As with the excessive information growth in the web, retrieving the exact segment of information even for a simple query, has transformed to a difficult and resource expensive state. Specially, in e-learning domain it is vital to search knowledge frequently and focusing on a limited well defined search space. IPedagogy is a question answering system which works with natural language powered queries and retrieve answers from selected information clusters by reducing the search space of information retrieval. In addition, IPedagogy is empowered by several natural language processing techniques which direct the system to extract the exact answer for a given query. System is evaluated with the use of mean reciprocal rank and it is noted that system has 0.73 of average accuracy level for 10 sets of questions where each set is consisted of 35 questions. 2012-01-01T00:00:00Z