https://dl.ucsc.cmb.ac.lk/jspui/handle/123456789/4303 2026-04-28T08:13:32Z 2026-04-28T08:13:32Z SILVA, S. M. https://dl.ucsc.cmb.ac.lk/jspui/handle/123456789/4543 2021-08-12T08:17:59Z 2021-08-12T00:00:00Z

Title: REST Service Discovery Based on Ontology Model Authors: SILVA, S. M. Abstract: RESTful web services are the new drift that is used for most of the present technical solutions when creating stateless web services. At present world moves towards RESTful web services, the number of available web services is rapidly increasing thereby service discovery can be a challenging task. The present service discovery approaches have deficiencies in semantics, lack of inefficiency, and lower precision rates. The web service usage can be categorized as ‘Provider Developers’ and ‘Consumer Developers’. Provider Developers develop APIs and publish along with Open API specification. Published web services are consumed by Consumer Developers. Consumer Developers integrate thirdparty web services in their solutions yet face difficulties in finding the best suitable service for their needs. Most traditional service discovery approaches depend on semantic specifications like OWL-S. OWL-S is the universal ontology specification to represent RESTful service semantics. This specification was initially created for WSDL and up to the present, there are only a few conversions available for RESTful service to OWL-S. To convert a REST service to a semantic specification, the syntactic of the RESTful service needs to be available. The objective of this Research Study is to propose a solution to reducing the present gap between syntactic and semantics of RESTful service. At present most RESTful service developers incorporate Open API specification formerly known as Swagger to provide syntactically. The main use of the Open API Specification document provides guided documentation for consumers on how to invoke web service. In this document, synthetics are hidden, which can be extremely useful for service discovery, but mostly not used at present. The proposed study aims towards the use of Open API specification to extract syntactic and map syntactic to OWL-S semantic specification. The approach further proposes to provide a keyword-based search engine that can be used to search web services based on IOPE conditions by leveraging the generated semantic specification. As proof of concept for this proposed approach, Lufthansa Swagger API was used to generate semantic specification and service grounding. The search engine was developed to query by keyword and Input/ Output condition based.

2021-08-12T00:00:00Z Senanayaka, G. H. M. C. https://dl.ucsc.cmb.ac.lk/jspui/handle/123456789/4542 2021-08-12T06:08:06Z 2021-08-12T00:00:00Z

Title: Methodology to Authorize Bank Cheque Automatically Authors: Senanayaka, G. H. M. C. Abstract: This study shows the automation of a simple cheque captured by a camera or a scanner. The bank cheque is a declining bank instrument. The cheque is still one of the payment methods in Sri Lanka. It is mostly used by the corporate community. While I am studying the research, I have contacted several people to inquire about cheques and its realization process. Unfortunately, most of them are not sentient of the check realization process or details printed on the cheque. In-order to possess cheque issuing facility, a person should have a cheque account where the bank is offering a cheque book. There are several areas in a cheque for its realization process. Those areas are date, pay, bearer, amounts in words and amounts in figures, signature, and magnetic ink area. Each of these areas plays a salient role in cheque realization process. In the date area, cheque issued date is mentioned. Generally a cheque is valid for 6 months of period. Therefore if a cheque issued date is more than 6 months, it is considered as an expired cheque. Amounts in words and amounts in figures should match with each other, otherwise it is an invalid cheque. Also, the issuer signature should be there on the cheque signature area. The signature should validate with the signature stored in the bank’s database. If there is a miss-match, the cheque is consider as an invalid cheque. Bank systems can identify unique chque number, branch of the cheque account, cheque account number by using magnetic ink are details. From the pay area, bank officer can identify the payee details (Cash cheque). Currently, above-mentioned processes have been done manually by bank officers [23]. According to the cheque clearance type, it can change the time taken to clear the cheque. There are three cheque clearance types. Inward cheques, outward cheques and transfers. Inward cheques are cheques a bank received from a 3rd party cheque clearance organization. Transfers are a bank received its cheques by customers. Outward cheques are cheques that a bank received other bank cheques from its customers. Inward cheques and transfers are done by the bank while transferring outward cheques to a 3rd party clearance organization. In this study, when identifying the areas, first the cheque area will be identified and extracted from the given input image; then, the system will remove noise and resize the image for a defined size and crop key areas to process the optical character recognition and comparison. For noise removal, it is using Gaussian filter while the Tesseract Optical Character Recognition Engine is used to read English characters in the cheque. Also, it is using Scale Invariant Feature Transform algorithm to identify signature on the cheque. By applying optical character recognition and comparison techniques, the realization process is automated. The accuracy of the system for printed character identification is 90%, handwritten character identification is 60%. Signature identification accuracy by using image comparison techniques is 70%.

2021-08-12T00:00:00Z Semini, K. A. H. https://dl.ucsc.cmb.ac.lk/jspui/handle/123456789/4541 2021-08-12T06:01:13Z 2021-08-12T00:00:00Z

Title: Determine the domestic hematology reference range for healthy adults in Sri Lanka Authors: Semini, K. A. H. Abstract: Hematology science is a subsection in medical science. It is one of the very useful things to measure the healthiness of a person. There is a standard hematology referential range for each hematology attribute. This standard hematology referential range is built many years ago by considering the Gaussian population. All countries use this standard referential range to measure the healthiness of the people. But lately some countries identify that the referential ranges can be changed according to various reasons and using the standard referential range to measure healthiness is not accurate. Therefore, many countries started researches to find a local hematology referential range for their own countries and successfully established them. Through these researches they able to found other hidden patterns related to hematology. Sri Lanka is not a Gaussian country. Hence, using the same standard hematology referential range maybe not accurate for our country. Therefore, finding a local referential range for the White Blood Cell count is the goal of this research. The compatibility of the standard hematology referential range of white Blood Cell count with Sri Lanka was checked through this research. The dataset used for the research contained 600 records related to the full blood count reports. Next, the dataset was separated as a training dataset and testing dataset. The dataset was analyzed using the WEKA data mining tool. Machine learning algorithms are used to build the model by using the training dataset. Several models are built by using classification algorithms and one model was selected by considering its accuracy. The selected model was evaluated by using the testing dataset. The local referential range for White Blood Cell count is found by using the evaluation. There is a difference between the standard White blood cell referential range and the local white blood cell referential range. Therefore, Applying the standard white blood cell referential range for Sri Lankans may be not accurate.

2021-08-12T00:00:00Z SALLAY, N.S. https://dl.ucsc.cmb.ac.lk/jspui/handle/123456789/4540 2021-08-12T05:54:48Z 2021-08-12T00:00:00Z

Title: User Emotion based Deepmoji Desktop Partner Authors: SALLAY, N.S. Abstract: The user emotion based deepmoji desktop partner is developed to address the emotional awareness of virtual assistants. Developing a response generation model which gives responses according to the emotions of the text is the solution proposed. Despite of being a computer application, people do not accept “google assistant” or “siri” as a friend because they lack in emotional intelligence and empathetic interactions in conversations. Emotional intelligence of computers has gained a notable attention of researchers because of its extensive application esteem and high potential in developing a tremendous market value. Sentiments are intrinsic value of human beings and humans have the ability of identifying others sentiments adopt the conversations, according to the emotions of the interacting parties. The proposed system develop a model which identifies emotion of the user by using the input text and generate response according to the emotion captured. People identify emotions by facial expressions, gestures and intensity of voice tone etc. The proposed solution is focused to develop OS independent AI desktop partner to interact with users based on their emotions, captured through facial expressions and texts. According to the review on past attempts on achieving emotional intelligence, technologies and different processes on achieving emotional awareness , Facial Expression Recognition and Sentiment Analysis techniques were used for the development and Deepmoji is used to train the AI model to classify the sentiments behind the phases. Accuracy of the emotions directly effect the empathetic characteristic of the conversation. Therefore capturing the correct emotion is a crucial task. The system implementation has two main modules, emoji module which is the user interface of the desktop partner and the chat module. Group of IT professionals and non-IT professionals were selected to evaluate the application and results of a validated questionnaire containing questions based on performance, emoji accuracy, appropriateness with the comparison of other existing virtual assistants were evaluated. Questionnaire was evaluated using Cronbach’s Alpha test resulting Cronbach’s Alpha at 0.75 which is a higher positive level. The result of the evaluation indicates that the proposed concept is a proper software solution for the problem of emotionally aware virtual assistants.This dissertation includes the methodology, design, implementation and the evaluation of the implemented system prototype.

2021-08-12T00:00:00Z