Science
Permanent URI for this communityhttp://repository.kln.ac.lk/handle/123456789/1
Browse
4 results
Search Results
Item Detecting plagiarism in multiple Sinhala documents(International Research Conference on Smart Computing and Systems Engineering - SCSE 2018, 2018) Ganepola, G.A.U.E.; Wijayasiriwardhane, T.K.Availability of unlimited information resources over the Internet and the advancement of the Internet search engines such as Google to locate those resources much easily have contributed to an increase of plagiarism. Though there are a number of software tools available for detecting plagiarism in multiple English documents, no such a tool is yet available for the Sinhala language. This paper presents a novel language dependent approach to detect plagiarism in multiple Sinhala documents. It uses stemming, stop word removal and synonym replacement for text preprocessing and term frequency-inverse document frequency (tf-idf) and cosine similarity for similarity comparison. A prototype software tool was developed and interlinked with an operational Sinhala WordNet to demonstrate the viability of the proposed approach. The prototype tool was validated against a sample of Sinhala assignments from secondary school students. The assignments were also examined by an expert to determine whether they had actually been plagiarized. When compared the results of the prototype tool against those of the expert judgment, we found that our proposed approach for plagiarism detection in multiple Sinhala documents performs with an accuracy of over 80%.Item A haptic feeding GPS navigation solution for visually impaired people(International Research Conference on Smart Computing and Systems Engineering - SCSE 2018, 2018) Rajatheja, M.K.B.C.; Wijayasiriwardhane, T.K.According to the World Health Organization (WHO), it is estimated that 285 million people are visually impaired worldwide and out of which 39 million of people are blind. Further, about 90 percent of the visually impaired people in the world live in low-income settings. Among many difficulties that they encounter in their day-to-day activities, the visually impaired people are often disadvantaged particularly when travelling due their inability to see the obstacles and visual signs of directions that are essential to navigate not only through the unfamiliar terrains but also in the familiar environments. Therefore, the visually impaired people usually use a white cane to detect obstacles on their path whilst get the assistance of the trained guide dogs for navigation. However, when they roam in an unfamiliar environment, they always have to rely on a third party for finding their directions. In this paper, we presents a novel Global Positioning System (GPS) and Google Map Direction Application Programming Interface (API) based navigation solution for the visually impaired people with a simple haptic direction feeding interface as an alternative to the sonification systems available. Our objective of this research is to develop an economically viable haptic feeding GPS navigation system for the visually impaired people in order to help them with their day-to-day activities such as reaching for public services, socializing with people and exploring the world more confidently than ever before.Item WatchDog: An Advanced Surveillance System(Faculty of Science, University of Kelaniya, Sri Lanka, 2016) Ganepola, G.A.U.E.; Wijayasiriwardhane, T.K.Surveillance systems have become an integral part of the business world today due to the intensive care given to ensure the security of properties with a considerable monetary value. As a result, Closed-Circuit Television (CCTV) cameras are widely used in organizations. However, these systems have added an additional complexity to the user’s day-to-day work due to considerations like footage review and storage. The most common solution to this problem is incorporation of intelligence and automation to these systems. Typically, image processing and machine learning concepts are employed to implement such surveillance systems. However, the currently available advanced surveillance systems are not affordable for small and medium enterprises. The most widely used freely available advanced surveillance systems only detect motion. On the other hand, the systems that can identify the presence of people and even recognize them cost a considerable amount that does not fit into the budget of most, small scale businesses. Further, the most of the available free surveillance systems have not been designed in a way to achieve both storage efficiency and giving feedback on footages. In fact, most of them do record the footage 24x7. To address all those issues, in this paper, we present “WatchDog”, an advanced surveillance system that is implemented as a 100% free and open source product with features like detection of human presence, storage efficiency mode where the footage is stored only when there is a human in the frame, feedback and reporting facilities and recognizing people in the footage. The system detects people, and only those frames are recorded in high quality while rest of the video is saved in low quality to achieve storage efficiency. Using facial feature recognition, the system can predict factors such as gender and age of people in the footage. At the end of each day, the system produces a report with detailed information. This report would be a great relief from the user’s point of view since it drastically reduces the time to review the footages when required. Viola Jones algorithm, Haar features, Integral image, Adaboost and Cascading concepts are used for Human detections and facial feature recognition in this system. Our aim of this research is to answer the 3 major problems in surveillance systems such as affordability, storage efficiency and intelligence all at once.Item An algorithm for plagiarism detection in Sinhala language(Faculty of Science, University of Kelaniya, Sri Lanka, 2016) Basnayake, S.F.; Wijekoon, H.; Wijayasiriwardhane, T.K.According to the Merriam-Webster dictionary, the simple definition of the verb plagiarize is, “to use the words or ideas of another person as if they were your own words or ideas”. Many software tools to aid in detecting plagiarism is available for English language, but equivalent tools are not yet available specifically for Sinhala language. Though language independent tools that work on many languages are available, they generally give poor results as they do not consider language specific features. There are some detection methods proposed for Asian languages like Hindi, Malayalam, Arabic and Persian which have some close relationship and similar properties of Sinhala language. All of those methods use language specific rules and they even outperform the commercially available tools. These findings are evidence that the language specific plagiarism detection is more effective than the language independent plagiarism detection as some paraphrasing techniques can be used to mislead the language independent systems.Sinhala language is constitutionally recognized as the official language of Sri Lanka, along with Tamil. Due to the complexity of the language structure and rules of grammar, the language independent tools seem to provide poor results when used for plagiarism detection in Sinhala documents. In this research, we propose a novel plagiarism detection algorithm built around content based methods specific to Sinhala language. The methodology of this study follows both experimental and build approaches. The proposed plagiarism detection system has two modules namely, text pre-processing module and the similarity detection module. The text pre-processing module pre-process the text files to standardize the text sources using techniques such as stop word removal, number replacement, lemmatization, synonym recognition and creating n-grams. Then the similarity detection module analyses the pre-processed text using Jaccard coefficient and cosine similarity coefficient to measure the similarity between two documents. A prototype of Sinhala language plagiarism detection system will be implemented using the proposed method and several combinations of the above techniques will be used to discover the best combination. Testing and statistical performance evaluation will be carried out using a sample of source text files and plagiarized text files in Sinhala language by taking expert judgements also into the consideration. The final outcome of this research study is to develop an effective software application for plagiarism detection in Sinhala language documents.