Research Publications Authored by SLIIT Staff
Permanent URI for this communityhttps://rda.sliit.lk/handle/123456789/4195
This collection includes all SLIIT staff publications presented at external conferences and published in external journals. The materials are organized by faculty to facilitate easy retrieval.
Browse
13 results
Filters
Advanced Search
Filter by
Settings
Search Results
Publication Embargo An Analysis on Different Distance Measures in KNN with PCA for Android Malware Detection(IEEE, 2022-11-30) Dissanayake, S; Gunathunga, S; Jayanetti, D; Perera, K; Liyanapathirana, C; Rupasinghe, LAs Majority of the market is presently occupied by Android consumers, Android operating system is a prominent target for intruders. This research shows a dynamic Android malware detection approach that classifies dangerous and trustworthy applications using system call monitoring. While the applications were in the execution phase, dynamic system call analysis was conducted on legitimate and malicious applications. Majority of relevant machine learning-based studies on detecting android malware frequently employ baseline classifier settings and concentrate on selecting either the best attributes or classifier. This study examines the performance of K Nearest Neighbor (KNN), factoring its many hyper-parameters with a focus on various distance metrics and this paper shows performance of KNN before and after performing Principal Component Analysis (PCA). The findings demonstrate that the classification performance may be significantly improved by using the adequate distance metric. KNN algorithm shows decent accuracy and improvement of efficiency such as decreasing the training time After PCA.Publication Embargo Non-Verbal Bio-Markers for Automatic Depression Analysis(IEEE, 2021-12-02) Yashodhika, G. B. O; De Silva, L. S. R.; Chathuranaga, W. W. P K; Yasasmi, D. L. R; Samarasinghe, P; Pandithakoralage, S; Piyawardana, VDetection of early depression risk is essential to help the affected individual to get timely medical treatment. However, automatic Depression Risk Analysis has not received significant focus in prior studies. This paper aims to propose an Automatic Depression Risk Analyzer based on non-verbal biomarkers; facial and emotional features, head posture, linguistic, mobile utilization, and biometrics. The analysis has shown that facial and emotional features can learn to identify depression risk better when compared with the head pose and emotional features. Moreover, the study shows that Depression Risk Analysis based on linguistic performed well with 95% accuracy for Sinhala content and 96% accuracy for contextual in English. Identifying the depression risk based on the biometrics, the sleep pattern analysis obtained 95% accuracy with the K Nearest Neighbour (KNN). Further, the mobile utilization analysis with the KNN model achieved 81% accuracy towards the Depression Risk Analysis. The accuracy of Depression Risk Analysis can be improved by extending analytic models to work as a single model. Furthermore, The models have been integrated with a mobile application that allows users to get a comprehensive Depression Risk Analysis based on each biomarker. These additional methods will function together to provide a more accurate on assessing depression risk.Publication Embargo Analysis of the ‘Toll Free Agricultural Advisory Service’ Data as Decision Support Tool for the Department of Agriculture(IEEE, 2022-07-18) Rajapaksha, N; Dias, NThe Department of Agriculture’s Toll-Free Agricultural Advisory Service was formed with the 1920 short code and is connected to all land and mobile telephone service providers in Sri Lanka. This short code allowed farmers and other stakeholders to contact technical officers which Agriculture Instructors immediately. All the information was gathered into the 1920 call center database. Farmers all over the island bring their agricultural problems to the 1920 Agricultural Advisory Service. Nevertheless, it can be seen that they do not do any analysis of these problems. This big data if properly examined has the potential to assist the country on a massive scale in the future. This study for carrying out to explore the possibility of introducing decision support for the 1920 reporting system to generate enhanced analytics and to make it easier to make informed decisions by the top management of the Department of Agriculture, more efficiently and effectively than the reporting method previously.Publication Embargo Skeleton Based Periodicity Analysis of Repetitive Actions(IEEE, 2022-04-07) Wedasingha, N; Samarasinghe, P; Seneviratne, L; Puiatti, A; Papandrea, M; Dhanayaka, DThis paper investigates the problem of detecting and recognizing repetitive actions performed by a human. Repetitive action analysis play a major role in detecting many behavioral disorders. In this work, we present a robust framework for detecting and recognizing repetitive actions performed by a human subject based on periodic and aperiodic action analysis. Our framework uses focal joints in the human skeleton for the analysis of repetitive actions which are substantiated by the principles of human anatomy and physiology. Using Non-deterministic Finite Automata (NFA) techniques, in this paper, we introduce a novel model to transform repetitive action count to differentiate the periodicity in human action. Experimental results on a dataset consisting of 371 video clips show that our algorithm outperforms the state-of-art (RepNet) [1] in simultaneous multiple repetitive action counts. Further, while the proposed model and RepNet give comparable results in counting periodic repetitive actions, our model performance surpass RepNet significantly on analysing non-periodic repetitive behavior.Publication Embargo Analysis of Searching Algorithms in Solving Modern Engineering Problems(IEEE, 2021-08-11) Rathnayake, B. R. M. S. R. B.; Marzuk, H; Senadheera, R. I. A; Vijeyakumar, S; Abeygunawardhana, P. K. WMany current engineering problems have been solved using artificial intelligence search algorithms. To conduct this research, we selected certain key algorithms that have served as the foundation for many other algorithms present today. This article exhibits and discusses the practical applications of A*, Breadth-First Search, Greedy, and Depth-First Search algorithms. We looked at several recent research publications on these algorithms (for example, maze solver robots, the eight-puzzle problem, medication prediction, and travel advice) and critically examined their benefits, drawbacks, and challenges. We’ve also done some experimentation with a Python application to see how well these algorithms perform.Publication Embargo Singlish Sentiment Analysis Based Rating For Public Transportation(IEEE, 2021-01-27) Sharounthan, B; Nawinna, D. P; De Silva, RAs the primary transportation mode in Sri Lanka, Public transportation is tightly attached with the daily life of the people. The important factor in transportation is providing a door to door mobility. This paper presents a study focused on measuring the service quality of public transportation based on the comments and feedbacks provided by the passengers with the aim of producing a better service for users. Comments were gained from social media and were used to produce a comprehensive rating mechanism to rate the transportation service providers. This tool was developed using natural language processing techniques using the data from the Sri Lankan context. With the popularity of Social Media in Sri Lanka, many people use Singlish (Sinhala written using English scripts) for online communication. The rating engine presented in this paper is capable of performing Sentiment analysis on comments given in Singlish Language in the Transportation domain.Publication Embargo Analysis on the Risk and the Categorization on Test Automation in Sri Lankan Software Industry(IEEE, 2021-12-09) Sundaralingam, S; Rajapaksha, S. KDelivering quality software to customer is the key objective of software industry. One of the essential fragment of life cycle of software is software testing. In software testing test automation is playing a major role. If test automation cannot be practiced in proper way the delivery of the software quality would impact directly and leads to loss of customer, which is a failure of business. Test automation has several problems which needs to address in each stage. Test automation cause several issues when execute test automation in a company. All these issues need to be handled by different people, therefore initially issues need to be identified and classified and then solve properly. This research is to identify the improvements to categorize the problems automatically and find the solution for the problem in test automation process and hence to practice the test automation in healthier way in order to achieve better software quality. Test automation issue are analyzed and the solutions are proposed. On which stage, the test automation is causing problems and how to solve them are recommend in this research, Test automation issues are categorized and under relevant category therefore issues can be solved speedily. The issues are passed as sentence and they are categorized under the relevant category to fix them quickly. The sentences are preprocessed and conducted feature selection using filter methods and predict under appropriate category. The issue has been cleaned in preprocess stage. Implemented LSTM base algorithm using filter method to categorize the issues. In this research an implementation to categorize test automation problems are formed. Recommendation and solutions are proposed on test automation which would aid to practice test automation in better way and that would leads to better software quality delivery.Publication Embargo Analysis and performance of CMA blind deconvolution for image restoration(Wiley Online Library, 2015-09) Samarasinghe, P; Kennedy, R. AIn this paper we study the applicability of classical blind deconvolution methods such as constant modulus algorithm (CMA) for blind adaptive image restoration. The requirements such as the source to be white, uniformly distributed and zero mean, which yield satisfactory convergence in the data communication application context, are revisited in the image restoration context, where a linear deblur kernel needs to be blindly adapted to compensate for an unknown image blur kernel with the objective to recover a source ground truth image. Through analysis and performance studies, we show that the performance of CMA is adversely affected by the intrinsic spatial correlation of natural images and by any deviation of their distribution from being platykurtic. We also show that decorrelation techniques designed to overcome spatial correlation cannot be effectively applied to rectify CMA performance for blind adaptive image restorationPublication Embargo Analysis and enhancements of a cognitive based complexity measure(IEEE, 2017-06-25) De Silva, D. I; Kodagoda, N; Kodituwakku, S. R; Pinidiyaarachchi, A. JAs stated by Tom DeMacro, something that cannot be measured is uncontrollable. Thus, a number of metrics have been developed to measure the complexity associated with software by considering various aspects such as size, control flow and data flow between modules, cognitive informatics etc. Amongst these aspects, cognitive informatics is recognized as a promising aspect in measuring software complexity. Thus, majority of the complexity metrics that were proposed after the introduction of cognitive informatics have been proposed mainly based on the cognitive aspect. Amongst them, Chhillar and Bhasins' weighted composite complexity measure is one of the few metrics that had attempted to measure the complexity of a program by considering more than three or more complexity factors. After a thorough analysis, in a previous study, the authors identified that the weighted composite complexity measure could be further improved by considering more complexity factors. This paper extends the previous study to identify the most appropriate factors that could be considered by the weighted composite complexity measure. Using the opinions of the industry experts, the authors were able to discover that compound conditional statements, threads and recursion could also be considered by the weighted composite complexity measure. Accordingly, the weighted composite complexity measure was enhanced to capture the complexities that arise due to those factors. The paper also includes a demonstration of the complexity calculation method of the improved weighted composite complexity measure with the use of three sample java programs, which were written by incorporating the above mentioned factors. In addition, an application of the weighted composite complexity measure to the same programs are also given in the paper, to illustrate the changes in complexity values of the two measures.Publication Embargo Analysis of the Dimensional Change of Woven Fabrics from Loom State to Finished State(IEEE, 2018-05-30) Kandemulla, K. A. S. M; Maduwantha, A. R. L; Fernando, E. A. S. K; Niles, S. N; Jayawardena, T. S. SDimensional change of a woven fabric is a challenge in woven fabric production. The phenomenon originates from the dimensional instability of the fabric. Shrinkage is a combined result of numerous factors such as relaxation, dyeing, finishing and the effect of machinery. The significance of this problem has been investigated by several researchers, who focused mainly on the geometry of the fabric during the weaving phase (loom stage) only. To investigate the dimensional changes that occur within a particular woven structure, a number of fabric samples were sent through various finishing processes such as, washing, dyeing & finishing, under the laboratory conditions. The changes were measured either in terms of dimensional change or EPI and PPI values. Using the experimental data and theoretical analysis, a mathematical model has been developed and validated. However initially the focus is laid on plain woven fabrics and it is expected to be further extended to the other woven structures as well.