Smart Computing and Systems Engineering (SCSE)

Permanent URI for this communityhttp://repository.kln.ac.lk/handle/123456789/18936

Browse

Now showing 1 - 20 of 278

Adding Commonsense to Robotic Application Using Ontology-Based Model Retraining
(Department of Industrial Management, Faculty of Science, University of Kelaniya Sri Lanka, 2022) Pradeepani, M. K. T.; Jayawardena, C.; Rajapaksha, U. U. S.
In terms of the level of technological capability in the world today, the use of automated robotics is common in various fields. There are large projects going on in many industries that collaborate between robots and other robots, as well as humans and robots. In hospital environments, care for people with medical needs and their needs and used to make appropriate suggestions to their problems. Robots can also be found in certain areas that can respond quickly as an emergency rescue agent. Furthermore, robots, which can be seen in the hotel industry as waiters and as farm assistants in agriculture, have a great tendency to be used as multi-tasking agents in many fields. In each of these areas, robots must co-operate with humans. In that situation, the importance of the exchange of mutual knowledge between robots-robots and between humans-robots comes into the picture. What matters here is not only the quantitative vastness of knowledge but also the ability to understand each other in the same medium. Although the common sense that people need in their day-to-day work is completely obvious to humans, the commonsense knowledge domain needs to be implanted in robots. Whatever concept is defined for adding commonsense to robotics, it should be a consistent concept that can be logically constructed so that it can be understood by a machine. As will be discussed later in the paper, different methods have been used in various related works to add a different kind of domain knowledge to robotics. The objective of this paper is to provide an improved retrained model for robotics in order to give them the ability to act more human-like when performing tasks. By using the proposed model robots are able to answer the incomplete command or inquiries related to a given context. One of the objectives of this work is to use the ontology-based, commonsense-support existing knowledge base as a mechanism to retrain and build a new model.
Adoptability of Chaos Engineering with DevOps to Stimulate the Software Delivery Performance
(Department of Industrial Management, Faculty of Science, University of Kelaniya Sri Lanka, 2023) Arsecularatne, Merishani; Wickramarachchi, Ruwan
The efficiency of the business processes has a major impact on improving the productivity of organisations. Many organisations use IT-related tools, primarily software, to enhance the efficiency of their business processes. Therefore, timely and reliable delivery of software products has become a top priority. As a result, advancing the concept of “Agility”, organisations implement DevOps practices. However, maintaining the quality of the software delivery service has become an issue due to several challenges related to the implementation of DevOps. Hence, this study was conducted with the aim of understanding the DevOps-related challenges and how “chaos engineering” can be applied along with DevOps to address those challenges. The practice of "chaos engineering" contributes to the reduction of chaos. A systematic literature review was conducted to investigate the concept of “chaos engineering” and the challenges that DevOps-implemented organisations face. Later, a qualitative study was conducted to see how chaos engineering practices can be used to address the identified DevOps challenges. Based on the thoughts and views of the industry experts who participated in this study, it was revealed that implementing chaos engineering with DevOps helps organisations address most of the DevOps challenges both directly and indirectly. Also, the study suggests a methodology to implement chaos engineering with DevOps within organisations to successfully overcome DevOps-related challenges.
Affective gaming in real-time emotion detection and music emotion recognition: Implementation approach with electroencephalogram
(Department of Industrial Management, Faculty of Science, University of Kelaniya, Sri Lanka, 2020) Kalansooriya, Pradeep; Ganepola, G.A.D. ,; Thalagala, T.S.
Affective Gaming can be considered as the concept of detecting the real-time emotional state of a player during various stages in gameplay and then enhancing the user interactivity accordingly to the emotional state. Based on this conception, this paper presents the research phase of the development of an Affective Car Racing computer game. The designs were created based on the theory of “Affective Loop” in games. Affective Loop consists of Emotion Elicitation, Emotion Detection/Modelling and finally Emotion Expression by Game Engine. This paper considers the second and third subphases of this loop. Designs are done for these two phases based on technologies that are still not been utilized by many game developers when designing a game. Emotion Detection/Modelling phase is introduced with a technique of capturing Electroencephalography (EEG) signals for predicting the real-time emotion of the player while interacting with the game engine. Emotion Expression phase considers the concept of Music Emotion Recognition (MER), which is a novel concept for the Gaming Industry. The authors had trained SVM models for emotion modeling via EEG Signals that will be captured by the Emotiv Epoc 14 channel device. The authors had classified the Rock and Electronic genre of music via Multi-Label RAKEL classification (Precision score of 75%) to play music excerpts based on the effect of the gamer during gameplay.
Agent based modeling for unordered traffic in Sri Lanka – An investigation into pedestrian behavior
(International Research Conference on Smart Computing and Systems Engineering - SCSE 2018, 2018) Rathnayaka, K.R.K.S.
Rising traffic congestion is an inescapable condition in large and growing metropolitan areas across the world. Main entities of a traffic scenario are pedestrians and vehicles. Police make different rules to control the traffic congestions and from an infrastructure development perspective, authorities take actions to construct underground and overhead pedestrian bridges, fences along pavements, islands, etc. However, most of these initiatives end up with unexpected results, mostly since traffic congestion is an emerging macro-level pattern of complex micro-level behaviors of pedestrians and drivers. The study proposes Agent-Based Modeling and Simulation (ABMS) approach, which applies computational methods to study the issues in complex systems. When considering a simulation environment, software agents interact with each other similar to the way real world vehicles and pedestrians behave. This lets us study traffic congestion emerging as a macro-level pattern. Identifying the overall impact of behaviors of drivers and pedestrians to the congestion by extending the previous work, is the aim of this research. The research uses ABMS environment called NetLogo to develop the simulator and Kiribathgoda junction in Western Province, Sri Lanka as the testbed. Coming up with an effective traffic simulator for the unordered traffic conditions in Sri Lanka, which could be used by policy makers to analyze different traffic congestion scenarios and test different solutions to reduce traffic, is the main objective of this research.
AHP integrated MILP approach to minimize transportation cost to prioritize distribution requirements
(International Research Conference on Smart Computing and Systems Engineering - SCSE 2018, 2018) Madushika, I.K.; Wijayanayake, A.
Customer satisfaction can be considered as the most important factor for any business as it is tightly linked to revenue and determines the company’s growth and the sustainability. Further it is the leading indicator of customer repurchases and loyalty. Final outcome of the effective supply chain (SC) management is to make the customer loyal and if failed it would result to transfer the customer towards the competitor. Understanding this importance, research in supply chain management (SCM) has grown significantly in recent years. Many organizations have identified that customer satisfaction (CS) and the SC cost are linked and it is impossible to optimize both at the same time. Many studies have been done under different situations to minimize transportation cost (TC) as it ultimately reduces a tremendous amount of SC cost. The need for a reliable approach to optimize customer satisfaction while minimizing the transportation cost has been raised in many occasions as improving customer satisfaction is a goal sought by many businesses in the logistic industry. This requirement becomes critical when the distributor has to select a set of customer orders to be delivered when the supply is less than the demand. Therefore, the objective of this study was to develop a model to find a way to optimally satisfy the customer orders, while minimizing the transportation cost. As a result, a customer focused approach is presented by incorporating Analytic Hierarchy Process (AHP) and then employing a mixed integer linear programming (MILP) model to find the optimal solution. The proposed model addresses customer satisfaction while minimizing the transportation costs
Alapana Generation Using Finite State Machines and Generative Adversarial Networks
(Jayatharan Vithushigan; Alwis Dileeka (2023), Alapana Generation Using Finite State Machines and Generative Adversarial Networks, International Research Conference on Smart Computing and Systems Engineering (SCSE 2023), Department of Industrial Management, Faculty of Science, University of Kelaniya Sri Lanka. Page 6, 2023) Jayatharan, Vithushigan; Alwis, Dileeka
The recent advancements in deep learning techniques and computational power have promoted the development of novel approaches for music generation. In this study, generating alapana, an improvisational form of Carnatic music was proposed, by leveraging Generative Adversarial Networks (GANs) and Finite State Machines (FSM). The goal is to create melodious alapana sequences that follow a given input Raga, ensuring continuity and coherence throughout the generated musical piece. The proposed approach incorporates Carnatic music theory rules into the generation process to enhance the structural coherence of the generated alapana. Additionally, various hyperparameter settings were explored to achieve the best performance. The Fréchet Audio Distance, Percentage of Correct Pitches and the Subjective evaluation through human listeners are the evaluation metrics of this approach. The result of this study demonstrates the potential of using GANs and FSM for generating continuous and pleasing alapana sequences in Carnatic music, contributing to the growing body of research in computational music generation.
Analysis and detection of potentially harmful Android applications using machine learning
(International Research Conference on Smart Computing and Systems Engineering - SCSE 2018, 2018) Kavneth, G.A.S.; Jayalal, S.
With the rapid advancement of technology today, smartphones have become more and more powerful and attract a huge number of users with new features provided by mobile device operating systems such as Android and iOS. Android extended its lead by capturing 86% of the total market in 2017 (Gartner, 2017) and became the most popular mobile operating system. However, this huge demand and freedom has made the hackers and cybercriminals more curious to generate malicious apps towards the Android operating system. Thus, research on effective and efficient mobile threat analysis becomes an emerging and important topic in cybersecurity research area. This paper proposes a static-dynamic hybrid malware detecting scheme for Android applications. While the static analysis could be fast, and less resource consuming technique and dynamic analysis can be used for high complexity and deep analysis. The suggested methods can automatically deliver an unknown application for both static and dynamic analysis and determine whether Android application is a malware or not. The experimental results show that the suggested scheme is effective as its detection accuracy can achieve to 93% ∼ 100%. The findings have been more accurate in identifying Android malwares rather than separating those two static and dynamic behaviors. Furthermore, this research compares the machine learning algorithms for static and dynamic analysis of the Android malwares and compare the accuracy by the data used to train the machine learning models. It reveals Deep Neural Networks and SVM can be used for and higher accuracy. In addition, era of the training and testing dataset highly effect the accuracy of the results regarding Android applications.
Analysis of Factors Influencing the Virtual Learning Environment in a Sri Lankan Higher Studies Institution
(IEEE International Research Conference on Smart computing & Systems Engineering (SCSE) 2019, Department of Industrial Management, Faculty of Science, University of Kelaniya, Sri Lanka, 2019) Charanya, R.; Kesavan, M.
A project is commonly acknowledged as a successful project when the aim of the project is achieved positively. A system called Virtual Learning Environment (VLE) was designed among the students and university academic staff to encourage a positive approach in knowledge achievement and support active learning within the university. This study was carried out to analyze the factors influencing the VLE system and explore the relationship between the students and university academic staff on the system. The factors influencing VLE were identified through the literature review and the interviews which were conducted among the university academic staff and the industry experts. A paper-based questionnaire survey was carried out among the students and university academic staff in order to measure the severity of the factors influencing the VLE system. The respondents chosen for this study were the undergraduate students and university academic staff from Vavuniya Campus of the University of Jaffna, who used the above created VLE system. There were 120 responses from the students and 30 responses from the university academic staff. The students and university academic staff were requested to indicate their level of contribution on various factors in the survey questionnaire with a 5-point Likert scale and the Relative Importance Index (RII) was calculated for each factor. The severity of each factor was identified based on its RII value. The factors were ranked based on their severity and Spearman’s rank correlation coefficient was calculated. It was found that there was 26.9% of positive degree of agreement between the students and university academic staff on the factors influencing VLE. This paper also explores some recommendations to improve the usage of VLE system
Analysis of historical accident data to determine accident prone locations and cause of accidents
(International Research Conference on Smart Computing and Systems Engineering - SCSE 2018, 2018) Ifthikar, A.; Hettiarachchi, S.
Road traffic accidents causes great distress and destroy the lives of many individuals. Inspite of different attempts to solve this problem, it still resides as a major cause of death. This paper proposes a system to analyse historical accident data and subsequently identify accident-prone areas and their relevant causes via clustering accident location coordinates. This system, once developed, can be used to warn drivers and also to aid fully autonomous automobiles to take precautions at accident-prone areas.
Analyzing Factors that Impact on Performance of Pickers in Third-Party Logistics Warehouses in Sri Lanka
(Department of Industrial Management, Faculty of Science, University of Kelaniya Sri Lanka, 2022) Prasadika, A. P. K. J.; Wijayanayake, A. N.; Niwunhella, D. H. H.
Order picking is the most crucial and expensive operation in a warehouse which affects customer satisfaction and the profitability of the warehouse. Picker is the employee who is responsible for the order picking process. So, picker performance is very important in improving the overall performance of the warehouse. Therefore, identifying the factors that have an impact on the performance of the pickers is advantageous. The main objective of this research is to identify the relationship between factors that has an impact on picker and picker performance through the Partial Linear Square – Structural Equation Modelling (PLS-SEM) technique using SmartPLS software. Initially, the most important twelve factors were identified by reviewing the past literature and industry experts’ opinions. They were divided into three main categories based on the characteristics and to reduce the complexity of the model which are picker-related factors, management-related factors, and warehouse-related factors. The data analysis was done in two steps to discover direct and moderator relationships, separately. The product type that the pickers handle is the moderator used in this study. The results of the PLS-SEM analysis show that picker-related factors and warehouse-related factors have a significant impact on picker performance at the significance level of 0.05, while management-related factors have a significant effect on picker performance at the significance level of 0.10. Further, the product type moderates all three relationships. The outcomes of the study help the managers of the warehouses to improve the performance of the pickers so that the overall performance of the warehouse can be improved.
Anomaly detection in cloud network data
(Department of Industrial Management, Faculty of Science, University of Kelaniya, Sri Lanka, 2020) Yasarathna, Tharindu Lakshan; Munasinghe, Lankeshwara
Cloud computing is one of the most rapidly expanding computing concepts in the modern IT world. Cloud computing interconnects data and applications served from multiple geographic locations. A large number of transactions and the hidden infrastructure in cloud computing systems have presented a number of challenges to the research community. Among them, maintaining the cloud network security has become a key challenge. For example, detecting anomalous data has been a key research area in cloud computing. Anomaly detection (or outlier detection) is the identification of suspicious or uncommon data that significantly differs from the majority of the data. Recently, machine learning methods have shown their effectiveness in anomaly detection. However, identifying anomalies or outliers using supervised learning methods still a challenging task due to the class imbalance and the unpredictable nature and inconsistent properties or patterns of anomaly data. One-class classifiers are one feasible solution for this issue. In this paper, we mainly focused on analyzing cloud network data for identifying anomalies using one-class classification methods namely One Class Support Vector Machine(OCSVM) and Autoencoder. Here, we used a benchmark data set, YAHOO Synthetic cloud network data set. To the best of our knowledge, this is the first study that used YAHOO data for detecting anomalies. According to our analysis, Autoencoder achieves 96.02 percent accuracy in detecting outliers and OCSVM achieves 79.05 percent accuracy. In addition, we further investigated the effectiveness of a one class classification method using another benchmarked data set, UNSW-NB15. There we obtained 99.10 percent accuracy for Autoencoder and 60.89 percent accuracy for OCSVM. The above results show the neural network-based methods perform better than the kernel-based methods in anomaly detection in cloud network data.
Applicability of crowdsourcing for traffic-less travelling in Sri Lankan context
(International Research Conference on Smart Computing and Systems Engineering - SCSE 2018, 2018) Senanayake, J.M.D.; Wijayanayake, J.
Traffic is one of the most significant problem in Sri Lanka. Valuable time can be saved if there is a proper way to predict the traffic and recommend the best route considering the time factor and the people’s satisfaction on various transportation methods. Therefore, in this research using crowdsourcing together with data mining techniques, data related to user mobility were collected and studied and based on the observations, an algorithm has been developed to overcome the problem. By using developed techniques, the best transportation method can be predicted. Therefore, people can choose what will be the best time slots & transportation methods when planning journeys. The algorithm correctly predict the best traffic-less traveling method for the studied area of each given day & the given time. Throughout this research it has been proven that to determine the best transportation method in Sri Lankan context, data mining concepts together with crowdsourcing can be applied. Based on a thorough analysis by extending the data set of the collection stage, it was shown that this research can be extended to predict the best transportation method with consideration of existing traffic in all the areas.
Application of AlexNet convolutional neural network architecture-based transfer learning for automated recognition of casting surface defects
(Department of Industrial Management, Faculty of Science, University of Kelaniya Sri Lanka, 2021) Thalagala, Shiron; Walgampay, Chamila
Automated inspection of surface defects is beneficial for casting product manufacturers in terms of inspection cost and time, which ultimately affect overall business performance. Intelligent systems that are capable of image classification are widely applied in visual inspection as a major component of modern smart manufacturing. Image classification tasks performed by Convolutional Neural Networks (CNNs) have recently shown significant performance over the conventional machine learning techniques. Particularly, AlexNet CNN architecture, which was proposed at the early stages of the development of CNN architectures, shows outstanding performance. In this paper, we investigate the application of AlexNet CNN architecture-based transfer learning for the classification of casting surface defects. We used a dataset containing casting surface defect images of a pump impeller for testing the performance. We examined four experimental schemes where the degree of the knowledge obtained from the pre-trained model is varied in each experiment. Furthermore, using a simple grid search method we explored the best overall setting for two crucial hyperparameters. Our results show that despite the simple architecture, AlexNet with transfer learning can be successfully applied for the recognition of casting surface defects of the pump impeller.
Application of Game Theory on financial benefits and employee satisfaction: Case study of a state bank of Sri Lanka
(Department of Industrial Management, Faculty of Science, University of Kelaniya Sri Lanka, 2021) Jayasekara, D. D. G. T.; Wijayanayake, A. N.; Dissanayake, A. R.
The principal agent problem revolves around the competing interest between shareholders and the employees. The organization focus is on maximizing shareholder wealth, while employees try to obtain the maximum benefits for themselves. As per the motivational theories, people have different types of needs. Therefore, management should focus on a wide range of factors to motivate the employees to work to their full potential in the interest of the organization. The study focuses on both employee and the management of a state bank. The organization is always eager to minimize the cost and maximize the profit. Game Theory was used to provide a mathematical framework for understanding the optimal outcome and what the tradeoffs are to achieve that outcome. The objective is to find the right balance between financial gains and employee satisfaction. To fulfill that objective, one needs to evaluate the benefits given to employees, the effectiveness of those benefits on employees and finally recommend an effective benefits allocation mix to the organization, which will address both employee and the top management of the bank.
An Application of Transfer Learning Techniques in Identifying Herbal Plants in Sri Lanka
(IEEE International Research Conference on Smart computing & Systems Engineering (SCSE) 2019, Department of Industrial Management, Faculty of Science, University of Kelaniya, Sri Lanka, 2019) Azeez, Y.R.; Rajapakse, C.
Sri Lanka has a considerable collection of plant species that have been utilized for generations as medicinal treatments. Knowledge regarding herbal plants is restricted mainly among practitioners in traditional medicine. Available systems studied; had no proper methodology to search information regarding herbal plants, which can be identified through analyzing an image of an herbal plant given. Systematic literature review was done based on herbal plants in Sri Lanka, transfer learning and plant image recognition and two open ended interviews were conducted with traditional medicine practitioners. As main objective of the study, reorganization of Information was done building a technique to enhance capability of identifying herbal plants based on deep convolutional neural networks and image processing techniques which would ultimately assist more locals with identification. Five herbal plant types were chosen to analyze further in detail and the images of the plants were acquired from web and also images photographed via 13MP camera creating a data set validated through traditional medical practitioners. Images were preprocessed and retrained on Inception-v3, Resnet, MobileNet and Inception Resenet V2 based on transfer learning. Algorithm was finetuned using image processing techniques for preprocessing and prototype was tested 5 times reaching highest average accuracy of 95.5% on Resnet for the identification of 5 different plant types. Conclusively, this study enhanced the capability of searching herbal plants by reorganizing the information
An approach to coexistence analysis between agility and ERP implementation
(International Research Conference on Smart Computing and Systems Engineering - SCSE 2018, 2018) Rajakaruna, R.J.P.K.; Wijayanayake, J.
Business organizations tend to re-engineer their business processes by adopting Enterprise Resource Planning (ERP) systems in order to gain a competitive advantage. ERPs offer countless benefits by enabling an enterprise to operate as an integrated, process oriented and real time enterprise. But the issue is re-engineering with ERP ranks among slow-moving, costly and challenging processes of an organization. Many ERP specialists regard agile approaches positively, to mitigate the common ERP implementation challenges. Agile implementation of ERPs is still under research area. This research discusses on the need of agile approaches in ERP implementations and how agility and ERP implementations can coexist. In this case our research question is “Can the common ERP implementation challenges be solved by using agile approaches?” and if so, “How these challenges can be solved?” This study also seeking for uplift the level of awareness on the applicability of agility for ERP implementation projects and these findings can be effectively used by ERP Implementers, Vendors, Consultants, Project Managers and Researchers in their respective projects.
Architectural framework for an interactive learning toolkit
(Department of Industrial Management, Faculty of Science, University of Kelaniya Sri Lanka, 2021) Jayasiriwardene, Shakyani; Meedeniya, Dulani
At present, a significant demand has emerged for online educational tools that can be used as replacement for classroom education. Due to the ease of access, the preference of many users is focused on m-learning applications. This paper presents an architectural framework for an interactive mobile learning toolkit. This study explores different software design patterns and presents the implementation details of the prototype. As a case study, the application is applied for the primary education sector in Sri Lanka, as there is a lack of adaptive learning mobile toolkits that allow teachers and students to interact effectively. The study is concluded to be user-friendly, understandable, useful, and efficient through a System Usability Study.
Aspect-based sentiment analysis on hair care product reviews
(Department of Industrial Management, Faculty of Science, University of Kelaniya, Sri Lanka, 2020) Kothalawala, Malki; Thelijjagoda, Samantha
Nowadays, with almost everything being shared online, people are more verbal about their consumer experiences with products via reviews. Reviews can be vital for manufacturers to get insights into consumer opinions and consumers in their purchase decisions. Sentiment analysis, referring to the extraction of subjective opinions on a particular subject within a text, is a field within Natural Language Processing, that can convert this unstructured information hidden within reviews into structured information expressing public opinion. In regards to a specific product group like hair care products, certain brands are rising in the market due to their positive public opinion on particular aspects. While ecommerce websites facilitate users to view the reviews, they do not display which reviews contain which type of opinion on which aspect at a glance. This research aims to introduce an automated process that focuses on determining the polarity of online consumer reviews on different aspects of hair care products by using Aspect-based Sentiment Analysis. The system consists of processes like data gathering, pre-processing, aspect extraction and polarity detection and follows a sequential approach to achieve the intended goal. Consequently, by deciphering the aspect-wise polarity of the reviews, the implemented system demonstrates an accuracy of 85% from the test data for overall aspects, enabling consumers to get an at a glance idea about the public opinion and manufacturers to identify their strong and weak points.
An assessment of machine learning-based training tools to assist Dyslexic patients
(International Research Conference on Smart Computing and Systems Engineering - SCSE 2018, 2018) Sathsara, G.W.C.; Rupasinghe, T.D.; Sumanasena, S.P.
Dyslexia is a language based disability, where the patients often have difficulties with reading, spelling, writing and pronouncing words. The reading speed of Dyslexics tend to be lower than their equivalents, because of slow letter and word processing. Inspite of this disorder, a dyslexic person can be trained to read in normal speed. There are manual methods and some technical improvements can be reported such as the live-scribe smart pen, Dragon Naturally Speaking, Word processors, and Video Games. This study provides an assessment about the Machine Learning (ML) based techniques used for Dyslexic patients via a systematic review of literature, and a proposed ML based algorithm that will lay foundation for future research in the areas of machine learning, augmented and healthcare training devices.
Autism spectrum disorder diagnosis support model using InceptionV3
(Department of Industrial Management, Faculty of Science, University of Kelaniya Sri Lanka, 2021) Lakmini, Herath; Marasingha, M. A. J. C.; Meedeniya, Dulani; Weerasinghe, Vajira
Autism spectrum disorder (ASD) is one of the most common neurodevelopment disorders that severely affect patients in performing their day-to-day activities and social interactions. Early and accurate diagnosis can help decide the correct therapeutic adaptations for the patients to lead an almost normal life. The present practices of diagnosis of ASD are highly subjective and time-consuming. Today, as a popular solution, understanding abnormalities in brain functions using brain imagery such as functional magnetic resonance imaging (fMRI), is being performed using machine learning. This study presents a transfer learning-based approach using Inception v3 for ASD classification with fMRI data. The approach transforms the raw 4D fMRI dataset to 2D epi, stat map, and glass brain images. The classification results show higher accuracy values with pre-trained weights. Thus, the pre-trained ImageNet models with transfer learning provides a viable solution for diagnosing ASD from fMRI images.