Smart computing & Systems Engineering - (SCSE - 2019)
Permanent URI for this collectionhttp://repository.kln.ac.lk/handle/123456789/20146
Browse
Item MRI based Glioma segmentation using Deep Learning algorithms(IEEE International Research Conference on Smart computing & Systems Engineering (SCSE) 2019, Department of Industrial Management, Faculty of Science, University of Kelaniya, Sri Lanka, 2019) Kaldera, H. N. T. K.; Gunasekara, S. R.; Dissanayake, M. B.Primary brain tumors can be malignant (cancerous) or benign (non-cancerous). Out of primary brain tumors, gliomas are the most common and, high grade gliomas carry a poor prognosis. In our paper, we present a technique to segment the glioma cells in Magnetic Resonance Imaging (MRI) using faster Region based Convolutional Neural Network (R-CNN) and edge detection techniques in image processing algorithms. This study identifies the region of interest that is glioma cells, with higher confidence level and localize the tumor on the MRI with the tumor mask. Further, analysis shows that with the proposed technique it is possible to achieve an average detection accuracy, sensitivity, Dice score and confidence level of 99.81%, 87.72%, 91.14% and 93.6% respectivelyItem Occupancy Monitoring System for Workplace Washroom(IEEE International Research Conference on Smart computing & Systems Engineering (SCSE) 2019, Department of Industrial Management, Faculty of Science, University of Kelaniya, Sri Lanka, 2019) Godakandage, V. M. P.; Kothalawala, K. R. M.; Chathumali, E. J. A.; Madhubhashana, A. W.With regard to rapid technological advancements majorly influencing our daily lives, Internet of Things (IoT) has been a topic of broad and current interest in the recent years. The capabilities of IoT can assist in revolutionizing the way people live and work, thereby improving quality of life. With the impact of IoT only continuing to propagate in the future, it can be used as a means of easing our day-to-day struggles. Therefore, with the assistance of IoT along with a few hardware, the proposed system, addresses the displeasing reality of queues and several visits for the washrooms due to them coming forth occupied. Thus, the focus of the intended system is on delivering a pleasant washroom experience for employees in an office environment providing them with an at-desk indication on the occupancy of the washroom cubicles reducing queues and disappointmentsItem Candidate Recruitment Based on Automatic Answer Evaluation Using WordNet(IEEE International Research Conference on Smart computing & Systems Engineering (SCSE) 2019, Department of Industrial Management, Faculty of Science, University of Kelaniya, Sri Lanka, 2019) Kasundi, J.; Ganegoda, G.U.Any organization’s future survival in the industry mainly depends on the decisions they take today and recruiting a new employee is one of those critical decisions that an organization has to take. Recruitment process of an organization should have the capability to find the right person to the right job. Most of the organizations today, interview candidates to test their job skills but not their personality level. But recruiting the most skilled person does not work out in a good manner always. Especially for the positions like leaders, they have to consider about the personality of the employee. And also, in the industries like IT industry, employees are supposed to work in project teams but not individually. That is where personality matters the most. To work in a team, all the members should be able to corporate with each other without facing any difficulty. Therefore candidate recommendation chatbot system is suggested and it is capable of evaluating both technical skills and personality traits of the candidate and providing a final recommendation based on the scores obtained to those two sections. The system mainly contains four modules; Question Generation and Dialogue Flow Maintaining Module, Technical Answers Evaluating Module, Vocabulary Based Personality Evaluating Module and Candidate Recommendation Module. This paper will be discussing about the answer evaluation module of the system which contains an ontology to store java related technical questions and answers and has used WordNet to measure the correctness of the answersItem 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 informationItem Sinhala Handwritten Postal Address Recognition for Postal Sorting(IEEE International Research Conference on Smart computing & Systems Engineering (SCSE) 2019, Department of Industrial Management, Faculty of Science, University of Kelaniya, Sri Lanka, 2019) Ifhaam, M.F.A.; Jayalal, S.Sri Lankan post office mail sorting process is done manually, even today. Though employees are well experienced, it takes considerable time and employees need to work overtime in places like Central Mail Exchange (CME). With major issues like unclear handwriting, having trouble to recognize some uncommon or ambiguous names, and carrying these duties twice a day create a negative impact on the efficiency of the postal delivery system. In the prevailing system, forward mails and delivery mails are the two categories of separating mails at the sorting centers. Delivery mails are the posts which can be delivered to its destination directly. Forward mails are the ones which need to be sent to an appropriate post office that can deliver the particular post to its destination. Majority of Sri Lankans use Sinhala language for their day to day activities. The primary objective of the research is to identify the automatic way of forwarding the letter to the next post office from the current post office. Proposed system is focused on the recognition of Sinhala handwriting using Optical Character Recognition (OCR) and image processing technologies. Data collected under different criteria were used for training and testing the solution. Genetic Algorithm (GA) was used to generate more optimized results faster with higher accuracy. Given addresses are written in the default format. This format can be extended to more formats as improvements in future. The algorithm shows accuracy over 92% for addresses which are recognized with 3 misrecognized characters. This algorithm can be used on practice scenario as the AI Recognition has more than 79 % of accuracy.Item An Infectious Disease Medical Policy Simulation and Gaming(IEEE International Research Conference on Smart computing & Systems Engineering (SCSE) 2019, Department of Industrial Management, Faculty of Science, University of Kelaniya, Sri Lanka, 2019) Kurahashi, S.This paper analyses a new type of infectious disease by an agent-based simulation and gaming model based on Ebola fever and dengue fever. The mathematical model such as SIR (Susceptible, Infected, Recovered) has been used to model these infectious diseases. Besides, a simulation and gaming model enables to represent the decision-making of each citizen on the computer, and al-so reveals the pandemic by the contact process among people in the model. The study challenges to design an infectious disease model in which some health policies are introduced including vaccine stocks, antiviral medicine stocks, medical staff and so on. Aside from the policies, a gaming simulation of a new type of infectious disease, which has not yet an effective vaccine, is also implemented in the model. We created a medical policy decision game dealing with infections using a serious game approach. As results of experiments, it has been found that preventive vaccine, antiviral medicine stocks and the number of medical staffs are crucial factors to prevent the spread. Besides, a modern city is vulnerable to dengue fever due to commuting by train. It has also been found that self-control and restraint on immigration are essential, and decision-making for vaccine reserve amount and medical support to the partner country where the infection has spread.Item Prediction of User Intentions Using Web History(IEEE International Research Conference on Smart computing & Systems Engineering (SCSE) 2019, Department of Industrial Management, Faculty of Science, University of Kelaniya, Sri Lanka, 2019) Samarasinghe, K.T.C.S.; Jayalal, S.In the present internet has become much more necessary thing to humans and we use it as a way of sharing information and way of communication. If the networks can identify the user’s intentions, it will be affecting to increase productivity and personalization. Predicting user intention(s) is interesting and useful for many applications such as threat identification, imposing restrictions and cashing web details. The aim of this research is to develop a method to predict user intention using supervised machine learning methods with user’s past historical behaviours. Experiments in this study used access log on a local server and focused on creating single user prediction and multiuser generalize prediction models. Experimental models were created based on several multi-classifier algorithms, such as Support Vector Machine (SVM), Multilayer Perceptron (MLP) and K-Nearest Neighbor (KNN). KNN based models outperform other used algorithms. Also results in this study show that there is some sort of behavioural patterns for peoples to use the internet according to the time and the groups they interactItem A Blockchain-based decentralized system to ensure the transparency of organic food supply chain(IEEE International Research Conference on Smart computing & Systems Engineering (SCSE) 2019, Department of Industrial Management, Faculty of Science, University of Kelaniya, Sri Lanka, 2019) Basnayake, B. M. A .L.; Rajapakse, C.Low quality agricultural products are added to the market daily. Over usage of chemicals in the production process, use of uncertified chemicals and mechanisms for preservation and ripening processes, are the major issues that impact on agricultural product’s quality as well as overall health of the consumers. Mechanisms to identify the quality of the agricultural products are highly demanded due to the lack of transparency in the current process. Blockchain technology is emerging as a decentralized and secure infrastructure which can replace involvement of a third party to verify the transactions within the system. The purpose of the research was to implement a Blockchain based solution to verify the food quality and the origin of the agricultural supply chain. A public Blockchain concept was selected instead of a private Blockchain in this study to ensure transparency by allowing any person to access the network. Instances of the smart contract were created for each physical product and deployed to Blockchain network. A Quick Response code which contained the address of the instance, was a reference to the virtual product. All the actors who are involved in the supply chain must be able to interact with the system to achieve the transparency. Each transaction and events related to a product is validated by peers of the Blockchain system. Product ownership was changed for each relevant transaction. A token-based mechanism was used to indicate the farmers’ reputation with their products. Farmers could place a certification request regarding their products and, they can gain reputation tokens for each certification done by peers. A unique Quick Response code was used to identify each product within the supply chain. The proposed system has been implemented as a prototype and validated within the studyItem Modelling & simulation of the hydration process of cement for rapid concrete constructions(IEEE International Research Conference on Smart computing & Systems Engineering (SCSE) 2019, Department of Industrial Management, Faculty of Science, University of Kelaniya, Sri Lanka, 2019) Sandaruwan, S.M.D.T.; Pallegedera, A.Hydration is series of exothermic reactions which occurs between cement and water. It is difficult to predict the exact behaviour of hydration process. It was modelled using Affinity Hydration model and was simulated using finite element approach and which was then validated with realistic parameters. Time dependent simulation has been carried out for various geometries to non-isothermal conditions inside the model. Modelling and simulation was performed in both polystyrene insulation and wooden insulation for different environmental conditions. Temperature, degree of hydration and rate of hydration was obtained using simulation and was verified with data from the realistic experimental data from literatureItem Communication framework for vehicular ad-hoc networks using Blockchain: Case study of Metro Manila Electric Shuttle automation project(IEEE International Research Conference on Smart computing & Systems Engineering (SCSE) 2019, Department of Industrial Management, Faculty of Science, University of Kelaniya, Sri Lanka, 2019) Kulathunge, A.S.; Dayarathna, H.R.O.E.Vehicular Networks or the Vehicular Ad-hoc Networks (VANET) are experiencing revolutionary growth in research and industry, but still suffers from various breaches such as poor decentralization of communication, security vulnerabilities, scalability and trust issues in its communication as well as in its design. Major issues identified in VANET, are trust, data accuracy, and reliability of communication in the communication channel. Blockchain technology is a technology adopted by crypto currency, namely Bitcoin, which is recently used to build trust and reliability in peer-to-peer networks. This study proposes a communication framework for VANET exploring capabilities of blockchaining. Metro Manila Electric Shuttle Automation Project is used as a case study to verify the communication framework. It fulfills Vehicle-to-Vehicle (V2V) as well as Vehicle-to-Infrastructure (V2I) communication requirements of the considered project. It includes an Intelligent Toll Payment (ITP) system (V2I communication) and automated vehicular following, known as goose tracking (V2V and V2I communication), and those covering main communication requirements. Further, a simulator named SimulatorZ is implemented to model Goose Tracking which should support multi-vehicle simulation to understand data requirements of master and slave vehicles and the timing of communication. Communication framework provides trustworthiness for vehicles behavior, cashless secure transaction between two untrusted party as well as rewards and penalties for vehicles’ actions. Data communication in goose tracking is done with 10ms latency between two vehicles and 1-10-5 reliability. Slave vehicles’ movements depends on master vehicle’s speed, position, angle and the timestampItem A Novel Computational Method to Capture FPGA Technology Trends from Patent Information.(IEEE International Research Conference on Smart computing & Systems Engineering (SCSE) 2019, Department of Industrial Management, Faculty of Science, University of Kelaniya, Sri Lanka, 2019) Shibata, M.; Takahashi, M.This paper provides a novel trend analysis of FPGA development with Machine Learning. Recently, demands for the computing power are expanding due to reform of industrial structure such as the Industry 4.0 and the explosive expansion of AI. In this paper, we reveal the technical development trend of the leading FPGA companies from the patent information with Machine Learning. We focus on the classification codes in the patent and employ Link Mining method as the analytical method. Link Mining is a conventional method to analyze the structural features of things. It simplifies the objects and the relations as the nodes and the edges. With the proposed method, we succeed in revealing the companies’ focused technology fields, the transition of focusing areas, and their differences and common points from the results of extracting the graphs’ featuresItem GPS guided auto-sensing system for motor vehicles(IEEE International Research Conference on Smart computing & Systems Engineering (SCSE) 2019, Department of Industrial Management, Faculty of Science, University of Kelaniya, Sri Lanka, 2019) Ranasinghe, D.C.R.; Wanniarachchi, W.K.I.L.; Anuradha, U.A.D.N.Driver errors are the most common cause of traffic accidents. Mobile phones, in-car entertainment systems, traffic volume increases, road systems becoming complicated contribute towards such driver errors. This paper introduces developing a GPS guided auto pilot system for vehicles. This system will be a driverless vehicle system. The user has to give the location of the destination to the system and then the system will automatically navigate to the given destination. These systems are currently used in aircraft, submarines and ships but not used in ground vehicles. Use of such systems in the open street is more complex than use of such systems in air or marine systems. The possible route to the destination must be selected by the vehicle after the destination coordinates are given by the user. Then the vehicle navigates through the open streets without colliding with other moving or non-moving objects. GPS sensor takes real time coordinates of the vehicle and decide the direction to be moved with respect to the given destination coordinates and pass control signals to the motor controller. While navigating, the vehicle keeps appropriate safe distance and speed with the vehicles in front of it. If the lane is not clear, the vehicle applies breaks to avoid collisions. Sonar sensors are used to detect the object in the road as they are more convenient in the outdoor applications. With further developments, this system will be able to assist drivers who drive long trips and play a vital role in minimizing road accidentsItem Part of speech tagging for Twitter conversations using Conditional Random Fields model(IEEE International Research Conference on Smart computing & Systems Engineering (SCSE) 2019, Department of Industrial Management, Faculty of Science, University of Kelaniya, Sri Lanka, 2019) Fanoon, A.R.F.S.; Uwanthika, G.A.I.Part-of-Speech Tagging is the technology of assigning the appropriate parts-of-speech to a word. Part-of-speech tagging is very useful in information retrieval, information extraction, and speech processing. This research presents a part-of-speech tagging, especially for twitter text data. The process of part-of-speech tagging for twitter conversation is a difficult task. Several approaches have been made to develop an accurate tagging system but most of them are relevant to news text data and web contents. Therefore, this research intends to develop a part-of-speech tagger model for twitter speech. using CRF toolkit. The system was developed for nearly 1000 twitter conversations employing Conditional Random Field stochastic model. The data for twitter speech was downloaded from the internet. A POS-tagged text corpus, template file and CoNLL file for both training and testing database were prepared accordingly. The training was carried out for both the unigram model as well as the bigram model. The performance of the system over these models was obtained through this examination which showed a significant efficiency, calculated from the number of correctly tagged words and the total number of wordsItem Data Mining Approach for Identifying Suitable Sport for Beginners(IEEE International Research Conference on Smart computing & Systems Engineering (SCSE) 2019, Department of Industrial Management, Faculty of Science, University of Kelaniya, Sri Lanka, 2019) Amarasena, P.T.; Kumara, B. T. G. S.; Jointion, S.Anthropometric measurements are generally used to determine and predict achievement in different sports. An athlete’s anthropometric and physical characteristics may perform important preconditions for successful participation in any given sport. Further, anthropometric profiles indicate whether the player would be suitable for the competition at the highest level in a specific sport. Recently, more researches have been carried out on Sport Data mining. In this study, we propose an approach to identify the most suitable sport for beginners using data mining and anthropometric profiles. We propose clustering base approach. We apply a spatial clustering technique called the Spherical Associated Keyword Space which is projected clustering result from a three-dimensional sphere to a two dimensional (2D) spherical surface for 2D visualization. Empirical study of our approach has proved the effectiveness of clustering resultsItem Use of LIME for Human interpretability in Sinhala document classification(IEEE International Research Conference on Smart computing & Systems Engineering (SCSE) 2019, Department of Industrial Management, Faculty of Science, University of Kelaniya, Sri Lanka, 2019) Kumari, P. K. S.; Haddela, P.S.With advancement of technology in Sri Lanka, use of Sinhala text usage has grown rapidly over the time where automatic categorization is helpful for efficient content management. As a result, experts tend to use machine learning application to categorize this large volume of data in an efficient and accurate manner. Most of these learning models are operating in a black-box where there is no way to understand how the model has decided which category an instance is assigned. Understanding the reason behind why learning model makes these predictions is very important to trust such models and to provide reasonable justifications in real world application. Intention of this research is to present the work carried on related to document classification model prediction interpretation where a set of text classifiers has been studied with use of SinNG5, freely available Sinhala Document corpusItem 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 systemItem VoiceNote: An Intelligent tool for monetary transactions with integrated voice support(IEEE International Research Conference on Smart computing & Systems Engineering (SCSE) 2019, Department of Industrial Management, Faculty of Science, University of Kelaniya, Sri Lanka, 2019) Hashan, B.; Abeyrathna, Y.; Kaluaratchi, M.; Piyalath, A.; Thelijjagoda, S.The smart phone has become a critical aspect of our daily lives, with many applications providing solutions to different problems that we encounter. Fintech have become a major priority in the present world. The use of petty cash has run its course throughout the world. Credit cards have proven to be successful in creating a cashless environment. Combining the smartphone with financial planning ability will be a powerful tool. In the meantime, customers in the modern society expect more convenient methods to make financial transaction with enhanced security measures. This paper describes how a QR based payment system which can be controlled by voice commands simplifies business operations between customer and vendor. QR code based mobile payments represent a relatively new technology that can be used in the new business arena of payments using smartphones. It provides a flexible and cashless environment for users. It is more secure and easier to; pay in supermarkets, shopping malls, as well as the user can share money with their friends and families, even can be manipulated by voice commands. The use of such devices in the payment process has lots of advantages in terms of speed and comfort when accessing services, and also improves the security and integrity of transactions, and the simplicity with user friendly interactions. To evaluate the potential of QR code-based voice support payment system, in the context of business transactions, VoiceNote updates monetary transaction in realtime and uses encryption and decryption methods for security. The transaction details can be analyzed and forecast through a web dashboard. VoiceNote research findings shows that transaction time is reduced by an average of 64 seconds when compared with a cash transaction and an average reduction of 13.5 seconds when compared with card transactionsItem Linguistics Analytics in Data Warehouses Using Fuzzy Techniques(IEEE International Research Conference on Smart computing & Systems Engineering (SCSE) 2019, Department of Industrial Management, Faculty of Science, University of Kelaniya, Sri Lanka, 2019) Asanka, P.P.G.D.; Perera, A.S.A data warehouse is used intensively in many industry domains to gain competitive advantage over its competitors. In modern data warehouses, linguistic analytics is an important aspect, so that it has the ability to take more precious decisions. In most of the data warehouse implementations, it is designed for crisp analysis. Crisp analysis has its own limitations and boundaries with the major assumptions that every situation belongs to one state and denial to other states. Hence, crisp data warehouse does not allow to carry out linguistic analytics. When a fuzzy data warehouse is implemented, because of the fuzzy nature of the data warehouse, linguistic analytics can be done to a certain extent. In this research, non-functional requirements such as performance and configuration are also covered so that this method can be implemented in the real worldItem Industry 4.0 maturity assessment of the Banking Sector of 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) Bandara, O.K.K.; Tharaka, V.K.; Wickramarachchi, A.P.R..Technological advancements have created massive changes in the way of performing businesses in this era. Whilst in creating the transition of physical world to a virtual world, industry 4.0 plays a significant role. Thus, the development of the concept of industry 4.0 revolutionize the way of conducting businesses. This concept was first limited to manufacturing sector thus with the evolvement of customer behaviour, service sector also applied these concepts to offer a better customer satisfaction. As modern customer expectations have risen with technology, Sri Lankan banking sector focussed to deliver their services strategy by enabling advanced technologies. Hence there is an essential need to define, formulate a set of guidelines in order to assess the progress of the current state of Sri Lankan banking sector in their journey of adapting industry 4.0. So, this scrutiny assesses the maturity of Sri Lankan banking sector by application of an industry 4.0 maturity model developed by the authors. The results of this study indicates that Sri Lankan banking sector is in the third maturity level of the model “Defined” as the overall maturity is 3.668.Item Automated, low-cost pedestrian crossing carriage for efficient traffic control and pedestrian safety(IEEE International Research Conference on Smart computing & Systems Engineering (SCSE) 2019, Department of Industrial Management, Faculty of Science, University of Kelaniya, Sri Lanka, 2019) Yasaswin, B.A.O.S.; Jinasena, T.M.K.K.Disorganized city planning and a huge rise in use of automobiles on the road have caused massive traffic congestion in cities across the world. Pedestrian crossing designed to facilitate movement across the road network, have unfortunately become a hindrance to movements of traffic. Though the smart zebra lines had been introduced, it has not contributed much to reduce the time that holds vehicle lines under the traffic lights. Moreover, the establishment of transfer hubs and underground crossings remain silent in local context because of their cost. Even though there are plenty of pedestrian crossing mechanisms available, they are not secure and not ideal for the disabled, elderly, children, and the sick. Considerable numbers of police officers have to spend their time on traffic controlling duties though it’s inefficient and wastage of human resources. A number of studies have focused on automated vehicles and robots as tools to ease problems of congestion. This paper, it focuses on the design of an automated guided carriage system for pedestrian transportation in an efficient and secure manner