International Research Conference of UWU-2019

Permanent URI for this collection

https://erepo.lib.uwu.ac.lk/handle/123456789/42

Browse

Now showing 1 - 20 of 35

An Accurate Indoor Navigation Method Using Radio Signals and Machine Learning Techniques
(Uva Wellassa University of Sri Lanka, 2019-02) Nimaladasa, M.B.C.K.; Herath, H.H.S.B.; Koshila, P.K.; Wimaladharma, S.C.T.I.
Navigation is the process of identifying positions of the passengers and then display feasible paths to guide them to their destinations. Global Positioning System (GPS) is suitable for outdoor navigation. Due to the lack of GPS signal reception inside buildings, new technologies should be emerged for navigating inside the buildings and covered areas. The main objective of this study is to propose an accurate and reliable schema to navigate passengers inside unfamiliar indoor environments along the shortest path to their destinations. The proposed navigation process consists of tracking the passenger, identifying shortest path and continuously guide passengers to their destinations on the fly. Triangulation technique is employed on Wi-Fi signals coming from at least three WiFi routers to identify the position of the passenger. Wi-Fi routers are recognized using their MAC addresses and then triangulation algorithm is applied. Proximity algorithm is used together with triangulation algorithm to increase accuracy. The map of the indoor area is scaled via x and y axes and positions are identified as coordinates of it. The path to the destination is animated through these coordinates. Shortest path between current and destination location is calculated using Dijkstra’s algorithm. Prototypical development is achieved by proofing the concept for feasibility of the proposed indoor navigation architecture. It can be concluded that, a significant accuracy can be achieved by using Wi-Fi technology, triangulation algorithm, proximity algorithm and Dijkstra’s algorithm. Further improvements on accuracy of proposed indoor navigation architecture can be achieved by incorporating Radio Frequency Identification or Bluetooth beacons technologies together with Wi-Fi technology.
Application of Image Processing and Neural Network Technique for Rice Grading
(Uva Wellassa University of Sri Lanka, 2019-02) Wasana, P.L.D.; Fernando, P.S.R.; Lakmal, M.K.A.; Illoshini, P.A.A.; Wilson, R.S.I.; Ekanayake, E.M.U.W.J.B.
When considering the agricultural industry, Rice is a principal food source in Asian countries. It is the most commonly and widely used grain in the local consumer market. Thus, analyzing the quality of rice is important. The quality of Rice will depend on the milling. Most mill owners do not have a proper method of measuring the quality of rice. Calculations are currently carried out using the Vernier Caliper in research centers, but it is a time-consuming task. Though there are some machines for automating this process, its usage is very low because of the high cost. Rice can primarily be classified based on colour and shape. Here we analyzed the two genres, Red Kekulu rice and Samba rice produced by Bombuwala rice research center. This paper introduces the rice classification method according to image processing approaches and neural network. Physical characteristics of the grain such as major and minor axis length, perimeter, area, colour and chalkiness are used to classify the rice grains. Identifying broken rice and wastages are the major objectives of the grading system. We have compared the proposed system results with manual measurements and visual observations. Matlab tool is used for image acquisition, preprocessing, segmentation, feature extraction and training the data set. This proposed grading system has scales such as premium, grade A, grade B and it was defined under supervision of rice researchers using broken rice and wastage content. The proposed image processing methods can reduce the time of operation and increase the accuracy. Finally, with the proposed grading system consumers will be able to receive information regarding the quality of the rice.
Augmentative and Alternative Communication Application for Adults with Language Difficulties: An Application Developed in Sinhala Language
(Uva Wellassa University of Sri Lanka, 2019-02) Gunawardana, D.A.Y.K.; Jayathunaga, R.M.; De Silva, A.H.H.G.; Ekanayake, E.M.U.W.J.B.; Wilson, R.L.S.
Many adults can experience acquired disorders such as stroke, Parkinson, amyotrophic lateral sclerosis that can interfere with their ability to communicate with others. Currently, adult individuals who experience these kinds of difficulties need to rely on low- technology options such as printed out alphabet boards to express themselves. The number of words that a person used to communicate with others is much larger than the number of words printed on the boards, hence they face difficulties in communicating with the others. To address this issue, a text-based Augmentative & Alternative Communication system was developed in the Sinhala language for adult persons with speech disorders. The system comprises of three components keyboard layout for Sinhala fonts, next word prediction, and the text-to-speech converter. The methodology of the study was applied as follows. The requirements of the patients were collected from the Disability Rehabilitation Department at the Ragama Base Hospital. The requirements were analyzed case by case and a keyboard layout was designed by taking all the requirements into consideration. The most important module of this system is the next word predictor. This module assists a patient to predict the next word once he selects a word. The RNN neural network model was trained with a typical set of words that such a person often used. The word sequence was constructed from the requirements identified from the interviews with such patient and the health care professionals who have been working in this field for a significant period. A model was trained to perform text-tospeech using TensorFlow libraries. Once, the word predictor constructs the sentence, the whole sentence is converted into voice at once. The initial evaluation of the system was conducted only with patients who are being received treatments at the Ragama Hospital. The test results show that the system is able to communicate easily with patients in decent accuracy.
Automated Collection of Customer Feedback Using Facial Expression and Machine Learning Techniques
(Uva Wellassa University of Sri Lanka, 2019-02) Jayarathna, H.M.P.P.; Priyanga, E.A.I.; De Silva, B.P.; Karunarathne, K.R.R.; Perera, R.M.; Senanayake, S.H.D.
Today, feedback of customers is crucial for businesses and organizations. It is the main method of identifying the customer service, quality and future improvements of the service. Nowadays most of the modern companies are focusing on digitalized approaches to collect customer feedback where the users can instantly rate the service. In order to take the feedback from customers in a digitalized way, there are some machines and methods available such as happy-or-not feedback machine. Analyzing the feedback is the only way of measuring the performance of the customer service officers. But the main problem of these systems is that they only allow the users to rate the service manually and such that it allows to add expressions as they wish, rendering it unreliable. Also, there is no way to measure the customer service and employees’ performance by computing. There are some methods to measure the customer service, such as crucial customer service metric. This metric can be used to measure the quality of the customer service. But, there is no automated and robust way to measure the customer service. This research introduces a device that applies the theories of the customer service metrics such as customer request volume, first response time, number of replies, customer satisfaction score etc. Machine Learning techniques are used to capture facial expressions and voice detection. The device facilitates measuring of customer service performance of employees autonomously by monitoring the employee involved in customer service and rates their results. The device captures the employees’ expressions and apply the values into the customer service metrics and produces the overall performance. It can measure the real rating of the customer service without the need for customer interaction. This device could be beneficial in any field where customer satisfaction is crucial. The effectiveness of this device are yet to be obtained after being applied on a real world scenario.
Concentration Device for Increasing Productivity Through the Improvement of Pomodoro Technique Using Colour Psychology
(Uva Wellassa University of Sri Lanka, 2019-02) Priyanga, E.A.I.; De Silva, B.P.; Jayarathna, H.M.P.P.; Karunarathne, K.R.R.; Perera, R.M.
Nowadays mobile devices play a considerable role in the technology revolution, and people have been especially addicted to the Social Medias through smart phones. One of the major challenges that people face today is time consumption due to this addiction on these activities in all day. Most of the time children are the major victims of this problem and they cannot keep the concentration on a particular work due to this addiction and this is a reason to reduce brain power as well as the memory losing. At present, some smartphone applications are used to solve the above problems. These applications are supposed to be developed to increase the concentration on work for a particular task to make it true. The major drawback of this mobile applications is losing the concentration, when other unnecessary notifications are appeared suddenly. Also the mind is impelling to use social media and other activities instead of doing current activity. There are several techniques for preserving the concentration such as yoga, build willpower etc. Among them highly recommend technique to increase concentration on work is called Pomodoro technique. Researchers have developed a device that help to retain the concentration on work by using this technique. This device contain RGB led, LED, small speaker and a push button. It is projecting spectrum colors, when the device in the deactivate mode. After pressing the button device follows that technique and make the user concentration on their work. Researchers have improved the technique from this device by using beep sounds and colour changes for each and every ten minutes of working. When worked time is completed device projecting spectrum colors using RGB led. Therefore, it is like a reward for the user. In the future, team members are focused on monitoring the user and make the device as an IOT device to store and get the reports with working statics.
A Cost Effective Method for Pavement Roughness Computation
(Uva Wellassa University of Sri Lanka, 2019-02) Galagoda, D.Y.; Amarasingha, N.
Pavement Roughness can be expressed as the anomalies in a pavement surface, which will affect the ride quality of a vehicle and the vehicle delay costs, fuel expenditure and tires and other expenses. Roughness can be expressed as International Roughness Index (IRI). Sri Lanka as a developing country lack of fund allocations has become a major issue for government authorities. Therefore, it is very important to have a proper database for proper planning of road networks. As the number of smartphone users is increasing, applications using smartphone sensors are also developing. In this research android applications were used to estimation of road roughness which can be used to collect road condition data cost effectively. Smartphones were attached to the front windshield of a test vehicle horizontally/landscape mode and standing vertically from road. Data collection was done by selecting the "Start/stop sampling" option in 'AndroSensor' and 'Roadroid' android applications by selecting video, photo or non –video mode with the defined route, maintaining 80km/hr speed. The study was done on 20 national roadway sections in Sri Lanka. The statistical analysis showed the percentage of similarity of the results of the measurement of evenness of pavement roads; between two smartphone application is 97.8% and linear regression model (R2= 0.754) based on the relationship between estimated IRI values and existing IRI values evaluated using laser profiler which were obtained from Road Development Authority. Based on result from the experiment, smartphone application can be determined as an equipment that can be used to determine the surface roughness of pavements, as it provides data efficiently and with technical benefits.
A Customizable Virtual Reality Application for Enhancement of Method of Loci
(Uva Wellassa University of Sri Lanka, 2019-02) Perera, R. M.; Priyanga, E.A.I.; De Silva, B. P.; Karunarathne, K.R.R.; Jayarathna, H.M.P.P.; Senanayake, S.H.D.
The ability of memorizing more information can be considered as a measurement of intelligence, especially in the long-term memory. There are several ways to recall the memory such as mental memory tree, memory map, etc. These methods are based on the visualization of facts. The Loci method is one of the best methods which allows quick recall of information through visualization and the use of spatial memory. This method enables to memorize by linking information with various symbols. However, that method has been proven to be effective for centuries, it is still not widely adopted by most of the people due to the complications of understanding the technique. This difficulty of visualizing and usage of this method renders it less useful to a majority. Various studies on enhancement of method of loci have been done through the years. These studies are not providing customizable approach to the end-user. This research also enhances this application by enabling the end-users with the ability of customizing the solution making it applicable in a broad range. The solution introduced in this research is a Virtual Reality based software application developed using Unity3D Game Engine and Google Cardboard Virtual Reality Software Development Kit. It renders a memory palace along with the ability of customization allowing the user to store information along the palace path. The researchers have developed a mobile application which can be run on any device that supports Google Cardboard Virtual Reality. This application has the potential of aiding the user with the ability of memorizing various information with ease. This can be applied in a wide range of fields such as education and psychological treatment. The researchers have planned to further develop the application allowing users to use various mind palace templates according to their preferences.
Data Mining Approach for Landslide Prediction Using Support Vector Machine for Rathnapura District, Sri Lanka
(Uva Wellassa University of Sri Lanka, 2019-02) Madawala, C. N.; Kumara, B.T.G.S.; Indrathilaka, L.
Haphazard development activities on mountain slopes and inadequate attention to construction aspects have led to the increase of landslide and consequently sustaining damages to lives and infrastructure. Nearly 3275 sq.km of area spread over the Rathnapura District, seems to be highly prone to land sliding and mass wasting of 2178 sq.km. Landslides occurred in many regions of Rathnapura district Eheliyagoda, Ayagama, Kalawana, and Nivithigala DS divisions, and nearly 90 deaths have reported according to National Research Building Organization (NBRO) 2017 records. Most landslides or potential failures could be predicted fairly and accurately if proper investigations were performed in time. The primary objective of this study is landslidehazard mapping and risk evaluation to determine the real extent, timing, and severity of landslide processes in Rathnapura district, where such knowledge will provide the most significant benefit to government officials, consulting engineering firms, and the general public in avoiding the landslide hazard or in mitigating the losses. Data mining approach can be used to develop prediction models using existing data. Support Vector Machine (SVM) was selected for this study to possess a strong capability to predict landslides by causative factors, slope, land use, elevation, geology, Soil Materials and triggering factor; rainfall was extracted and applied to the SVM. This research introduces a methodology to produce a more relevant and accurate prediction of the landslide and identify the relationship between the hydrological characteristics, soil characteristics and the landslide vulnerability within the study area. Moreover, an improvement of the hazard monitoring, accuracy of early warning and disaster mitigation was performed. The SVM procedure was found that all of the factors had relatively positive effects on the landslide. Based on these results indicate that SVMs can be useful and practical for landslide susceptibility analysis.
Design and Develop an E-Kanban System Based on Lean Manufacturing Concepts to Optimize Supply Chain Management in Apparel Industry in Sri Lanka.
(Uva Wellassa University of Sri Lanka, 2019-02) Chathurani, V.D.B.; Herath, H. M. A. I. S.; Ranasinghe, R. A. K. H.; Ratnayake, A.M.B; Ellepola, C.S.D.
Apparel sector, a fast-growing industry uses several Lean manufacturing concepts. Kanban, is considered as a popular method which is used to reduce unnecessary costs and wastage of the production process. It is an efficient method of managing supply chain process in apparels. Most of the factories do not utilize the technology and advancement in technology to the fullest potential in material handling although many factories follow manual Kanban and Lean manufacturing concepts. This research was conducted with the intention of designing and developing an e- kanban system. As a results of obtained from a statistical survey, background study and interviews, 87.5% expected to modify the existing system. Accordingly, Kanban system was converted into Electronic kanban system (E-kanban) using Radio-Frequency Identification (RFID) technology. Arduino mega, RFID module and RFID tags were used to design the system. To input data to the system, the C# interface was used. Then the number of Kanban to write data to the RFID tags were automatically calculated. RFID tags use filtering to prevent repetition. When the material is moving with the RFID tags in the line, the overall progress in the production process could be easily viewed. The research considers about the economic aspects as it proposes material saving through reducing paperwork and other printing materials. As this system pre-defines all the optimum things to be done, it is expected to reduce the workload and the stress levels of the employees. E-kanban system is strongly recommended in terms of its environmental friendliness. Finally, the concept was tested for user acceptance by conducting a simple survey and interviews. Each feature of the model was accepted by 86.7% of the respondents. Thus, it can be concluded that the system can be used for predictive analysis on decision making with manual and traditional lean concepts.
Determine a Software Usability Model to Improve User Experience in Generation Z Oriented Software Applications
(Uva Wellassa University of Sri Lanka, 2019-02) Pathirana, W.P.N.H.; Wickramaarachchi, D.N.
User Experience (UX) which focuses on having a deep understanding of users, their needs, their abilities, and their limitations, is one of the most important consideration when developing software applications today. Developing sustainable software application considering the main users of the application is the aim of any software company. Main users of software application are people who belong to workforce. New addition to the workforce is Generation Z and it will continue in the future. Therefore, it is important to pay extra attention to increase usability of software for generation Z who are exposed to digital technologies from their early age which may lead them to have different characteristics, expectations as digital natives than previous generations. Moreover, the literature indicates that they have emotional connection with digital world, more trust in digital sources and high regards for experience and pleasure it gives. In this research generation Z’s software usability issues and their expectation towards software applications were identified through literature review and surveys conducted via questionnaires and interviews with generation Z software users, software developers and UX engineers. To address all these requirements, the features which should be incorporated were proposed as the last step and they were validated by software engineers and user experience engineers. Based on the findings, a new model was determined by identifying specific usability challenges in generation Z to improve software usability. Moreover, this study has come up with feasible technologies, approaches that can be incorporated when developing software applications for generation Z.
Developing a Lead Generation Mechanism to Identify People’s Contact Points Using Web Data Analytics
(Uva Wellassa University of Sri Lanka, 2019-02) Senanayake, J.M.D.; Pathirana, W.P.N.H.
With the popularity of Internet & social media, the volume of data which is being shared through the web has been increased. As a result of that, various paths have been opened to conduct research studies in the area of data science & data mining. Developing a proper mechanism after doing a thorough analysis of web data to identify people’s contact points will be an interesting research study since in this era, people usually tend to keep their digital foot print in the world wide web either by purposely or mistakenly. In this research, a mechanism for lead generation has been introduced by mining & analyzing publicly & freely available web data. Based on some given search criteria, using data extraction through web crawling techniques combining with Named Entity Recognition (NER) algorithms persons’ names were identified at the first stage. Afterwards by performing an in depth search of the web, people’s contact points such as telephone details, email addresses, occupations, interested areas were collected & then analyzed them by applying big data analytics techniques together with data mining to find the high accuracy data. In this process any kind of privacy violation is not happening since this mechanism is only using publicly available data. The final outcome contains very useful data set to many parties specially for financing & marketing industries since they can have an accurate target audience to perform their promotional activities. Not only that but also this research is beneficial for any person since they can have well oriented data regarding the criteria that they want to look at.
Developing Simple and Economical Prototype to Measure the Internal and External Quality Parameters On Poultry Eggs
(Uva Wellassa University of Sri Lanka, 2019-02) Ranchagoda, B.S.; Udayangani, J.T.C.; Sandaruwan, T.H.S.S.; Wickramarathne, S.D.H.S.; Abeyrathne, E.D.N.S.
Egg quality is based on the characters of an egg that affect its acceptability to the consumer. There are several quality parameters used to identify the quality eggs; both internal and external. Internal quality refers to measuring the egg albumin and yolk distribution and yolk color whereas external quality refers to egg size, weight, shape and shell thickness. According to the quantitative and qualitative parameters there are different grading systems available for measuring quality and classify eggs with different groups and price levels. However, still there is no user friendly and economical method to measure the egg yolk color, shape, weight and shell thickness from a single machine. The study attempts to design a prototype to fill this gap. The egg weight is measured by using load cell which is connected to a liquid crystal display and to the computer. When the egg is placed on the cell the value is displayed both on the computer screen and display. The shell thickness is measured using a digital Vernier caliper. The value is displayed once it is placed between the two arms of the Vernier caliper, which is connected to the computer via an Arduino board. The yolk color and egg shape are measured using image processing techniques. In both processes an RGB image is taken and it is converted to a gray scale image. Then a histogram is developed using the pixel count of each point through length and width. Finally, by analyzing the histogram the output is given. The completed prototype was tested and accuracy was measured. Each feature of the model was accepted by more than 60% of accuracy. After all, a survey was done for testing the user acceptance with the participation of selected 20 poultry farmers, and that accuracy level was appreciated by more than 80% of respondents.
Development of Non-Destructive Image Analysis Protocol to Assess the Quality of In-Vitro Propagated Orchid Plantlets
(Uva Wellassa University of Sri Lanka, 2019-02) Weerakkody, E. H.; Kaliyadasa, P.E.; Jayasekara, N. E. C.
In-vitro propagated plants are vulnerable to external changes leading poor growth performances depends on the vigour at hardening stage. The accurate procedure to evaluate in-vitro propagated plants, prior to hardening is vital through incorporating modern technologies such as image processing, to mitigate the drawbacks in visual evaluation which is used at present. Therefore, this study focuses on developing an image analysis protocol to assess the quality of in-vitro propagated Orchid plants. Digital photographs of the culture vessels of Orchid plants which were at the stage of acclimatization were taken inside an illuminated chamber. A visual scoring scale was developed in a scale of 0 to 5 to rank individual plantlets in each vessel. Plant images were isolated from the background and mean red (R), green (G) and blue (B) values were calculated from the segmented images. Through the RGB values, Yellowness, Hue (H), Saturation (S) and Intensity (I) values and thereby Dark Green Colour Index (DGCI) were calculated. Further vegetation indices such as Photosynthetic Vigour Ratio (PVR), Plant Pigment Ratio (PPR), Redness Index (RI), and Green Leaf Index (GLI) were also calculated. The visual evaluation score, DGCI, Yellowness and vegetation indices values were tested to determine the correlation between visual evaluation score and other values obtained using digital photographs. Among all indices, strong correlation (p<0.05) was observed in PVR and RI and then the composite of the values were accordingly regressed with visual evaluation score to select healthy and chlorotic tissues. The high possibility of the use of PVR and RI values composite (PR) to determine the quality of in-viro propagated plantlets, was determined by high R squared value. The function for the quality of the Orchid plants was developed using constant coefficient and coefficient of PR, obtained through regression that could easily apply to select the high quality plantlets.
Distinguish Garnet Mineral from Pulmuddai Beach Sand Using Image Processing Techniques
(Uva Wellassa University of Sri Lanka, 2019-02) Hirosh, D.M.H.; Darshana, J.V.A.; Doratiyawa, H.M.M.S.; Wilson, R.S.I.; Mehendran, Y.; Jaliya, R.G.C.
Beach sand is one of the major minerals producing source in Sri Lanka. Pulmuddai Beach, rich in Ilmenite, Rutile and Zircon and Garnet and it is the largest mineral processing plant in Sri Lanka. It's a great necessity to explore high mineral localities for production. In the industrial level, the percentage of a specific mineral is calculated using a visual inspection through a microscope which is manual and time-consuming. The research introduces an innovative method to distinguish Garnet mineral from sand using image processing techniques. In this study, 1125 visible light RGB (Red, Green, Blue) images and 1125 Infrared (IR) images of beach sand were captured in a controlled light environment. RGB color composite images and IR images were analyzed separately to identify Garnet mineral from the gang and to calculate Garnet percentage. For the machine learning classification purpose, contrast, variance, mean, median, min, max, range, kurtosis, skewness, standard deviation and correlation were extracted from sand grains images. Then RGB, HSV (Hue, Saturation, Value) and RGBIR (Red, Green, Blue and Infrared) color models were used through a machine learning model. The highest accuracy of 63% of separation accuracy was given by the HSV color model. The accuracy could be increased by introducing more images to the machine learning process. The final model was built based on the HSV color model since it has the high accuracy of separation. Then the HSV model subjected to object counting model, area-based counting model and volume based counting model to identify the most suitable method for the percentage calculations. Among these three methods, an object counting model produced the more accuracy results with 57%. Thus, the HSV color model incorporates with object counting model produces the best combination to identify Garnet and calculate its percentage.
E-Business Decision Support System for Online Shopping using MAS with Ontology and JADE Methodology
(Uva Wellassa University of Sri Lanka, 2019-02) Kannan, K.; Raja, K.; Rajakumar, A.; Nizar Banu, P.K.
E-Business systems are playing a crucial role in human’s day to day life. It acts as an interface between the product manufacturer and the end users thereby reducing the time and cost. It also offers a variety of choices in products based on product ratings for quality, pricing, and services. The customers of the e-commerce ecosystem can do everything online and even make the payments. Recommender systems suggest/help the customer for shopping the products based on their interest and their usage. JADE (Java Agent Development Framework) is FIPA (Foundation for Intelligent Physical Agents), that enable automated agents to perform intelligent tasks efficiently. JADE is an open Framework with stable and optimal database agents in the distributed environment. MAS (Multi-Agent System) offers the methodologies for the financial transaction in an EBusiness environment. The recent implementation of MAS with the current Web methodologies (JACK, JADE, etc.) serves as the building blocks for the upcoming ecommerce platforms for taking core decisions and negotiations. With the help of AgentOriented Programming Languages, the functionalities/roles in the use cases are created as Agents. Though this domain is growing exponentially, constructing an ontology for a dedicated purpose is a challenging task to define various concepts and actions. Thus, the e-business ecosystem invites fruitful research solutions for time-constrained applications and secure transactions. In this article, we propose a framework that combines the JADE, ontology and Multi-Agent System based web service composition to increase the efficiency of the system with optimal services. Also, our proposed system aims at providing a secure E-Payment under the availability of financial institutions. The proposed framework is tested under different cases and it is inferred that the system will offer an efficient process for the secured and time-saving E-Commerce transactions.
Effective C-RBAC Framework Based on Role Provisioning for Data Protection in Business Application Systems
(Uva Wellassa University of Sri Lanka, 2019-02) Auxilia, M.; Raja, K.; Kannan, K.
Security plays a key role in any business organization for the purpose of information sharing and privacy. However, there is a lack of privacy and safety among the information. Business data and organizational data are considered to be the highly sensitive data because of the impact that may result in the business process. The employees of any organization are the real assets for their concern and it’s the responsibility of the organization should have a clear vision about the activity of all the employees under legal business development. In this article, new RBAC (Role Based Access Control) framework is developed to navigate the process for a particular employee and their services in any business organization. RBAC framework is especially developed to provide security based on role provisioning during information sharing. AgZKPk (Aggregate Zero Knowledge Proof knowledge) and OCBE (Oblivious Commitment Based Envelope) Protocols are used for role enrollment for RBAC concept (condition policies). In this paper, C-RBAC (Cloud– Role Based Access Control) framework is proposed which can fit in any business organization application. In this C-RBAC, PEP (Policy Enforcement Point) is used to avoid unwanted information sharing with the neighbouring employee or peers. The analysis is done based on the security level for several security algorithms in C-RBAC framework. C-RBAC framework with RSA provide well security based on number of employee with the data handled by the particular employee than the existing RBAC framework with AES (Asymmetric Encryption Standard) and RSA (Rivest–Shamir–Adleman) in terms of number of information they can handle per user. Our analysis revels few threats that arise due to sharing of data and violation in agreements. Also, it is inferred that by adopting our proposed framework, we can avoid data leaks and can protect the data even within the organization.
Exploring the Effectiveness of Search Engine Optimization Tactics for Dynamic Websites in Sri Lankan Context
(Uva Wellassa University of Sri Lanka, 2019-02) Niranjika, L.G.H.U.; Samarasinghe, G.D.
Visibility of a business, both in online and offline are important to grow businesses. In this modernizing digital era, businesses need to understand the significance of web presence in search engines through SEO strategies where it can make better ROI compared to traditional marketing. Therefore, than the international methodical SEO strategies, locally tactics have to optimize singly. The purpose of this study is to explore SEO tactics for dynamic websites in Sri Lankan context & evaluating its effectiveness than international SEO practices in terms of Google.lk. The main objective of this research is to investigate state-of-art SEO practices for dynamic websites to make search engines friendly with regards to rank it in Google search engines and examine which SEO optimization factors affecting the most. Further, the methodology of this study aimed to develop a conceptual framework to experiment the propositions. The mix approach used and survey questionnaire was distributed to 20 SEO experts out of 123 & 100 internet users from 2,400 who were supported to gather the experimental data for www.officestationery.lk. The research proceeded with simple random sampling technique and SPSS and MS Excel were used to analyze the data. Based on the SEO checklist it was implemented over the experimental website of www.officestationery.lk and proved that content optimization from on-page factors and backlinks from off-page factors are the underlying factors to rank in Google.lk. The findings of the literature review and the case study analysis indeed revealed to constructs and established the important factors out of all elements. This also revealed that there is no sense of keep relying on outdated SEO tactics as Meta tags or deep technical factors to rank in search engines. Therefore, for any dynamic website these primitive findings and recommendation approach are significantly important to be visible in Google.lk.
A Game-Based Driving Learning System for Sri Lankan Driving Learners to Enrich the Awareness of Road Rules
(Uva Wellassa University of Sri Lanka, 2019-02) Sapumohotti, C.H.V.; Sampath, A.G.A.; Sampath, J.D.B.; Wimaladharma, S.T.C.I.
Traffic safety is becoming an important problem in most of the countries. Based on investigations it has been identified that the unawareness of road rules, lack of practice of sudden reactions in hazardous situations are the major causes for accidents. Though there are many driving simulators available, most of them have not addressed the road rules and hazardous incidences that a driver must be aware. Also they are lacking of a proper evaluation of the driving skills and awareness of the driver. Primary objective of the system is to provide a driving learning platform for the learners, trainers as well as evaluators to overcome the existing challenges, which has mainly focused on creating a virtual environment to facilitate the training and testing process in the local context and main areas of violating road rules and regulations by drivers are taken into account. In order to provide a realistic road environment, virtual environments are modeled based on different criteria. Artificial Intelligence techniques like non-player characters and objects, are employed. Through that, the responsiveness and intelligent behavior of the simulator has been improved. One of the major components of the simulator is the driver evaluation: a point based method defined upon the rules, road conditions and driving ethics established in the country. Further, the virtual environment provides all the road conditions available, countryside as well as the urban traffic conditions with different weather conditions. The effectiveness of the developed simulator is measured by allowing a selected group of learners to use the simulator for a specific period and assess their driving skills in a real driving environment. It can be concluded that training the learners in a virtual environment that similar to the real environment with a proper assessment of their driving skills, awareness of the rules and road signs, and the driving ethics will solve most of the problems we face today.
A Genetic Algorithm Approach to the Integrated InventoryDistribution Problem of a Retail Supply Chain of Perishables
(Uva Wellassa University of Sri Lanka, 2019-02) Sandaruwani, G.P.M.; Rupasinghe, T.D.
Managing retail supply chains of perishables is significantly complex due to the limited shelf life and the higher level of demand uncertainty at retail level. After conducting a comprehensive literature review, it is concluded that the consumer buying behavior for perishables at retail level is highly dependent on the freshness and the availability of the products on the display. The most highlighted fact in the literature about perishables in retailing is the importance of achieving a better service level at the lowest possible cost. Thus, the objective of the study was made threefold. Firstly, we formulate an integrated inventory – distribution problem of a three echelon retail supply chain as a Mixed Integer Non-linear programming model. The novelty of the proposed model is that we address demand uncertainty, freshness dependency of demand, display availability dependency of demand and the perishability simultaneously in the same formulation. Furthermore, we propose separate formulations for different issuing policies at both retail and distribution center levels. Secondly, the developed models are validated by solving small size instances of the problem using LINGO 17.0 Optimization software. Most of the real world scenarios involve multi – retailers, multi – distributors, multi – products with large instances which makes the proposed model NP-hard. Therefore, a genetic algorithm which achieves high quality near-optimal solutions in a reasonable time, is proposed to solve larger instances of the problem finally. The authors have elaborated the GA with numerical examples and compared the results. The outcome of the study proposes the GA approach as the best solution to reduce the total cost while providing a higher service level.
Identification of Anomalous Clients’ Request by Analyzing Server Log File using Apache Hadoop Framework and Tableau
(Uva Wellassa University of Sri Lanka, 2019-02) Bavathuja, V.; Raahini, S.; Ramashini, M.; Wimaladharma, S.T.C.I.
Information systems provide information about its state and operation in the form of log records. These records are composed of log entries containing information related to a specific event, which can be related to security. Potential security breaches can be revealed by analyzing log files and looking for anomalies that occurred at a certain time during the device operation. Log files from proxy server of Uva Wellassa University of Sri Lanka will be analyzed using Hadoop Framework and Apache Pig in order to identify anomalous clients’ Request. Anomalous clients’ request identification refers to the problem of finding pattern in data that do not conform to expected behavior. These nonconforming patterns are often referred to as anomalies, outliers or exceptions in different application domains. Log files of a proxy server are created and maintained by the server itself and analyzing theses files will offer a valuable insight into server usage while they can be used in various applications, such as detecting intrusions on the web. The log files will be stored in Hadoop Distributed File System. Data preprocessing and analyzation will be done using Apache Pig: a platform for analyzing large data sets. The analyzed data will be reported through Tableau dashboard. According to the research study, the total number of records after cleaning is 817,426 and 856 unique IP addresses have accessed the proxy server from the period of Thursday, 26 April 2018 01:14:48.138 to the period of Friday, 27 April 2018 10:31:23.834. Several findings including the total visits and bandwidth were found and displayed using graph and charts. This information along with other findings can be applied to find solutions for many legitimate problems such as, user/customer behavior analysis, etc.

Browse

Browsing International Research Conference of UWU-2019 by Subject "Computer Science"

Results Per Page

Sort Options