Science
Permanent URI for this communityhttp://repository.kln.ac.lk/handle/123456789/1
Browse
6 results
Search Results
Item Ridesharing android application for traffic control(2018) Yeshani, R. B.From past few years, usage of personal vehicles was highly increased and reported heavy traffic densities in urban areas. Most of the vehicles that result to increase of traffic are personal vehicles used by just one or two people inside. Ridesharing concept can therefore be used to reduce traffic in urban transportation system. Vehicle drivers can offer their free seats to passengers who want to travel in similar directions. Ridesharing concept is very effective to reduce travelling expenses, road traffic, and fuel consumption. Though the traditional ridesharing systems are suitable for long-distance travel, in most of the time, they are not flexible for short distance rides. Map route is represented as set of road segments and junctions. Driver and rider routes matching is performed using these junctions and road segment details. Ridesharing has to find matching driver and rider routes by compare each junction, road segment. Route matching for a road routes is complex and computational intensive task by comparing each node details with every other node in routes. This research applies graph theories and algorithms to simplify algorithmic complexities, reduce order of computations of the problem. Road network can be models as a graph. Open Street Maps (OSM) map data is freely available. The road network is populated into the graph database using the road details extracted from OSM map. Then all drivers’ and riders’ routes are populated into the graph database. Most matching route is the route pair with highest number of identical graph nodes and road segments. Graph database systems has inbuilt graph algorithm related quires to optimize the performance. Arangodb is used as graph database system. A prototype system has been built for Android Mobile phones. Android application communicates to server application runs on Google cloud, through Firebase database, which handle real-time usage and user connection management. Server application runs matching process, finds out the best matching ride according to the passenger’s request. This system provides more accurate, fast, and more efficient ridesharing mobile application.Item 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.Item Machine learning based model for Android malware analysis and detection.(International Research Symposium on Pure and Applied Sciences, 2017 Faculty of Science, University of Kelaniya, Sri Lanka., 2017) Kavneth, G. A. S.; Jayalal, S.Rapid advancement of technology has enabled smartphones to become extremely powerful. They are capable of attracting a considerable amount of users with new features provided by mobile device operating systems such as Android and iOS. Android extended its lead by capturing 86 percent of the total market in 2017, and became the most popular mobile operating system. The Android operating system, which is found on a wide range of devices is owned by Google and powered by the Linux kernel. It is an open source operating system that enables mobile application developers to access unlocked hardware and develop new apps as they wish. However, this huge demand and freedom has made the hackers and cybercriminals more curious to generate malicious apps towards the Android operating system. They constantly target the security vulnerabilities in the operating system to gain access within the system. Even though, Google provides a primary set of security services, there are possibilities for potentially harmful applications in the Google Play store and other third party application stores. Thus, research on effective and efficient mobile threat analysis becomes an emerging and important topic in cybersecurity research area. Many researchers proposed various security analysis and evaluation strategies such as static analysis and dynamic analysis. In this research, we propose a hybrid approach, which aggregates the static and dynamic analysis for detecting security threats and attacks by Android malware application. This approach has two phases. First phase is the static analysis for applications, which will analyze the mobile application without execution. This focuses on extracting app APK file and examining permission requests made by Android apps that have declared in AndroidManifest.xml, as a means for detecting malwares. Because, in most of cases extra permissions granted by applications will allow the attacker to exploit the device. As the next phase, we perform dynamic analysis for mobile application. This phase focuses on runtime data obtained from the applications such as CPU, scheduler information from every running application, network calls, sensor data and so forth. For both phases, we have used supervised, machine learning based algorithms to train models and recognize malwares. In the first phase, potentially harmful applications can be identified as well as in the proposed hybrid mechanism, which is a combination of both phases. Data that was collected by several cybersecurity research centers were used for the evaluation of the proposed hybrid approach and both real-life malware and benign app data demonstrated a good detection performance with high scalability. The initial findings have been more accurate in identifying Android malwares rather than separating those two static and dynamic behaviors.Item “MySight” – A Mobile based Solution for the blind community(Faculty of Science, University of Kelaniya, Sri Lanka, 2016) Nimalarathna, L.B.O.D.; Senanayake, S.H.D.Reading is an ultimate goal of human beings which is unfortunately not available for people affected by blindness. They can only read things which are in Braille system. But we all know that every book has not been converted to Braille system. The main problem of blind people for studying is that they cannot read and learn from textbooks. Therefore, it would be extremely useful to find a method, such that a blind person could read newspapers, textbooks, bills, etc. without the Braille system. Android platform can be used to enable this opportunity for blind people for the purpose of reading out loud any printed document or anything written using a standard font. This research is completely focused on finding a way which could let blind people be exposed to a new kind of reading. The main objective of this research was to develop an android application which could identify words and various kinds of symbols written using a standard font in a given document, and then convert them to an audible format such that a blind person could understand. It will be effective for a blind person by providing voice notifications and smart touch techniques. The first step was to find an appropriate and efficient Optical Character Recognition (OCR) technique which compatible with the Android platform. In order to fulfill that requirement, the Tesseract OCR library was used. After lying dormant for more than 10 years, Tesseract is now behind the leading commercial engines because of its accuracy. The next step was interface designing. In this application, there are two main interfaces. One is for capturing the text, and another one is for displaying the detected text. There are several operations that can be performed once it detects the text, such as, ‘read again’ function. Then, the OCR implementation for the Android platform has been successfully completed. For the future improvements, the application should be enhanced to guide the blind person to capture the image of the paper or the page of a book. For that, the OpenCV library can be used for paper detection and the smart voice commands for giving instructions to the blind.Item Simultaneous control of multiple line-loads each connected separately in series with a designed unit (Control using Radio Frequency and a Mobile device)(2016) Cooray, B.N.P.; Perera, W.S.K.; Kalingamudali, S.R.D.A unit which can be connected separately in series with each load to control multiple line-loads simultaneously using Radio Frequency (RF) and a mobile device has been developed during this study. Series connected remotely controllable regulators are not widely available commercially and the few available do not have the facility to control the multiple line loads using a mobile application along with a RF remote controller and also they are very expensive and even require an alternative wiring system. The designed regulator provides the convenience of controlling the current flow through appliances connected to a single line power supply. A triac is used to control the power supplied to the load, since it can control the current flow in both halves of an AC current. The gate terminal is triggered by using a diac. A Switch Mode Power Supply, powers the active components of the regulator using the voltage drop across the triac. The Bluetooth (HC-06) and RF (315 MHz RF receiver) modules are programmed to receive inputs from the user to switch ON/OFF or control the voltage supplied to appliances such as fans and light bulbs. The Graphical User Interface enables the user to control the appliances easily and much faster than in normal usage of mechanical switches. The timer which allows the user to define time intervals for predefined output levels, can set desired levels of outputs for the appliances. This feature is not currently available in normal regulators. The suggested method facilitate simultaneous use of RF and the mobile devices as well as the ability to control several appliances with a single unit enabling energy conservation and ease of use. The cost of designing the unit with discrete components being less than US$ 17, it can be concluded that the model is cost effective since this method suggests two modes of control of the appliances along with timer settings. [1-9].Item Learning tool on data structures and algorithms using Android(Department of Zoology and Environmental Management, University of Kelaniya, Kelaniya, Sri Lanka., 2016) Sajeetha, T.Android is now the most used mobile operating system in the world. Learning by means of mobile phones is becoming a new approach towards education, and it is unique in its own way and offers learning opportunities anywhere and anytime. An effort is made to enhance the learning opportunity and attractive learning method. The learning tool for Data structure and Algorithm, DS Teacher, is designed to help the learners to get a clear picture about this subject area. This DS Teacher includes Data structures (eg: stack, queue, etc..) with animated examples, Algorithms and C++ program code. This tool helps the students to learn in an effective way. A study was undertaken to investigate the impact of such an environment enabled by android platform on the learning process among second year undergraduates of Eastern University, Sri Lanka. Questionnaire was given to seventy-five students to check the effectiveness of the system. Excel pie chart is used to analyze the effectiveness. Findings showed that the respondents were very receptive to the interactivity, accessibility, and convenience of the system. Overall, the mobile learning system DS Teacher can be utilized as an inexpensive tool but complements undergraduates’ learning process.