Research Papers - Dept of Computer Systems Engineering

Permanent URI for this collection https://rda.sliit.lk/handle/123456789/1253

Browse

Now showing 1 - 20 of 55

Embargo
An adaptive based approach to improve the stability of two wheel mobile manipulator
(IEEE, 2007-11-05) Abeygunawardhana, P. K. W; Toshiyuki, M
Mobile manipulator with two wheel will play vital role when robot working with limited space. On the other hand, improvement of two wheel vehicle will explore the technology to improve welfare and industrial robots like wheelchair robot. Two wheeled mobile manipulator has been already implemented using inverted pendulum control. But system error is relatively large. Although the stability improvement using passivity theory was reported, it was not succeed with trajectory motion. Therefore, performance improvement which will be achieved through changing the PD controller gains is proposed in this paper. Disturbance observer has been employed to cancel the disturbances.
Embargo
An adaptive routing algorithm for Cognitive Packet Network infrastructure based on neural networks
(IEEE, 2011-08-16) Madubashitha, D. K. D; Wijesinghe, W. M. S. S; Kamaladiwela, K. A. S. R; Ranaweera, M. G. P; Wijekoon, J; Abeygunawardhana, P. K. W
This paper examines the possibility of introducing an intelligent routing protocol to the Internet, based on the Cognitive Packet Network (CPN) architecture with respect to the Quality of Service (QoS) delivered to the end users. In the present with increasing populations of countries it is clear that present infrastructure does not hold the sufficient capacity to deliver the expected level of service to the end users. Since there is an eminent need for a solution for improving the QoS in the Internet, this research focuses to provide a new network architecture which would improve the QoS, provide reliable and efficient service which can fulfill the ever growing Internet usage demand. This is achieved through a new network architecture known as CPN which is based on the basis of providing the best and user desired QoS. The main underlying technology behind the CPN will be a neural network. The neural network will be learning the changes in the network and adapt to the situation through the knowledge gathered. The packets will collectively learn about the network thus the load on the routers will be minimized. This mechanism completely replaces the need of a routing table thus making routing far more efficient when comparing to current routing protocols like Open Shortest Path First (OSPF). Final outcome of the research is coming to the conclusion that the future of the Internet is with the neural network based intelligent, dynamically adapting and learning CPN infrastructure instead of current packet switched network.
Embargo
An adaptive routing algorithm for Cognitive Packet Network infrastructure based on neural networks
(IEEE, 2011-08-16) Madubashitha, D. K. D; Wijesinghe, W. M. S. S; Kamaladiwela, K. A. S. R; Ranaweera, M. G. P; Wijekoon, J; Abeygunawardhana, P. K. W
This paper examines the possibility of introducing an intelligent routing protocol to the Internet, based on the Cognitive Packet Network (CPN) architecture with respect to the Quality of Service (QoS) delivered to the end users. In the present with increasing populations of countries it is clear that present infrastructure does not hold the sufficient capacity to deliver the expected level of service to the end users. Since there is an eminent need for a solution for improving the QoS in the Internet, this research focuses to provide a new network architecture which would improve the QoS, provide reliable and efficient service which can fulfill the ever growing Internet usage demand. This is achieved through a new network architecture known as CPN which is based on the basis of providing the best and user desired QoS. The main underlying technology behind the CPN will be a neural network. The neural network will be learning the changes in the network and adapt to the situation through the knowledge gathered. The packets will collectively learn about the network thus the load on the routers will be minimized. This mechanism completely replaces the need of a routing table thus making routing far more efficient when comparing to current routing protocols like Open Shortest Path First (OSPF). Final outcome of the research is coming to the conclusion that the future of the Internet is with the neural network based intelligent, dynamically adapting and learning CPN infrastructure instead of current packet switched network.
Embargo
Ai based greenhouse farming support system with robotic monitoring
(IEEE, 2020-11-16) Fernando, S; Nethmi, R; Silva, A; Perera, A; De Silva, R; Abeygunawardhana, P. K. W
Greenhouses plays a major role in today's agriculture since farmers can grow plants under controlled climatic conditions and can optimize production. The greenhouses are usually built in areas where the climatic conditions for the growth of plants are not optimal so requires some artificial setups to bring about productivity. Automating process of a greenhouse requires monitoring and controlling of the climatic parameters. This paper is an attempt to minimize the cost of maintaining greenhouse environments using new technologies. The end goal of this research an automated system to optimally monitor and control the environmental factors inside greenhouse by monitoring temperature, soil moisture, humidity and pH through a cloud connected mobile robot which can detect unhealthy plants using image processing and machine learning. The mobile robot navigates through a predefined map of greenhouse. Database server has created to store gathered real-time data. And the necessary accurate data represent by using proper application for analyzing.
Embargo
Analysis of Searching Algorithms in Solving Modern Engineering Problems
(IEEE, 2021-08-11) Rathnayake, B. R. M. S. R. B.; Marzuk, H; Senadheera, R. I. A; Vijeyakumar, S; Abeygunawardhana, P. K. W
Many current engineering problems have been solved using artificial intelligence search algorithms. To conduct this research, we selected certain key algorithms that have served as the foundation for many other algorithms present today. This article exhibits and discusses the practical applications of A*, Breadth-First Search, Greedy, and Depth-First Search algorithms. We looked at several recent research publications on these algorithms (for example, maze solver robots, the eight-puzzle problem, medication prediction, and travel advice) and critically examined their benefits, drawbacks, and challenges. We’ve also done some experimentation with a Python application to see how well these algorithms perform.
Embargo
Augmented Reality Based Smart Supermarket System with Indoor Navigation using Beacon Technology (Easy Shopping Android Mobile App)
(IEEE, 2018-12-21) Jayananda, P. V. K; Seneviratne, D. H. D; Abeygunawardhana, P. K. W; Dodampege, L. N; Lakshani, A. M. B
Augmented reality (AR) applications have recently become popular on modern smartphones. We explore the effectiveness of this mobile AR technology in the context of grocery shopping, in particular as a means to assist shoppers in navigating to the desired products and making healthier and beneficial decisions as they decide which grocery products to buy and even do shopping while staying at home. A supermarket is a customer base premises; means the customer is the one who decides what he is going to purchase and the customer satisfaction may be crucial. In-house shopping in supermarkets has earned popularity among majority of the customers and at the same time most of the customers looking for remote shopping which they can do get the shopping experience just sitting at home. Shopping malls has combined with the IT industry and create more innovative and creative apps, which are beneficial for both the customer and seller parties. So, the main objective of this work is to design a fully functional mobile application that has an innovative positioning and navigation system using AR core technology and Augmented Reality. The other major parts of this application are customer base shopping list handling, personalized recommendations by object detection using AR and remote shopping. Overall the scope of study involves research on AR core technology, Augmented Reality and other additional technologies. The idea of this work can be broadly applied to mobile devices such as mobile phones as an added physical shopping mall functionality using above mention technologies. The proposed Easy Shopping android based mobile app has been tested at the KEELS supermarket in Sri Lanka.
Embargo
Automated Smart Checkup Portal Network System to Check the Vision and Hearing of the Patients
(IEEE, 2019-12-05) Dias, A. A. T. K; Vithusha, J; Liyadipita, L. A. M. T. J; Abeygunawardhana, P. K. W
The human eye and ear are impressive systems in the body. Vision and Hearing are the main functions of those organs. We should regularly check our vision and hearing, It's the most reliable ways to maintain good vision and hearing. Not only that, every patient must keep a medical history and previous checkup records, those related to vision and hearing and those results should be real-time processed. Therefore, we have built an Automated Centralized Smart EE (eye and ear) Checkup Portal Network System. We have designed and developed an automated centralized vision and hearing checkup rooms network, Automated centralized live traffic indicating cloud-based web application to establish in every hospital.
Embargo
Casterless Wheelchair Robot Using Inverted Pendulum Control
(IEEE, 2006-08-08) Abeygunawardhana, P. K. W; Toshiyuki, M
Power assist wheelchair robot is playing a key role in the field of medical welfare robotics. But, to a certain extend, there is a setback in development due to presence of caster wheels. Hence, this paper proposes a casterless wheelchair and its control on a straight line path. That is, straight line driving of two wheel power assist wheelchair robot was proposed in this paper while keeping stability of wheelchair body itself. Balancing of wheelchair body is proposed to achieve by controlling the inverted pendulum mounted on the wheelchair. Control equations of the system are derived using Lagrange equation of motion. Two separate controllers are designed for two wheels. In addition to these two controllers, there is another controller for pendulum. Body controller is designed combining pendulum controller and wheel controller. Disturbance observer is used to cancel disturbance effects. Simulation was carried out to prove the applicability of the proposed system
Embargo
Cbeyond: Mathematical Learning Tool for Primary Level Visual Impaired Students
(IEEE, 2018-08-08) Chinthaka, W; Abeygunawardhana, P. K. W
Blindness or visual impairment is a common obstacle for the development of a society. They paradigm, feel and sense the world divergently so that, they have to face so many challenges in day today life. One of the most dreadful challenges arises when considering about the learning curriculum of a blind kid, specially a stream like mathematics. Therefore, when they grow up they try to build their careers in areas where the use of mathematics is minimal. This is because learning or practicing mathematics demands rich in visual abilities and the world is still lack of providing them enough facilities and proper technical solutions to make their learning curriculum easier. They are using Braille system to represent numbers and mathematical calculations at present. Before going to the braille system, the kids need to get used to the specific patterns for the numbers and mathematical operators, so that they are using a special wooden number board that has nine star shaped blocks carved on it and an object called tiff. It is an extremely tedious task for a young blind kid to perform number identification, therefore a teacher should always be there for them. A primary level blind kid normally takes up to three years just to identify the pattern of numbers from zero to nine and four basic mathematical operators. Even more time consume for the Mathematical calculations. In this paper, an innovative tool is introduced which will enable blind kids to learn and practice mathematics like sighted students.
Embargo
Code Vulnerability Identification and Code Improvement using Advanced Machine Learning
(IEEE, 2019-12-05) Ruggahakotuwa, L; Rupasinghe, L; Abeygunawardhana, P. K. W
Cyber-attacks are fairly mundane. The misconfigurations of the source code can result in security vulnerabilities that potentially encourage the attackers to exploit them and compromise the system. This paper aims to discover various mechanisms of automating the detection and correction of vulnerabilities in source code. Usage of static and dynamic analysis, various machine learning, deep learning, and neural network techniques will enhance the automation of detecting and correcting processes. This paper systematically presents the various methods and research efforts of detecting vulnerabilities in the source code, starting with what is a software vulnerability and what kind of exploitation, existing vulnerability detection methods, correction methods and efforts of best researches in the world relevant to the research area. A plugin will be developed which is capable of intelligently and efficiently detecting the vulnerable source code segment and correcting the source code accurately in the development stage.
Embargo
Code Vulnerability Identification and Code Improvement using Advanced Machine Learning
(IEEE, 2019-12-05) Ruggahakotuwa, L; Rupasinghe, L; Abeygunawardhana, P. K. W
Cyber-attacks are fairly mundane. The misconfigurations of the source code can result in security vulnerabilities that potentially encourage the attackers to exploit them and compromise the system. This paper aims to discover various mechanisms of automating the detection and correction of vulnerabilities in source code. Usage of static and dynamic analysis, various machine learning, deep learning, and neural network techniques will enhance the automation of detecting and correcting processes. This paper systematically presents the various methods and research efforts of detecting vulnerabilities in the source code, starting with what is a software vulnerability and what kind of exploitation, existing vulnerability detection methods, correction methods and efforts of best researches in the world relevant to the research area. A plugin will be developed which is capable of intelligently and efficiently detecting the vulnerable source code segment and correcting the source code accurately in the development stage.
Embargo
Compact optical system for imaging type two-dimensional spectroscopic tomography
(IEEE, 2013-12-17) Abeygunawardhana, P. K. W; Nakada, S; Suzuki, S; Nishiyama, A; Ishimaru, I
Spectroscopic measurement is being widely used for non-invasive blood sugar measurement in recent past. Imaging type two-dimensional spectroscopic tomography has been designed using wave front division interferometer. Variable phase filter, which has fixed mirror and movable mirror, has been used to introduce the phase shift between rays. Capability of measuring biogenic substances using this method has been proved. For the quantitative analysis with high accuracy, the correction of the background such as the light-source fluctuation and the phase-shift uncertainty is inevitable issue. Background noises and vibrations in test bed are part of the causes that could results such errors. This paper proposes a new closed optical system to improve the system performance. One-shot type spectroscopic tomography and Smooth Impact Drive Mechanism are used here.
Open Access
Control of two wheel mobile manipulator on a rough terrain using reaction torque observer feedback
(Library of Science, 2010-04-01) Abeygunawardhana, P. K. W; Murakami, T
The mobile manipulator has the potential to become an efficient industrial robot due to its mobility and dexterity. Moreover, it has expanded the operational area of the mobile manipulator due to its ability to work in a limited space. However, adaptability to unknown environments has still not been developed to date. Therefore, adaptation of the mobile manipulator for unknown environments especially for rough/irregular terrain is discussed in this paper. Information about the environment, a key factor when aiming for compliance with an unknown and/or unstructured environment, was collected using a reaction torque observer. In order to adapt to the environment, compliance control was applied to the mobile manipulator. In this paper, we present a novel control strategy we have developed that can deal with unknown environments through the effective use of inverted pendulum control. Simulation and experiments were carried out to ensure the validity of the proposed method. The method could be confirmed as effective according to the results obtained.
Embargo
Controlling dye coverage instead of addition of organic acid to reduce dye aggregation in dye-sensitized solar cells
(Elsevier, 2020-05-15) Feng, Q; Sewvandi, G. A; Kakimoto, M; Chen, C; Hu, D; Abeygunawardhana, P. K. W
The photo-generated electron injection yield of dye-sensitized solar cells (DSSCs) based on donor-acceptor conjugated dyes is lowered by the aggregation of surface adsorbed organic dyes that pose a low-photoenergy conversion efficiency. Coadsorbates used to prevent the aggregation cause to decompose or detach the dye molecules anchored on the TiO2 surface. In this study, the effect of coadsorption of organic acid and organic dyes on photovoltaic performances was systematically scrutinized by means of adsorption isotherms and photovoltaic measurements. Our laboratory synthesized {0 1 0}-faceted TiO2 (PA TiO2) and P25 TiO2 were used as mesoporous nanocrystals, D149 organic dye was used as a sensitizer and cheno-deoxycholic acid, CDA, was used as a coadsorbate. The coadsorption of CDA reduces the adsorption parameters, maximum adsorption density (Qm) and adsorption constant (Kad), and the reduction depended on the type of TiO2. The photovoltaic performance indicates that the D149 dye has the best dye coverage at around 70% for the effective photovoltaic energy conversion. The coadsorption of CDA increased the photovoltaic performances of DSSCs based on P25 TiO2 but, CDA decreased the photovoltaic performances of DSSCs based on PA TiO2 due to the reduction of the dye coverage below 70%. The results suggest that the coadsorption of organic acids is not necessary if the particular TiO2 can maintain its coverage at the best coverage. Thus, the requirement of coadsorbates to reduce the dye aggregation depends on the type of TiO2 used in DSSCs.
Embargo
Design and implementation of an autonomous indoor surveillance robot based on raspberry pi
(IEEE, 2019-12-05) Dharmasena, T; Abeygunawardhana, P. K. W
In recent years robotics has influenced many fields including the security and surveillance domain. Due to convenience and flexibility more and more security robots tend to be deployed in place of humans for routine activities such as area sweeps. While there are many kinds of research have been done regarding this concern, many of the solutions cost more due to their implementation complexity while low-cost implementations are only capable of doing simple activities such as following given local coordinates. This paper describes an autonomous surveillance robot that is being developed while keeping the development costs as low as possible and is capable of performing routine patrols autonomously in indoor environments and detect anomalies around it such as temperature fluctuations, unauthorized personals and report them back to a central computer. This robot can be controlled remotely by security personals to facilitate manual inspections. Due to the development architecture of the robot, more software-based features can be added easily.
Embargo
Digital Preservation and Noise Reduction using Machine Learning
(IEEE, 2021-12-09) Aravinda, K. P; Sandeepa, K. G. H; Sedara, V. V; Chamodya, A. K. Y. L; Dharmasena, T; Abeygunawardhana, P. K. W
This paper proposes a digital preservation solution for Sinhala audios to conserve those as documents with noise reduction. The solution has implemented multiple noise reduction techniques as a pre-processing step to remove unwanted internal and external noises. A two-step, two-way noise reduction process is applied to produce clean audios based on Deep Convolutional Neural Network (DCNN) and adaptive filter-based techniques. This approach implements two separate noise reduction models for internal and external noises. After that, the speech recognition decoder recognizes the speech and converts it to a Unicode document by acoustic, language, and pronunciation models using extracted audio features from the denoised audio. Further, noise reduction models are decoupled from the preservation solution and exposed as a sub solution for multilingualism noise reduction, supporting English and Sinhala audios.
Embargo
Drown Prevention and Flood prediction using smart embedded devices
(IEEE, 2019-12-05) Samarasinghe, D; De Silva, P. M; Mudalige, T. U; Gamage, M. K. I; Abeygunawardhana, P. K. W
Drowning and Flood becomes major negative impact to the mankind and infrastructure. Drowning is caused by the when person go into deeper areas or else due to a person's health condition. Flood is a natural disaster commonly caused by the run of rivers due to excessively highly rainy season or due to environment effect or global warming effect. Hence IoT with sensor technology support us to efficiently cover up this impact for mankind. This research support for each mankind to survive from the drowning threat and this may help for people to survive from the natural disaster like flooding. This research presents two IoT Devices consisting with sensors and monitoring system to determine the flood level, the user condition and water level when user in the water. Then generating alert via the mobile application to notify the user. Machine learning algorithms were implemented to perform the level classification.
Embargo
Effective use of network device state information for network path selection
(IEEE, 2017-01-27) Abeygunawardhana, P. K. W; Wijekoon, J. L
Network path selection defines the methodology of selecting the best routes and forwarding traffic in a network service provider (NSP). NSPs use routing protocols that are optimized for a single arbitrary metric (i.e., administrative weight), which is commonly calculated according to the link state information, to select network paths. Despite the advantages, link-state protocols lack the ability to select network paths by considering the states of network devices such as the effect of routers for network path selection. Apparently, studying possible techniques for selecting network paths based on the state information of network devices, e.g., routers, has become obligatory. This paper hypothesis to calculate a composite path selection metric by employing the state information of network devices; the proposed method selects the network paths based on the cumulative packet traveling time. By simulating proposed method using an ISP topology, the proposed method is examined for the effectiveness of using network device state information for network path selection.
Embargo
Effective use of network device state information for network path selection
(IEEE, 2017-01-27) Wijekoon, J; Abeygunawardhana, P. K. W
Network path selection defines the methodology of selecting the best routes and forwarding traffic in a network service provider (NSP). NSPs use routing protocols that are optimized for a single arbitrary metric (i.e., administrative weight), which is commonly calculated according to the link state information, to select network paths. Despite the advantages, link-state protocols lack the ability to select network paths by considering the states of network devices such as the effect of routers for network path selection. Apparently, studying possible techniques for selecting network paths based on the state information of network devices, e.g., routers, has become obligatory. This paper hypothesis to calculate a composite path selection metric by employing the state information of network devices; the proposed method selects the network paths based on the cumulative packet traveling time. By simulating proposed method using an ISP topology, the proposed method is examined for the effectiveness of using network device state information for network path selection.
Embargo
An empirical study on slow and limited adoption of internet banking by Sri Lankan customers
(IEEE, 2011-08-16) Weerasekara, S; Abeygunawardhana, P. K. W
Usage of internet is rapidly increasing in Sri Lanka. However, usage of internet banking is very slow compared to increase of internet users. This study will focus on four main possible areas which may effect to slow adaptation of Internet Banking as Awareness & Knowledge of Internet Banking, Perceived Characteristics of Internet Banking, Consumer Resistance to Change, Legal Support and IS Security. Based on the data gathered, these 4 conditions are tested using statically analysis method.