Browsing by Author "Jayawardena, C"

Now showing 1 - 20 of 62

Embargo
Adding Common Sense to Robots by Completing the Incomplete Natural Language Instructions
(IEEE, 2022-07-18) De Silva, G. W. M. H. P.; Rajapaksha, S; Jayawardena, C
This system is developed to identify and complete the human’s instructions or incomplete sentences given by a user as a command. It would facilitate the interaction between the human and mobile service robots. However, when humans give the instruction, there can be incompleteness or else missing the information related to the environment. That is because humans, generally based on common sense, depending on the environment. Then the human brain can complete all those incomplete sentences by using common sense knowledge. This paper itself introduced a model of a service robot who can compete with the given incomplete instructions, display the related sentences or words, and finally move to the related objects in the environment. First, it will consider and identify the objects in the environment and then consider the given natural language instruction by humans. As a first step of the approach, complete the incomplete sentences. Those sentences are coming as natural language instructions. By parsing it into as the frame can identify the related words by using the created model or can call as language model and here used some identify words from the human common sense also, then the service robot will learn about the commonsense knowledge automatically from the parsing sentences as a speaker. Considering all the parsing sentences, it calculates and measures the accuracy of this service robot model. Simply this is a commonsense reasoning model. The result of the provided solution can enable the robot model that works in a ROS environment to identify and automatically perform the tasks.
Embargo
An alternative approach for developing socially assistive robots
(IEEE, 2014-08-12) Sarrafzadeh, A; Jayawardena, C
This paper presents the design of the socially as-sistive companion robotic wheelchair named RoboChair. Unlike in most current companion robotics projects, the approach of RoboChair is not to build a completely new robotic device. Instead, the focus of the RoboChair project is to convert an already useful device (i.e. wheelchair) to a socially assistive companion robot. The authors argue that there are number of advantages in this approach. The proposed robotic chair is a mobile robot that can carry a person. It is equipped with several measuring devices for measuring vital signs. The robot chair is capable of engaging users with interactive dialogs through a touch screen and by using human-robot interaction techniques. It has a scalable modular software architecture so that adding new hardware and software modules is straightforward. The software framework is based on Robot Operating System (ROS) open source robotic middleware.
Embargo
Analysis of Cyber-Attack in Big Data IoT and Cyber-Physical Systems-A Technical Approach to Cybersecurity Modeling
(IEEE, 2019-03-29) Sen, S; Jayawardena, C
The Internet of Things (IoT) and Cyber-Physical Systems (CPS) are generating widespread data. Their success depends on a well secured infrastructure, which necessitates providing a robust infrastructure by securing the CPS and IoT system setup against the possibility of cyberattacks. With an increased utilization of CPS as well as widespread implementation of IoT with low power wireless sensors, the security vulnerability is growing, and increasing the possibility of cyberattacks. This paper has discussed models of how different categories of CPS can be stabilized in the event of a disaster, and analyzed how possible cyberattacks can be mitigated by taking a technical approach to model the cybersecurity.
Embargo
Analysis of network techniques and cybersecurity for improving performance of big data IoT and cyber-physical communication internetwork
(IEEE, 2019-02-13) Sen, S; Jayawardena, C
The Internet of Things (IoT) and Cyber-Physical Systems (CPS), are generating wide spread data. The success of these trio depends on a well performed cyber-communication infrastructure. This necessitates improving the performance of the cyber-communication internetwork; this performance improvement includes optimization of network techniques as well as the security of the cyber-network. Internet infrastructure has been upgraded to higher level ever than before, where we are enjoying technologies like fibre, 10-gig ethernet and even 100-gig ethernet, but there is no guarantee of communication in the cyber space, internet still providing packet delivery on "best effort" basis. On the other side, cyber hackers are targeting big physical infrastructures, industrial hardware in addition to the financial institutions. Therefore, it has become vital to address secure and faster data communications, in order to improve the Performance of the Internetwork.
Embargo
Approximate decision making by natural language commands for robots
(IEEE, 2006-11-06) Watanabe, K; Jayawardena, C; Izumi, K
Inferring the correct meaning of natural language commands, as judged by the person who issues commands, is mandatory for natural language commanded robotic systems. There have been some successful research on this; but one of the important and related aspects has not been addressed, i.e. the possibility of learning from natural language commands. Since natural language commands are generated by human users, they contain valuable information. Nevertheless, the learning from such commands, as well as the interpretation of them face many challenges due to the inherent subjectiveness of natural languages. In this paper, we propose a decision making process for natural language commanded robots which is influenced by certain characteristics of human decision making process. The proposed concept is demonstrated with an experiment conducted using a robotic manipulator. First, the robot is controlled with natural language commands to perform some pick and place operations during which the robot builds a knowledge base. After learning, the robot is capable of performing approximately similar tasks by making approximate decisions with the gained knowledge. For the decision making a probabilistic neural network is used
Embargo
Artificial Intelligence Based Smart Library Management System
(IEEE, 2021-12-01) Jayawardena, C; Reyal, S; Kekirideniya, K. R; Wijayawardhana, G. H. T; Rupasinghe, D. G. I. U; Lakranda, S. Y. R. M
The concept of a smart library system is to operate in a library with minimal human intervention. The proposed system handles basic library functions such as issuing books, returning books, reserving books, collecting late return fines, antitheft detection, and managing booking inventory using IoT technologies such as RFID and Raspberry Pi. The first key criterion is shelves management, which provides a unique key and uses RFID technology to identify and arrange the books. The succeeding category is providing users with book recommendations by penalizing hidden layer activations to encourage only a few nodes to activate when a single sample is an input. The dimensionality reduction neural network method was used to select the optimal seating arrangement. The LSTM algorithm will be used to make predictions to provide an efficient service to library users.
Embargo
Automated Exam Paper Marking System for Structured Questions and Block Diagrams
(IEEE, 2018-12-21) Jayawardena, R. R. A. M. P; Thiwanthi, G. A. D; Suriyaarachchi, P. S; Withana, K. I; Jayawardena, C
Exam paper marking has always been an exhaustive process which requires a lot of time and effort. We intend to address this issue by automating the marking of structured type questions and three diagram type questions, i.e. block diagram, logic circuit, and flowchart questions. A web-based system was developed to collect answers, mark and provide feedback to students. We investigated the application of Natural Language Processing (NLP) when marking structured questions. Graph matching using Depth-First Search (DFS) and Breadth-First Search (BFS) was employed in marking diagram type questions. The accuracy of logic circuit and flowchart diagram marking were tested by simulating and converting the diagrams into Python programs respectively. The implemented system has been made available to users as a plug-in in the opensource learning management system Moodle.
Open Access
Benefits and problems of health-care robots in aged care settings: A comparison trial
(WILEY, 2015-09-13) Broadbent, E; Kerse, N; Peri, K; Robinson, H; Jayawardena, C; Kuo, T; Datta, C; Stafford, R; Butler, H; MacDonald, B. A; Robins, B
Aim This study investigated whether multiple health-care robots could have any benefits or cause any problems in an aged care facility. Method Fifty-three residents and 53 staff participated in a non-randomised controlled trial over 12 weeks. Six robots provided entertainment, communication and health-monitoring functions in staff rooms and activity lounges. These settings were compared to control settings without robots. Results There were no significant differences between groups in resident or staff outcomes, except a significant increase in job satisfaction in the control group only. The intervention group perceived the robots had more agency and experience than the control group did. Perceived agency of the robots decreased over time in both groups. Overall, we received very mixed responses with positive, neutral and negative comments. Conclusions The robots had no major benefits or problems. Future research could give robots stronger operational roles, use more specific outcome measures, and perform cost–benefit analyses.
Embargo
Carrier frequency offset estimation for OFDM system using extended kalman filter
(IEEE, 2008-12-12) Senevirathna, S. B; Jayawardena, C; Perera, S. S; Perera, C. L; Ranasignhe, D; Wijerathna, S. R; Bandara, T. N
The ability of Orthogonal Frequency Division Multiplexing (OFDM) systems to achieve higher data rates and facilitate bandwidth friendly communication is impaired by the presence of Carrier Frequency Offset (CFO) in the OFDM communication system. CFO can be caused by Doppler frequency shift, or by the differences of the transmitter and the receiver local oscillator frequencies. We propose a new method for CFO estimation for (OFDM) communication systems, with experimental proof which was gathered in the process of real world data transmission using the OFDM communication system in a simulation environment (MATLAB).
Embargo
Case studies for model driven engineering in mobile robotics
(IEEE, 2011-05-09) MacDonald, B; Roop, p; Abbas, T; Datta, C; Jayawardena, C; Diprose, J; Hosking, J; Bhatti, Z
Case studies for model driven engineering in mobile robotics Page 1 Case studies for model driven engineering in mobile robotics Bruce MacDonald Partha S Roop Tanveer Abbas Chandimal Jayawardena Chandan Datta Jamie Diprose* John Hosking* Zeeshan E Bhatti Robotics Laboratory Department of Electrical and Computer Engineering *Department of Computer Science University of Auckland 9 May 2011 Page 2 Outline • Model driven engineering • Case studies: 1. Customization tools for different human roles 2. Defining interactions 3. Programming by demonstration 4. Visual programming 5. Safety critical robotics Page 3 Model driven engineering Designer provides high level specification • Sound formal model – Ideal case: amenable to formal checking • Visual design tools • Cognitively appropriate for human designer roles eg medication management in healthcare – Developers (software development …
Open Access
Comparative Analysis of Deep Learning Models for Multi-Step Prediction of Financial Time Series
(researchgate.net, 2020-10-21) Aryal, S; Nadarajah, D; Rupasinghe, P.L; Jayawardena, C; Kasthurirathna, D
Financial time series prediction has been a key topic of interest among researchers considering the complexity of the domain and also due to its significant impact on a wide range of applications. In contrast to one-step ahead prediction, multi-step forecasting is more desirable in the industry but the task is more challenging. In recent days, advancement in deep learning has shown impressive accomplishments across various tasks including sequence learning and time series forecasting. Although most previous studies are focused on applications of deep learning models for single-step ahead prediction, multi-step financial time series forecasting has not been explored exhaustively. This paper aims at extensively evaluating the performance of various state-of-the-art deep learning models for multiple multi-steps ahead prediction horizons on real-world stock and forex markets dataset. Specifically, we focus on Long-Short Term Memory (LSTM) network and its variations, Encoder-Decoder based sequence to sequence models, Temporal Convolution Network (TCN), hybrid Exponential SmoothingRecurrent Neural Networks (ES-RNN) and Neural Basis Expansion Analysis for interpretable Time Series forecasting (N-BEATS). Experimental results show that the latest deep learning models such as NBEATS, ES-LSTM and TCN produced better results for all stock market related datasets by obtaining around 50% less Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE) scores for each prediction horizon as compared to other models. However, the conventional LSTM-based models still prove to be dominant in the forex domain by comparatively achieving around 2% less error values.
Embargo
Comparative analysis of the application of Deep Learning techniques for Forex Rate prediction
(2019-12-05) Nadarajah, D; Aryal, S; Kasthurirathna, D; Rupasinghe, L; Jayawardena, C
Forecasting the financial time series is an extensive field of study. Even though the econometric models, traditional machine learning models, artificial neural networks and deep learning models have been used to predict the financial time series, deep learning models have been recently employed to do predictions of financial time series. In this paper, three different deep learning models called Long Short-Term Memory (LSTM), Convolutional Neural Network (CNN) and Temporal Convolution Network (TCN) have been used to predict the United States Dollar (USD) to Sri Lankan Rupees (LKR) exchange rate and compared the accuracy of the models. The results indicate the superiority of CNN model over other models. We conclude that CNN based models perform best in financial time series prediction.
Embargo
Comparative analysis of the application of Deep Learning techniques for Forex Rate prediction
(IEEE, 2019-12-05) Aryal, S; Nadarajah, D; Kasthurirathna, D; Rupasinghe, L; Jayawardena, C
Forecasting the financial time series is an extensive field of study. Even though the econometric models, traditional machine learning models, artificial neural networks and deep learning models have been used to predict the financial time series, deep learning models have been recently employed to do predictions of financial time series. In this paper, three different deep learning models called Long Short-Term Memory (LSTM), Convolutional Neural Network (CNN) and Temporal Convolution Network (TCN) have been used to predict the United States Dollar (USD) to Sri Lankan Rupees (LKR) exchange rate and compared the accuracy of the models. The results indicate the superiority of CNN model over other models. We conclude that CNN based models perform best in financial time series prediction.
Embargo
Comparative analysis of the application of Deep Learning techniques for Forex Rate prediction
(IEEE, 2019-12-05) Aryal, S; Nadarajah, D; Kasthurirathna, D; Rupasinghe, L; Jayawardena, C
Forecasting the financial time series is an extensive field of study. Even though the econometric models, traditional machine learning models, artificial neural networks and deep learning models have been used to predict the financial time series, deep learning models have been recently employed to do predictions of financial time series. In this paper, three different deep learning models called Long Short-Term Memory (LSTM), Convolutional Neural Network (CNN) and Temporal Convolution Network (TCN) have been used to predict the United States Dollar (USD) to Sri Lankan Rupees (LKR) exchange rate and compared the accuracy of the models. The results indicate the superiority of CNN model over other models. We conclude that CNN based models perform best in financial time series prediction.
Open Access
Controlling a robot manipulator with fuzzy voice commands using a probabilistic neural network
(Springer-Verlag, 2006-07-06) Jayawardena, C; Watanabe, K; Izumi, K
Natural language commands are generated by intelligent human beings. As a result, they contain a lot of information. Therefore, if it is possible to learn from such commands and reuse that knowledge, it will be a very efficient process. In this paper, learning from such information rich voice commands for controlling a robot is studied. First, new concepts of fuzzy coachplayer system and sub-coach are proposed for controlling robots with natural language commands. Then, the characteristics of the subjective human decision making process are discussed and a Probabilistic Neural Network (PNN) based learning method is proposed to learn from such commands and to reuse the acquired knowledge. Finally, the proposed concept is demonstrated and confirmed with experiments conducted using a PA-10 redundant manipulator.
Embargo
Cybersecurity and Network Performance Modeling in Cyber-Physical Communication for BigData and Industrial IoT Technologies
(IEEE, 2019-07-26) Sen, S; Jayawardena, C
The information and networking technology have been revolutionized with the inception of recent evolution of Cyber-Physical Systems (CPS) and the Internet of Things (IoT). The next generation distributed computing systems i.e., CPS and IoT are highly interconnected and deeply embedded with the physical world. By capitalizing the advantages and opportunities of these technologies, Industrial-IoT has been fueling smart industrial processes. The execution and application of these processes generate huge amount of data, which leads the distributed computing systems to carefully consider information and data management reliably and securely; also facilitating the necessary automation as well as ensuring timely information exchange. But the current internet doesn't guarantee the network performance and secure transportation; in addition the physical systems are becoming more insecure when interconnected to the cyber systems. These bottlenecks are leading to the necessity of improving performance and security in the cyber-physical communication. Considering those pervasive requirements, this paper has modeled network performance as well as system security with a view to improve these components which could heel the reliable cyber-communication challenges.
Unknown
A decision making model for optimizing social relationship for side-by-side robotic wheelchairs in active mode
(IEEE, 2016-06-26) Nguyen, V; Jayawardena, C
Nowadays, not only the ability to navigate to destinations but also the ability to navigate in harmony in crowded environments is a crucial feature that helps mobile robots to be accepted in daily routines of humans. In the case of wheelchairs that can move in parallel to a caregiver (side-by-side), this requirement is more complex as the navigation should be comfortable to the wheelchair user, caregiver, as-well-as surrounding people. This study aims to propose a novel decision model for robotic wheelchairs for passing obstacles when moving side-by-side with a human. The proposed model was developed by studying human behavior.
Embargo
Deployment of a service robot to help older people
(IEEE, 2010-10-18) Jayawardena, C; Kuo, I. H; Unger, U; Igic, A; Wong, R; Watson, C. I; Stafford, Q. R; Broadbent, E; Tiwari, P; Warren, J; Sohn, J; MacDonald, B. A
This paper presents the first version of a mobile service robot designed for older people. Six service application modules were developed with the key objective being successful interaction between the robot and the older people. A series of trials were conducted in an independent living facility at a retirement village, with the participation of 32 residents and 21 staff. In this paper, challenges of deploying the robot and lessons learned are discussed. Results show that the robot could successfully interact with people and gain their acceptance.
Embargo
Deployment of a service robot to help older people
(IEEE, 2010-10-18) Jayawardena, C; Kuo, I. H; Unger, U; Igic, A; Wong, R; Watson, C.I; Stafford, R.Q; Broadbent, E; Tiwari, P; Warren, J; Sohn, J; MacDonald, B.A
This paper presents the first version of a mobile service robot designed for older people. Six service application modules were developed with the key objective being successful interaction between the robot and the older people. A series of trials were conducted in an independent living facility at a retirement village, with the participation of 32 residents and 21 staff. In this paper, challenges of deploying the robot and lessons learned are discussed. Results show that the robot could successfully interact with people and gain their acceptance.
Embargo
Design, implementation and field tests of a socially assistive robot for the elderly: Healthbot version 2
(IEEE, 2012-06-24) Jayawardena, C; Kuo, I; Datta, C; Stafford, R.Q; Broadbent, E; MacDonald, B. A
This paper presents the second version of a mobile service robot (HealthBot) designed for older people. The lessons learned from studies of the first version of the robot at a retirement village, and design decisions for the second version, are discussed. Technical requirements of field trials, a focus on cognitive human-robot interactions, the importance of working together in a multidisciplinary team, and the necessity for rapid iterative development suggested a new software framework. The features of new framework are discussed and implementation details are presented. Details of field trials and user acceptance results are presented. Results are promising for older-user acceptance of the robot.