Research Publications Authored by SLIIT Staff
Permanent URI for this communityhttps://rda.sliit.lk/handle/123456789/4195
This collection includes all SLIIT staff publications presented at external conferences and published in external journals. The materials are organized by faculty to facilitate easy retrieval.
Browse
4 results
Search Results
Publication 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, CForecasting 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.Publication Embargo The application of “Off-the-shelf” components for building IMUs for navigation research(IEEE, 2014-10-27) Abhayasinghe, N; Murray, IInertial measurement units (IMU) are commonly used in pedestrian and robotic navigation applications and research. Although many IMUs are commercially available, almost all of them are non-customizable and they process the collected raw data before presenting them to the user. However, this creates a limitation for researchers due to the fact that they have to rely on a set of per-processed data. Further, available resources and features such as SD card slots, wireless connectivity, available in the IMU may not suit one's research. This paper provides a survey on availability and usage of different off-the-shelf devices to build a custom made IMU. The authors considered open-source microcontroller platforms, low cost MEMS sensors and low cost accessories in this survey so that the IMUs will be affordable to many people. A range of sensors, their features, available processor options and different types of wired and wireless communication options available are discussed. Particular emphasis is made on the ability to modify or add functionality to commonly available hardware. Possible technical issues in assembling the IMU and calibrating sensors are also discussed in this paper. Technologies available for constructing a housing and mounting systems for the IMU best suited to the application are also discussed in this paper. As an example, IMUs developed and implemented by the authors with different housing designs specifically created for particular applications are presented. This survey indicated that off-the-shelf components can effectively be used to build custom-made IMUs to suit the particular research interest or application best.Publication Embargo The application of “Off-the-shelf” components for building IMUs for navigation research(IEEE, 2014-10-27) Abhayasinghe, N; Murray, IInertial measurement units (IMU) are commonly used in pedestrian and robotic navigation applications and research. Although many IMUs are commercially available, almost all of them are non-customizable and they process the collected raw data before presenting them to the user. However, this creates a limitation for researchers due to the fact that they have to rely on a set of per-processed data. Further, available resources and features such as SD card slots, wireless connectivity, available in the IMU may not suit one's research. This paper provides a survey on availability and usage of different off-the-shelf devices to build a custom made IMU. The authors considered open-source microcontroller platforms, low cost MEMS sensors and low cost accessories in this survey so that the IMUs will be affordable to many people. A range of sensors, their features, available processor options and different types of wired and wireless communication options available are discussed. Particular emphasis is made on the ability to modify or add functionality to commonly available hardware. Possible technical issues in assembling the IMU and calibrating sensors are also discussed in this paper. Technologies available for constructing a housing and mounting systems for the IMU best suited to the application are also discussed in this paper. As an example, IMUs developed and implemented by the authors with different housing designs specifically created for particular applications are presented. This survey indicated that off-the-shelf components can effectively be used to build custom-made IMUs to suit the particular research interest or application best.Publication 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, CForecasting 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.