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

Filters

2019 - 201912020 - 20231

Advanced Search

Filter by

Settings

Subject: search.filters.subject.Time series analysis

Search Results

Now showing 1 - 2 of 2
  • Thumbnail Image
    PublicationOpen Access
    Introduction of a Simple Estimation Method for Lane-Based Queue Lengths with Lane-changing Movements
    (Springer, 2023-03) Jayatilleke, S; Wickramasinghe, V; Amarasingha, N
    Traffic congestions are increased globally due to rapid urbanization and expedited economic developments in many countries. Vehicle queue is a governing aspect of traffic congestion, studied over the past decades. Most of the existing queue estimation approaches are limited to homogeneous traffic conditions. However, the traffic conditions in many developing countries are heterogeneous and are heavily influenced by mixed vehicle composition, lane changing, and gap-filling behaviours. This study aims to estimate the queue length at signalized intersections having heterogeneous traffic conditions. The heterogeneity was assimilated with the consideration of Passenger Car Units (PCU) in the measurements of the traffic flow and the lane-changing movement within the considered road section. The influential factors of the queue length were contemplated with the arrival flow, discharge flow, outbound lane change, inbound lane change, and signal configuration. A Vector Auto Regression (VAR) model was developed to estimate queue length, with a lag time of 15 s for each variable. The results have indicated a higher accuracy in the queue estimation as well as the practical application for prediction, constituting the traffic characteristics of the formed vehicle queue. The R squared of the VAR model was 0.97, along with a Mean Absolute Percentage Error (MAPE) of 21.55%. The model estimation results of right turning lanes were well accurate with MAPE ranging from 15 to 17%, whilst for through movement lanes, accuracy was slightly low with MAPE in the range of 23–26%. The study manifests the functionality of the developed methodology for accurate queue estimations, asserting the practical applicability of VAR models in other locations constituting mixed traffic. © 2022, The Institution of Engineers (India).
  • Thumbnail Image
    PublicationEmbargo
    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.