Hansika Hewamalage

Dr. Hansika Hewamalage

UNSW Sydney, Sydney, New South Wales, Australia

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
2 December 2022 in Data Mining and Knowledge Discovery
Verified
Journal Article
Open access
PDF file
HHHansika Hewamalage
Hansika Hewamalage
KAKlaus Ackermann
Klaus Ackermann
CBChristoph Bergmeir
Christoph Bergmeir
Recent trends in the Machine Learning (ML) and in particular Deep Learning (DL) domains have demonstrated that with the availability of massive amounts of time series, ML and DL techniques are competitive in time series forecasting. Nevertheless, the different forms of non-stationarities associated with time series challenge the capabilities of data-driven ML models. Furthermore, due to the domain of forecasting being fostered mainly by statisticians and econometricians over the years, the concepts related to forecast evaluation are not the mainstream knowledge among ML researchers. We demonstrate in our work that as a consequence, ML researchers oftentimes adopt flawed evaluation practices which results in spurious conclusions suggesting methods that are not competitive in reality to be seemingly competitive. Therefore, in this work we provide a tutorial-like compilation of the details associated with forecast evaluation. This way, we intend to impart the information associated with forecast evaluation to fit the context of ML, as means of bridging the knowledge gap between traditional methods of forecasting and adopting current state-of-the-art ML techniques.We elaborate the details of the different problematic characteristics of time series such as non-normality and non-stationarities and how they are associated with common pitfalls in forecast evaluation. Best practices in forecast evaluation are outlined with respect to the different steps such as data partitioning, error calculation, statistical testing, and others. Further guidelines are also provided along selecting valid and suitable error measures depending on the specific characteristics of the dataset at hand.

21 April 2020 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
KBKasun Bandara
Kasun Bandara
CBChristoph Bergmeir
Christoph Bergmeir
HHHansika Hewamalage
Hansika Hewamalage
Generating forecasts for time series with multiple seasonal cycles is an important use case for many industries nowadays. Accounting for the multiseasonal patterns becomes necessary to generate more accurate and meaningful forecasts in these contexts. In this article, we propose long short-term memory multiseasonal net (LSTM-MSNet), a decomposition-based unified prediction framework to forecast time series with multiple seasonal patterns. The current state of the art in this space is typically univariate methods, in which the model parameters of each time series are estimated independently. Consequently, these models are unable to include key patterns and structures that may be shared by a collection of time series. In contrast, LSTM-MSNet is a globally trained LSTM network, where a single prediction model is built across all the available time series to exploit the cross-series knowledge in a group of related time series. Furthermore, our methodology combines a series of state-of-the-art multiseasonal decomposition techniques to supplement the LSTM learning procedure. In our experiments, we are able to show that on data sets from disparate data sources, e.g., the popular M4 forecasting competition, a decomposition step is beneficial, whereas, in the common real-world situation of homogeneous series from a single application, exogenous seasonal variables or no seasonal preprocessing at all are better choices. All options are readily included in the framework and allow us to achieve competitive results for both cases, outperforming many state-of-the-art multiseasonal forecasting methods.

1 October 2022 in International Journal of Forecasting
Verified
Journal Article
Closed access
KBKasun Bandara
Kasun Bandara
HHHansika Hewamalage
Hansika Hewamalage
RGRakshitha Godahewa
Rakshitha Godahewa
PGPuwasala Gamakumara
Puwasala Gamakumara

22 September 2022 in Designs
Verified
Journal Article
Open access
PDF file
AMAlfonso Angel Medina-Santana
Alfonso Angel Medina-Santana
HHHansika Hewamalage
Hansika Hewamalage
LCLeopoldo Eduardo Cárdenas-Barrón
Leopoldo Eduardo Cárdenas-Barrón
Providing sustainable energy to rural communities is considered in Sustainable Development Goal 7. Off-grid renewable energy systems arise as an affordable solution due to their portability and the availability of renewable sources for rural communities. In this work, to deal with the uncertainties of solar resources, we employ two deep learning models (feed forward and recurrent neural networks) to predict renewable sources in a long-term horizon. To this aim, the approach presented takes into account the necessity of a high enough resolution in the forecasting output. As a case study, we employ open source data for a location in Michoacan, Mexico as well as open source programming frameworks to ensure the replicability of the numerical experiments. The results show that our prediction model performs excellently with respect to the baseline methods (ARIMA, exponential smoothing, and seasonal naive) in terms of the evaluation metrics MASE (18.5% of reduction with respect to seasonal naive), RMSE (24.7%), WAPE (13.1%), MAE (12.9%), and APB (8.9%).

1 December 2015
Verified
Conference Paper
Closed access
BHBhagya Hettige
Bhagya Hettige
HHHansika Hewamalage
Hansika Hewamalage
CRChathuranga Rajapaksha
Chathuranga Rajapaksha
NWNuwan Wajirasena
Nuwan Wajirasena
APAkila Pemasiri
Akila Pemasiri
IPIndika Perera
Indika Perera
With the technological advancement in mobile computing industry the field of electronic commerce has gone through a paradigm shift. Today's customers are more inclined towards using sophisticated mobile assistants, to help them in shopping, indoor navigation etc. rather than struggling on their own. In the literature it can be found that several attempts have been taken to address this cause. Majority of those attempts are based on marker based object identification. But current scale and the trends of the electronic commerce industry demand shopping assistants who are following markerless object identification methods due to limitations like the limited number of objects that can be identified. In order to support more usable electronic commerce applications, this paper focuses on the feasibility of deploying common and readily available feature tracking algorithms which can provide the object identification capability without having fiducial markers.