Oras Baker

Prof. Dr. Oras Baker

orcid

Research Focus & Metrics

Academic Career Length

23Years (2004-Present)

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

Representative Publications

View All Publications
1 June 2019 in Journal of Software
Verified
Journal Article
Closed access
QNQuy Nguyen
Quy Nguyen
OBOras Baker
Oras Baker

OBOras Baker
Oras Baker
ZZZahra Ziran
Zahra Ziran
Massimo MecellaMassimo Mecella
Massimo Mecella
KSKasthuri Subaramaniam
Kasthuri Subaramaniam
SPSellappan Palaniappan
Sellappan Palaniappan
This study proposes a data-driven approach to leveraging large-scale COVID-19 datasets to enhance the predictive modeling of disease spread in the early stages. We systematically evaluate three machine learning models—ARIMA, Prophet, and LSTM—using a comprehensive framework that incorporates time-series analysis, multivariate data integration, and a Multi-Criteria Decision Making (MCDM) technique to assess model performance. The study focuses on key features such as daily confirmed cases, geographic variations, and temporal trends, while considering data constraints and adaptability across different scenarios. Our findings reveal that LSTM and ARIMA consistently outperform Prophet, with LSTM achieving the highest predictive accuracy in most cases, particularly when trained on 20-week datasets. ARIMA, however, demonstrates superior stability and reliability across varying time frames, making it a robust choice for short-term forecasting. A direct comparative analysis with existing approaches highlights the strengths and limitations of each model, emphasizing the importance of region-specific data characteristics and training periods. The proposed methodology not only identifies optimal predictive strategies but also establishes a foundation for automating predictive analysis, enabling timely and data-driven decision-making for disease control and prevention. This research is validated using data from New Zealand and its major trading partners—China, Australia, the United States, Japan, and Germany—demonstrating its applicability across diverse contexts. The results contribute to the development of adaptive forecasting frameworks that can empower public health authorities to respond proactively to emerging health threats.

17 November 2021
Verified
Conference Paper
Closed access
OBOras Baker
Oras Baker
QYQing Yuan
Qing Yuan
The online tourism industry has significantly developed in recent years. One prominent feature of a tourism recommender system is to assist the users in finding out potential attractions based on their preferences. A recommender system is a specific type of intelligent system, which exploits historical user ratings on items or additional information. In this research, we developed and implemented a tourism recommender system that consists of two Machine Learning algorithms. The first proposed model is the Factorisation Machines (FM), and the second model is the Normalized Discounted Cumulative Gain (NDCG) with Deep Neural Network (DNN) system, utilised to improve the search results. The evaluation shows that the FM method is effective and highly aggregated with low-frequency user rating data and could produce high-quality outputs. Finally, we expand on current trends and provide new perspectives of this new exciting development in the field of recommender systems.

17 November 2020
Verified
Conference Paper
Closed access
OBOras Baker
Oras Baker
CTChuong Nguyen Thien
Chuong Nguyen Thien
Data warehouse and big data have become the trend to help organise data effectively. Business data are originating in various kinds of sources with different forms from conventional structured data to unstructured data, it is the input for producing useful information essential for business sustainability. This research will navigate through the complicated designs of the common big data and data warehousing technologies to propose an effective approach to use these technologies for designing and building an unstructured textual data warehouse, a crucial and essential tool for most enterprises nowadays for decision making and gaining business competitive advantages. In this research, we utilised the IBM BigInsights Text Analytics, PostgreSQL, and Pentaho tools, an unstructured data warehouse is implemented and worked excellently with the unstructured text from Amazon review datasets, the new proposed approach creates a practical solution for building an unstructured data warehouse.

17 November 2020
Verified
Conference Paper
Closed access
OBOras Baker
Oras Baker
PKPrabhjot Kaur
Prabhjot Kaur
Customer Relationship Management (CRM) solutions are helping businesses to grow by maintaining healthy relationships with the existing customers and building strong relationships with new customers. However, SaaS-CRM solutions are more desirable options for SME’s as these solutions are less expensive and unsophisticated to implement as compared to on-premise CRM. The main aim of this research is to identify to what extent the SMEs in Southland are aware of SaaS-CRM and what are the factors that affect their decision for adoption. A survey was used to collect data from 35 SME’s operating in the region of Southland, New Zealand. The results showed that only 10% of the SME’s use cloud CRM solutions and different factors such as relative advantage, perceived ease of use, perceived usefulness, technology readiness, top management support, trust in vendor, and regulatory support affect their cloud CRM adoption decisions.

17 November 2020
Verified
Conference Paper
Closed access
YCYoon Kin Cheah
Yoon Kin Cheah
OBOras Baker
Oras Baker
New Zealand is a popular tourist destination for global tourists, where several cities in New Zealand attract a multitude of tourists annually. This research aims to exploit mobile technologies, including mobile augmented reality (MAR) and location-based service to implement a mobile tourist guide known as InvercARgill, to help promote tourism in Invercargill. The research focuses on the design and implementation of InvercARgill, where the functionality and usability are prioritised. Besides, the client-server architecture of InvercARgill, along with various SDKs and APIs exploited for the implementation are discussed in this paper. Lastly, results of the research reveal that InvercARgill could enhance the tourist’s travel experience in Invercargill by distributing tourist information of various attractions through MAR and location-based service on the smartphone, as well as reducing the travel time to various attractions in Invercargill