MAKE AN APPOINTMENT

In this 21st Century, the internet has become our escape path. It has been a convenient tool that assisted in simplifying our everyday tasks. This tool has become the beacon in this millennium. This is no longer a want, but it is a necessity. We use this tool every day from the cars we drive, to our travel plans, medical, banking enquiries, personal profiling, traffic monitoring and so forth. Big Data indefinitely permeates all aspects of our modern life. Nonetheless, Big Data seemingly controls everything around us. More often, the influence of Big Data in our daily lives is opaque and invisible. Something that we as users would choose to ignore. Seemingly how much of our lives is influenced by Big Data?

RM1.4 Million

funding

6 Projects

3 Faculties

3 Years

2017 - 2020

ABOUT PROGRAMME

In this 21st Century, the internet has become our escape path. It has been a convenient tool that assisted in simplifying our everyday tasks. This tool has become the beacon in this millennium. This is no longer a want, but it is a necessity. We use this tool every day from the cars we drive, to our travel plans, medical, banking enquiries, personal profiling, traffic monitoring and so forth. Nevertheless, the technology, which accumulates to Big Data, has allowed us to become an open book towards everyone and everything. For instance, if you use a smartphone or social media, it will determine a great deal of what you watch, read, listen and many more. Big Data indefinitely permeates all aspects of our modern life. Nonetheless, Big Data seemingly controls everything around us. More often, the influence of Big Data in our daily lives is opaque and invisible. Something that we as users would choose to ignore. Seemingly how much of our lives is influenced by Big Data?

Knowledge is indefinitely power. Data is knowledge and that knowledge is incredibly powerful. It can be either for social, financial analysts, governments, travel analysts or business owners. With this vast amount of information, along with increasingly developed means of disseminating the data could potentially mean that we are able to control the risks and effects that Big Data will have in our decision-making. This information has such a wide range of uses for a wide range of disciplines, which in turn has positively become a trend for future improvement. 

ABOUT PROJECTS

This flagship programme is divided into a series of projects which involves staffs from the following Schools and Faculties: School of Computing, School of Hospitality, Tourism & Events, and Taylor’s Business School.

 

TRAVEL BEHAVIOUR MODELLING USING DATA FROM SMART MOBILE APPLICATION

Overview

In this research, a study on current social behaviour of urban Malaysians towards the use of transport will be carried out. The study will include their perception towards transport and climate change, their travel habits, their choice of transport and the issues pertaining to transport and travel patterns. Data will be collected in two-folds: (a) Through an online survey and (b) Using Mobile device to track travel behaviour.

All these data will be analysed using Big Data Techniques and a "Malaysian Urban Travel Behaviour" model will be conceptualised. Based on outcome of these analysis, a framework will be proposed to drive smart mobility programmes.

(a) To develop a model for urban travel behaviour and visualise this behaviour.
(b) To develop a framework or policy for smart mobility in Malaysian cities.

Key Experts
VIRTUAL TOURISM IN 3D VIRTUAL WORLDS

Overview

While corporeal patterns of mobility continue to increase, virtual tourism has become a widespread social practice in contemporary society. Despite this, tourists' experiences in virtual tourist destinations remain relatively unexplored. This is particularly true if virtual tourist's gendered identities and patterns of behaviour in virtual destinations are referred to. In order to fill this gap, this project explores tourists' patterns of behaviour travelling in Virtual Worlds (ex. Second Life). Driven by an interpretivist approach, this project will employs virtual ethnography, also known as netnography. The findings will reveal how virtual tourists explore the environment and provides a more in-depth understanding of their needes and expectation in the virtual worlds.

(a) To develop a model for tourists’ motivation traveling to an actual destination after experiencing a virtual destination.
(b) To develop a framework for the destination marketers in virtual worlds to advertise their destinations in virtual worlds.

Key Experts
SPATIAL BIG DATA AND IOT FOR COASTAL EROSION AND FLOOD MITIGATION AND PREDICTION

Overview

While corporeal patterns of mobility continue to increase, virtual tourism has become a widespread social practice in contemporary society. Despite this, tourists' experiences in virtual tourist destinations remain relatively unexplored. This is particularly true if virtual tourist's gendered identities and patterns of behaviour in virtual destinations are referred to. In order to fill this gap, this project explores tourists' patterns of behaviour travelling in Virtual Worlds (ex. Second Life). Driven by an interpretivist approach, this project will employs virtual ethnography, also known as netnography. The findings will reveal how virtual tourists explore the environment and provides a more in-depth understanding of their needes and expectation in the virtual worlds.

a) To develop a model for tourists’ motivation traveling to an actual destination after experiencing a virtual destination.
b) To develop a framework for the destination marketers in virtual worlds to advertise their destinations in virtual worlds.

Key Experts
MODELLING & VISUALISATION OF AIR POLLUTION AND ITS IMPACT ON HEALTH

Overview

The pollutants namely ozone (O3), nitrogen dioxide (NO2), carbon monoxide (CO), particulate matter (PM10) and sulfur dioxide (SO2) samples will be collected from the study area namely Greater Kuala Lumpur. The hybrid land use regression (LUR) model will be developed to estimate the pollutants concentration (µgm^(-3)) using the predictor variables namely density residential land, industry, port, urban green, forest area, number of buildings, area of water and traffic intensity. The LUR model is one of the most widely used exposure assessment tools in air pollution epidemiological researches to estimate the pollutants concentration. These estimation will be used for the quantification of the health impact namely all-cause mortality and respiratory and cardiovascular morbidity. The health impact due to air pollution will be determined and the concentration response functions will be established. The concentration response functions (odd ratios) will be obtained using three types of regression models (linear, logistic, cox).

a)To develop an advanced methodology for assessment of population exposure to air pollution using a hybrid spatial model which consists of Land Use Regression (LUR) model, dispersion model and spatial GARMA model

b)To validate the hybrid spatial model by comparing the predicted levels of the modelled pollutant to sampled levels at sites not included in the prediction modelc)To quantify the effect of air pollutants on cardiovascular diseases, respiratory diseases, and all-cause mortality using the hybrid spatial model and regression model

Key Experts
CYBER RISK AND BANK STABILITY: AN EMPIRICAL STUDY

Overview

Cyber threats have been growing worldwide and a complete protection is hardly possible despite installation of a high-cost IT infrastructure. Hence, we conjecture that cyber threats could make a bank unstable with the advancement of internet technology that has helped to liberalize financial sectors by diminishing time and locational limitations. However, in the absence of a complete security framework, internet could make the banking system vulnerable to cyber threats that requires a banking institution to invest adequately in cyber infrastructure. Given this background this study intends to identify the optimal level of cyber investment that helps a bank to be stable by controlling its IT related operational risks.

1. Do inadequate infrastructure against cyber risk leads a bank to be more prone to failure?
2. Do strong infrastructure against cyber threats leads to higher bank overheads and thereby higher earnings uncertainty?

Key Experts
CRIMENET: A FRAMEWORK FOR GRAPHIC VISUALISATION OF CRIMINAL AND TERRORIST NETWORKS USING EXTREME LEARNING AND PREDICTIVE MODELLING

Overview

The communication data and social networking applications are becoming increasingly important for criminal network analysis nowadays, and these data provide a digital trace which can be regarded as a hidden clue to support the crack of criminal cases. Additionally, performing a timely and effective analysis on it can predict criminal intents and take efficient actions to restrain and prevent crimes. Although the primary work of our research is to suggest an analytical process with interactive strategies as a solution to the problem of characterizing criminal groups constructed from the communication data and social networking artifacts, current analysis tools lack the learning and prediction components in its overall design structure.

This research is expected to assist law enforcement agencies in the task of discovering the potential suspects and exploring the underlying structures of criminal network hidden behind the communication and social networking data and the Tor1 technology in dark internet2. This research got its inspiration from scenario and attack graph analysis from the cybersecurity domain. This process allows for network analysis with commonly used metrics to identify the core members. It permits exploration and visualization of the network with the goal of improving the comprehension of interesting microstructures.

Most importantly, it also allows extracting community structures in an appropriate level with the label supervision strategy. Our work concludes by illustrating the application of our interactive strategies to a real-world criminal investigation.

a) To design the overall framework for criminal and terrorist visualization network tool.
b) To design a novel extreme deep learning algorithm for graphical bas theed visualization systems.
c) To design a new algorithm for comparing the validity and accuracy of graph-based systems.
d) To develop a criminal and terrorist visualization and prediction tool for crime prevention and criminal network analysis.

Key Experts

CONTACT US

Centre for Research Management
Director
Adeline Yong Sui Yen

crm@taylors.edu.my

OTHER RECOMMENDED PROGRAMMES