Involved Projects:- Data analytics for providing measurable optimisation insights into complex conveyor system at PortRoles:- Directly engaging with clients at various stages of the project and presenting weekly progress.- Extracting the data directly from the client’s data base and PI server.- Integrating data received in different formats.- Visualising time series operational data to observe patterns/trends and translating them into business insights.- Analysing data using state of art data analytics.- Developing data visualisation dashboards in Power BI (with Python integration).- Developing models.- Preparing presentations.- Writing reports.

Involved Projects:- Investigation of SAG mill Oscillation events and review of Advanced Process Control System.- Investigation and optimisation of the detrimental effect of pebble crushing on the AG milling process.- Process optimisation of two-stage grinding circuit that produces zinc, copper and lead concentrates.- Mill liner design and order optimisation that produces copper, gold, silver and uranium concentrates.Roles:- Extracting and integrating data received in different format.- Analysing process (operational) data from milling circuits.- Visualising data to observe patterns and trends, and translating them into business insights.- Developing statistical models.- Performing hypothesis tests.- Preparing presentations.- Writing reports.

Utilised state-of-art data analytics techniques to solve complex problems in mineral processing, particularly in comminution circuilt.Key Contributions:- Developed advanced data analytical techniques for labeling operating states in industrial data (PI data) from mineral processing plants.- Identified steady state conditions in SAG mill and detected overloading in ball mill using the time series pattern detection techique, i.e. Dynamic Time Warping.- Applied domain knowledge to guide data analytics and develop metrics for testing reliability (i.e. quality) of the data.- Leveraged machine learning techniques for clustering, pattern detection (in time series data), and classification.- Presented research findings at international conferences, seminars, and directly to industry stakeholders at mine sites.

Involved Projects:- Machine Learning Model for Scat Hold-Up Events (AG Mills): Reviewed and enhanced predictive models for scat hold-up events, improving accuracy and performance.- Microservices Platform Development: Conducted a case study on developing a microservices platform using Django.Roles and responsibilities:- Collaborated with project leads and metallurgists to understand and address the business challenges.- Visualised operational data to explore meaningful insights.- Pre-processed raw PI data to prepare it for machine learning applications.- Applied mineral processing domain knowledge in feature selection.- Introduced a technique for data alignment to deal with time lag problem.- Prepared reports and presentation sides.- Presented key finding to both technical and non-technical teams at Interlate.

Provided instruction and supervised undergraduate students’ capstone projects in applied data science projects in various domains.

Major Projects:- Loan Repayment Project (Spotter Loan): Developed an interactive R Shiny dashboard to categorise borrowers into risk categories using financial data. This tool is now implemented in the business for tracking borrower risk profiles.- Transport Accident Commission (TAC) Project: Explored and analyzed TAC transaction data, presenting insights through an interactive dashboard using Apache Superset for the Australian Government agency.Roles & Responsibilities:- Integrated data from various sources.- Pre-processed raw transactional data for analysis and visual presentation.- Collaborated with stakeholders to understand business problems and project requirements.- Conducted data exploration to extract actionable business insights.- Created data visualisations using R and Shiny for financial risk categorisation.- Developed interactive dashboards and prepared presentations to convey findings to both technical and non-technical audiences.- Performed statistical analysis of the data.- Developed machine learning models.- Prepared presentation slides.

Developed course materials, delivered lectures, conducted experimental labs, and assessed exams and other assignments.