This month's newsletter focuses on the activities in September including a teaching award and two publications.
IN THE SPOTLIGHT
Congratulations to A/Prof Adriano Polpo on receiving the Science and Engineering School’s Excellence in Teaching Award. It has been a difficult time to teach over the last couple of years with online teaching, curriculum changes and some big changes in student numbers and student backgrounds. It is especially impressive to stand out as an award winner in that context. The Awards were presented at the School Awards and Student Prizes Event 1 September.
Congratulations to Eden Li and Sandy Spiers on publishing papers based on their research with our industry partners
Theme 4 Eden Li and Mark Griffin published - "Unpacking human systems in data science innovations: Key innovator perspectives." Technovation128: 102869.
This study, supported by Roy Hill, contributes the advancement of innovation management theories and calls attention to guiding and engaging individuals through providing support and removing barriers to data science at different organisational levels. More practically, innovation managers could use this as a guide to optimise work systems and inform pathways to improve organisation data science efforts.
This study, co-authored with the Alcoa Data Science Team, solves the scheduling model for realistic scenarios involving two Bayer refineries based in Western Australia. Unlike generic implementations of Benders decomposition, they show that the subproblems can be solved explicitly using a specialist algorithm
TEAM NEWS
Gabriel Gonzalez successfully gained full time employment with Andritz Pty Ltd. Once of the goals of an ITTC is support researchers transition into industry, Following Mojtaba earlier this year, Gabriel is the second researcher from CTMTDS to obtain full time employment with the resources industry.
Answering logical questions on technical knowledge graphs has been historically studied using graph query languages. These approaches can question complete knowledge graphs where answers are inferred from existing connected information links. However, knowledge graphs built from industry data are often incomplete with unconnected links, making it hard for the query language to find the answers when traversing missing links. Recently, the incomplete knowledge graph demanded embedding approaches that can return answers without the need to traverse a knowledge graph.
In this talk, Chau outlined the challenges of unstructured data in technical knowledge graphs and existing embedding approaches to answer logical queries. Chau will conclude by looking at a case study of possible query structures on a technical knowledge graph.
Managing a remote workforce on alternating shifts with specific schedules requires efficient worker utilisation. Each worker's ability to handle one task at a time underscores the importance of optimal assignments for timely project completion. Moreover, forming effective teams becomes essential when considering tasks requiring multiple workers.
The motivation behind Ponpot’s research lies in recognising the expense and fluctuating availability of human resources, especially in remote positions. With limited resources, efficient utilisation becomes paramount, driving our exploration into resource allocation strategies that ensure optimal outcomes. This presentation tackles a challenging problem related to forming teams, assignments, and job schedules in each shift.
Ponpot considers a given number of limited flexible workers capable of performing any job, who are distributed among different teams in different shifts to undertake various tasks. He aims to minimise the overall schedule completion time while adhering to constraints. His solution provides a manager with the number of human resources required in each shift. He provides information essential for planning and scheduling resources.
CTMTDS Newsletter 20, September 2023
This month's newsletter focuses on the activities in September including a teaching award and two publications.
IN THE SPOTLIGHT
Congratulations to A/Prof Adriano Polpo on receiving the Science and Engineering School’s Excellence in Teaching Award. It has been a difficult time to teach over the last couple of years with online teaching, curriculum changes and some big changes in student numbers and student backgrounds. It is especially impressive to stand out as an award winner in that context. The Awards were presented at the School Awards and Student Prizes Event 1 September.
Congratulations to Eden Li and Sandy Spiers on publishing papers based on their research with our industry partners
Theme 4 Eden Li and Mark Griffin published - "Unpacking human systems in data science innovations: Key innovator perspectives." Technovation 128: 102869.
This study, supported by Roy Hill, contributes the advancement of innovation management theories and calls attention to guiding and engaging individuals through providing support and removing barriers to data science at different organisational levels. More practically, innovation managers could use this as a guide to optimise work systems and inform pathways to improve organisation data science efforts.
Theme 3 Sandy Spiers, Hoa Bui and Ryan Loxton published - "Bayer digestion maintenance optimisation with lazy constraints and Benders decomposition" in Annals of Operations Research Volume 328 Issue 2, September 2023
This study, co-authored with the Alcoa Data Science Team, solves the scheduling model for realistic scenarios involving two Bayer refineries based in Western Australia. Unlike generic implementations of Benders decomposition, they show that the subproblems can be solved explicitly using a specialist algorithm
TEAM NEWS
Gabriel Gonzalez successfully gained full time employment with Andritz Pty Ltd. Once of the goals of an ITTC is support researchers transition into industry, Following Mojtaba earlier this year, Gabriel is the second researcher from CTMTDS to obtain full time employment with the resources industry.
INTERNATIONAL CONFERENCES
Michael Small presented the Research of Theme 2 in Naples at University of Naples Federico II for Dynamics Days Europe speaking in a Symposium on predicting extreme values from time series to talk about our work over the last three years with Transforming Maintenance through Data Science; an ARC Training Centre The University of Western Australia using nonlinear time series and machine learning (and in particular reservoir computing) for predictive maintenance with our partners BHP Roy Hill and Alcoa CSIRO Curtin University Minerals Research Institute of Western Australia (MRIWA)
Events
Researcher Catch-up for September 2023
Eden Li hosts Research presentations by PhD candidates Chau Nguyen and Ponpot JartnillaphandChau Nguyen presented - Answering Logical Queries on Technical Knowledge Graphs
Answering logical questions on technical knowledge graphs has been historically studied using graph query languages. These approaches can question complete knowledge graphs where answers are inferred from existing connected information links. However, knowledge graphs built from industry data are often incomplete with unconnected links, making it hard for the query language to find the answers when traversing missing links. Recently, the incomplete knowledge graph demanded embedding approaches that can return answers without the need to traverse a knowledge graph.
In this talk, Chau outlined the challenges of unstructured data in technical knowledge graphs and existing embedding approaches to answer logical queries. Chau will conclude by looking at a case study of possible query structures on a technical knowledge graph.
Ponpot Jartnillaphand presented - Optimising Maintenance Teams
Managing a remote workforce on alternating shifts with specific schedules requires efficient worker utilisation. Each worker's ability to handle one task at a time underscores the importance of optimal assignments for timely project completion. Moreover, forming effective teams becomes essential when considering tasks requiring multiple workers.
The motivation behind Ponpot’s research lies in recognising the expense and fluctuating availability of human resources, especially in remote positions. With limited resources, efficient utilisation becomes paramount, driving our exploration into resource allocation strategies that ensure optimal outcomes. This presentation tackles a challenging problem related to forming teams, assignments, and job schedules in each shift.
Ponpot considers a given number of limited flexible workers capable of performing any job, who are distributed among different teams in different shifts to undertake various tasks. He aims to minimise the overall schedule completion time while adhering to constraints. His solution provides a manager with the number of human resources required in each shift. He provides information essential for planning and scheduling resources.
New Publications September 2023
Eden Li and Mark Griffin published "Unpacking human systems in data science innovation: Key innovator perspectives"
Sandy Spiers, Hoa Bui , Ryan Loxton, Moussa Reda Mansour etal published - Bayer digestion maintenance optimisation with lazy constraints and Benders decomposition
Stay tuned for our next issue where we will cover:
Do you have news to share?
Please email [email protected]