After an intense half a year, all the background activity led by my colleague Lawrence Molloy finally led to hands-on cultural heritage documentation on Country for the Gunditjmarra traditional owners of Budj Bim in March this year. These three days were of data collection were followed by months of data processing, primarily by our fantastic students that processed the UAV (drone) and UGV (robot) data. Finally, we were able to interpret the landscape quantitatively and support the UNESCO bid with visualizations.
We also managed to put a short communication about the start of this great collaboration to Nature ( https://www.nature.com/articles/d41586-019-02315-y ).
And some eye candy here:
The intense first semester is now over for me. I had a great time, interacting with amazing masters students of Spatial Databases and of Spatial Information Programming, and introducing a new generation of students to GIS in the Applications of GIS course. It was a very rewarding period, and I am sure that many of these students will continue in a spatial career.
I have also engaged in cultural heritage documentation, trying a highly unusual deployment of our Husky robot in complex conditions. While the first data collection trip may not have been as optimal as we hoped, we have learned a lot. This will inform a lot of our current research.
And of course, there was intense research activity going on, with a crop of papers out the door. Ehsan and Haonan are making a great progress exploring place-related question answering with conference papers at AGILE and SEMEVAL’19 [1,2]. Ivan’s paper on association rule mining for automated error detection in spatial data has appeared in JOSIS (part of the ARC DP Self-Healing Maps). Rob, Elham, Nick and I have finally managed to publish our investigation of using spatial mixing models to improve metropolitan scale influenza forecasting (that was a looong review period). Yet, not as long as the one for , which is now showing on the journal website, yet is still not online (pre-print is of course here).
Stephan and I have also engaged with Mike Batty’s commentary in EPB , and this has triggered a nice discussion.
I hope you have a fun read!
- Hamzei, E., Li, H., Vasardani, M., Baldwin, T., Winter, S. and Tomko, M. (in press, to appear 2020). Place questions and human-generated answers: A data analysis approach. Geospatial Technologies for Local and Regional Development. Proceedings of the 22nd AGILE Conference on Geographic Information Science. Kyriakidis, P., Hadjimitsis, D., Skarlatos, D. and Mansourian, A., Springer Heidelberg (link, pre-print)
- Li, H., Wang, M., Vasardani, M., Tomko, M., & Baldwin, T. (2019). UniMelb at SemEval-2018 Task 12: Multi-model combination for toponym resolution. Paper presented at the SemEval-2019: 13th International Workshop on Semantic Evaluation, Minneapolis, Minnesota, USA.(link , paper)
- Winter, S., Tomko, M., Vasardani, M., Richter, K.-F., Khoshelham, K., & Kalantari, M. (accepted, 2019). Infrastructure-Independent Indoor Localization and Navigation. ACM Computing Surveys. (pre-print)
- Moss, R., Naghizade, E., Tomko, M., & Geard, N. (2019). What can urban mobility data reveal about the spatial distribution of infection in a single city? BMC Public Health, 19(656). doi:10.1186/s12889-019-6968-x (link , paper)
- Winter, S., & Tomko, M. (2019). Beyond Digital Twins — A Commentary. Environment and Planning B: Urban Analytics and City Science, 46(2), 395-398. doi:10.1177/2399808318816992 (link , paper)
- Majic, I., Naghizade, E., Winter, S., & Tomko, M. (2019). Discovery of topological constraints on spatial object classes using a refined topological model. Journal of Spatial Information Science. doi:10.5311/JOSIS.2019.18.459 (link , paper)
We have acquired an exciting new piece of equipment – a Clearpath Robotics Husky Autonomous Ground Vehicle, fully kitted with a variety of sensors, including automotive-standard Velodyne LIDAR. This will be a great boost to our research on autonomous mapping. Get in touch, for all from sensing ( in collaboration with colleagues) to data processing and storage, to coverage planning.
Desired skills: ROS/Python/C++/Matlab.
This week our paper (with Stephen Marshall [UCL], Jorge Gil [Chalmers], Karl Kropf [Oxford Brookes University] and Lucas Figueiredo [UFPB), Brazil]): “Street network studies: from networks to models and their representations.” appeared as Open Access in Networks and Spatial Economics.
This is our contribution to the debate on modeling street networks, trying to disentangle issues of modeling, representation, and analysis. It should also be a useful paper for all considering aspects of reproducibility of street analysis research. What nice outcome from a few fantastic workshops, in particular, the Urban Networks workshop in Ghent!
(cite as: Marshall, S., Gil, J., Kropf, K., Tomko, M. and Figueiredo, L. (2018). “Street network studies: from networks to models and their representations.” Networks and Spatial Economics: 15. link: https://doi.org/10.1007/s11067-018-9427-9 )
Understanding the association between customer demographics and behaviour is critical for operators of indoor retail spaces. In our new study published in EPj Data Science, we explore associations based on a combined understanding of customer Cyber (online), Physical (Where?), and Social behaviour. We combine the results of a traditional questionnaire with large-scale WiFi access logs which capture customer cyber and physical behaviour. We investigate the predictability of user demographics based on CPS behaviors captured from both sources and provide strong support for demographic studies based on large-scale logs data capture.
This is the most recent publication from the fruitful ARC LP TRIIBE collaboration, with colleagues Yongli Ren, Flora Salim, Jeff Chan and Mark Sanderson (all RMIT).
Ren, Y., M. Tomko, F. D. Salim, J. Chan and M. Sanderson (2018). “Understanding the predictability of user demographics from cyber-physical-social behaviours in indoor retail spaces.” EPJ Data Science 7(1): 1-21. DOI: 10.1140/epjds/s13688-017-0128-2
The paper can be freely accessed here: http://rdcu.be/DZkO
It is a special feeling when your PhD student publishes their first paper! Congratulations to Ivan Majic (that’s Magic with a “J“) for the first workshop paper – a great start for the PhD, keep on the good work!
Reference: Majic, I., Winter, S., & Tomko, M. (2017). Finding equivalent keys in OpenStreetMap: semantic similarity computation based on extensional definitions. In GeoAl’17: 1st ACM SIGSPATIAL Workshop on Artificial Intelligence and Deep Learning for Geographic Knowledge Discovery, . Los Angeles Area, CA, USA: ACM. (pre-print)
I am excited that one of our main papers from TRIIBE (lead author Yongli Ren, RMIT) has been accepted to TKDE.”
Working with large-scale WiFi sensing data is never easy, and with the bulk the amount of noise increases as well. Here we present a method that clearly demonstrates the interplay, and the benefits of combining the physical location, as well as the search and browsing histories of indoor visitors (in an aggregate, privacy aware way) to improve contextual recommendations in indoor spaces.
Ren, Y., M. Tomko, F. Salim, J. Chan, C. L. A. Clarke and M. Sanderson (accepted, 2017). “A Location-Query-Browse Graph for Contextual Recommendation.” IEEE Transactions on Knowledge and Data Engineering. DOI:10.1109/TKDE.2017.2766059 (pre-print, publisher link)
P.S.> apologies for the huge delay in posting. Many more news are overdue.