If you're at #AGIT2025, I'd love to see you at our #MobilityDataScience workshop focused on #PublicTransport tomorrow morning
09:00-10:15 Session 1A: WS: Mobility Data Science & KI – Potenziale für den öffentlichen Verkehr
If you're at #AGIT2025, I'd love to see you at our #MobilityDataScience workshop focused on #PublicTransport tomorrow morning
09:00-10:15 Session 1A: WS: Mobility Data Science & KI – Potenziale für den öffentlichen Verkehr
#MobilityDataAnalytics & #GIScience all around:
Attending the @emeraldseu GA today. Presented progress on #Trajectools and our #explainableAI & #activeLearning for #MobilityDataScience. While simultaneously traveling to #AGIT2025
New @movingpandas 0.22 and #Trajectools 2.6 just landed
Over 50% runtime reduction for many #MovementDataAnalytics tasks
And here's @martinfleis et al.'s new street network generalization tool:
Another interesting new paper on street network analysis, HT @gboeing
it's surprisingly hard to count intersections
Direct links for convenience ...
Paper: https://www.mdpi.com/2071-1050/17/8/3634
Code: https://github.com/plus-mobilitylab/netascore/tree/v0.9.0
New versions of @movingpandas and #Trajectools have just landed:
#MovingPandas 0.21.3 https://github.com/movingpandas/movingpandas/releases/tag/v0.21.3
Trajectools 2.5 https://codeberg.org/movingpandas/trajectools/releases/tag/v2.5
Please update your MovingPandas install to get all the improvements in #QGIS Trajectools https://plugins.qgis.org/plugins/processing_trajectory/#plugin-versions
The quest for a fair TimeGPT benchmark
At the end of yesterday's #TimeGPT for mobility post, we concluded that TimeGPT's trainingset probably included a copy of the popular BikeNYC timeseries dataset and that, therefore, we were not looking at a fair comparison ...
http://anitagraser.com/2025/03/29/the-quest-for-a-fair-timegpt-benchmark/
Only one more week to submit to ACM TSAS special issue on Urban Mobility https://dl.acm.org/pb-assets/static_journal_pages/tsas/pdf/TSAS_Special_Issue_Urban_Mobility-1737749682787.pdf
HT https://mastodon.social/@luis_de_sousa/113946946892555809
Today I'm at #edbticdt2025 to present MobiML, our latest contribution to facilitate #MachineLearning from movement data, building on @movingpandas, #pymeos, and others
More details:
https://github.com/movingpandas/mobiml
New #IOT research using yours truely:
Koszewski et al. (2025). Utilizing IoT Sensors and Spatial Data Mining for Analysis of Urban Space Actors’ Behavior in University Campus Space Design.
https://doi.org/10.3390/s25051393
"Trajectories were processed by the MovingPandas Python library, which offers several valuable processing algorithms"
For the full list of publications we're aware of, check out:
The EMERALDS project @emeraldseu is hosting an MLOps webinar "EMERALDS Data Infrastructure and Development Frameworks” on 21 February, at 11:30 CET, see https://emeralds-horizon.eu/events/emeralds-webinar-data-infrastructure-and-development-frameworks
The talks explore the design and implementation of a dedicated #MLOps platform built with specialised #mobility libraries and tools. This platform is tailored to support ML engineers in the development and deployment of machine learning models for real-world applications
#Moveapps is looking for a Technical Assistant (m/f/d) proficient in #RStats and/or #Python to improve their #MovementDataAnalytics plattform
I've had smoother releases
But hey, #MovingPandas 0.21 is here https://github.com/movingpandas/movingpandas/releases
Make sure to update if you want to use the new #QGIS #Trajectools plugin version which will be released soon
New #bicycle research #preprint using yours truly:
Skåntorp et al. (2024). Data-driven bicycle driving cycles via mixed-integer programming
"we utilized the #KalmanFilter from the #MovingPandas library"
http://dx.doi.org/10.13140/RG.2.2.19928.10240
For the full list of publications we're aware of, check out:
Updated my collection of open source projects in the #MobilityDataScience / #MovementDataAnalytics with new findings from #SDSL2024
https://github.com/anitagraser/movement-analysis-tools
Any more suggestions welcome
Leaving Prague with tons of new ideas and impressions.
Thanks @martinfleis and team for organizing and hosting this 2nd edition of SDSL. Looking forward to many more to come
Pleasure to see more and more use from students:
"we utilize the stop detection tools provided by MovingPandas"
Wicaksono, S. B. (2024). From Data Cleaning to Predictive Models: A Strategic Approach to Analyzing Bus and Ship Trajectories. Master Thesis in Data Science, Department of Mathemetics, University of Padova.
New #MovingPandas tutorial: taking #OGC #MovingFeatures full circle with MF-JSON
Read #MFJSON to TrajectoryCollection and write it out again in the standard MovingPoint JSON encoding
#MobileDataManagement #MobilityDataScience #MovementDataAnalytics