Program of the meetup

 

SAM: Open Source Python toolkit for time series analysis

Royal HaskoningDHV recently published their first open source package called SAM (Smart Asset Management). This Python package has already been used internally for years and forms the basis of many of our forecasting and anomaly detection models. During this presentation we will talk about the SAM package and we'll give some examples and use cases to help other data scientists to use it themselves or even better: contribute to the project!

Presented by: Ruben Peters - Senior Data Scientist at Royal HaskoningDHV

Automated subtitling at RTL

Having subtitles is important for making all of our content accessible for everybody, including people with hearing problems. However, manual subtitling is expensive and time-consuming. This is why we are doing a pilot for automating the subtitling process. The task is non-trivial and consists of more building blocks than you might have expected. From transformers and language models to pipelines and business constraints. In this talk you will get a sneak peek into these building blocks.

Presented by: Sanne Eggengoor - Data scientist at RTL

Towards Automatic Inference of Layouts of Traffic Intersections for Smart Cities 

Intersection-topology descriptions can help to improve traffic flow, but currently require significant manual creation effort. This paper describes ongoing work on a combination of algorithms to extract the drive lines across intersections from images and point clouds, captured by a ground-based vehicle. The extraction is based on paint striping and edge-of-road line features, which are clustered in subsequent stages into lane separators for all legs of the intersection. The GEO recall with paint striping is 0.29, and significantly contributes to successfully inferring the junction. However, this score decreases when edge-of- road features are added which is counter-intuitive. We indicate ways to combat this problem and further improve our results.

Presented by: Julien Vijverberg - Senior Scientist at CycloMedia Technology B.V.

Date, time and agenda

Date and Time

Date: Friday 21st of October
Start time: 15:00

Agenda

15.00 - 15.30 SAM: Open Source Python toolkit for time series analysis
15.30 - 16.00 Automated subtitling at RTL
16.00 - 16.30 Towards Automatic Inference of Layouts of Traffic Intersections for Smart Cities  
16.30 - 19.00 Borrel - Drinks and Snacks

For whom is this meetup

This meetup is created for data scientists and engineers who are looking
for an extra dose of knowledge, inspiration, and insights.