Data Analytics

Chair: Sandjah Bhulai (Vrije Universiteit Amsterdam)

Speaker: Joost Berkhout (Vrije Universiteit Amsterdam and CWI)

Abstract: In this talk a modern industrial plant is considered that produces a large variety of composite biomaterials. Incoming orders are processed in real-time and slotted into a production schedule to meet the required delivery deadline. The scheduling problem is complicated because of numerous constraints, chief among them the limited storage capacity for intermediate or finished products and avoiding contamination between product runs. Solving this complicated scheduling problem currently requires comprehensive manual intervention by experienced planning experts. As a result, it is labor-intensive and lacks flexibility. Moreover, it misses the chance of utilizing the wealth of sensory production data in an industry 4.0 era to enhance the scheduling. This talk presents an algorithm that combines mixed integer linear optimization and evolutionary computing to solve the scheduling problem in the industry 4.0 setting.

Title: Transaction-driven mobility analysis for travel mode choices
Speaker: Jesper Slik (Vrije Universiteit Amsterdam)

Abstract: Urban planning can benefit tremendously from a better understanding of where, when, why, and how people travel. Through advances in technology, detailed data on the travel behavior of individuals has become available. This data can be leveraged to understand why one prefers one mode of transportation over another one. In this paper, we analyze a unique dataset through which we can address this question. We show that the travel behavior in our dataset is highly predictable, with an accuracy of 97\%. The main predictors are reachability features, more so than specific travel times. Moreover, the travel type (commute or personal) has a considerable influence on travel mode choice.

Title: A Diffusion-based Analysis of a Multi-Class Road Traffic Network
Speaker: Jaap Storm (Vrije Universiteit Amsterdam)

Abstract: In traffic flow theory, a major focus is to describe and predict traffic dynamics on road networks. To this end, a broad range of traffic models to develop mechanisms that effectively control streams of vehicles. In this talk, we will discuss a stochastic traffic flow model that describes the evolution of vehicles over a road network of arbitrary topology. Our setup is capable of handling multiple types of vehicles, with a very wide-class of macroscopic fundamental diagrams. With the model, we can efficiently evaluate the efficacy of control policies in traffic, using stochastic metrics. This will be illustrated with several numerical examples.