Nico Jahn

Helping to improve the machine learning infrastructure and develop solutions for our clients.

Helping to improve the machine learning infrastructure and develop solutions for our clients.

A software engineer who further developed and optimized Neural APC. Creating training and inference workflow for the algorithm with special needs.

My area of responsibility was the server infrastructure. This included updating and managing the Windows domain controller of the faculty, managing the software systems (distribution of packets), and keeping the Windows clients from crashing due to Windows updates. A good mixture of ubuntu and Windows servers, as well as macOS and Windows clients.

Real-time load information in public transport is of high importance for both passengers and service providers. Neural algorithms have shown a high performance on various object counting tasks and play a continually growing methodological role in developing automated passenger counting systems. However, the publication of public-space video footage is often contradicted by legal and ethical considerations to protect the passengers’ privacy. This work proposes an end-to-end Long Short-Term Memory network with a problem-adapted cost function that learned to count boarding and alighting passengers on a publicly available, comprehensive dataset of approx.13,000 manually annotated low-resolution 3D LiDAR video recordings (depth information only) from the doorways of a regional train. These depth recordings do not allow the identification of single individuals. For each door opening phase, the trained models predict the correct passenger count (ranging from 0 to 67) in approx.96% of boarding and alighting, respectively. Repeated training with different training and validation sets confirms the independence of this result from a specific test set.

Automatic passenger counting (APC) in public transportation has been approached with various machine learning and artificial intelligence methods since its introduction in the 1970s. It is mainly used for revenue sharing, which (in Germany alone) is in the billions annually and supply planning, which is essential for services of general interest. While equivalence testing is becoming more popular than difference detection (Student’s t-test), the former is much more difficult to pass to ensure low user risk. On the other hand, recent developments in artificial intelligence have led to algorithms that promise much higher counting quality (lower bias). However, gradient-based methods (including Deep Learning) typically run into local optima. In this work, we explore and exploit various aspects of machine learning to increase the reliability, performance, and counting quality of the Neural APC 3D depth video-based LSTM neural network. We perform a grid search with several fundamental parameters: the selection and size of the training set, which is similar to cross-validation, and the initial network weights and randomness during the training process. Using this experiment, we show how aggregation techniques such as ensemble quantiles can reduce bias, and we give an idea of the overall spread of the results. We utilize the test success chance, a simulative metric based on the empirical distribution. We also employ a post-training Monte Carlo quantization approach and introduce cumulative summation to turn counting into a stationary method and allow unbounded counts. All in all, our numerous additions provide a major quality increase to the NAPC.