This paper introduces M3fed, a novel solution for federated learning of movement anomaly detection models. This innovation has the potential to improve data privacy and reduce communication costs in machine learning for movement anomaly detection. We present the novel federated learning (FL) strategies employed to train M3fed, perform an example experiment with maritime AIS data, and evaluate the results with respect to communication costs and FL model quality by comparing classic centralized M3and the new federated M3fed.

Data exploration is an essential task for gaining an understanding of the potential and limitations of novel datasets. This paper discusses the challenges related to exploring large Automatic Identification System (AIS) datasets. We address these challenges using trajectory-based analysis approaches implemented in distributed computing environments using Spark and GeoMesa. This approach enables the exploration of datasets that are too big to handle within conventional spatial database systems. We demonstrate our approach using a case study of 4 billion AIS records.

Exploratory analysis is an important tool to formulate hypotheses about data and build data-driven models. To efficiently explore massive movement datasets, researcher and analysts require appropriate exploratory analysis tools. However, there is a lack of appropriate tools for movement data exploration that can handle large data volumes. We therefore propose a novel scalable distributed exploratory analysis model for massive movement datasets with billions of records which we call M3. M3 is more flexible than classical aggregation approaches that use grids with aggregate statistics and it can be updated incrementally with large amounts of data. We demonstrate this new model and its implementation in Apache Spark using massive ship and vehicle movement data with up to 3.9 billion records.

Human mobility modeling for either transportation system development or individual location based services has a tangible impact on people's everyday experience. In recent years cell phone data has received a lot of attention as a promising data source because of the wide coverage, long observation period, and low cost. The challenge in utilizing such data is how to robustly extract people's trip sequences from sparse and noisy cell phone data and endow the extracted trips with semantic meaning, i.e., trip purposes.In this study we reconstruct trip sequences from sparse cell phone records. Next we propose a Bayesian trip purpose classification method and compare it to a Markov random field based trip purpose clustering method, representing scenarios with and without labeled training data respectively. This procedure shows how the cell phone data, despite their coarse granularity and sparsity, can be turned into a low cost, long term, and ubiquitous sensor network for mobility related services.

Existing visual surveillance systems typically require that human operators observe video streams from different cameras, which becomes infeasible if the number of observed cameras is ever increasing. In this paper, we present a new surveillance system that combines automatic video analysis (i.e., single person tracking and crowd analysis) and interactive visualization. Our novel visualization takes advantage of a high resolution display and given 3D information to focus the operator's attention to interesting/ critical areas of the observed area. This is realized by embedding the results of automatic scene analysis techniques into the visualization. By providing different visualization modes, the user can easily switch between the different modes and can select the mode which provides most information. The system is demonstrated for a real setup on a university campus.

We present a crowd analysis approach computing a representation of the major pedestrian flows in complex scenes. It treats crowds as a set of moving particles and builds a spatio-temporal model of motion events. A Growing Neural Gas algorithm encodes optical flow particle trajectories as sequences of local motion events and learns a topology which is the base for trajectory distance computations. Trajectory prototypes are aligned with a two-open-ends version of Dynamic Time Warping to cope with fragmented trajectores. The trajectories are grouped into an automatically determined number of clusters with self-tuning spectral clustering. The clusters are compactly represented with the help of Principal Component Analysis, providing a technique for unusual motion detection based on residuals. We demonstrate results for a publicly available crowded video and a scene with volunteers moving according to defined origin-destination flows.