The accurate detection of the mobile context information of public transportation vehicles and their passengers is a key feature to realize intelligent transportation systems. A topical example is in-vehicle presence detection that can, e.g., be used to ticket passengers automatically. Unfortunately, most existing solutions in this field suffer from low spatiotemporal accuracy which impedes their use in practice. In previous work, we addressed this challenge through a deep learning-based framework, called DeepMatch, that allows us to detect in-vehicle presence with a high degree of accuracy. DeepMatch utilizes the smartphone of a passenger to analyse and match the event streams of its own sensors with the event streams of counterpart sensors provided by a reference unit that is installed inside the vehicle. This is achieved through a new learning model architecture using Stacked Convolutional Autoencoders to compress sensor input streams by feature extraction and dimensionality reduction as well as a deep convolutional neural network to match the streams of the user phone and the reference device. The sensor stream compression is offloaded to the smartphone, while the matching is performed in a server. In this paper, we introduce DeepMatch2. It is an amended version of DeepMatch that reduces the amount of data to be transferred from the user and reference devices to the server by the factor of four. Further, DeepMatch2 improves the already good accuracy of DeepMatch from 97.81% to 98.51%. Moreover, we propose a travel inference algorithm, based on DeepMatch2, to detect the duration of whole passenger trips in public transport vehicles with a high degree of precision. This is needed to create intelligent and highly reliable auto-ticketing systems. Thanks to the high accuracy of 98.51% by DeepMatch2, the inferences can be carried out with a negligible error rate.

Recent developments in the field of indoor RealTime Locating Systems (RTLS) using mobile devices stimulate decision support for users. For instance, smartphone-based navigation in shops can enable location-aware recommendations of certain products to customers. An impeding factor to realize such systems is that they need the exact position of products. Existing product localization solutions, however, are based on tagging or manual location registering which tend to be quite costly and laborious. In this paper, we propose an automated product localization approach solving this problem. Our system infers the location of products based on the results of accumulating two sets of customer data, i.e., the locations at which the customers stop for picking up items as well as the list of the items, they purchase. These two data sets are accumulated for a large number of users, making it possible to build correct mappings between the products and their positions. We introduce a basic version of our localization algorithm and two extensions. One helps to improve calculating the position of relocated products while the other one fosters a faster localization using a smaller number of user data sets. We discuss the results of various simulation runs which give evidence that our system has a good potential to work in practice.