Search

Excessive alcohol consumption causes disability and death. Digital interventions are promising means to promote behavioral change and thus prevent alcohol-related harm, especially in critical moments such as driving. This requires real-time information on a person's blood alcohol concentration (BAC). Here, we develop an in-vehicle machine learning system to predict critical BAC levels. Our system leverages driver monitoring cameras mandated in numerous countries worldwide. We evaluate our system with n=30 participants in an interventional simulator study. Our system reliably detects driving under any alcohol influence (area under the receiver operating characteristic curve [AUROC] 0.88) and driving above the WHO recommended limit of 0.05g/dL BAC (AUROC 0.79). Model inspection reveals reliance on pathophysiological effects associated with alcohol consumption. To our knowledge, we are the first to rigorously evaluate the use of driver monitoring cameras for detecting drunk driving. Our results highlight the potential of driver monitoring cameras and enable next-generation drunk driver interaction preventing alcohol-related harm.

The phenomenon of distribution shift (DS) occurs when a dataset at test time differs from the dataset at training time, which can significantly impair the performance of a machine learning model in practical settings due to a lack of knowledge about the data's distribution at test time. To address this problem, we postulate that real-world distributions are composed of latent Invariant Elementary Distributions (I.E.D) across different domains. This assumption implies an invariant structure in the solution space that enables knowledge transfer to unseen domains. To exploit this property for domain generalization, we introduce a modular neural network layer consisting of Gated Domain Units (GDUs) that learn a representation for each latent elementary distribution. During inference, a weighted ensemble of learning machines can be created by comparing new observations with the representations of each elementary distribution. Our flexible framework also accommodates scenarios where explicit domain information is not present. Extensive experiments on image, text, and graph data show consistent performance improvement on out-of-training target domains. These findings support the practicality of the I.E.D assumption and the effectiveness of GDUs for domain generalisation.

Driver identification has emerged as a vital research field, where both practitioners and researchers investigate the potential of driver identification to enable a personalized driving experience. Within recent years, a selection of studies have reported that individuals could be perfectly identified based on their driving behavior under controlled conditions. However, research investigating the potential of driver identification under naturalistic conditions claim accuracies only marginally higher than random guess. The paper at hand provides a comprehensive summary of the recent work, highlighting the main discrepancies in the design of the machine learning approaches, primarily the window length parameter that was considered. Key findings further indicate that the longitudinal vehicle control information is particularly useful for driver identification, leaving the research gap on the extent to which the lateral vehicle control can be used for reliable identification. Building upon existing work, we provide a novel approach for the design of the window length parameter that provides evidence that reliable driver identification can be achieved with data limited to the steering wheel only. The results and insights in this paper are based on data collected from the largest naturalistic driving study conducted in this field. Overall, a neural network based on GRUs was found to provide better identification performance than traditional methods, increasing the prediction accuracy from under 15\% to over 65\% for 15 drivers. When leveraging the full field study dataset, comprising 72 drivers, the accuracy of identification prediction of the approach improved a random guess approach by a factor of 25., Comment: 10 pages, 16 figures, 6 equations

The reactions of the human body to physical exercise, psychophysiological stress and heart diseases are reflected in heart rate variability (HRV). Thus, continuous monitoring of HRV can contribute to determining and predicting issues in well-being and mental health. HRV can be measured in everyday life by consumer wearable devices such as smartwatches which are easily accessible and affordable. However, they are arguably accurate due to the stability of the sensor. We hypothesize a systematic error which is related to the wearer movement. Our evidence builds upon explanatory and predictive modeling: we find a statistically significant correlation between error in HRV measurements and the wearer movement. We show that this error can be minimized by bringing into context additional available sensor information, such as accelerometer data. This work demonstrates our research-in-progress on how neural learning can minimize the error of such smartwatch HRV measurements., Comment: Adjunct Proceedings of the 2019 ACM International Joint Conference on Pervasive and Ubiquitous Computing and the 2019 International Symposium on Wearable Computers

Prosumers in many regions are facing reduced feed-in tariffs and currently have no possibility to influence the level of remuneration for the locally produced solar energy. Peer-to-peer communities may offer an alternative to the feed-in tariff model by enabling prosumers to directly sell their solar energy to local consumers (possibly at a rate that is beneficial for both consumer and prosumer). The Quartierstrom project investigates a transactional energy system that manages the exchange and remuneration of electricity between consumers, prosumers and the local electric grid provider in the absence of intermediaries. This whitepaper describes the prototypical real-world system being implemented in the town of Walenstadt, Switzerland, with 37 participating households. The community members of this pilot project pay a reduced tariff for grid usage if the electricity produced by a prosumer is sold to another community member, which is located on the same voltage or grid level downstream a substation1. Such a tariff structure incentivizes local balancing, i.e. locally produced energy can be consumed locally whenever possible to avoid costs from higher grid levels. The blockchain is a novel technology suitable to log the produced and consumed units of energy within a community, making it possible to implement market places. In those marketplaces, both prosumers and consumers can indicate a price at which they are willing to sell / buy locally produced solar energy without the intermediation of a utility. The key goals of this project are the assessment of A) the technical, economical and ecological feasibility of a blockchain-based community energy system regarding local utilization of solar energy, grid quality and energy efficiency and B) resulting dynamics regarding local market prices and user acceptance., Comment: Energy, solar, local market, auction, blockchain, user-interaction