Physical activity has not been objectively measured in prospective cohorts with sufficiently large numbers to reliably detect associations with multiple health outcomes. Technological advances now make this possible. We describe the methods used to collect and analyse accelerometer measured physical activity in over 100,000 participants of the UK Biobank study, and report variation by age, sex, day, time of day, and season. Participants were approached by email to wear a wrist-worn accelerometer for seven days that was posted to them. Physical activity information was extracted from 100Hz raw triaxial acceleration data after calibration, removal of gravity and sensor noise, and identification of wear / non-wear episodes. We report age- and sex-specific wear-time compliance and accelerometer measured physical activity, overall and by hour-of-day, week-weekend day and season. 103,712 datasets were received (44.8% response), with a median wear-time of 6.9 days (IQR:6.5–7.0). 96,600 participants (93.3%) provided valid data for physical activity analyses. Vector magnitude, a proxy for overall physical activity, was 7.5% (2.35mg) lower per decade of age (Cohen’s d = 0.9). Women had a higher vector magnitude than men, apart from those aged 45-54yrs. There were major differences in vector magnitude by time of day (d = 0.66). Vector magnitude differences between week and weekend days (d = 0.12 for men, d = 0.09 for women) and between seasons (d = 0.27 for men, d = 0.15 for women) were small. It is feasible to collect and analyse objective physical activity data in large studies. The summary measure of overall physical activity is lower in older participants and age-related differences in activity are most prominent in the afternoon and evening. This work lays the foundation for studies of physical activity and its health consequences. Our summary variables are part of the UK Biobank dataset and can be used by researchers as exposures, confounding factors or outcome variables in future analyses.

Smart home environments are designed to provide services that help improve the quality of life for the occupant via a variety of sensors and actuators installed throughout the space. Many automated actions taken by a smart home are governed by the output of an underlying activity recognition system. However, activity recognition systems may not be perfectly accurate, and therefore inconsistencies in smart home operations can lead users reliant on smart home predictions to wonder “Why did the smart home do that?” In this work, we build on insights from Explainable Artificial Intelligence (XAI) techniques and introduce an explainable activity recognition framework in which we leverage leading XAI methods (Local Interpretable Model-agnostic Explanations, SHapley Additive exPlanations (SHAP), Anchors) to generate natural language explanations that explain what about an activity led to the given classification. We evaluate our framework in the context of a commonly targeted smart home scenario: autonomous remote caregiver monitoring for individuals who are living alone or need assistance. Within the context of remote caregiver monitoring, we perform a two-step evaluation: (a) utilize Machine Learning experts to assess the sensibility of explanations and (b) recruit non-experts in two user remote caregiver monitoring scenarios, synchronous and asynchronous, to assess the effectiveness of explanations generated via our framework. Our results show that the XAI approach, SHAP, has a 92% success rate in generating sensible explanations. Moreover, in 83% of sampled scenarios users preferred natural language explanations over a simple activity label, underscoring the need for explainable activity recognition systems. Finally, we show that explanations generated by some XAI methods can lead users to lose confidence in the accuracy of the underlying activity recognition model, while others lead users to gain confidence. Taking all studied factors into consideration, we make a recommendation regarding which existing XAI method leads to the best performance in the domain of smart home automation and discuss a range of topics for future work to further improve explainable activity recognition.

One of the primary challenges in the field of human activity recognition (HAR) is the lack of large labeled datasets. This hinders the development of robust and generalizable models. Recently, cross modality transfer approaches have been explored that can alleviate the problem of data scarcity. These approaches convert existing datasets from a source modality, such as video, to a target modality, such as inertial measurement units (IMUs). With the emergence of generative AI models such as large language models (LLMs) and text-driven motion synthesis models, language has become a promising source data modality as well - as shown in proof of concepts such as IMUGPT. In this work, we conduct a large-scale evaluation of language-based cross modality transfer to determine their effectiveness for HAR. Based on this study, we introduce two new extensions for IMUGPT that enhance its use for practical HAR application scenarios: a motion filter capable of filtering out irrelevant motion sequences to ensure the relevance of the generated virtual IMU data, and a set of metrics that measure the diversity of the generated data facilitating the determination of when to stop generating virtual IMU data for both effective and efficient processing. We demonstrate that our diversity metrics can reduce the effort needed for the generation of virtual IMU data by at least 50%, which opens up IMUGPT for practical use cases beyond a mere proof of concept.

Mobile phone data are an interesting new data source for official statistics. However, multiple problems and uncertainties need to be solved before these data can inform, support or even become an integral part of statistical production processes. In this article, we focus on arguably the most important problem hindering the application of mobile phone data in official statistics: detecting home locations. We argue that current efforts to detect home locations suffer from a blind deployment of criteria to define a place of residence and from limited validation possibilities. We support our argument by analysing the performance of five home detection algorithms (HDAs) that have been applied to a large, French, Call Detailed Record (CDR) data set (~18 million users, five months). Our results show that criteria choice in HDAs influences the detection of home locations for up to about 40% of users, that HDAs perform poorly when compared with a validation data set (resulting in 358-gap), and that their performance is sensitive to the time period and the duration of observation. Based on our findings and experiences, we offer several recommendations for official statistics. If adopted, our recommendations would help ensure more reliable use of mobile phone data vis-à-vis official statistics.

We designed and evaluated an assumption-free, deep learning-based methodology for animal health monitoring, specifically for the early detection of respiratory disease in growing pigs based on environmental sensor data. Two recurrent neural networks (RNNs), each comprising gated recurrent units (GRUs), were used to create an autoencoder (GRU-AE) into which environmental data, collected from a variety of sensors, was processed to detect anomalies. An autoencoder is a type of network trained to reconstruct the patterns it is fed as input. By training the GRU-AE using environmental data that did not lead to an occurrence of respiratory disease, data that did not fit the pattern of “healthy environmental data” had a greater reconstruction error. All reconstruction errors were labelled as either normal or anomalous using threshold-based anomaly detection optimised with particle swarm optimisation (PSO), from which alerts are raised. The results from the GRU-AE method outperformed state-of-the-art techniques, raising alerts when such predictions deviated from the actual observations. The results show that a change in the environment can result in occurrences of pigs showing symptoms of respiratory disease within 1–7 days, meaning that there is a period of time during which their keepers can act to mitigate the negative effect of respiratory diseases, such as porcine reproductive and respiratory syndrome (PRRS), a common and destructive disease endemic in pigs.

The ubiquitous availability of smartphones and smartwatches with integrated inertial measurement units (IMUs) enables straightforward capturing of human activities through collecting movement data. For specific applications of sensor-based human activity recognition (HAR), however, logistical challenges and burgeoning costs render especially the ground-truth annotation of such data a difficult endeavor, resulting in limited scale and diversity of datasets available for deriving effective HAR systems and less than ideal recognition capabilities. Transfer learning, i.e., leveraging publicly available labeled datasets to first learn useful representations that can then be fine-tuned using limited amounts of labeled data from a target domain, can alleviate some of the performance issues of contemporary HAR systems. Yet they can fail when the differences between source and target conditions are too large and/or only few samples from a target application domain are available—each of which are typical challenges in real-world human activity recognition scenarios. In this article, we present an approach for economic use of publicly available labeled HAR datasets for effective transfer learning. We introduce a novel transfer learning framework—Cross-Domain HAR—which follows the teacher-student self-training paradigm to more effectively recognize activities with very limited label information. It bridges conceptual gaps between source and target domains, including sensor locations and type of activities. Cross-Domain HAR enables substantial performance improvements over the state-of-the-art in sensor-based HAR scenarios. Through our extensive experimental evaluation on a range of benchmark datasets we specifically demonstrate the effectiveness of our approach for practically relevant few-shot activity recognition scenarios. We also present a detailed analysis into how the individual components of our framework affect downstream performance and provide practical suggestions for using the framework in real-world applications.