Electrocardiogram (ECG) recording systems are increasingly being integrated into consumer wearable systems such as smartwatches, providing users with access to clinically-relevant information about their heart activity anytime, anywhere. The increasing adoption of in-ear wearables, known as earables, as well as their stable position on the body, makes them an attractive prospect for ECG integration. However, this comes with several challenges. Other biosignals, including those from the brain and surrounding muscles, are detectable at the ear in the same frequency bands with much higher amplitudes. This means that the ECG signal-to-noise ratio (SNR) can be extremely low at this location. The few existing denoising approaches mostly rely on autoencoders. In some cases they fail to recover the ECG morphology, and their black-box nature does not allow for explainability or understanding of limitations. To address these issues, we introduce a novel system to record and denoise ear-ECG signals, leveraging open-source hardware and the Extended Kalman Filter. In-ear audio recording of heart sounds is used to accurately determine timings of cardiac cycles. From these timings, a short-term ensemble average ECG signal is calculated, which is used to fit the parameters of a dynamical ECG model to an individual user. The Kalman filter is then applied to the full time series ECG for denoising, using the dynamical model for its state prediction steps, and heart sounds as phase measurements. We have evaluated the system with data collected from 18 participants. The results report a mean SNR of 6.4 dB, mean absolute QT interval error of 54 ms, and heart rate error of 3 BPM, demonstrating the system's potential for continuous, non-invasive, user-friendly ECG monitoring.

Gait behaviour is a key health metric. Temporal, spatial and kinetic walking gait parameters are valuable in enhancing sport performance and early health diagnostics Full gait assessment requires a gait clinic and existing wearable gait tracking systems typically measure isolated subsets of parameters tailored to specific applications. This is useful when the condition to be monitored is known, but fails to offer a comprehensive view of an individual’s gait traits when their pathology is unknown or changing, or a general assessment is required. To support holistic walking gait tracking, we introduce WalkEar, a novel sensing platform designed to simultaneously track gait parameters using commodity earbuds. WalkEar operates by detecting gait events to derive temporal gait parameters and segment the IMU data. WalkEar then progresses earable gait assessment by, for the first time, estimating kinetic gait parameters and reconstructing the vGRF curve using machine learning. Each parameter is calculated on a step-to-step basis for gait variability and asymmetry. We developed an earbud prototype and collected data from 13 participants using gold standard force plates and instrumented treadmill ground truth. Extensive experiments demonstrate the promising performance of WalkEar, achieving an overall MAPE of 5.1% in estimating gait, 2.0% MAPE on kinetic gait parameters, and an NRMSE of 5.3% for vGRF curve reconstruction.

Template matching methods can benefit from multi-cores architecture in order to parallelise and accelerate the matching of multiple templates. We present WLCSSCuda: a GPU accelerated implementation of the Warping Longest Common Subsequence (WLCSS) pattern recognition algorithm. We evaluate our method on 4 NVIDIA GPUs and 4 multi-cores CPUs. We observe a 67-times speedup for the GPU implementation in the best case against the multithreaded CPU implementation.

We have completed the collection of one of the richest accurately annotated mobile dataset of modes of transportation and locomotion. To do this, we developed a highly reliable Android application called DataLogger capable of recording multisensor data from multiple synchronized smartphones simultaneously. The application allows real-time data annotation. We explain how we designed the app to achieve high reliability and ease of use. We also present an evaluation of the application in a big-data collection (750 hours, 950 GB of data, 17 different sensor modalities), analysing the data loss (less than 0.4%) and battery consumption (≈ 6% on average per hour). The application is available as open source.

We explain how to obtain a highly versatile and precisely annotated dataset for the multimodal locomotion of mobile users. After presenting the experimental setup, data management challenges and potential applications, we conclude with the best practices for assuring data quality and reducing loss. The dataset currently comprises 7 months of measurements, collected by smartphone's sensors and a body-worn camera, while the 3 participants used 8 different modes of transportation. It comprises 950 GB of sensor data, which corresponds to 750 hours of labelled data. The obtained data will be useful for a wide range of research questions related to activity recognition, and will be made available to the community1.