arXiv subjects

Robert Harle

Publications and source records attributed to Robert Harle.

6 recordsLinked to original sources

arXiv2026

Pixel Watch: Robust Heart Rate Sensing from Multipath PPG and On-Device Deep Learning Trained on 10,000 hours of Free-Living and Fitness Data

The Pixel Watch 2 (PW2) is the first Google smartwatch to combine multipath photoplethysmography (PPG) with deep learning-based heart rate inference, designed to significantly improve sensing accuracy during motion-heavy activities. The device processes 10 optical channels using an on-device, 15-layer temporally dilated convolutional neural network (~300K parameters) to yield a 1 Hz heart rate output. Crucial to this model's performance was its training on a massive dataset comprising 10,000 hours of data from 962 participants, curated from a broader corpus of controlled and free-living activities. We evaluated the PW2's sensing performance across two independent validation sets: an in-house fitness dataset (229 participants, 250 hours) and an external free-living dataset (27 participants, 1000+ hours). The system achieved 95% Limits of Agreement of -10.34 to 8.66 BPM during exercise and -6.57 to 7.48 BPM during free-living activities, demonstrating substantially tighter error margins than previous Google devices. Finally, we discuss key design lessons, emphasizing that large-scale deep learning was instrumental in fully leveraging multipath PPG hardware over traditional signal processing approaches.

cs.HC↗

arXiv2025

Adaptive Cardio Load Targets for Improving Fitness and Performance

Cardio Load, introduced by Google in 2024, is a measure of cardiovascular work (also known as training load) resulting from all the user's activities across the day. It is based on heart rate reserve and captures both activity intensity and duration. Thanks to feedback from users and internal research, we introduce adaptive and personalized targets which will be set weekly. This feature will be available in the Public Preview of the Fitbit app after September 2025. This white paper provides a comprehensive overview of Cardio Load (CL) and how weekly CL targets are established, with examples shown to illustrate the effect of varying CL on the weekly target. We compare Cardio Load and Active Zone Minutes (AZMs), highlighting their distinct purposes, i.e. AZMs for health guidelines and CL for performance measurement. We highlight that CL is accumulated both during active workouts and incidental daily activities, so users are able top-up their CL score with small bouts of activity across the day.

cs.HC↗

arXiv2025

Scaling laws in wearable human activity recognition

Many deep architectures and self-supervised pre-training techniques have been proposed for human activity recognition (HAR) from wearable multimodal sensors. Scaling laws have the potential to help move towards more principled design by linking model capacity with pre-training data volume. Yet, scaling laws have not been established for HAR to the same extent as in language and vision. By conducting an exhaustive grid search on both amount of pre-training data and Transformer architectures, we establish the first known scaling laws for HAR. We show that pre-training loss scales with a power law relationship to amount of data and parameter count and that increasing the number of users in a dataset results in a steeper improvement in performance than increasing data per user, indicating that diversity of pre-training data is important, which contrasts to some previously reported findings in self-supervised HAR. We show that these scaling laws translate to downstream performance improvements on three HAR benchmark datasets of postures, modes of locomotion and activities of daily living: UCI HAR and WISDM Phone and WISDM Watch. Finally, we suggest some previously published works should be revisited in light of these scaling laws with more adequate model capacities.

cs.LG↗

arXiv2021

EarGate: Gait-based User Identification with In-ear Microphones

Human gait is a widely used biometric trait for user identification and recognition. Given the wide-spreading, steady diffusion of ear-worn wearables (Earables) as the new frontier of wearable devices, we investigate the feasibility of earable-based gait identification. Specifically, we look at gait-based identification from the sounds induced by walking and propagated through the musculoskeletal system in the body. Our system, EarGate, leverages an in-ear facing microphone which exploits the earable's occlusion effect to reliably detect the user's gait from inside the ear canal, without impairing the general usage of earphones. With data collected from 31 subjects, we show that EarGate achieves up to 97.26% Balanced Accuracy (BAC) with very low False Acceptance Rate (FAR) and False Rejection Rate (FRR) of 3.23% and 2.25%, respectively. Further, our measurement of power consumption and latency investigates how this gait identification model could live both as a stand-alone or cloud-coupled earable system.

cs.HC↗

arXiv2017

Semi-automated Signal Surveying Using Smartphones and Floorplans

Location fingerprinting locates devices based on pattern matching signal observations to a pre-defined signal map. This paper introduces a technique to enable fast signal map creation given a dedicated surveyor with a smartphone and floorplan. Our technique (PFSurvey) uses accelerometer, gyroscope and magnetometer data to estimate the surveyor's trajectory post-hoc using Simultaneous Localisation and Mapping and particle filtering to incorporate a building floorplan. We demonstrate conventional methods can fail to recover the survey path robustly and determine the room unambiguously. To counter this we use a novel loop closure detection method based on magnetic field signals and propose to incorporate the magnetic loop closures and straight-line constraints into the filtering process to ensure robust trajectory recovery. We show this allows room ambiguities to be resolved. An entire building can be surveyed by the proposed system in minutes rather than days. We evaluate in a large office space and compare to state-of-the-art approaches. We achieve trajectories within 1.1 m of the ground truth 90% of the time. Output signal maps well approximate those built from conventional, laborious manual survey. We also demonstrate that the signal maps built by PFSurvey provide similar or even better positioning performance than the manual signal maps.

cs.RO↗

arXiv2017

A Contextual Investigation of Location in the Home Using Bluetooth Low Energy Beacons

Location sensing is a key enabling technology for Ubicomp to support contextual interaction. However, the laboratories where calibrated testing of location technologies is done are very different to the domestic situations where `context' is a problematic social construct. This study reports measurements of Bluetooth beacons, informed by laboratory studies, but done in diverse domestic settings. The design of these surveys has been motivated by the natural environment implied in the Bluetooth beacon standards - relating the technical environment of the beacon to the function of spaces within the home. This research method can be considered as a situated, `ethnographic' technical response to the study of physical infrastructure that arises through social processes. The results offer insights for the future design of `seamful' approaches to indoor location sensing, and to the ways that context might be constructed and interpreted in a seamful manner.

cs.HC↗