Daniel Roggen
YOU?
Author Swipe
View article: Assisting annotators of wearable activity recognition datasets through automated sensor-based suggestions
Assisting annotators of wearable activity recognition datasets through automated sensor-based suggestions Open
Wearable Activity Recognition consists of recognizing actions of people from on-body sensor data using machine learning. Developing suitable machine learning models typically requires substantial amounts of annotated training data. Manuall…
View article: Physically Plausible Data Augmentations for Wearable IMU-based Human Activity Recognition Using Physics Simulation
Physically Plausible Data Augmentations for Wearable IMU-based Human Activity Recognition Using Physics Simulation Open
The scarcity of high-quality labeled data in sensor-based Human Activity Recognition (HAR) hinders model performance and limits generalization across real-world scenarios. Data augmentation is a key strategy to mitigate this issue by enhan…
View article: Scaling laws in wearable human activity recognition
Scaling laws in wearable human activity recognition Open
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 li…
View article: WIMUSim: simulating realistic variabilities in wearable IMUs for human activity recognition
WIMUSim: simulating realistic variabilities in wearable IMUs for human activity recognition Open
Introduction Physics simulation has emerged as a promising approach to generate virtual Inertial Measurement Unit (IMU) data, offering a solution to reduce the extensive cost and effort of real-world data collection. However, the fidelity …
View article: In Shift and In Variance: Assessing the Robustness of HAR Deep Learning Models Against Variability
In Shift and In Variance: Assessing the Robustness of HAR Deep Learning Models Against Variability Open
Deep learning (DL)-based Human Activity Recognition (HAR) using wearable inertial measurement unit (IMU) sensors can revolutionize continuous health monitoring and early disease prediction. However, most DL HAR models are untested in their…
View article: Intuition Brain Health Study: a smartphone- and smartwatch-based virtual, observational study using multimodal mobile sensing to classify and detect mild cognitive impairment
Intuition Brain Health Study: a smartphone- and smartwatch-based virtual, observational study using multimodal mobile sensing to classify and detect mild cognitive impairment Open
Smart devices are utilized by billions worldwide. The ubiquity of consumer-grade smart devices provides opportunities to robustly capture real-world cognition. Intuition (NCT05058950) was a virtual, observational study that enrolled 23,004…
View article: DISPEL: A Python Framework for Developing Measures From Digital Health Technologies
DISPEL: A Python Framework for Developing Measures From Digital Health Technologies Open
Goal: This paper introduces DISPEL, a Python framework to facilitate development of sensor-derived measures (SDMs) from data collected with digital health technologies in the context of therapeutic development for neurodegenerative disease…
View article: Digital Mobility Measures: A Window into Real‐World Severity and Progression of Parkinson's Disease
Digital Mobility Measures: A Window into Real‐World Severity and Progression of Parkinson's Disease Open
Background Real‐world monitoring using wearable sensors has enormous potential for assessing disease severity and symptoms among persons with Parkinson's disease (PD). Many distinct features can be extracted, reflecting multiple mobility d…
View article: Summary of SHL Challenge 2023: Recognizing Locomotion and Transportation Mode from GPS and Motion Sensors
Summary of SHL Challenge 2023: Recognizing Locomotion and Transportation Mode from GPS and Motion Sensors Open
In this paper we summarize the contributions of participants to the fifth Sussex-Huawei Locomotion-Transportation (SHL) Recognition Challenge organized at the HASCA Workshop of UbiComp/ISWC 2023. The goal of this machine learning/data scie…
View article: Speeding up deep neural architecture search for wearable activity recognition with early prediction of converged performance
Speeding up deep neural architecture search for wearable activity recognition with early prediction of converged performance Open
Neural architecture search (NAS) has the potential to uncover more performant networks for human activity recognition from wearable sensor data. However, a naive evaluation of the search space is computationally expensive. We introduce neu…
View article: Hierarchical Feature Recovery for Robust Human Activity Recognition in Body Sensor Networks
Hierarchical Feature Recovery for Robust Human Activity Recognition in Body Sensor Networks Open
With the advances in Body Sensor Networks (BSNs) and textile-integrated sensing, more sensor data becomes available from which human activities are recognised. However, some sensors may become unavailable unexpectedly in practice. Previous…
View article: The 25th Edition of the International Symposium on Wearable Computers
The 25th Edition of the International Symposium on Wearable Computers Open
This year marks the 25th edition of ISWC—International Symposium on Wearable Computers—which is the leading research venue for all the topics related to wearables. The conference was held September 21st—24th, 2021, with workshops dedicated…
View article: Opportunity++: A Multimodal Dataset for Video- and Wearable, Object and Ambient Sensors-Based Human Activity Recognition
Opportunity++: A Multimodal Dataset for Video- and Wearable, Object and Ambient Sensors-Based Human Activity Recognition Open
DATA REPORT article Front. Comput. Sci., 20 December 2021 | https://doi.org/10.3389/fcomp.2021.792065
View article: Three-Year Review of the 2018–2020 SHL Challenge on Transportation and Locomotion Mode Recognition From Mobile Sensors
Three-Year Review of the 2018–2020 SHL Challenge on Transportation and Locomotion Mode Recognition From Mobile Sensors Open
The Sussex-Huawei Locomotion-Transportation (SHL) Recognition Challenges aim to advance and capture the state-of-the-art in locomotion and transportation mode recognition from smartphone motion (inertial) sensors. The goal of this series o…
View article: Locomotion and Transportation Mode Recognition from GPS and Radio Signals: Summary of SHL Challenge 2021
Locomotion and Transportation Mode Recognition from GPS and Radio Signals: Summary of SHL Challenge 2021 Open
In this paper we summarize the contributions of participants to the fourth Sussex-Huawei Locomotion-Transportation (SHL) Recognition Challenge organized at the HASCA Workshop of UbiComp/ISWC 2021. The goal of this machine learning/data sci…
View article: Detecting Freezing of Gait with Earables Trained from VR Motion Capture Data
Detecting Freezing of Gait with Earables Trained from VR Motion Capture Data Open
Freezing of Gait (FoG) is a common disabling motor symptom in Parkinson’s Disease (PD). Auditory cueing provided when FoG is detected can help mitigate the condition, for which earables are potentially well suited as they are capable of mo…
View article: Soft Gel-free ECG electrodes based on Biocompatible Coconut-Oil and Carbon Black
Soft Gel-free ECG electrodes based on Biocompatible Coconut-Oil and Carbon Black Open
Recent developments in telemedicine have caused significant interest in the prolonged monitoring of bioelectric signals. This drives the search for easy-to-use, biocompatible, and environmentally friendly alternatives to conventional resis…
View article: Strain Sensors: Coco Stretch: Strain Sensors Based on Natural Coconut Oil and Carbon Black Filled Elastomers (Adv. Mater. Technol. 2/2021)
Strain Sensors: Coco Stretch: Strain Sensors Based on Natural Coconut Oil and Carbon Black Filled Elastomers (Adv. Mater. Technol. 2/2021) Open
An inexpensive biocompatible strain sensor constituting of an elastomer filled with natural coconut oil and carbon black is shown by Pasindu Lugoda and co-workers in article number 2000780. The easily manufacturable and eco-friendly fabric…
View article: Coco Stretch: Strain Sensors Based on Natural Coconut Oil and Carbon Black Filled Elastomers
Coco Stretch: Strain Sensors Based on Natural Coconut Oil and Carbon Black Filled Elastomers Open
A biocompatible inexpensive strain sensor constituting of an elastomer filled with natural coconut oil (CNO) and carbon black (CB) is presented here. Strain sensors are widely utilized for applications in human activity recognition, health…
View article: Transportation mode recognition fusing wearable motion, sound and vision sensors
Transportation mode recognition fusing wearable motion, sound and vision sensors Open
We present the first work that investigates the potential of improving the performance of transportation mode recognition through fusing multimodal data from wearable sensors: motion, sound and vision. We first train three independent deep…
View article: Flexible Temperature Sensor Integration into E-Textiles Using Different Industrial Yarn Fabrication Processes
Flexible Temperature Sensor Integration into E-Textiles Using Different Industrial Yarn Fabrication Processes Open
Textiles enhanced with thin-film flexible sensors are well-suited for unobtrusive monitoring of skin parameters due to the sensors’ high conformability. These sensors can be damaged if they are attached to the surface of the textile, also …
View article: Benchmarking deep classifiers on mobile devices for vision-based transportation recognition
Benchmarking deep classifiers on mobile devices for vision-based transportation recognition Open
Vision-based human activity recognition can provide rich contextual information but has traditionally been computationally prohibitive. We present a characterisation of five convolutional neural networks (DenseNet169, MobileNet, ResNet50, …
View article: WLCSSCuda: a CUDA accelerated template matching method for gesture recognition
WLCSSCuda: a CUDA accelerated template matching method for gesture recognition Open
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…
View article: Message from the UIC 2019 Program Chairs
Message from the UIC 2019 Program Chairs Open
As the computational and ubiquitous intelligence is significantly transforming our daily life, the IEEE UIC 2019 Conference has become a great venue for both researchers and practitioners to present leading work on ubiquitous intelligence …
View article: Flexible Sensors—From Materials to Applications
Flexible Sensors—From Materials to Applications Open
Flexible sensors have the potential to be seamlessly applied to soft and irregularly shaped surfaces such as the human skin or textile fabrics. This benefits conformability dependant applications including smart tattoos, artificial skins a…
View article: Enabling Reproducible Research in Sensor-Based Transportation Mode Recognition With the Sussex-Huawei Dataset
Enabling Reproducible Research in Sensor-Based Transportation Mode Recognition With the Sussex-Huawei Dataset Open
Transportation and locomotion mode recognition from multimodal smartphone sensors is useful to provide just-in-time context-aware assistance. However, the field is currently held back by the lack of standardized datasets, recognition tasks…
View article: A Case Study for Human Gesture Recognition from Poorly Annotated Data
A Case Study for Human Gesture Recognition from Poorly Annotated Data Open
In this paper we present a case study on drinking gesture recognition from a dataset annotated by Experience Sampling (ES). The dataset contains 8825 "sensor events" and users reported 1808 "drink events" through experience sampling. We fi…
View article: Thigh-Derived Inertial Sensor Metrics to Assess the Sit-to-Stand and Stand-to-Sit Transitions in the Timed Up and Go (TUG) Task for Quantifying Mobility Impairment in Multiple Sclerosis
Thigh-Derived Inertial Sensor Metrics to Assess the Sit-to-Stand and Stand-to-Sit Transitions in the Timed Up and Go (TUG) Task for Quantifying Mobility Impairment in Multiple Sclerosis Open
Introduction: Inertial sensors generate objective and sensitive metrics of movement disability that may indicate fall risk in many clinical conditions including multiple sclerosis (MS). The Timed-Up-And-Go (TUG) task is used to assess pati…
View article: The University of Sussex-Huawei Locomotion and Transportation Dataset for Multimodal Analytics With Mobile Devices
The University of Sussex-Huawei Locomotion and Transportation Dataset for Multimodal Analytics With Mobile Devices Open
Scientific advances build on reproducible research which need publicly available benchmark datasets. The computer vision and speech recognition communities have led the way in establishing benchmark datasets. There are much less datasets a…