Edge algorithms for wearables: an overview of a truly multi-disciplinary problem

Beach, Christopher; Balaban, Ertan; Casson, Alexander J.

doi:10.1016/b978-0-12-819246-7.00014-0

Cited by 8 publications

(10 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, much larger is the impact on the data storage/transmission with 7 data streams from each electrode (1 bio‐potential, 3 accelerometer, 3 gyroscope). The raw bio‐signal data rate is 2,200 bps, while from the IMU it is 21,120 bps, reducing battery life by a factor of approximately 10 [ 34 ]. In practical use a trade‐off between battery lifetime, miniaturisation/size of batteries, and the potential for improved data quality from the incorporation of IMUs is thus required.…”

Section: Resultsmentioning

confidence: 99%

Motion artefact removal in electroencephalography and electrocardiography by using multichannel inertial measurement units and adaptive filtering

Beach

Balaban

et al. 2021

Healthcare Tech Letters

Self Cite

View full text Add to dashboard Cite

This paper presents a new active electrode design for electroencephalogram (EEG) and electrocardiogram (ECG) sensors based on inertial measurement units to remove motion artefacts during signal acquisition. Rather than measuring motion data from a single source for the entire recording unit, inertial measurement units are attached to each individual EEG or ECG electrode to collect local movement data. This data is then used to remove the motion artefact by using normalised least mean square adaptive filtering. Results show that the proposed active electrode design can reduce motion contamination from EEG and ECG signals in chest movement and head swinging motion scenarios. However, it is found that the performance varies, necessitating the need for the algorithm to be paired with more sophisticated signal processing to identify scenarios where it is beneficial in terms of improving signal quality. The new instrumentation hardware allows data driven artefact removal to be performed, providing a new data driven approach compared to widely used blind-source separation methods, and helps enable in the wild EEG recordings to be performed.

show abstract

Section: Resultsmentioning

confidence: 99%

Motion artefact removal in electroencephalography and electrocardiography by using multichannel inertial measurement units and adaptive filtering

Beach

Balaban

et al. 2021

Healthcare Tech Letters

Self Cite

View full text Add to dashboard Cite

show abstract

“…3 increase in height by around 10 µW over the baseline. This potentially could be used in opportunistic transmission [43] as the device can predict that there is a high probability of there being more power available on the hour and wait to do its power-hungry operations (such as wireless transmission [44]) at this point. Comparing this figure to an average of 135 µW over 3.5 ms that is required to transmit a single byte of data on the Bluetooth Low Energy (BLE) Nordic Semiconductor nRF52832 device [45] (assuming V cc = 3.0 V), the energy required for full opportunistic transmissions is some way from being directly realizable.…”

Section: ) Variations In Power Across the Daymentioning

confidence: 99%

Estimation of kinetic energy harvesting potential for self-powered wearable devices with 67,000 participants from the UK Biobank

Beach¹,

Casson²

2021

Preprint

Self Cite

View full text Add to dashboard Cite

Energy harvesting from human motion can reduce reliance on battery recharging in wearable devices and lead to improved adherence. However, to date, studies estimating energy harvesting potential have largely focused on small scale, healthy, population groups in laboratory settings rather than free-living environments with population level participant numbers. Here, we present the largest scale investigation into energy harvesting potential by utilising the activity data collected in the UK Biobank from over 67,000 participants. This paper presents detailed stratification into how the day of the week and participant age affect harvesting potential, as well as how the presence of conditions (such as diabetes, which we investigate here), may affect the expected energy harvester output. We process accelerometery data using a kinetic energy harvester model to investigate power output at a high temporal resolution. Our results identify key differences between the times of day when the power is available and an inverse relationship between power output and participant age. We also identify that the presence of diabetes substantially reduces energy harvesting output, by over 21%. The results presented highlight a key challenge in wearable energy harvesting: that wearable devices aim to monitor health and wellness, and energy harvesting aims to make devices more energy autonomous, but the presence of medical conditions may lead to substantially lower energy harvesting potential. The findings indicate how it is challenging to meet the required power budget to monitor diseases when energy autonomy is a goal.

show abstract

“…Connected cables yield a bulky BMI setup limiting subjects' degrees of movement freedom. While wireless technology allows better user comfort, it introduces major drawbacks such as short battery life and privacy concerns [8]. Moreover, offline analysis leads to long delays in the information extraction.…”

Section: Introductionmentioning

confidence: 99%

“…However, many challenges need to be addressed in edge processing for BMI devices. Analyzing a large amount of sensor data at the edge requires miniaturized processing engines that provide enough compute power to extract useful information in real-time, while at the same time consume low power and are energy-efficient for a prolonged battery life [8]. A popular family of microcontroller units (MCUs) is the ARM Cortex-M series.…”

Section: Introductionmentioning

confidence: 99%

“…Resource-efficient yet accurate classification algorithms are also crucial for a successful smart wearable device [8], especially for EEG applications where the high variability across subjects and among different recording sessions poses big challenges [9]. Deep neural networks (DNNs) have demonstrated impressive results in many fields, from outperforming humans in computer vision [17], vastly improving solutions for image processing [18] and speech recognition [19], natural language processing [20], large-scale recommender systems [21], and data analysis for sensors such as radar [22] that are not directly understandable by humans.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Sub-100uW Multispectral Riemannian Classification for EEG-based Brain--Machine Interfaces

Wang¹,

Cavigelli²,

Schneider³

et al. 2021

Preprint

View full text Add to dashboard Cite

motor imagery (MI) brain-machine interfaces (BMIs) enable us to control machines by merely thinking of performing a motor action. Practical use cases require a wearable solution where the classification of the brain signals is done locally near the sensor using machine learning models embedded on energy-efficient microcontroller units (MCUs), for assured privacy, user comfort, and long-term usage. In this work, we provide practical insights on the accuracy-cost trade-off for embedded BMI solutions. Our multispectral Riemannian classifier reaches 75.1% accuracy on a 4-class MI task. The accuracy is further improved by tuning different types of classifiers to each subject, achieving 76.4%. We further scale down the model by quantizing it to mixed-precision representations with a minimal accuracy loss of 1% and 1.4%, respectively, which is still up to 4.1% more accurate than the state-of-the-art embedded convolutional neural network. We implement the model on a low-power MCU within an energy budget of merely 198µJ and taking only 16.9 ms per classification. Classifying samples continuously, overlapping the 3.5 s samples by 50% to avoid missing user inputs allows for operation at just 85µW. Compared to related works in embedded MI-BMIs, our solution sets the new state-of-the-art in terms of accuracy-energy trade-off for near-sensor classification.

show abstract

Edge algorithms for wearables: an overview of a truly multi-disciplinary problem

Cited by 8 publications

References 51 publications

Motion artefact removal in electroencephalography and electrocardiography by using multichannel inertial measurement units and adaptive filtering

Motion artefact removal in electroencephalography and electrocardiography by using multichannel inertial measurement units and adaptive filtering

Estimation of kinetic energy harvesting potential for self-powered wearable devices with 67,000 participants from the UK Biobank

Sub-100uW Multispectral Riemannian Classification for EEG-based Brain--Machine Interfaces

Contact Info

Product

Resources

About