Wearable electric potential sensing

Pouryazdan, Arash; Prance, R. J.; Prance, H.; Roggen, Daniel

doi:10.1145/2968219.2968286

Cited by 16 publications

(4 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By using this tool, different human tasks can be differentiated. Several studies have documented using this sensing technique for multiple purposes, including non-invasive respiration and cardiac monitoring [14], wearable devices to detect hair touch and restless leg movement [15] and passive tracking of movements [16]. However, we have not found a report on the use of capacitive sensors for the monitoring of hand movements in the context of PD.…”

Section: Non-contact Capacitive Sensormentioning

confidence: 90%

A non-contact system for the assessment of hand motor tasks in people with Parkinson’s disease

et al. 2021

View full text Add to dashboard Cite

Clinical diagnosis of Parkinson’s disease (PD) motor symptoms remains a problem. Most of the current studies focus on objective evaluations to make the evaluation more reliable. Most of these systems are based on the use of inertial and electromyographic sensors that require contact with the body part being assessed. Contact sensors restrict natural movement, may be uncomfortable and may require preparation of the body, which may cause irritation. As an alternative to contact sensors for the study of hand motor tasks performed by subjects with and without PD, electrical potential sensing technology is used in this research. A custom hardware has been designed to enable data collection by hand movement. A micro-machine system validated the developed system, and a relationship model was established between hand displacement and non-contact capacitive (NCC) sensor response. An experiment was conducted, including 57 subjects, 30 with PD (experimental group) and 27 healthy control group, followed by an analysis of statistical features extracted from the instantaneous mean frequency (IMNF) of NCC sensor. These results were compared with those obtained from gyroscope signals that are considered in the field to be the gold standard. As a result, NCC responses were correlated linearly with hand displacement (R2 = 0.7692 and $${\text{R}}_{\text{adj}}^{2}$$ R adj 2 = 0.7631). The statistical evaluation of IMNF features showed, that both, contact and non-contact sensors, were able to discriminate movement patterns of the control group from the experimental one. The results confirm statistical similarity between features extracted from NCC and gyroscope signals.

show abstract

Section: Non-contact Capacitive Sensormentioning

confidence: 90%

A non-contact system for the assessment of hand motor tasks in people with Parkinson’s disease

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Electric potential sensing (EPS) was reported as a new modality for scratch sensing [14]. This work only reported a visual observation that EPS signals are correlated to scratch, but the authors did not demonstrate any automated activity recognition based on this modality.…”

Section: Related Workmentioning

confidence: 99%

“…Furthermore, BlueSense can be extended with expansion boards comprising additional sensors. In this work, we used an expansion board with an EPS sensor [14].…”

Section: Sensor Set Upmentioning

confidence: 99%

“…Electric Potential Sensor, shown in Figure 1 (b), streams the voltage data using ADC channel to Bluesense [15]. Once the electric field is disrupted [14] it can be observed in the signal. Also, EPS sensor has the ability to detect 50 Hz grid voltage when the computer is connecting to the power source, which allows to accurately detect typing to a computer, once it is connected to a power source.…”

Section: Sensor Set Upmentioning

confidence: 99%

See 1 more Smart Citation

Multimodal fusion of IMUs and EPS body-worn sensors for scratch recognition

Jocys

Pouryazdan

Roggen

2020

Proceedings of the 14th EAI International Conference on Pervasive Computing Technologies for Healthcare

View full text Add to dashboard Cite

Itching may be caused by different skin diseases. In order to develop and evaluate how much itching affects a person's daily life, it is useful to develop automated means to recognize the action of scratching. We present an investigation of sensors and algorithms to realize a wearable scratch detection device. We collected a dataset, where each user wore 4 IMU (Inertial Measurement Units) sensors and one EPS (electric potential sensor). Data was collected from 9 users, where each user followed a 40 minute protocol, which involved scratching different parts of head, shoulder and leg, as well as other activities such as walking, drinking water, brushing teeth and sitting next to the computer. The dataset contains 813 scratching instances and 5h 15 min of recorded data. We investigate trade-offs between number of devices worn, and hence comfort, and recognition performance. We trained k-NN and Random Forest using between 1 to 5 of the best features per channel to detect scratches. We conclude that scratch can be detected with 80.7% by using Random Forest on hand coordinates, which require 4 devices. However, f1 score of 70% can be achieved with k-NN with IMU and EPS data, which only requires 1 device. Moreover, fusion of IMU data with EPS data improved the accuracy and reduced the standard deviation between the folds. This expands the state of the art by opening up new trade-offs between accuracy and comfort for future research in skin conditions.

show abstract

Personalization of Proposed Services in a Sensor-Based Remote Care Application

Makssoud

2021

Advances in Computer Vision and Computational Biology

View full text Add to dashboard Cite

Wearable electric potential sensing

Cited by 16 publications

References 5 publications

A non-contact system for the assessment of hand motor tasks in people with Parkinson’s disease

A non-contact system for the assessment of hand motor tasks in people with Parkinson’s disease

Multimodal fusion of IMUs and EPS body-worn sensors for scratch recognition

Personalization of Proposed Services in a Sensor-Based Remote Care Application

Contact Info

Product

Resources

About