Cardiac and Respiratory Parameter Estimation Using Head-mounted Motion-sensitive Sensors

Hernández, Javier; Li, Yin; Rehg, James M.; Picard, Rosalind W.

doi:10.4108/phat.1.1.e2

Cited by 18 publications

(27 citation statements)

References 36 publications

(37 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Various studies propose methods for detecting breathing with wearable devices. For example, Haescher et al presented a method of respiration detection by sensing changes in an accelerometer and a gyroscope from a smartwatch or a HMD [7,8,9]. This method can detect respiration only when the user’s posture remains stable.…”

Section: Related Workmentioning

confidence: 99%

Evaluation on Context Recognition Using Temperature Sensors in the Nostrils

Kodama

Terada

Tsukamoto

2019

Sensors

View full text Add to dashboard Cite

We can benefit from various services with context recognition using wearable sensors. In this study, we focus on the contexts acquired from sensor data in the nostrils. Nostrils can provide various contexts on breathing, nasal congestion, and higher level contexts including psychological and health states. In this paper, we propose a context recognition method using the information in the nostril. We develop a system to acquire the temperature in the nostrils using small temperature sensors connected to glasses. As a result of the evaluations, the proposed system can detect breathing correctly, workload at an accuracy of 96.4%, six behaviors at an accuracy of 54%, and eight behaviors in daily life at an accuracy of 86%. Moreover, the proposed system can detect nasal congestion, therefore, it can log nasal cycles that are considered to have a relationship with the autonomic nerves and/or biological states.

show abstract

Section: Related Workmentioning

confidence: 99%

Evaluation on Context Recognition Using Temperature Sensors in the Nostrils

Kodama

Terada

Tsukamoto

2019

Sensors

View full text Add to dashboard Cite

show abstract

“…Breathing is measured using airflow, with a sensor put next to the nose or the mouth, or by detecting chest movement, with sensors placed on the body [2]. Breathing has been extracted using stretch sensors, an inertial measurement unit (IMU) strapped to the chest [44], a head-mounted IMU + egocentric camera [26], and a wrist-mounted IMU [27,54].…”

Section: Measuring Breathingmentioning

confidence: 99%

“…Future work might consider extending to measure both thoracic and abdominal respiration -preliminary observations show that this data is encoded within the current IMU's signal, and thus could be used to add more information about the breathing pattern. One could also extract heart rate from the acceleration as per [26,27].…”

Section: Challenges and Limitationsmentioning

confidence: 99%

Breeze

Frey

Grabli

Slyper

et al. 2018

Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

Digitally presenting physiological signals as biofeedback to users raises awareness of both body and mind. This paper describes the effectiveness of conveying a physiological signal often overlooked for communication: breathing. We present the design and development of digital breathing patterns and their evaluation along three output modalities: visual, audio, and haptic. We also present Breeze, a wearable pendant placed around the neck that measures breathing and sends biofeedback in real-time. We evaluated how the breathing patterns were interpreted in a fixed environment and gathered qualitative data on the wearable device's design. We found that participants intentionally modified their own breathing to match the biofeedback, as a technique for understanding the underlying emotion. Our results describe how the features of the breathing patterns and the feedback modalities influenced participants' perception. We include guidelines and suggested use cases, such as Breeze being used by loved ones to increase connectedness and empathy.Signals such as heart rate and electrodermal activity (EDA), which measures perspiration, can also serve as proxies for social interactions [37]. Breathing presents an advantage over such signals because it can easily be modulated. In the field of human-computer interaction (HCI), breathing and other physiological signals have been used mainly as input [35,39]. Instead, we employ these technologies to support humanhuman communication as advocated by [13].We envision a future where interfaces can "connect" people at a distance, enforcing a bond between close ones through shared wearable biofeedback. While trying to develop such an arXiv:1802.04995v1 [cs.HC]

show abstract

“…However, estimating energy expenditure from visual data has not yet been explored. The only work reports estimating heart rate from a head-mounted wearable camera and sensors [26,27]. In our work, we show that reasoning on egocentric video data can be an effective estimate of energy expenditure under a free-living setting.…”

Section: Energy Expenditure Estimationmentioning

confidence: 99%

Jointly Learning Energy Expenditures and Activities Using Egocentric Multimodal Signals

Nakamura

Yeung

Alahi

et al. 2017

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

Physiological signals such as heart rate can provide valuable information about an individual's state and activity. However, existing work on computer vision has not yet explored leveraging these signals to enhance egocentric video understanding. In this work, we propose a model for reasoning on multimodal data to jointly predict activities and energy expenditures. We use heart rate signals as privileged self-supervision to derive energy expenditure in a training stage. A multitask objective is used to jointly optimize the two tasks. Additionally, we introduce a dataset that contains 31 hours of egocentric video augmented with heart rate and acceleration signals. This study can lead to new applications such as a visual calorie counter.

show abstract

Cardiac and Respiratory Parameter Estimation Using Head-mounted Motion-sensitive Sensors

Cited by 18 publications

References 36 publications

Evaluation on Context Recognition Using Temperature Sensors in the Nostrils

Evaluation on Context Recognition Using Temperature Sensors in the Nostrils

Breeze

Jointly Learning Energy Expenditures and Activities Using Egocentric Multimodal Signals

Contact Info

Product

Resources

About