Easing Power Consumption of Wearable Activity Monitoring with Change Point Detection

Culman, Cristian; Aminikhanghahi, Samaneh; Cook, Diane J.

doi:10.3390/s20010310

Cited by 28 publications

(24 citation statements)

References 59 publications

(69 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A detailed discussion about such methods, which are also used in context with electrical vehicles, can be found elsewhere. [ 109–113 ] The energy requirement for sweat‐based system could vary with the type of electrodes as briefly discussed in Section 3.…”

Section: Key Components Of Energy‐autonomous Wearable Systemsmentioning

confidence: 99%

Energy Autonomous Sweat‐Based Wearable Systems

et al. 2021

View full text Add to dashboard Cite

The continuous operation of wearable electronics demands reliable sources of energy, currently met through Li‐ion batteries and various energy harvesters. These solutions are being used out of necessity despite potential safety issues and unsustainable environmental impact. Safe and sustainable energy sources can boost the use of wearables systems in diverse applications such as health monitoring, prosthetics, and sports. In this regard, sweat‐ and sweat‐equivalent‐based studies have attracted tremendous attention through the demonstration of energy‐generating biofuel cells, promising power densities as high as 3.5 mW cm−2, storage using sweat‐electrolyte‐based supercapacitors with energy and power densities of 1.36 Wh kg−1 and 329.70 W kg−1, respectively, and sweat‐activated batteries with an impressive energy density of 67 Ah kg−1. A combination of these energy generating, and storage devices can lead to fully energy‐autonomous wearables capable of providing sustainable power in the µW to mW range, which is sufficient to operate both sensing and communication devices. Here, a comprehensive review covering these advances, addressing future challenges and potential solutions related to fully energy‐autonomous wearables is presented, with emphasis on sweat‐based energy storage and energy generation elements along with sweat‐based sensors as applications.

show abstract

Section: Key Components Of Energy‐autonomous Wearable Systemsmentioning

confidence: 99%

Energy Autonomous Sweat‐Based Wearable Systems

et al. 2021

View full text Add to dashboard Cite

show abstract

“…The window size for ambient sensor readings is 30 readings (they do not arrive at equallyspaced time intervals) and for wearable sensor readings is 5 seconds. These window sizes have demonstrated success for activity recognition in earlier studies [25], [37], [47]. Each ambient sensor is identified based on its location and its type.…”

Section: B Activity Recognitionmentioning

confidence: 99%

Fusing Ambient and Mobile Sensor Features Into a Behaviorome for Predicting Clinical Health Scores

Cook

Schmitter‐Edgecombe

2021

IEEE Access

View full text Add to dashboard Cite

Advances in machine learning and low-cost, ubiquitous sensors offer a practical method for understanding the predictive relationship between behavior and health. In this study, we analyze this relationship by building a behaviorome, or set of digital behavior markers, from a fusion of data collected from ambient and wearable sensors. We then use the behaviorome to predict clinical scores for a sample of n = 21 participants based on continuous data collected from smart homes and smartwatches and automatically labeled with corresponding activity and location types. To further investigate the relationship between domains, including participant demographics, self-report and external observation-based health scores, and behavior markers, we propose a joint inference technique that improves predictive performance for these types of high-dimensional spaces. For our participant sample, we observe correlations ranging from small to large for the clinical scores. We also observe an improvement in predictive performance when multiple sensor modalities are used and when joint inference is employed.

show abstract

“…Current wearables that employ local network connectivity with mobile phones using protocols such as Bluetooth Low Energy likely represent a pragmatic compromise in terms of power. Developments in power optimization, such as through algorithms that identify optimal periods of sampling (Culman et al, 2020), may result in more efficient wearables and might be suitable for lower-risk patient groups in the community. In some instances, although individual parameters might be insufficient to differentiate between "normal" and "abnormal" physiology, the integration of different signals through a multi-modal approach may also increase the specificity of early warning systems.…”

Section: Challenges To Implementationmentioning

confidence: 99%

Continuous physiological monitoring using wearable technology to inform individual management of infectious diseases, public health and outbreak responses

Ming

Sangkaew

Chanh

et al. 2020

International Journal of Infectious Diseases

View full text Add to dashboard Cite

Optimal management of infectious diseases is guided by up-to-date information at the individual and public health levels. For infections of global importance, including emerging pandemics such as COVID-19 or prevalent endemic diseases such as dengue, identifying patients at risk of severe disease and clinical deterioration can be challenging, considering that the majority present with a mild illness. In our article, we describe the use of wearable technology for continuous physiological monitoring in healthcare settings. Deployment of wearables in hospital settings for the management of infectious diseases, or in the community to support syndromic surveillance during outbreaks, could provide significant, costeffective advantages and improve healthcare delivery. We highlight a range of promising technologies employed by wearable devices and discuss the technical and ethical issues relating to implementation in the clinic, focusing on low-and middle-income countries. Finally, we propose a set of essential criteria for the rollout of wearable technology for clinical use.

show abstract

Easing Power Consumption of Wearable Activity Monitoring with Change Point Detection

Cited by 28 publications

References 59 publications

Energy Autonomous Sweat‐Based Wearable Systems

Energy Autonomous Sweat‐Based Wearable Systems

Fusing Ambient and Mobile Sensor Features Into a Behaviorome for Predicting Clinical Health Scores

Continuous physiological monitoring using wearable technology to inform individual management of infectious diseases, public health and outbreak responses

Contact Info

Product

Resources

About