Design and Implementation of Practical Step Detection Algorithm for Wrist-worn Devices

Cho, Yunhoon; Cho, Hyuntae; Kyung, Chong-Min

doi:10.1109/jsen.2016.2603163

Cited by 30 publications

(20 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the classification phase, most studies used a machine learning-based approach; however, researchers are still using threshold-based approaches in some studies [2,16,64,65,69,70]. This is because a threshold-based approach must determine the critical points of classification, which are affected by changes in context and long usage needs.…”

Section: Discussionmentioning

confidence: 99%

“…This is because a threshold-based approach must determine the critical points of classification, which are affected by changes in context and long usage needs. Consequently, we have seen that most studies for recognizing a single activity, such as falling [64], steps [65,69], computing activity [16], CPR [2], and hair touch detection [70], used the threshold-based approach. On the other hand, to recognize the more complex activities that are sensitive to context, such as the activity of ambulation [66], eating [3], and mood [72], the machine learning approach was used.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

A Review of Wrist-Worn Wearable: Sensors, Models, and Challenges

2018

View full text Add to dashboard Cite

Wearable technology impacts the daily life of its users. Wearable devices are defined as devices embedded within clothes, watches, or accessories. Wrist-worn devices, as a type of wearable devices, have gained popularity among other wearable devices. They allow quick access to vital information, and they are suitable for many applications. This paper presents a comprehensive survey of wearable computing as a research field and provides a systematic review of recent work specifically on wrist-worn wearables. The focus of this research is on wrist-worn wearable studies because there is a lack of systematic literature reviews related to this area. This study reviewed journal and conference articles from 2015 and 2017 with some studies from 2014 and 2018, resulting in a selection of 54 studies that met the selection criteria. The literature showed that research in wrist-worn wearables spans three domains, namely, user interface and interaction studies, user studies, and activity/affect recognition studies. Our study then concludes with challenges and open research directions.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

A Review of Wrist-Worn Wearable: Sensors, Models, and Challenges

2018

View full text Add to dashboard Cite

show abstract

“…As shown in Figure 2, a trivial solution with respect to the noisy signals is to use a low-pass filter to minimize the effect of the high-frequency noise [18]. The peaks of the smoothed signal represent the occurrence of the steps.…”

Section: A Motivationmentioning

confidence: 99%

“…For smartphone data, which is not firmly attached to the body, the signal magnitude is computed instead of the orthogonal axis of the sensor. In [10], [18], the authors apply low-pass filtering to remove interference. In [26], the authors limit the time interval between two peaks to reduce misjudgments.…”

Section: B Related Workmentioning

confidence: 99%

ParaLabel: Autonomous Parameter Learning for Cross-Domain Step Counting in Wearable Sensors

et al. 2020

View full text Add to dashboard Cite

Wearable step counters, also referred to as activity trackers, have been developed for health and activity monitoring, as well as for step tracking. These trackers, however, produce unreliable measurements during slow walking and when walking with assistive devices (i.e., aided walking). To address this challenge, in this article, we introduce, ParaLabel, a filter-based step counting algorithm that is reliable against various walking velocities and intensities. ParaLabel addresses this problem by learning a filter cutoff frequency autonomously in a new domain without the need for collecting sensor data and manually tuning the algorithm parameter for a different velocity and/or pattern of walking. We formulate this problem as a transfer learning problem in which the new filter cutoff frequency is transferred from a bank containing previously fine-tuned parameters from different domain(s). Our extensive analysis using real data collected from 15 participants while wearing an accelerometer sensor on their chest, wrist, or left pocket demonstrates the superiority of ParaLabel to two commercially available trackers worn on the same body location, and state-of-the-art techniques. ParaLabel achieves 96.3% − 99.9% accuracy during walking on a treadmill at three different velocities, 98.2%−99.9% accuracy during walking with a shopping cart, and 89.3%−97.3% accuracy while walking with the aid of a walker. Index Terms-Step counting, wearable sensors, peak detection, low-pass filter, frequency components, K-nearest neighbor, time-domain features, cross-subject transfer learning. I. INTRODUCTION I NTERNET-OF-THINGS (IoT) has emerged as a promising paradigm for interconnecting computing devices such as wearable sensors and smartphones with cloud computing platforms for seamless interactions, health monitoring, and clinical decision making. Wearable trackers, as a rapidly growing component of IoT, have gained much attention recently due to their potentials to improve the health and well-being of their users. Promoting physical activity levels is an important factor to sustain and improve cardiovascular health [1]-[3].

show abstract

“…Amulet’s pedometer application used a previously validated step-count algorithm from the literature that uses a wrist-mounted accelerometer. 25…”

Section: Introductionmentioning

confidence: 99%

Use of Amulet in behavioral change for geriatric obesity management

et al. 2019

View full text Add to dashboard Cite

Background Obesity in older adults is a significant public health concern. Weight-loss interventions are known to improve physical function but risk the development of sarcopenia. Mobile health devices have the potential to augment existing interventions and, if designed accordingly, could improve one’s physical activity and strength in routine physical activity interventions. Methods and results We present Amulet, a mobile health device that has the capability of engaging patients in physical activity. The purpose of this article is to discuss the development of applications that are tailored to older adults with obesity, with the intention to engage and improve their health. Conclusions Using a team-science approach, Amulet has the potential, as an open-source mobile health device, to tailor activity interventions to older adults.

show abstract

Design and Implementation of Practical Step Detection Algorithm for Wrist-worn Devices

Cited by 30 publications

References 19 publications

A Review of Wrist-Worn Wearable: Sensors, Models, and Challenges

A Review of Wrist-Worn Wearable: Sensors, Models, and Challenges

ParaLabel: Autonomous Parameter Learning for Cross-Domain Step Counting in Wearable Sensors

Use of Amulet in behavioral change for geriatric obesity management

Contact Info

Product

Resources

About