An orientation free adaptive step detection algorithm using a smart phone in physical activity monitoring

Huang, Yan; Zheng, Huiru; Nugent, Chris; McCullagh, Paul; Black, Norman D.; Burns, William C. G.; Tully, Mark; McDonough, Suzanne

doi:10.1007/s12553-012-0035-2

Cited by 13 publications

(17 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The smartphone is popular, has wide functionality, can provide feedback and is considered to be feasible for physical activity self-monitoring. [18] A recent study indicated that an iPhone/iPod Touch can predict movement with an accuracy similar to that of other accelerometer-based devices. [31] Earlier research has shown that walking on soft surfaces can reduce walking speed and increase the step error score.…”

Section: Discussionmentioning

confidence: 97%

“…[15] A pedometer application was reasonably accurate when carried in a trouser (pants) pocket in one study, [17] while no differences between five positions were found in another study. [18] Another factor to consider when using a pedometer is how valid it is when measuring in different environments. The walking pattern and speed may vary in different environments, for example, on flat versus hilly terrains.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Investigation of the validity and reliability of a smartphone pedometer application

Åkerberg¹,

Söderlund

Lindén³

2016

European Journal of Physiotherapy

View full text Add to dashboard Cite

The aim of this study was to investigate the validity and measurement agreement of a smartphone pedometer application and a traditional pedometer, both compared to manual step count, in six environments. The study also examined the relative reliability of two positions of the smartphone pedometer application in the six environments. Twenty participants carried two smartphones (iPhone 4S) with the same pedometer application (Pedometer FREE GPSþ) in two device positions together with a traditional pedometer (Yamax LS2000) while walking in six environments. The pedometer application in the chest position (app chest) differed significantly from the manual step count when walking uphill (p ¼ 0.003), the application in the trouser (pants) position (app pants) differed for downhill (p ¼ 0.001) and the traditional pedometer (trad ped) differed upstairs (p ¼ 0.007). The measurement agreement was high for app pants uphill, app chest downhill and trad ped downstairs. The relative reliability was fair for app chest, but poor for app pants. In conclusion, the pedometer application and traditional pedometer were valid for step self-monitoring in some environments, and the measurement agreement compared to manual step count was mainly medium to high. The relative reliability for the smartphone pedometer application was partly acceptable. Smartphones could be useful in some environments for physical activity self-monitoring. ARTICLE HISTORY

show abstract

Section: Discussionmentioning

confidence: 97%

Section: Introductionmentioning

confidence: 99%

Investigation of the validity and reliability of a smartphone pedometer application

Åkerberg¹,

Söderlund

Lindén³

2016

European Journal of Physiotherapy

View full text Add to dashboard Cite

show abstract

“…Accelerometers are utilized to detect the walking stride in many studies [30], [31]. Most of methods use the peak value of forward acceleration to detect the walking cycle.…”

Section: Step Detectionmentioning

confidence: 99%

A New Application of Smart Walker for Quantitative Analysis of Human Walking

Wang

Dune

Merlet

et al. 2015

Computer Vision - ECCV 2014 Workshops

View full text Add to dashboard Cite

Abstract. This paper presents a new nonintrusive device for everyday gait analysis and health monitoring. The system is a standard rollator equipped with encoders and inertial sensors. The assisted walking of 25 healthy elderly and 23 young adults are compared to develop walking quality index. The subjects were asked to walk on a straight trajectory and an L-shaped trajectory respectively. The walking trajectory, which is missing in other gait analysis methods, is calculated based on the encoder data. The obtained trajectory and steps are compared with the results of a motion capture system. The gait analysis results show that new index obtained by using the walker measurements, and not available otherwise, are very discriminating, e.g., the elderly have larger lateral motion and maneuver area, smaller angular velocity during turning, their walking accuracy is lower and turning ability is weaker although they have almost the same walking velocity as the young people.

show abstract

“…A wide range of sampling frequencies has been used to record human movement. For counting steps or monitoring energy expenditure, the sampling frequency is not critical and can be lower than 10 Hz [1], [6]- [8]. However, when accelerometers are used for more complex gait pattern analysis, sampling rates range from 50-200 Hz [2], [9].…”

Section: Introductionmentioning

confidence: 99%

“…Amplitude can be used to set a minimum threshold that, when surpassed, identifies a step [6], [8], [9], [11], [12]. The time between each step is often used to set a time-frame during which a second step is not expected ("locking period") [7]- [9], [13].…”

Section: Introductionmentioning

confidence: 99%

A smartphone approach for the 2 and 6-minute walk test

Capela

Lemaire

Baddour

2014

2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society

View full text Add to dashboard Cite

The 2 and 6-minute walk tests (2-6MWT) are used by rehabilitation professionals as a measure of exercise capacity. Our research has produced a new 2-6MWT BlackBerry smartphone application (app) that can be used to run the 2-6MWT and also provide new information about how the person moves during the test. The smartphone is worn on a belt at the lower back to record phone sensor data while walking. This data is used to identify foot strikes, calculate the total distance walked and step timing, and analyze pelvis accelerations. Information on symmetry, walking changes over time, and poor walking patterns is not available from a typical 2-6MWT and could help with clinical decision-making. The 2-6MWT app was evaluated in a pilot test using data from five able-bodied participants. Foot strike time was within 0.07 seconds when compared to gold standard video recordings. The total distance calculated by the app was within 1m of the measured distance.

show abstract

An orientation free adaptive step detection algorithm using a smart phone in physical activity monitoring

Cited by 13 publications

References 25 publications

Investigation of the validity and reliability of a smartphone pedometer application

Investigation of the validity and reliability of a smartphone pedometer application

A New Application of Smart Walker for Quantitative Analysis of Human Walking

A smartphone approach for the 2 and 6-minute walk test

Contact Info

Product

Resources

About