iPhone as a physical activity measurement platform

Fujiki, Yuichi

doi:10.1145/1753846.1754146

Cited by 28 publications

(18 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Examples range from self-reported logging of exercise and nutrition to smartphone-based pedometers and GPS-based location sensing for running or cycling [10,24,26,31]. More elaborate sensing solutions (in particular entailing a feedback and/or social networking element) have also been developed, such as Nike+, whose sensors can communicate with third party exercise equipment [25].…”

Section: Gait As Input For Mobile Exercise Applicationsmentioning

confidence: 99%

Real-time gait classification for persuasive smartphone apps

Schneider

MacLean

Altun

et al. 2013

Proceedings of the 2013 International Conference on Intelligent User Interfaces

View full text Add to dashboard Cite

Persuasive technology is now mobile and context-aware. Intelligent analysis of accelerometer signals in smartphones and other specialized devices has recently been used to classify activity (e.g., distinguishing walking from cycling) to encourage physical activity, sustainable transport, and other social goals. Unfortunately, results vary drastically due to differences in methodology and problem domain. The present report begins by structuring a survey of current work within a new framework, which highlights comparable characteristics between studies; this provided a tool by which we and others can understand the current state-of-the art and guide research towards existing gaps. We then present a new user study, positioned in an identified gap, that pushes limits of current success with a challenging problem: the real-time classification of 15 similar and novel gaits suitable for several persuasive application areas, focused on the growing phenomenon of exercise games. We achieve a mean correct classification rate of 78.1% of all 15 gaits with a minimal amount of personalized training of the classifier for each participant when carried in any of 6 different carrying locations (not known a priori). When narrowed to a subset of four gaits and one location that is known, this improves to means of 92.2% with and 87.2% without personalization. Finally, we group our findings into design guidelines and quantify variation in accuracy when an algorithm is trained for a known location and participant.

show abstract

Section: Gait As Input For Mobile Exercise Applicationsmentioning

confidence: 99%

Real-time gait classification for persuasive smartphone apps

Schneider

MacLean

Altun

et al. 2013

Proceedings of the 2013 International Conference on Intelligent User Interfaces

View full text Add to dashboard Cite

show abstract

“…Gesture recognition based on data from an accelerometer is an emerging technique for gesture-based interaction after the rapid development of the MEMS technology. Accelerometers are embedded in most of the new generation personal electronic devices such as Apple iPhone [11], Nintendo wii mote [12] which provide new possibilities for interaction in a wide range of applications, such as home appliances, in offices, and in video games. In the sequel, we represent and sets by calligraphic upper case letters, R.…”

Section: Means Of Acquisitionmentioning

confidence: 99%

A Novel Accelerometer-Based Gesture Recognition System

Akl

Feng

Valaee

2011

IEEE Trans. Signal Process.

138

View full text Add to dashboard Cite

Gesture Recognition provides an efficient human-computer interaction for interactive and intelligent computing. In this work, we address the problem of gesture recognition using the theory of random projection and by formulating the recognition problem as an 1 -minimization problem. The gesture recognition uses a single 3-axis accelerometer for data acquisition and comprises two main stages: a training stage and a testing stage.For training, the system employs dynamic time warping as well as affinity propagation to create exemplars for each gesture while for testing, the system projects all candidate traces and also the unknown trace onto the same lower dimensional subspace for recognition. A dictionary of 18 gestures is defined and a database of over 3,700 traces is created from 7 subjects on which the system is tested and evaluated. Simulation results reveal a superior performance, in terms of accuracy and computational complexity, compared to other systems in the literature.ii

show abstract

“…Many walking monitoring apps are available to make the users aware about their walking behavior. Typically, these apps estimate energy expenditure by mapping the smartphone accelerometers' readings to caloric values [4][5] [6] [8]. The mapping assumes that the walking surface is leveled.…”

Section: Introductionmentioning

confidence: 99%

“…Each walking session was 3 min. Energy expenditure was measured through a respiration gas analyzer [1], a high-grade treadmill [3], and the iBurnCalorie app [4]. The respiration gas analyzer measures energy expenditure in Respiratory Exchange Ratio (RER) and is the gold standard for metabolic measurements.…”

Section: Introductionmentioning

confidence: 99%

Using Accelerometer Data to Estimate Surface Incline and Its Walking App Potential

Uyanik

Khatri

Majeti

et al. 2015

Proceedings of the 33rd Annual ACM Conference Extended Abstracts on Human Factors in Computing Systems

View full text Add to dashboard Cite

Walking is a fundamental human activity and its diminution a potential morbidity factor. Recent developments in mobile computing have enabled ubiquitous monitoring of walking activity via the smartphone accelerometers. Typically, walking apps map accelerometer values to caloric values through calibration algorithms. However, these calibration algorithms assume a flat surface, which is not always true and can introduce significant errors. In this paper, we outline a novel calibration method that estimates surface inclination for uphill walking, thus, improving the caloric estimation in walking apps.

show abstract

iPhone as a physical activity measurement platform

Cited by 28 publications

References 4 publications

Real-time gait classification for persuasive smartphone apps

Real-time gait classification for persuasive smartphone apps

A Novel Accelerometer-Based Gesture Recognition System

Using Accelerometer Data to Estimate Surface Incline and Its Walking App Potential

Contact Info

Product

Resources

About