Making sense of accelerometer measurements in pervasive physical activity applications

Fujiki, Yuichi; Tsiamyrtzis, Panagiotis; Pavlidis, Ioannis

doi:10.1145/1520340.1520497

Cited by 15 publications

(19 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The waist is included in both sessions as a master position. It is considered an ideal position to measure physical activity because it is close to the center of body mass ( [6], [9]). This is also supported in the results section of this study.…”

Section: Experimental Designmentioning

confidence: 99%

“…This important issue has not been investigated enough. Fujiki et al [6] developed positional calibration of accelerometer readings using real accelerometer signals obtained from different body locations, i.e., waist, thigh, ankle, hand, and arm. However, the study was based on stand-alone accelerometers, in which case body placement preferences are very different with respect to accelerometers embedded in mobile phones.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

iPhone as a physical activity measurement platform

Fujiki

2010

CHI '10 Extended Abstracts on Human Factors in Computing Systems

Self Cite

View full text Add to dashboard Cite

iPhone is emerging as a ubiquitous physical activity measurement platform due to its incorporated accelerometer sensor. The iPhone's capacity to accurately measure physical activity has not been put to scrutiny up to now, despite claims from an increasing number of applications. This study examines ways to perform accurate physical activity measurements with the iPhone, at various positions on the user's body. The study focuses on walking and running-the two most prevalent aerobic activities. For walking, a methodology has been developed that translates accelerometer values from peripheral body locations to equivalent readings on the waist and from there to metabolic units. For running, the limitation of iPhone to perform accurate metabolic measurements is documented. The formulas and results in this paper can readily be used by developers to increase the accuracy of fitness applications and improve user experience.

show abstract

Section: Experimental Designmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

iPhone as a physical activity measurement platform

Fujiki

2010

CHI '10 Extended Abstracts on Human Factors in Computing Systems

Self Cite

View full text Add to dashboard Cite

show abstract

“…Bouten also recognizes that static exercise can cause discrepancies between the IMA value and the actual energy expenditure. Later work by Steele et al [4] and Fujiki [5] et al use a different integration algorithm than IMA, but in essence the methods are similar. Fujiki [5] et al also provide further insight in the effect of sensor placement on the activity estimation.…”

Section: Related Workmentioning

confidence: 99%

“…Later work by Steele et al [4] and Fujiki [5] et al use a different integration algorithm than IMA, but in essence the methods are similar. Fujiki [5] et al also provide further insight in the effect of sensor placement on the activity estimation. Alternatively, pedometers can be used to estimate physical energy expenditure.…”

Section: Related Workmentioning

confidence: 99%

Keep on Moving! Activity Monitoring and Stimulation Using Wireless Sensor Networks

Bosch

Marin-Perianu

Marin-Perianu³

et al. 2009

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Because health condition and quality of life are directly influenced by the amount and intensity of daily physical activity, monitoring the level of activity has gained interest in recent years for various medical and wellbeing applications. In this paper we describe our experience with implementing and evaluating physical activity monitoring and stimulation using wireless sensor networks and motion sensors. Our prototype provides feedback on the activity level of users using a simple colored light. We conduct experiments on multiple test subjects, performing multiple normal daily activities. The results from our experiments represent the motivation for and a first step towards robust complex physical activity monitoring with multiple sensors distributed over a person's body. The results show that using a single sensor on the body is inadequate in certain situations. Results also indicate that feedback provided on a person's activity level can stimulate the person to do more exercise. Using multiple sensor nodes and sensor modalities per subject would improve the activity estimation performance, provided that the sensor nodes are small and inconspicuous.

show abstract

“…Both training and test data contain information about which feature vectors belong to which blocks. Though this study only uses waist data, analysis methods could be applied to data sets collected from other body locations in a similar manner [9]. …”

Section: Introductionmentioning

confidence: 99%

Bipart: Learning Block Structure for Activity Detection

Yang

Ding

et al. 2014

IEEE Trans. Knowl. Data Eng.

View full text Add to dashboard Cite

Physical activity consists complex behavior, typically structured in bouts which can consist of one continuous movement (e.g. exercise) or many sporadic movements (e.g. household chores). Each bout can be represented as a block of feature vectors corresponding to the same activity type. This paper introduces a general distance metric technique to use this block representation to first predict activity type, and then uses the predicted activity to estimate energy expenditure within a novel framework. This distance metric, dubbed Bipart, learns block-level information from both training and test sets, combining both to form a projection space which materializes block-level constraints. Thus, Bipart provides a space which can improve the bout classification performance of all classifiers. We also propose an energy expenditure estimation framework which leverages activity classification in order to improve estimates. Comprehensive experiments on waist-mounted accelerometer data, comparing Bipart against many similar methods as well as other classifiers, demonstrate the superior activity recognition of Bipart, especially in low-information experimental settings.

show abstract

Making sense of accelerometer measurements in pervasive physical activity applications

Cited by 15 publications

References 9 publications

iPhone as a physical activity measurement platform

iPhone as a physical activity measurement platform

Keep on Moving! Activity Monitoring and Stimulation Using Wireless Sensor Networks

Bipart: Learning Block Structure for Activity Detection

Contact Info

Product

Resources

About