Proceedings Article•
My act: an automatic daily caloric estimation based on physical activity data using smart phones
29 Aug 2013-pp 15
TL;DR: This work modifications the android application to classify into activities: sleep, rest, walk and run, and converts the activity to energy expenditure using MET data published in the compendium of physical activities tracking guide.
Abstract: At last year conference (i-CREATe 2012), we presented the android application that classified our daily physical and commuting activities. It was shown that the classification resulted in good accuracy (higher than 95% on average) and with reasonable battery consumption. We extend our previous work and focus on physical activity detection. We modify in this current work our application to classify into activities: sleep, rest, walk and run. Then we convert the activity to energy expenditure using MET data published in the compendium of physical activities tracking guide. We also provide the following relevant information: duration of each activity, step counts and distance obtained with walk and run activities. This tool can be used to automatically provide information on user's daily pattern of physical activity. We perform several tests of performance and show that although the application depends on several factors, it works very well in most situations.
References
More filters
TL;DR: A generic framework for the automated classification of human movements using an accelerometry monitoring system is introduced and a classifier to identify basic movements from the signals obtained from a single, waist-mounted triaxial accelerometer is developed.
Abstract: A generic framework for the automated classification of human movements using an accelerometry monitoring system is introduced. The framework was structured around a binary decision tree in which movements were divided into classes and subclasses at different hierarchical levels. General distinctions between movements were applied in the top levels, and successively more detailed subclassifications were made in the lower levels of the tree. The structure was modular and flexible: parts of the tree could be reordered, pruned or extended, without the remainder of the tree being affected. This framework was used to develop a classifier to identify basic movements from the signals obtained from a single, waist-mounted triaxial accelerometer. The movements were first divided into activity and rest. The activities were classified as falls, walking, transition between postural orientations, or other movement. The postural orientations during rest were classified as sitting, standing or lying. In controlled laboratory studies in which 26 normal, healthy subjects carried out a set of basic movements, the sensitivity of every classification exceeded 87%, and the specificity exceeded 94%; the overall accuracy of the system, measured as the number of correct classifications across all levels of the hierarchy, was a sensitivity of 97.7% and a specificity of 98.7% over a data set of 1309 movements.
520 citations
TL;DR: The use of the stable isotope technique, doubly labelled water, enables total daily energy expenditure to be measured accurately in free-living subjects and the factorial method for combining activity logs and data on the energy costs of activities can also provide detailed information on free- living subjects.
Abstract: Measurement of energy expenditure in humans is required to assess metabolic needs, fuel utilisation, and the relative thermic effect of different food, drink, drug and emotional components. Indirect and direct calorimetric and non-calorimetric methods for measuring energy expenditure are reviewed, and their relative value for measurement in the laboratory and field settings is assessed. Where high accuracy is required and sufficient resources are available, an open-circuit indirect calorimeter can be used. Open-circuit indirect calorimeters can employ a mask, hood, canopy or room/chamber for collection of expired air. For short-term measurements, mask, hood or canopy systems suffice. Chamber-based systems are more accurate for the long-term measurement of specified activity patterns but behaviour constraints mean they do not reflect real life. Where resources are limited and/or optimum precision can be sacrificed, flexible total collection systems and non-calorimetric methods are potentially useful if the limitations of these methods are appreciated. The use of the stable isotope technique, doubly labelled water, enables total daily energy expenditure to be measured accurately in free-living subjects. The factorial method for combining activity logs and data on the energy costs of activities can also provide detailed information on free-living subjects.
436 citations
23 May 2011
TL;DR: An activity recognition system on a smartphone is proposed where the uncertain time-series acceleration signal is analyzed by using hierarchical hidden Markov models by addressing the limitations on the memory storage and computational power of the mobile devices.
Abstract: As smartphone users have been increased, studies using mobile sensors on smartphone have been investigated in recent years. Activity recognition is one of the active research topics, which can be used for providing users the adaptive services with mobile devices. In this paper, an activity recognition system on a smartphone is proposed where the uncertain time-series acceleration signal is analyzed by using hierarchical hidden Markov models. In order to address the limitations on the memory storage and computational power of the mobile devices, the recognition models are designed hierarchy as actions and activities. We implemented the real-time activity recognition application on a smartphone with the Google android platform, and conducted experiments as well. Experimental results showed the feasibility of the proposed method.
232 citations
18 Jul 2010
TL;DR: In this paper, a smart phone equipped with an embedded 3D-accelerometer was worn on the belt for the purposes of data recording, and the data was processed to identify 6 activities offline (walking, posture transition, gentle motion, standing, sitting and lying).
Abstract: This paper presents details of a convenient and unobtrusive system for monitoring daily activities. A smart phone equipped with an embedded 3D-accelerometer was worn on the belt for the purposes of data recording. Once collected the data was processed to identify 6 activities offline (walking, posture transition, gentle motion, standing, sitting and lying). The processing technique adopted a novel hierarchical classification. In the first instance, rule-based reasoning is used to discriminate between motion and motionless activities. Following this the classification process utilizes two multiclass SVM (support vector machines) classifiers to classify the motion and motionless activities, respectively. The classifiers were trained on data from one subject and tested on 10 subjects. The experiments demonstrate that the hierarchical method can reduce misclassification between motion and motionless activities. The average accuracy was improved compared with using a single classifier by using this classification method (82.8% vs. 63.8%), and is important for providing appropriate feedback in free living applications.
80 citations
TL;DR: One activity classifier for the Android platform is tested that is able to run as a background application without an obvious impact on battery life and which reported high levels of accuracy.
22 citations