Name: evaluation of a smartphone-based human activity recognition system in a daily living environment
Uploaded: 2015-12-11T13:00:00
Description: Watch this Scientific Journal Video about Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment at JoVE.com

The authors acknowledge Evan Beisheim, Nicole Capela, Andrew Herbert-Copley for technical and data collection assistance. Project funding was received from the Natural Sciences and Engineering Research Council of Canada (NSERC) and BlackBerry Ltd., including smartphones used in the study.

This protocol was approved by the Ottawa Health Science Network Research Ethics Board.
1. Preparation
<ol>
	<li>Provide participants with an outline of the research, answer any questions, and obtain informed consent. Record participant characteristics (e.g., age, gender, height, weight, waist girth, leg height from the anterior superior iliac spine to the medial malleolus), identification code, and date on a data sheet. Ensure that the second smartphone that is used to capture video...

<ol>
	<li>Lara, O. D., Labrador, M. A. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=A+Survey+on+Human+Activity+Recognition+using+Wearable+Sensors.">A Survey on Human Activity Recognition using Wearable Sensors.</a> IEEE Communications Surveys Tutorials. 15 (3), 1192-1209 (2013).</li><li>Foerster, F., Smeja, M., Fahrenberg, J. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Detection+of+posture+and+motion+by+accelerometry:+a+validation+study+in+ambulatory+monitoring.">Detection of posture and motion by accelerometry: a validation study in ambulatory monitoring.</a> Computers in Human Behavior. 15 (5), 571-583 (1999).</li><li>Elsmore, T. F., Naitoh, P. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=.">.</a> Monitoring Activity With a Wrist-Worn Actigraph: Effects of Amplifier Passband and threshold Variations. , (1993).</li><li>Kripke, D. F., Webster, J. B., Mullaney, D. J., Messin, S., Mason, W. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=.">.</a> Measuring sleep by wrist actigraph. , (1981).</li><li>Lockhart, J. W., Pulickal, T., Weiss, G. M. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Applications+of+mobile+activity+recognition.">Applications of mobile activity recognition.</a> Proceedings of the 2012 ACM Conference on Ubiquitous Computing. , 1054-1058 (2012).</li><li>Incel, O. D., Kose, M., Ersoy, C. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=A+Review+and+Taxonomy+of+Activity+Recognition+on+Mobile+Phones.">A Review and Taxonomy of Activity Recognition on Mobile Phones.</a> BioNanoScience. 3 (2), 145-171 (2013).</li><li>Yang, C. C., Hsu, Y. L. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=A+Review+of+Accelerometry-Based+Wearable+Motion+Detectors+for+Physical+Activity+Monitoring.">A Review of Accelerometry-Based Wearable Motion Detectors for Physical Activity Monitoring.</a> Sensors. 10 (8), 7772-7788 (2010).</li><li>He, Y., Li, Y. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Physical+Activity+Recognition+Utilizing+the+Built-In+Kinematic+Sensors+of+a+Smartphone.">Physical Activity Recognition Utilizing the Built-In Kinematic Sensors of a Smartphone.</a> International Journal of Distributed Sensor Networks. 2013, (2013).</li><li>Vo, Q. V., Hoang, M. T., Choi, D. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Personalization+in+Mobile+Activity+Recognition+System+using+K-medoids+Clustering+Algorithm.">Personalization in Mobile Activity Recognition System using K-medoids Clustering Algorithm.</a> International Journal of Distributed Sensor Networks. 2013, (2013).</li><li>Dernbach, S., Das, B., Krishnan, N. C., Thomas, B. L., Cook, D. J. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Simple+and+Complex+Activity+Recognition+through+Smart+Phones.">Simple and Complex Activity Recognition through Smart Phones.</a> , 214-221 (2012).</li><li>Hache, G., Lemaire, E. D., Baddour, N. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Mobility+change-of-state+detection+using+a+smartphone-based+approach.">Mobility change-of-state detection using a smartphone-based approach.</a> IEEE International Workshop on Medical Measurements and Applications Proceedings (MeMeA). , 43-46 (2010).</li><li>Wu, H. H., Lemaire, E. D., Baddour, N. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Change-of-state+determination+to+recognize+mobility+activities+using+a+BlackBerry+smartphone.">Change-of-state determination to recognize mobility activities using a BlackBerry smartphone.</a> , 5252-5255 (2011).</li><li>Wu, H., Lemaire, E. D., Baddour, N. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Activity+Change-of-state+Identification+Using+a+Blackberry+Smartphone.">Activity Change-of-state Identification Using a Blackberry Smartphone.</a> Journal of Medical and Biological Engineering. 32 (4), 265-271 (2012).</li><li>Tundo, M. D., Lemaire, E., Baddour, N. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=Correcting+Smartphone+orientation+for+accelerometer-based+analysis.">Correcting Smartphone orientation for accelerometer-based analysis.</a> IEEE International Symposium on Medical Measurements and Applications Proceedings (MeMeA). , 58-62 (2013).</li><li>Tundo, M. D. <a target="_blank" href="http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed&cmd=Search&doptcmdl=Citation&defaultField=Title+Word&term=.">.</a> Development of a human activity recognition system using inertial measurement unit sensors on a smartphone. , (2014).</li></ol>

Human activity recognition with a wearable mobility monitoring system has received more attention in recent years due to the technical advances in wearable computing and smartphones and systematic needs for quantitative outcome measures that help with clinical decision-making and health intervention evaluation. The methodology described in this paper was effective for evaluating WMMS development since activity classification errors were found that would not have been present if a broad range of activities of daily living...

Ubiquitous sensing has become an engaging research area due to increasingly powerful, small, low cost computing and sensing equipment&#160;1. Mobility monitoring using wearable sensors has generated a great deal of interest since consumer-level microelectronics are capable of detecting motion characteristics with high accuracy&#160;1. Human activity recognition (HAR) using wearable sensors is a recent area of research, with preliminary studies performed in the 1980s and 1990s 2-4.
Modern smartphones contain the necessary sensors and real-time computation capability for mobility activity recognition. Real-time analysis on the device permits activity classification and data upload without user or investigator intervention. A smartphone with mobility analysis software could provide fitness tracking, health monitoring, fall detection, home or work automation, and self-managing exercise programs 5. Smartphones can be considered inertial measurement platforms for detecting mobile activities and mobile patterns in humans, using generated mathematical signal features calculated with onboard sensor outputs 6. Common feature generation methods include heuristic, time-domain, frequency-domain, and wavelet analysis-based approaches&#160;7.
Modern smartphone HAR systems have shown high prediction accuracies when detecting specified activities&#160;1,5,6,7. These studies vary in evaluation methodology as well as accuracy since most studies have their own training set, environmental setup, and data collection protocol. Sensitivity, specificity, accuracy, recall, precision, and F-Score are commonly used to describe prediction quality. However, little to no information is available on methods for &#34;concurrent activity&#34; recognition and evaluation of the ability to detect activity changes in real-time 1, for HAR systems that attempt to categorize several activities. Assessment methods for HAR system accuracy vary substantially between studies. Regardless of the classification algorithm or applied features, descriptions of gold standard evaluation methods are vague for most HAR research.
Activity recognition in a daily living environment has not been extensively researched. Most smartphone-based activity recognition systems are evaluated in a controlled manner, leading to an evaluation protocol that may be advantageous to the algorithm rather than realistic to a real-world environment. Within their evaluation scheme, participants often perform only the actions intended for prediction, rather than applying a large range of realistic activities for the participant to perform consecutively, mimicking real-life events.
Some smartphone HAR studies 8,9 group similar activities together, such as stairs and walking, but exclude other activities from the data set. Prediction accuracy is then determined by how well the algorithm identified the target activities. Dernbach et al. 9 had participants write the activity they were about to execute before moving, interrupting continuous change-of-state transitions. HAR system evaluations should assess the algorithm while the participant performs natural actions in a daily living setting. This would permit a real-life evaluation that replicates daily use of the application. A realistic circuit includes many changes-of-state as well as a mix of actions not predicable by the system. An investigator can then assess the algorithm&#39;s response to these additional movements, thus evaluating the algorithm&#39;s robustness to anomalous movements.
This paper presents a Wearable Mobility Monitoring System (WMMS) evaluation protocol that uses a controlled course that reflects real-life daily living environments. WMMS evaluation can then be made under controlled but realistic conditions. In this protocol, we use a third-generation WMMS that was developed at the University of Ottawa and Ottawa Hospital Research Institute 11-15. The WMMS was designed for smartphones with a tri-axis accelerometer and gyroscope. The mobility algorithm accounts for user variability, provides a reduction in the number of false positives for changes-of-state identification, and increases sensitivity in activity categorization. Minimizing false positives is important since the WMMS triggers short video clip recording when activity changes of state are detected, for context-sensitive activity evaluation that further improves WMMS classification. Unnecessary video recording creates inefficiencies in storage and battery use. The WMMS algorithm is structured as a low-computational learning model and evaluated using different prediction levels, where an increase in prediction level signifies an increase in the amount of recognizable actions.

<table border="0" cellpadding="0" cellspacing="0" width="1314">
	<tbody>
		<tr height="20">
			<td height="20" style="height:20px;width:516px;">Smartphone or wearable measurement device</td>
			<td style="width:627px;">Blackberry</td>
			<td style="width:108px;">Z10</td>
			<td style="width:64px;"></td>
		</tr>
		<tr height="20">
			<td height="20" style="height:20px;">Smartphone for video recording</td>
			<td>Blackberry</td>
			<td>Z10 or 9800</td>
			<td></td>
		</tr>
		<tr height="20">
			<td height="20" style="height:20px;">Phone holster</td>
			<td>Any</td>
			<td></td>
			<td></td>
		</tr>
		<tr height="20">
			<td height="20" style="height:20px;">Data logger application for the smartphone</td>
			<td>BlackBerry World - TOHRC Data Logger for BlackBerry 10</td>
			<td></td>
			<td><a href="http://appworld.blackberry.com/webstore/content/32013891/?countrycode=CA">http://appworld.blackberry.com/webstore/content/32013891/?countrycode=CA</a></td>
		</tr>
		<tr height="20">
			<td height="20" style="height:20px;">Wearable mobility measurement</td>
			<td>Custom Blackberry 10 and Matlab software for mobility monitoring</td>
			<td></td>
			<td><a href="http://www.irrd.ca/cag/smartphone/">http://www.irrd.ca/cag/smartphone/</a></td>
		</tr>
		<tr height="20">
			<td height="20" style="height:20px;">Video editing or analysis software</td>
			<td>Motion Analysis Tools</td>
			<td></td>
			<td><a href="http://www.irrd.ca/cag/mat/">http://www.irrd.ca/cag/mat/</a></td>
		</tr>
	</tbody>
</table>

evaluation of a smartphone-based human activity recognition system in a daily living environment

An evaluation method that includes continuous activities in a daily-living environment was developed for Wearable Mobility Monitoring Systems (WMMS) that attempt to recognize user activities. Participants performed a pre-determined set of daily living actions within a continuous test circuit that included mobility activities (walking, standing, sitting, lying, ascending/descending stairs), daily living tasks (combing hair, brushing teeth, preparing food, eating, washing dishes), and subtle environment changes (opening doors, using an elevator, walking on inclines, traversing staircase landings, walking outdoors). 
To evaluate WMMS performance on this circuit, fifteen able-bodied participants completed the tasks while wearing a smartphone at their right front pelvis. The WMMS application used smartphone accelerometer and gyroscope signals to classify activity states. A gold standard comparison data set was created by video-recording each trial and manually logging activity onset times. Gold standard and WMMS data were analyzed offline. Three classification sets were calculated for each circuit: (i) mobility or immobility, ii) sit, stand, lie, or walking, and (iii) sit, stand, lie, walking, climbing stairs, or small standing movement. Sensitivities, specificities, and F-Scores for activity categorization and changes-of-state were calculated.
The mobile versus immobile classification set had a sensitivity of 86.30% &#177; 7.2% and specificity of 98.96% &#177; 0.6%, while the second prediction set had a sensitivity of 88.35% &#177; 7.80% and specificity of 98.51% &#177; 0.62%. For the third classification set, sensitivity was 84.92% &#177; 6.38% and specificity was 98.17 &#177; 0.62. F1 scores for the first, second and third classification sets were 86.17 &#177; 6.3, 80.19 &#177; 6.36, and 78.42 &#177; 5.96, respectively. This demonstrates that WMMS performance depends on the evaluation protocol in addition to the algorithms. The demonstrated protocol can be used and tailored for evaluating human activity recognition systems in rehabilitation medicine where mobility monitoring may be beneficial in clinical decision-making.

The study protocol was conducted with a convenience sample of fifteen able-bodied participants whose average weight was 68.9 (&#177; 11.1) kg, height was 173.9 (&#177; 11.4) cm, and age was 26 (&#177; 9) years, recruited from The Ottawa Hospital and University of Ottawa staff and students. A smartphone captured sensor data at a variable 40-50 Hz rate. Sample rate variations are typical for smartphone sensor sampling. A second smartphone was used to record digital video at 1280x720 (720p) resolution.
<p class="jove_co...

Watch this Scientific Journal Video about Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment at JoVE.com

Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment

A standardized evaluation method was developed for Wearable Mobility Monitoring Systems (WMMS) that includes continuous activities in a realistic daily living environment. Testing with a series of daily living activities can decrease activity recognition sensitivity; therefore, realistic testing circuits are encouraged for valid evaluation of WMMS performance.

An evaluation method that includes continuous activities in a daily-living environment was developed for Wearable Mobility Monitoring Systems (WMMS) that ...

Research

JoVE Journal

Behavior

Construction of Microdrive Arrays for Chronic Neural Recordings in Awake Behaving Mice

State-of-the-art electrophysiological recordings from the brains of freely behaving animals allow researchers to simultaneously examine local field ...

Two-photon Calcium Imaging in Mice Navigating a Virtual Reality Environment

In recent years, two-photon imaging has become an invaluable tool in neuroscience, as it allows for chronic measurement of the activity of genetically ...

Development of a Virtual Reality Assessment of Everyday Living Skills

Cognitive impairments affect the majority of patients with schizophrenia and these impairments predict poor long term psychosocial outcomes.&#160; ...

A Protocol for Housing Mice in an Enriched Environment

Environmental enrichment (EE) is a housing environment for mice that boosts mental and physical health compared to standard laboratory housing. Our recent ...

A Method to Study Adaptation to Left-Right Reversed Audition

An unusual sensory space is one of the effective tools to uncover the mechanism of adaptability of humans to a novel environment. Although most of the ...

Use of a Video Scoring Anchor for Rapid Serial Assessment of Social Communication in Toddlers

Reciprocal social behavior (RSB), an early-emerging capacity to engage in social contingency&#8212;which is foundational for both social learning and ...

Measuring the Kinematics of Daily Living Movements with Motion Capture Systems in Virtual Reality

The inability to complete instrumental activities of daily living (IADL) is a precursor to various neuropsychological diseases. Questionnaire-based ...

Novel Object Recognition and Object Location Behavioral Testing in Mice on a Budget

Ethologically relevant behavioral testing is a critical component of any study that uses mouse models to study the cognitive effects of various ...

Impact of High-intensity Interval Exercise and Moderate-Intensity Continuous Exercise on the Cardiac Troponin T Level at an Early Stage of Training

An elevation in cardiac troponin T (cTnT), as a highly specific biomarker of cardiomyocyte damage, after moderate-intensity continuous exercise (MCE) has ...

Optogenetic Manipulation of Neuronal Activity to Modulate Behavior in Freely Moving Mice

Optogenetic modulation of neuronal circuits in freely moving mice affects acute and long-term behavior. This method is able to perform manipulations of ...