Die Autoren danken Evan Beisheim, Nicole Capela, Andrew Herbert-Copley für technische und Datenerfassungshilfe. Projektförderung wurde aus den Natur- und Ingenieurwissenschaften Research Council of Canada (NSERC) und Blackberry Ltd., einschließlich Smartphones in der Studie erhalten.

Dieses Protokoll wurde von der Ottawa Health Science Network Research Ethics Board genehmigt. 1. Vorbereitung <ol><li> Bieten den Teilnehmern einen Überblick über die Forschung, alle Fragen zu beantworten und zu erhalten, informierte Zustimmung. Rekordteilnehmer Eigenschaften (zB Alter, Geschlecht, Größe, Gewicht, Taillenumfang, Beinhöhe von der Spina iliaca anterior superior des Innenknöchels) Identifikationscode, und das Datum auf einem Datenblatt. Stellen Sie sicher, dass das zweite Smartphone, das verwendet wird, um Video aufzunehmen, um zumindest ein 30 Bildern pro Sekunde Aufnahmerate eingestellt ist. </li><li> Befestigen Sie eine Telefon Holster vorne rechts Gürtel oder Hose Taille des Teilnehmers. Starten Sie das Smartphone-Anwendung, die verwendet werden, um die Sensordaten (dh, Datenprotokollierung oder WMMS Anwendung) auf die Mobilität Mess Smartphone sammeln und sicherzustellen, dass die Anwendung in geeigneter Weise ausgeführt wird, wird. Legen Sie das Smartphone in das Holster, mit der Geräterückseite (hinten camera) nach außen zeigt. </li><li> Starten Sie digitale Videoaufzeichnung auf einer zweiten Smartphone. Nach Anonymität, notieren Sie die Vergleichsvideo, ohne dafür das Gesicht der Person, aber zu gewährleisten, um alle Aktivitätsübergänge aufzuzeichnen. Das Telefon kann Handheld zu sein. </li></ol> 2. Aktivitätsschaltung <ol><li> Folgen Sie den Teilnehmer und Video ihre Aktionen auf der zweiten Smartphone, während sie die folgenden Aktionen aus, vom Prüfer gesprochen ausführen: <ol><li> Aus dem Stand, schütteln Sie das Smartphone an den Start der Studie zeigen. </li><li> Weiterhin stehen für mindestens 10 sec. Diese stehen Phase kann für Telefon Orientierung Kalibrierung 14 verwendet werden. </li><li> Gehen Sie zu einem nahe gelegenen Stuhl und setz dich. </li><li> Aufstehen und gehen 60 Meter zu einem Aufzug. </li><li> Stehen und warten auf den Aufzug und dann in den Aufzug zu gehen. </li><li> Nehmen Sie den Aufzug in den zweiten Stock. </li><li> Drehen Sie und gehen Sie in der häuslichen Umgebung. </li><li> Gehen Sie ins Badezimmer und siformulieren Zähneputzen. </li><li> Simulieren Sie das Kämmen der Haare. </li><li> Simulieren Sie die Hände zu waschen. </li><li> Trockene Hände mit einem Handtuch. </li><li> Gehen Sie in die Küche. </li><li> Nehmen Sie Gerichte aus einem Rack und legen Sie sie auf den Tresen. </li><li> Füllen Sie einen Wasserkocher mit Wasser aus der Küchenspüle. </li><li> Setzen Sie den Wasserkocher auf dem Herd Element. </li><li> Legen Sie Brot in einem Toaster. </li><li> Gehen Sie bis zum Esszimmer. </li><li> Sitzen an einem Esstisch. </li><li> Simulieren Sie eine Mahlzeit am Tisch. </li><li> Stehen und gehen zurück in die Küchenspüle. </li><li> Spülen Sie das Geschirr und legen Sie sie in einem Rack. </li><li> Gehen Sie von der Küche zurück zum Aufzug. </li><li> Stehen und warten auf den Aufzug und dann in den Aufzug zu gehen. </li><li> Nehmen Sie den Aufzug in den ersten Stock. </li><li> Gehen Sie 50 Meter zu einem Treppenhaus. </li><li> Öffnen Sie die Tür und geben Sie das Treppenhaus. </li><li> Gehen Sie die Treppe (13 Stufen, rund Landung, 13 Stufen). </li><li> Öffnen Sie die Treppenhaustür in den Flur. </li><li> Biegen Sie rechts ab und gehen den Flur entlang zum 15 Meter. </li><li> Drehen Sie sich um und gehen Sie 15 Meter zurück zum Treppenhaus. </li><li> Öffnen Sie die Tür und geben Sie das Treppenhaus. </li><li> Gehen Sie die Treppe (13 Stufen, rund Landung, 13 Stufen). </li><li> Verlassen Sie das Treppenhaus und einen Raum betreten. </li><li> Liegen auf einem Bett. </li><li> Aufstehen und gehen 10 Meter zu einer Rampe. </li><li> Gehen Sie die Rampe, sich umdrehen, dann die Rampe hinunter (20 Meter). </li><li> Gehen Sie weiter in die Halle und öffnen Sie die Tür nach draußen. </li><li> 100 Meter zu Fuß auf dem gepflasterten Weg. </li><li> Drehen Sie sich um und gehen zurück in den Raum. </li><li> Gehen Sie in den Raum und stehen am Startpunkt. </li><li> Weiter stehend, und dann schütteln Sie das Smartphone an das Ende der Studie zeigen. </li></ol></li></ol> 3. Probe Fertigstellung <ol><li> Stoppen Sie die Videoaufnahme-Smartphone und bitten die Teilnehmer, zu entfernen und das Smartphone und Holster. Stoppen Sie die Datenprotokollierung oder WMMS Anwendung auf dem smartphone. Kopieren Sie die erfassten Bewegungsdaten-Dateien und die Videodatei von beiden Telefonen auf einen Computer für die Nachbearbeitung. </li></ol> 4. Nachbearbeitung <ol><li> Synchronisieren Timing zwischen dem Video und dem Sensor-Rohdaten durch Bestimmung der Zeit, als die Erschütterung Aktion gestartet. Diese Schüttelbewegung entspricht einer deutlichen Beschleunigungsmessersignal und Videorahmen. Erfragen Synchronisationsfehler durch Subtrahieren des Endes Schütteldauer von Anfang Schütteldauer, für Sensor und Video-Datenquellen. Zeitunterschiede sollten ähnlich zwischen den beiden Datensätzen sein. </li><li> Bestimmen Sie tatsächlichen Change-of-State-mal aus dem Gold-Standard-Video durch die Erfassung der Zeitdifferenz vom Beginn shake Zeit, um den Video-Frame an dem Übergang zwischen Aktivitäten. Verwenden Sie Video-Editing-Software, um Timing innerhalb 0,033 sec zu erhalten (dh, 30 Bilder pro Sekunde Videorate). Verwenden WMMS Software zu vergleichbaren Veränderungen-of-state aus den Sensordaten zu erzeugen. </li><li> Generieren Sie zwei Datensätzen, einemmit der wahren und über das zweite mit einer vorhergesagten Aktivitäten durch Markierung die Aktivität für jeden Videorahmen (basierend auf dem Zustandswechsel Timing) und dann Berechnen des vorhergesagten Zeit bei jedem Videoframes vom WMMS ausgegeben. Für WMMS Leistungsbewertung, berechnen wahren Positiven, falsche Negative, wahre Negative, False Positives zwischen dem Gold-Standard-Aktivität und WMMS vorhergesagten Aktivität. Verwenden Sie diese Parameter, um die Empfindlichkeit, Spezifität und F-Score Ergebnisse Maßnahmen zu berechnen. Hinweis: Ein Toleranzeinstellung von 3 Datenfenstern auf beiden Seiten des Fensters, die analysiert zur Bestimmung Change-of-State-Ergebnisse verwendet werden, und 2 Datenfenster für die Klassifikation Ergebnisse. Da beispielsweise 1 Sekunde Datenfenstern wurden zum WMMS in dieser Studie verwendet, 3 Sekunden vor und nach dem aktuellen Fenster untersucht, so dass aufeinanderfolgende Veränderungen innerhalb der Toleranz liegen ignoriert. Die Überlegung war, dass Zustandsänderungen, die in weniger als 3 Sekunden passieren kann für grobe huma ignoriert werdenn Bewegungsanalyse, da diese Staaten würden als transitorische werden. </li></ol>

<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>

The authors declare that they have no competing financial interests.

Menschliche Aktivitäten Erkennung mit einer tragbaren Mobilität Überwachungssystem hat mehr Aufmerksamkeit in den letzten Jahren aufgrund der technischen Fortschritte in der Wearable Computing und Smartphones und systematische Anforderungen für quantitative Zielparameter, die mit der klinischen Entscheidungsfindung und Gesundheit Intervention Evaluation helfen erhalten. Die in diesem Dokument beschriebenen Methode wirksam war für die Bewertung WMMS Entwicklung seit Aktivitätsklassifikation Fehler gefunden wurden, ...

Ubiquitous Erkundung hat sich zu einem Eingriffsforschungsbereich aufgrund von immer leistungsfähigeren, kleine, kostengünstige Computing und Erfassungsgeräte 1. Mobility Überwachung mit tragbaren Sensoren hat ein großes Interesse erzeugt, da Verbraucher-Level-Mikroelektronik sind zum Aufspüren von Bewegungseigenschaften mit hoher Genauigkeit 1. Menschliche Aktivitäten Erkennung (HAR) unter Verwendung von tragbaren Sensoren ist ein neues Forschungsgebiet, die Vorstudien in den 1980er und 1990er Jahren durchgeführt 2-4. Moderne Smartphones enthalten die notwendigen Sensoren und Echtzeitberechnung Fähigkeit zur Mobilität Aktivitätserkennung. Echtzeit-Analyse auf dem Gerät erlaubt Aktivität Klassifikation und Daten-Upload ohne Benutzereingriff oder Prüfer. Ein Smartphone mit Mobilitätsanalysesoftware konnte Fitness Tracking, Gesundheitsberichterstattung liefern, fallen Erkennung, zu Hause oder der Arbeit Automatisierung und selbstverwaltende exercise Programme 5. Smartphones kann als Trägheitsmessplattformen zur Detektion mobilen Aktivitäten und mobile Muster bei Menschen mit generierten mathematischen Signalmerkmale mit integrierten Sensorausgänge 6 berechnet. Erzeugungsverfahren gemeinsames Merkmal umfassen Heuristik Zeitbereich, Frequenzdomäne und Wavelet-Analyse basierende Ansätze 7. Modernes Smartphone HAR Systeme wurden bei der Erkennung bestimmter Aktivitäten 1,5,6,7 hohe Vorhersagegenauigkeit angezeigt. Diese Studien unterscheiden sich in Bewertungsmethodik sowie die Genauigkeit, da die meisten Studien haben ihre eigenen Trainingsgruppe, Umwelt Konfiguration und Datenerfassung Protokoll. Sensitivität, Spezifität, Genauigkeit, Rückruf, Präzision und F-Score werden häufig verwendet, um Vorhersagequalität zu beschreiben. , Wenig bis gar keine Informationen ist jedoch auf Verfahren für &quot;paralleles Arbeiten&quot; Anerkennung und Bewertung der Fähigkeit, Aktivitätsänderungen in Echtzeit zu erfassen1, für die HAR-Systeme, die verschiedene Aktivitäten zu kategorisieren versuchen. Bewertungsmethoden für die Systemgenauigkeit HAR variieren erheblich zwischen den Studien. Unabhängig von der Klassifikationsalgorithmus oder angewandte Funktionen, sind Beschreibungen der Goldstandard Bewertungsmethoden vage für die meisten HAR Forschung. Aktivitätserkennung in einer täglichen Lebensumfeld wurde nicht umfassend erforscht. Esten Smartphone basierten Aktivitätserkennungssysteme werden in einer kontrollierten Art und Weise bewertet, was zu einer Bewertung Protokoll, das dem Algorithmus nicht realistisch, eine reale Umgebung vorteilhaft sein. Im Rahmen ihrer Bewertungsschema, Teilnehmer führen oft nur die Aktionen zur Vorhersage bestimmt, anstatt die Anwendung eine große Auswahl an realistischen Aktivitäten für die Teilnehmer nacheinander durchführen, imitiert wirklichen Leben Veranstaltungen. Einige Smartphone HAR studiert 8,9 Gruppe ähnliche Aktivitäten zusammen, wie Treppen und Wandern, Schließen jedoch andere Aktivitäten aus dem Datensatz. Vorhersagegenauigkeit wird dann, wie gut der Algorithmus identifiziert die Zielaktivitäten bestimmt. Dernbach et al. 9 hatten die Teilnehmer schreiben, die Tätigkeit, die sie dabei, bevor sie ausgeführt werden, zu unterbrechen kontinuierlichen Change-of-Zustandsübergänge waren. HAR-System Bewertungen sollten den Algorithmus zu bewerten, während die Teilnehmer führt natürlichen Aktionen in einem täglichen Lebenseinstellung. Dies würde eine reale Bewertung, die tägliche Nutzung der Anwendung repliziert ermöglichen. Eine realistische Schaltung enthält viele Änderungen-of-Staat als auch einen Mix von Maßnahmen durch das System nicht vorhersehbar. Ein Ermittler dann beurteilen Reaktion des Algorithmus auf diese zusätzlichen Bewegungen, wodurch die Bewertung Robustheit des Algorithmus, um anomale Bewegungen. Dieser Beitrag stellt eine tragbare Mobility Monitoring System (WMMS) Bewertungsprotokoll, das eine gesteuerte Kurs, der realen täglichen Lebenswelten spiegelt verwendet. WMMSAuswertung kann dann unter kontrollierten, aber realistischen Bedingungen durchgeführt werden. In diesem Protokoll verwenden wir eine der dritten Generation WMMS, die an der Universität von Ottawa und Ottawa Hospital Research Institute 11-15 entwickelt wurde. Die WMMS wurde für Smartphones mit einem Tri-Achsen-Beschleunigungsmesser und Gyroskop gestaltet. Die Mobilität Algorithmus Konten für Benutzer Variabilität, stellt eine Verringerung der Anzahl von False Positives für Änderungen-of-state Identifikation, und erhöht die Empfindlichkeit der Aktivität Kategorisierung. Minimierung von False Positives ist wichtig, da die WMMS löst kurzen Videoclip-Aufnahme wenn Aktivität Zustandsänderungen erkannt werden, für die kontextbezogene Aktivität Evaluierung, die WMMS Klassifizierung weiter verbessert. Unnötige Videoaufzeichnung erzeugt Ineffizienzen bei der Lagerung und Verwendung von Akkus. Die WMMS Algorithmus wird als Low-Rechenlernmodell strukturiert und ausgewertet mit verschiedenen Vorhersagewerken, in denen eine Erhöhung der Vorhersageniveau bedeutet eine Zunahme in der Mengevon erkennbaren Handlungen.

<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.

Das Studienprotokoll wurde mit einer Gelegenheitsstichprobe von fünfzehn nichtbehinderte Teilnehmer, deren Durchschnittsgewicht betrug 68,9 (± 11,1) kg durchgeführt, Höhe betrug 173,9 (± 11,4) cm, und Alter betrug 26 (± 9) Jahre, gerechnet ab Ottawa Krankenhaus rekrutiert und University of Ottawa Mitarbeiter und Studenten. Ein Smartphone erfassten Sensordaten mit einer variablen 40-50 Hz-Rate. Abtastrate Schwankungen sind typisch für Smartphone-Sensor Probenahme. Ein zweites Smartphone wurde verwendet, um digital...

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.

Evaluation eines Smartphone-basierte Personal Activity Recognition System in einem täglichen Lebens Umwelt

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

evaluation-smartphone-based-human-activity-recognition-system-daily

Research

JoVE Journal

Behavior

8.8K Aufrufe.  University of Ottawa. 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.

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

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 potentials (LFPs) from populations of neurons and action potentials from individual cells, as the animal engages in experimentally relevant tasks. Chronically implanted microdrives allow for brain recordings to last over periods of several weeks. Miniaturized drives and lightweight components allow for these long-term recordings to occur in small mammals, such as mice. By using tetrodes, which consist of tightly braided bundles of four electrodes in which each wire has a diameter of 12.5 &mu;m, it is possible to isolate physiologically active neurons in superficial brain regions such as the cerebral cortex, dorsal hippocampus, and subiculum, as well as deeper regions such as the striatum and the amygdala. Moreover, this technique insures stable, high-fidelity neural recordings as the animal is challenged with a variety of behavioral tasks. This manuscript describes several techniques that have been optimized to record from the mouse brain. First, we show how to fabricate tetrodes, load them into driveable tubes, and gold-plate their tips in order to reduce their impedance from M&Omega; to K&Omega; range. Second, we show how to construct a custom microdrive assembly for carrying and moving the tetrodes vertically, with the use of inexpensive materials. Third, we show the steps for assembling a commercially available microdrive (Neuralynx VersaDrive) that is designed to carry independently movable tetrodes. Finally, we present representative results of local field potentials and single-unit signals obtained in the dorsal subiculum of mice. These techniques can be easily modified to accommodate different types of electrode arrays and recording schemes in the mouse brain.

The design and assembly of microdrives for in vivo electrophysiological recordings of brain signals from the mouse is described. By attaching microelectrode bundles to sturdy driveable carriers, these techniques allow for long-term and stable neural recordings. The lightweight design allows for unrestricted behavioral performance by the animal following drive implantation.

Bau Microdrive Arrays für chronische Neural Recordings in Awake benimmt Mäuse

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

Forschung

Verhalten

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 identified cells during behavior1-6. Here we describe methods to perform two-photon imaging in mouse cortex while the animal navigates a virtual reality environment. We focus on the aspects of the experimental procedures that are key to imaging in a behaving animal in a brightly lit virtual environment. The key problems that arise in this experimental setup that we here address are: minimizing brain motion related artifacts, minimizing light leak from the virtual reality projection system, and minimizing laser induced tissue damage. We also provide sample software to control the virtual reality environment and to do pupil tracking. With these procedures and resources it should be possible to convert a conventional two-photon microscope for use in behaving mice.

Here we describe the experimental procedures involved in two-photon imaging of mouse cortex during behavior in a virtual reality environment.

Zwei-Photonen-Calcium Imaging in Mäuse Navigieren in einer Virtual-Reality-Umgebung

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; Treatment studies aimed at cognitive impairment in patients with schizophrenia not only require demonstration of improvements on cognitive tests, but also evidence that any cognitive changes lead to clinically meaningful improvements.&#160; Measures of &#8220;functional capacity&#8221; index the extent to which individuals have the potential to perform skills required for real world functioning. &#160;Current data do not support the recommendation of any single instrument for measurement of functional capacity.&#160; The Virtual Reality Functional Capacity Assessment Tool (VRFCAT) is a novel, interactive gaming based measure of functional capacity that uses a realistic simulated environment to recreate routine activities of daily living. Studies are currently underway to evaluate and establish the VRFCAT&#8217;s sensitivity, reliability, validity, and practicality.&#160;This new measure of functional capacity is practical, relevant, easy to use, and has several features that improve validity and sensitivity of measurement of function in clinical trials of patients with CNS disorders.

A challenge for proving treatment efficacy for cognitive impairments in schizophrenia is finding the optimizing measurement of skills related to everyday functioning.&#160; The Virtual Reality Functional Capacity Assessment Tool (VRFCAT) is an interactive gaming based computerized measure aimed at skills associated with everyday functioning, including baseline impairments and treatment related changes.

Entwicklung eines Virtual-Reality-Bewertung der Alltag Fähigkeiten

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 studies demonstrate that environmental enrichment decreases adiposity, increases energy expenditure, resists diet induced obesity, and causes cancer remission and inhibition in mice. EE typically consists of larger living space, a variety of &#8216;toys&#8217; to interact with, running wheels, and can include a number of other novel environmental changes. All of this fosters a more complex social engagement, cognitive and physical stimulations. Importantly, the toy location and type of toy is changed regularly, which encourages the mice to adapt to a frequently changing and novel environment. Many variables can be manipulated in EE to promote health effects in mice. Thus these approaches are difficult to control and must be properly managed to successfully replicate the associated phenotypes. Therefore, the goal of this video is to demonstrate how EE is properly set up and maintained to assure a complex, challenging, and controlled environment so that other researchers can easily reproduce the protective effects of EE against obesity and cancer.

Environmental enrichment for mice requires a complex and challenging setup, as well as comprehensive husbandry and handling techniques to assure robust metabolic and anti-cancer effects in the mice. This protocol provides detailed procedures to reproduce the above mentioned effects in mice.

Ein Protokoll für die Housing Mäuse in einer angereicherten Umwelt

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 previous studies have used special spectacles with prisms to achieve unusual spaces in the visual domain, a methodology for studying the adaptation to unusual auditory spaces has yet to be fully established. This study proposes a new protocol to set-up, validate, and use a left-right reversed stereophonic system using only wearable devices, and to study the adaptation to left-right reversed audition with the help of neuroimaging. Although individual acoustic characteristics are not yet implemented, and slight spillover of unreversed sounds is relatively uncontrollable, the constructed apparatus shows high performance in a 360&#176; sound source localization coupled with hearing characteristics with little delay. Moreover, it looks like a mobile music player and enables a participant to focus on daily life without arousing curiosity or drawing attention of other individuals. Since the effects of adaptation were successfully detected at the perceptual, behavioral, and neural levels, it is concluded that this protocol provides a promising methodology for studying adaptation to left-right reversed audition, and is an effective tool for uncovering the adaptability of humans to a novel environments in the auditory domain.

The present study proposes a protocol to investigate the adaptation to left-right reversed audition achieved only by wearable devices, using neuroimaging, which can be an effective tool for uncovering the adaptability of humans to a novel environment in the auditory domain.

Eine Methode zur Anpassung an den links-rechts studieren umgekehrt 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 ...

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 assessments of IADL are easy to use but prone to subjective bias. Here, we describe a novel virtual reality (VR) test to assess two complex IADL tasks: handling financial transactions and using public transportation. While a participant performs the tasks in a VR setting, a motion capture system traces the position and orientation of the dominant hand and head in a three-dimensional Cartesian coordinate system. Kinematic raw data are collected and converted into &#39;kinematic performance measures,&#39; i.e., motion trajectory, moving distance, and time to completion. Motion trajectory is the path of a particular body part (e.g., dominant hand or head) in space. Moving distance refers to the total distance of the trajectory, and time to completion is how long it took to complete an IADL task. These kinematic measures could discriminate patients with cognitive impairment from healthy controls. The development of this kinematic measuring protocol allows detection of early IADL-related cognitive impairments.

We designed a virtual reality test to assess instrumental activities of daily living (IADL) with a motion capture system. We propose a detailed kinematic analysis to interpret the participant&#39;s various movements, including trajectory, moving distance, and time to completion to evaluate IADL capabilities.

Messung der Kinematik des täglichen Lebens Bewegungen mit Motion-Capture-Systeme in der virtuellen Realität

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 physiological or pathological changes. The object location task (OLT) and the novel object recognition task (NORT) are two effective behavioral tasks commonly used to reveal the function and relative health of specific brain regions involved in memory. While both of these tests exploit the inherent preference of mice for the novelty to reveal memory for previously encountered objects, the OLT primarily evaluates spatial learning, which relies heavily on hippocampal activity. The NORT, in contrast, evaluates non-spatial learning of object identity, which relies on multiple brain regions. Both tasks require an open-field-testing arena, objects with equivalent intrinsic value to mice, appropriate environmental cues, and video recording equipment and the software. Commercially available systems, while convenient, can be costly. This manuscript details a simple, cost-effective method for building the arenas and setting up the equipment necessary to perform the OLT and NORT. Furthermore, the manuscript describes an efficient testing protocol that incorporates both OLT and NORT and provides typical methods for data acquisition and analysis, as well as representative results. Successful completion of these tests can provide valuable insight into the memory function of various mouse model systems and appraise the underlying neural regions that support these functions.

Here we provide a protocol which includes comprehensive instructions for the economical establishment of murine object location and novel object recognition behavioral testing, including the design, cost, and construction of required equipment as well as execution of behavioral testing, data collection, and analysis.

Neuartige Objekterkennung und Objektposition Verhaltens Tests bei Mäusen mit kleinem 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 been described. The exercise-induced cTnT response distorts the diagnostic role of the cTnT assay. Although high-intensity interval exercise (HIE) is growing in popularity and concerns remain about its safety, available data related to cTnT release after HIE is limited, which hampers the use of HIE as a health intervention. Here, we present three representative HIE protocols [traditional HIE (repeated 4 min cycling at 90% V&#775;O2max interspersed with 3 min rest, 200 kJ/session); sprint interval exercise (SIE, repeated 1 min cycling at 120% V&#775;O2max interspersed with 1.5 min rest, 200 kJ/session); and repeated sprint exercise (RSE, 40 x 6 s all-out sprints interspersed with 9 s rest)] and one representative MCE protocol (continuous cycling exercise at an intensity of 60% V&#775;O2max, 200 kJ/session). Forty-seven sedentary, overweight young women were randomly assigned to one of four groups (HIE, SIE, RSE, and MCE). Six bouts of respective exercise were performed by every single group, with each being 48 h apart. Meanwhile, for four groups, the duration of the entire testing period was identical, being 10 days. Before and after the first and final exercise bouts, an assessment was conducted of cTnT. The current study provides a frame of reference giving a clear picture of how a specific exercise session affects the circulating cTnT concentration at the early stage of training. The information may assist with clinical interpretations of post-exercise cTnT elevation and guide the prescription of exercise, especially for HIE.

Here, we present protocols of high-intensity interval and moderate-intensity continuous exercise to observe the response of circulating cardiac troponin T (cTnT) concentration to acute exercise over 10 days. The information may assist with clinical interpretations of post-exercise cTnT elevation and guide the prescription of exercise.

Auswirkungen von High-Intensity-Intervall-Übung und moderate Intensität kontinuierliche Übung auf dem kardialen Troponin T-Niveau in einem frühen Stadium des Trainings

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 single neurons and region-specific transmitter release, up to whole neuronal circuitries in the central nervous system, and allows the direct measurement of behavioral outcomes. Neurons express optogenetic tools via an injection of viral vectors carrying the DNA of choice, such as Channelrhodopsin2 (ChR2). Light is brought into specific brain regions via chronic optical implants that terminate directly above the target region. After two weeks of recovery and proper tool-expression, mice can be repeatedly used for behavioral tests with optogenetic stimulation of the neurons of interest.
Optogenetic modulation has a high temporal and spatial resolution that can be accomplished with high cell specificity, compared to the commonly used methods such as chemical or electrical stimulation. The light does not harm neuronal tissue and can therefore be used for long-term experiments as well as for multiple behavioral experiments in one mouse. The possibilities of optogenetic tools are nearly unlimited and enable the activation or silencing of whole neurons, or even the manipulation of a specific receptor type by light.
The results of such behavioral experiments with integrated optogenetic stimulation directly visualizes changes in behavior caused by the manipulation. The behavior of the same animal without light stimulation as a baseline is a good control for induced changes. This allows a detailed overview of neuronal types or neurotransmitter systems involved in specific behaviors, such as anxiety. The plasticity of neuronal networks can also be investigated in great detail through long-term stimulation or behavioral observations after optical stimulation. Optogenetics will help to enlighten neuronal signaling in several kinds of neurological diseases.

With optogenetic manipulation of specific neuronal populations or brain regions, behavior can be modified with high temporal and spatial resolution in freely moving animals. By using different optogenetic tools in combination with chronically implanted optical fibers, a variety of neuronal modulations and behavioral testing can be performed.

Optogenetische Manipulation der neuronalen Aktivität, um das Verhalten bei frei beweglichen Mäusen zu modulieren

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

Iterative Development of an Innovative Smartphone-Based Dietary Assessment Tool: Traqq

To collect dietary intake data in a fast and reliable manner, a flexible and innovative smartphone application (app) called Traqq was developed (iOS/Android). This app can be used as a food record and&#160;24-h recall (or shorter recall periods). Different sampling schemes can be created on either prespecified or random days/times within a predetermined period for both methods, with&#160;push notifications to urge the participants to register their food intake. In case of non-response, notifications are automatically rescheduled to ensure complete data collection. For use as a food record, respondents can access the app and log their food intake throughout the day. Food records close automatically at the end of the day; recalls close after submission of the consumed items. The recall as well as the food record module provide access to an extensive food list based on the Dutch food composition database (FCDB), which can be accustomed to fit different research purposes. When selecting a food item, respondents are simultaneously prompted to insert portion size, i.e., in household measures (e.g., cups, spoons, glasses), standard portion sizes (e.g., small, medium, large), or weight in grams, and eating occasion/time of consumption. Portion size options can be adjusted, e.g., only entry in grams in case of a weighed food record or time of consumption instead of eating occasion). The app also includes a My Dishes function, which allows the respondent to create their own recipes or product combinations (e.g., a daily breakfast) and only report the total quantity consumed. Subsequently, the app accounts for yield and retention factors. The data are stored on a secure server. If desired, additional questions, i.e., in general or those related to specific food items or eating occasions can be incorporated. This paper describes the development of the system (app and backend), including expert evaluations and usability testing.

This article describes the protocol for the development of an innovative smartphone-based dietary assessment application Traqq, including expert evaluations and usability testing.