Se ha denunciado esta presentación.
Utilizamos tu perfil de LinkedIn y tus datos de actividad para personalizar los anuncios y mostrarte publicidad más relevante. Puedes cambiar tus preferencias de publicidad en cualquier momento.
1/35
UCAmI
2015
DeustoTech-Deusto Institute of Technology, University of Deusto
http://www.morelab.deusto.es
December 2, 2...
2/35
UCAmI
2015
Outline
Introduction
System Design
Evaluation
Conclusion
3/35
UCAmI
2015
Introduction
System Design
Evaluation
Conclusion
4/35
UCAmI
2015
Introduction
Introduction
AT HOME
.
.
.
5/35
UCAmI
2015
Introduction
.
.
.
6/35
UCAmI
2015
Introduction
► Location-based services
► Foursquare, Twitter, Google Keep,…
► Low-level inference
► Physic...
7/35
UCAmI
2015
Introduction
► Socialization as a high-level useractivity
► based on environmentrecognition
► provides “so...
8/35
UCAmI
2015
Introduction
System Design
Evaluation
Conclusion
9/35
UCAmI
2015
System Design: Context capture
► Environments
► Bar, café, sports bar, disco and restaurant
► Characterist...
10/35
UCAmI
2015
System Design: Context capture
► Captured Data
► Audio
► RMSpoweranddBs
► Microphone
► Acceleration
► 3-a...
11/35
UCAmI
2015
Data processing
► 3 steps
► 1. Data fusion
► 2. Data transformation
► 3. Feature extraction
1. DataFusion...
12/35
UCAmI
2015
Data processing
► 1. Data fusion
► Timestamps
► Gathering halts
► Sample rate
► 50Hz,20Hz,10Hz,5Hz, 2Hzan...
13/35
UCAmI
2015
Data processing
► 1. Data fusion
► 2. Data transformation
► Raw to processed characteristics
1. DataFusio...
14/35
UCAmI
2015
Data processing
► 1. Data fusion
► 2. Data transformation
► 3. Featureextraction
1. DataFusion
2. Data
tr...
15/35
UCAmI
2015
Introduction
System Design
Evaluation
Conclusion
16/35
UCAmI
2015
Evaluation
► Training Set
► 10x5-fold cross validation
► Nexus 4 70h
► Test Set
► Nexus 4 30h
► HTC Desir...
17/35
UCAmI
2015
Evaluation
► Feature comparison
► Acceleration features comparison
► Vectornorm->Randomforest,SVMandk-NNl...
18/35
UCAmI
2015
Evaluation
► Contribution of eachsensor
► Training with the best performing feature of each sensor
► conc...
19/35
UCAmI
2015
Evaluation
► Window sizecomparison
► Common pattern: The smaller the window size, the worse the results
►...
20/35
UCAmI
2015
Evaluation
► Sample ratecomparison
► Smaller window sizes suffer more than biggerones when this parameter...
21/35
UCAmI
2015
Evaluation
► Classifier comparison
► Thebest is SVM
► + recall
► + AUC
► + accuracy
► Random Forest
► +sp...
22/35
UCAmI
2015
Evaluation
► The best performing
configuration
► SVM
► Features
► Linearacceleration
► FiltereddBs
► Log-...
23/35
UCAmI
2015
Introduction
System Design
Evaluation
Conclusion
24/35
UCAmI
2015
Conclusion
► Findings
► The preliminary results obtained seem promising regarding the recognition of new
...
25/35
UCAmI
2015
Thank you for your
attention
26/35
UCAmI
2015
DeustoTech-Deusto Institute of Technology, University of Deusto
http://www.morelab.deusto.es
Facing up so...
27/35
UCAmI
2015
All rights of images are reservedby the original owners*,the rest of the content
is licensed under a Crea...
Próximo SlideShare
Cargando en…5
×

de

Facing up social activity recognition using smartphone sensors Slide 1 Facing up social activity recognition using smartphone sensors Slide 2 Facing up social activity recognition using smartphone sensors Slide 3 Facing up social activity recognition using smartphone sensors Slide 4 Facing up social activity recognition using smartphone sensors Slide 5 Facing up social activity recognition using smartphone sensors Slide 6 Facing up social activity recognition using smartphone sensors Slide 7 Facing up social activity recognition using smartphone sensors Slide 8 Facing up social activity recognition using smartphone sensors Slide 9 Facing up social activity recognition using smartphone sensors Slide 10 Facing up social activity recognition using smartphone sensors Slide 11 Facing up social activity recognition using smartphone sensors Slide 12 Facing up social activity recognition using smartphone sensors Slide 13 Facing up social activity recognition using smartphone sensors Slide 14 Facing up social activity recognition using smartphone sensors Slide 15 Facing up social activity recognition using smartphone sensors Slide 16 Facing up social activity recognition using smartphone sensors Slide 17 Facing up social activity recognition using smartphone sensors Slide 18 Facing up social activity recognition using smartphone sensors Slide 19 Facing up social activity recognition using smartphone sensors Slide 20 Facing up social activity recognition using smartphone sensors Slide 21 Facing up social activity recognition using smartphone sensors Slide 22 Facing up social activity recognition using smartphone sensors Slide 23 Facing up social activity recognition using smartphone sensors Slide 24 Facing up social activity recognition using smartphone sensors Slide 25 Facing up social activity recognition using smartphone sensors Slide 26 Facing up social activity recognition using smartphone sensors Slide 27
Próximo SlideShare
MIGUEL ANGELO
Siguiente
Descargar para leer sin conexión y ver en pantalla completa.

0 recomendaciones

Compartir

Descargar para leer sin conexión

Facing up social activity recognition using smartphone sensors

Descargar para leer sin conexión

In the last years context awareness has become a reality in real-world applications. However, building comprehensive context recognition systems which are able to recognize both low and high-level context information remains a challenge. In this paper, we discuss environment recognition as a means to address the issue of recognizing a high-level user context, social activity. In many countries, bars, pubs and similar establishments are one of the main places where social engagement takes place, and thus we propose recognizing these types of environments using data collected from mobile device sensors as a proxy for inferring social activity. For this purpose, we discuss the common defining characteristics of these establishments and the sensors we will use to recognize them. After that, we introduce the design of our system. Finally, we present the preliminary evaluation carried out to assess the validity of our proposal.

Audiolibros relacionados

Gratis con una prueba de 30 días de Scribd

Ver todo
  • Sé el primero en recomendar esto

Facing up social activity recognition using smartphone sensors

  1. 1. 1/35 UCAmI 2015 DeustoTech-Deusto Institute of Technology, University of Deusto http://www.morelab.deusto.es December 2, 2015 Facing up social activity recognition using smartphone sensors Pablo Curiel,Ivan Pretel, AnaB. Lago
  2. 2. 2/35 UCAmI 2015 Outline Introduction System Design Evaluation Conclusion
  3. 3. 3/35 UCAmI 2015 Introduction System Design Evaluation Conclusion
  4. 4. 4/35 UCAmI 2015 Introduction Introduction AT HOME . . .
  5. 5. 5/35 UCAmI 2015 Introduction . . .
  6. 6. 6/35 UCAmI 2015 Introduction ► Location-based services ► Foursquare, Twitter, Google Keep,… ► Low-level inference ► Physical activity: walking, running, cycling,… ► High-level inference ► High-level user activities: cooking, reading novel,… ► Environments or surroundings: home, bar, public transport . . .
  7. 7. 7/35 UCAmI 2015 Introduction ► Socialization as a high-level useractivity ► based on environmentrecognition ► provides “social reminders” . . . @ @ @
  8. 8. 8/35 UCAmI 2015 Introduction System Design Evaluation Conclusion
  9. 9. 9/35 UCAmI 2015 System Design: Context capture ► Environments ► Bar, café, sports bar, disco and restaurant ► Characteristics ► Noisy places ► Stationary positions ► Artificially lighted places
  10. 10. 10/35 UCAmI 2015 System Design: Context capture ► Captured Data ► Audio ► RMSpoweranddBs ► Microphone ► Acceleration ► 3-axialacceleration ► Acceleration,gyroscopeand geomagneticsensors ► Ambient luminosity ► Luxes ► Luminositysensor. ► Screen status ► Used devices ► LG Nexus 4 (100 hours) ► HTC Desire 816 (20 hours)
  11. 11. 11/35 UCAmI 2015 Data processing ► 3 steps ► 1. Data fusion ► 2. Data transformation ► 3. Feature extraction 1. DataFusion 2. Data transformation 3. Featureextraction
  12. 12. 12/35 UCAmI 2015 Data processing ► 1. Data fusion ► Timestamps ► Gathering halts ► Sample rate ► 50Hz,20Hz,10Hz,5Hz, 2Hzand1Hz 1. Data Fusion 2. Data transformation 3. Featureextraction RMS,dBs Acceleration,gyroscope, compass Luminosity,screen
  13. 13. 13/35 UCAmI 2015 Data processing ► 1. Data fusion ► 2. Data transformation ► Raw to processed characteristics 1. DataFusion 2. Data transformation 3. Featureextraction RMS,dBs Acceleration,gyroscope, compass Luminosity,screen LPF(RMS), LPF(dBs) Lineal-acc.,earth-acc. log(lum),fixedLum, log(fixedLum) +
  14. 14. 14/35 UCAmI 2015 Data processing ► 1. Data fusion ► 2. Data transformation ► 3. Featureextraction 1. DataFusion 2. Data transformation 3. Feature extraction RMS,dBs Acceleration,gyroscope, compass Luminosity,screen Max,min,mean,median,standard deviation LPF(RMS), LPF(dBs) Lineal-acc.,earth-acc. log(lum),fixedLum, log(fixedLum) +
  15. 15. 15/35 UCAmI 2015 Introduction System Design Evaluation Conclusion
  16. 16. 16/35 UCAmI 2015 Evaluation ► Training Set ► 10x5-fold cross validation ► Nexus 4 70h ► Test Set ► Nexus 4 30h ► HTC Desire 20h ► Classifiers ► Random forest ► Support vector machine (SVM) - Gaussian radial basis function kernel ► k-Nearest Neighbours (k-NN) ► Naive Bayes classifier ► Parameters ► The best features to use ► The most suitable window sizes ► Classifier comparison ► Sensor sampling rate comparison ► Performance ► Recall ► Specificity ► AUC ► Accuracy What is thebest combination of parametersto detect bar-like environments?
  17. 17. 17/35 UCAmI 2015 Evaluation ► Feature comparison ► Acceleration features comparison ► Vectornorm->Randomforest,SVMandk-NNleadstobetterresults ► Typesofacceleration – Linear=“Earth-acceleration” – Baseacc.betterthanLinear&“Earth-acceleration”(RandomforestandSVM,4%) ► Audio features comparison ► dBbetter thanRMS: – SVM(4% - 9%), k-NN(6%-15%),Naive Bayes(2% -8%) ► Filteredbetter thanUnfiltered(k-NNis theonly exception) ► Luminosity features comparison ► Combinationoflog transformationandthe fixedversion is thebestchoice – RandomForest (1%), SVM(3%), k-NN(-),NaiveBayes(11%)
  18. 18. 18/35 UCAmI 2015 Evaluation ► Contribution of eachsensor ► Training with the best performing feature of each sensor ► concludedin theprevious comparisons ► Results ► Audioexclusion declines from15%to20% ► Accelerationexclusion declines from1%to10% ► Luminosityonlyuseful forSVMandNaiveBayes
  19. 19. 19/35 UCAmI 2015 Evaluation ► Window sizecomparison ► Common pattern: The smaller the window size, the worse the results ► Random Forest ► 240seconds ► 120or90 -> 2%performancelost ► SVM ► 120seconds ► 60seconds-> 2%performancelost ► k-NN classifier ► 180seconds ► 60seconds-> lessthan2%performancelost ► Naive Bayes ► 240seconds ► 120seconds -> 2% performancelost
  20. 20. 20/35 UCAmI 2015 Evaluation ► Sample ratecomparison ► Smaller window sizes suffer more than biggerones when this parameter is decreased
  21. 21. 21/35 UCAmI 2015 Evaluation ► Classifier comparison ► Thebest is SVM ► + recall ► + AUC ► + accuracy ► Random Forest ► +specificity
  22. 22. 22/35 UCAmI 2015 Evaluation ► The best performing configuration ► SVM ► Features ► Linearacceleration ► FiltereddBs ► Log-transformed fixedluminosity ► Capable of generalizing to new environments ► User anddevice dependencies Bar-like TP FN Other FP TN Bar-like TP FN Other FP TN ► Results
  23. 23. 23/35 UCAmI 2015 Introduction System Design Evaluation Conclusion
  24. 24. 24/35 UCAmI 2015 Conclusion ► Findings ► The preliminary results obtained seem promising regarding the recognition of new locations for the same user. ► However, generalization to new users seems to be more troublesome. ► Future work ► New data collection campaign which involves more users in order to better study these aspects ► Study what is the most descriptive value for eachfeature (mean, median, standard deviation, minimum and maximum) ► Searchfor better recognition results with separate classes for each type of bar-like environment, as this could potentially enable to better capture the particular characteristics each of these environments has.
  25. 25. 25/35 UCAmI 2015 Thank you for your attention
  26. 26. 26/35 UCAmI 2015 DeustoTech-Deusto Institute of Technology, University of Deusto http://www.morelab.deusto.es Facing up social activity recognition using smartphone sensors Pablo Curiel,IvanPretel, AnaB. Lago {pcuriel@deusto.es} {ivan.pretel@deusto.es} {anabelen.lago@deusto.es}
  27. 27. 27/35 UCAmI 2015 All rights of images are reservedby the original owners*,the rest of the content is licensed under a Creative Commons by-sa 3.0 license. * • http://mami.uclm.es/ucami-iwaal-amihealth-2015 • https://flic.kr/p/enRrs9 • https://www.iconfinder.com/yudha_ap • https://www.iconfinder.com/iconsets/stash • https://www.iconfinder.com/DemSt • https://www.iconfinder.com/paomedia • https://flic.kr/p/eD7GR • https://flic.kr/p/8G1yiU

In the last years context awareness has become a reality in real-world applications. However, building comprehensive context recognition systems which are able to recognize both low and high-level context information remains a challenge. In this paper, we discuss environment recognition as a means to address the issue of recognizing a high-level user context, social activity. In many countries, bars, pubs and similar establishments are one of the main places where social engagement takes place, and thus we propose recognizing these types of environments using data collected from mobile device sensors as a proxy for inferring social activity. For this purpose, we discuss the common defining characteristics of these establishments and the sensors we will use to recognize them. After that, we introduce the design of our system. Finally, we present the preliminary evaluation carried out to assess the validity of our proposal.

Vistas

Total de vistas

786

En Slideshare

0

De embebidos

0

Número de embebidos

106

Acciones

Descargas

6

Compartidos

0

Comentarios

0

Me gusta

0

×