Using barometric pressure data to recognize vertical displacement activities on smartphones

A method for detecting major vertical displacements in human activities is proposed.Prediction is based on barometers available on smartphones and inference models.Decision trees are a good choice for their high accuracy and low energy consumption.Barometers offer high accuracy, energy efficiency and independence from position. We introduce a novel, efficient methodology for the automatic recognition of major vertical displacements in human activities. It is based exclusively on barometric pressure measured by sensors commonly available on smartphones and tablets. We evaluate various algorithms to distinguish dynamic activities, identifying four different categories: standing/walking on the same floor, climbing stairs, riding an elevator and riding a cable-car. Activities are classified using standard deviation and slope of barometric pressure. We leverage three different inference models to predict the action performed by a user, namely: Bayesian networks, decision trees, and recurrent neural networks. We find that the best results are achieved with a recurrent neural network (reaching an overall error rate of less than 1%). We also show that decision tree classifiers can achieve good accuracy and offer a better trade-off between computational overhead and energy consumption; therefore, they are good candidates for smartphone implementations. As a proof of concept, we integrate the decision tree classifier in an App that infers user activity and measures elevation differences. Test results with various users show an average recognition accuracy rate of about 95%. We further show the power consumption of running barometric pressure measurements and analyse the correlation of pressure with environmental factors. Finally, we compare our approach to other standard methodologies for activity detection based on accelerometer and/or on GPS data. Our results show that our technique achieves similar accuracy while offering superior energy efficiency, independence from the sensor location, and immunity to environmental factors (e.g., weather conditions, air handlers).

[1]  Y.-K. Lee,et al.  Human Activity Recognition via an Accelerometer-Enabled-Smartphone Using Kernel Discriminant Analysis , 2010, 2010 5th International Conference on Future Information Technology.

[2]  Kaoru Sezaki,et al.  Beyond horizontal location context: measuring elevation using smartphone's barometer , 2014, UbiComp Adjunct.

[3]  Jie Liu,et al.  LittleRock: Enabling Energy-Efficient Continuous Sensing on Mobile Phones , 2011, IEEE Pervasive Computing.

[4]  Daniele Puccinelli,et al.  The human element as the key enabler of pervasiveness , 2011, 2011 The 10th IFIP Annual Mediterranean Ad Hoc Networking Workshop.

[5]  Gaetano Borriello,et al.  A Practical Approach to Recognizing Physical Activities , 2006, Pervasive.

[6]  Henry A. Kautz,et al.  Location-Based Activity Recognition using Relational Markov Networks , 2005, IJCAI.

[7]  Rita Cucchiara,et al.  A machine learning approach for human posture detection in domotics applications , 2003, 12th International Conference on Image Analysis and Processing, 2003.Proceedings..

[8]  C. N. Scanaill,et al.  A Review of Approaches to Mobility Telemonitoring of the Elderly in Their Living Environment , 2006, Annals of Biomedical Engineering.

[9]  Tim Esemann,et al.  Precise indoor altitude estimation based on differential barometric sensing for wireless medical applications , 2013, 2013 IEEE International Conference on Body Sensor Networks.

[10]  Daniele Puccinelli,et al.  Detecting energy leaks in Android app with POEM , 2015, 2015 IEEE International Conference on Pervasive Computing and Communication Workshops (PerCom Workshops).

[11]  Sabri Boughorbel,et al.  Child-activity recognition from multi-sensor data , 2010, MB '10.

[12]  Mohamed F. Younis,et al.  From MANET to people-centric networking: Milestones and open research challenges , 2015, Comput. Commun..

[13]  Sabrina Gaito,et al.  How many places around you , 2013 .

[14]  Salvatore Vanini,et al.  Adaptive context-agnostic floor transition detection on smart mobile devices , 2013, 2013 IEEE International Conference on Pervasive Computing and Communications Workshops (PERCOM Workshops).

[16]  Kristof Van Laerhoven,et al.  What shall we teach our pants? , 2000, Digest of Papers. Fourth International Symposium on Wearable Computers.

[17]  O. Mayora-Ibarra,et al.  Smartphone-centred wearable sensors network for monitoring patients with bipolar disorder , 2011, 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[18]  Ling Bao,et al.  Activity Recognition from User-Annotated Acceleration Data , 2004, Pervasive.

[19]  Gian Paolo Rossi,et al.  On the key features in human mobility: Relevance, time and distance , 2014, 2014 IEEE International Conference on Pervasive Computing and Communication Workshops (PERCOM WORKSHOPS).

[20]  Xingshe Zhou,et al.  Facilitating medication adherence in elderly care using ubiquitous sensors and mobile social networks , 2015, Comput. Commun..

[21]  Jürgen Schmidhuber,et al.  An Application of Recurrent Neural Networks to Discriminative Keyword Spotting , 2007, ICANN.

[22]  Christian Igel,et al.  Improving the Rprop Learning Algorithm , 2000 .

[23]  Gary M. Weiss,et al.  Activity recognition using cell phone accelerometers , 2011, SKDD.

[24]  Aboelmagd Noureldin,et al.  Using portable device sensors to recognize height changing modes of motion , 2014, 2014 IEEE International Instrumentation and Measurement Technology Conference (I2MTC) Proceedings.

[25]  Lin Sun,et al.  Activity Recognition on an Accelerometer Embedded Mobile Phone with Varying Positions and Orientations , 2010, UIC.

[26]  Adil Mehmood Khan,et al.  Activity Recognition on Smartphones via Sensor-Fusion and KDA-Based SVMs , 2014, Int. J. Distributed Sens. Networks.

[27]  Edith C. H. Ngai,et al.  Energy-efficient automatic location-triggered applications on smartphones , 2014, Comput. Commun..

[28]  Amir F. Atiya,et al.  New results on recurrent network training: unifying the algorithms and accelerating convergence , 2000, IEEE Trans. Neural Networks Learn. Syst..

[29]  Fabrice Theoleyre,et al.  Networking and communications for smart cities special issue editorial , 2015, Comput. Commun..

[30]  Daniele Puccinelli,et al.  When sensing goes pervasive , 2015, Pervasive Mob. Comput..

[31]  Thomas Gallagher,et al.  Using barometers to determine the height for indoor positioning , 2013, International Conference on Indoor Positioning and Indoor Navigation.

[32]  Jürgen Schmidhuber,et al.  LSTM recurrent networks learn simple context-free and context-sensitive languages , 2001, IEEE Trans. Neural Networks.

[33]  Young-Joo Suh,et al.  GPS tethering for energy conservation1 , 2015, 2015 IEEE Wireless Communications and Networking Conference (WCNC).

[34]  Guang-Zhong Yang,et al.  Sensor Placement for Activity Detection Using Wearable Accelerometers , 2010, 2010 International Conference on Body Sensor Networks.

[35]  Daniel P. Siewiorek,et al.  Activity recognition and monitoring using multiple sensors on different body positions , 2006, International Workshop on Wearable and Implantable Body Sensor Networks (BSN'06).

[36]  Soundararajan Srinivasan,et al.  Multisensor Fusion in Smartphones for Lifestyle Monitoring , 2010, 2010 International Conference on Body Sensor Networks.

[37]  Friedrich Foerster,et al.  Detection of posture and motion by accelerometry : a validation study in ambulatory monitoring , 1999 .

[38]  Panayiotis Kotzanikolaou,et al.  Lightweight private proximity testing for geospatial social networks , 2016, Comput. Commun..

[39]  Silvia Giordano,et al.  Gesture-based soft authentication , 2015, 2015 IEEE 11th International Conference on Wireless and Mobile Computing, Networking and Communications (WiMob).

[40]  Nobuhiko Nishio,et al.  User activity recognition method based on atmospheric pressure sensing , 2014, UbiComp Adjunct.

[41]  T. Munich,et al.  Offline Handwriting Recognition with Multidimensional Recurrent Neural Networks , 2008, NIPS.

[42]  Gerhard Tröster,et al.  Recognizing Upper Body Postures using Textile Strain Sensors , 2007, 2007 11th IEEE International Symposium on Wearable Computers.

[43]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[44]  Mun Choon Chan,et al.  Using mobile phone barometer for low-power transportation context detection , 2014, SenSys.

[45]  Stefan Schmid,et al.  An LED-to-LED Visible Light Communication system with software-based synchronization , 2012, 2012 IEEE Globecom Workshops.

[46]  Emiliano Miluzzo,et al.  Tapping into the Vibe of the city using VibN, a continuous sensing application for smartphones , 2011, SCI '11.

[47]  Joseph Lstiburek,et al.  Air Pressure and Building Envelopes , 2002 .

[48]  Henry A. Kautz,et al.  Hierarchical Conditional Random Fields for GPS-Based Activity Recognition , 2005, ISRR.

[49]  Sethuraman Panchanathan,et al.  Analysis of low resolution accelerometer data for continuous human activity recognition , 2008, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing.

[50]  Hassan Artail,et al.  Integrating pressure and accelerometer sensing for improved activity recognition on smartphones , 2013, 2013 Third International Conference on Communications and Information Technology (ICCIT).

[51]  Paul Lukowicz,et al.  Active Capacitive Sensing: Exploring a New Wearable Sensing Modality for Activity Recognition , 2010, Pervasive.

[52]  Andrew McCallum,et al.  Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data , 2001, ICML.