Cloud-based Activity-aaService cyber-physical framework for human activity monitoring in mobility

Abstract This paper proposes Activity as a Service (Activity-aaService), a full-fledged cyber–physical framework to support community, on-line and off-line human activity recognition and monitoring in mobility. Activity-aaService is able to address the current lack of Cloud-Assisted Body Area Networks platforms and applications supporting monitoring and analysis of human activity for single individuals and communities. Activity-aaService is built atop the BodyCloud platform so enabling efficient BSN-based sensor data collection and local processing (Body-side), high performance computing of collected sensor data and data storing on the Cloud (Cloud-side), workflow-based programming of data analysis (Analyst-side), and advanced visualization of results (Viewer-side). Specifically, it provides specific, powerful and flexible programming abstractions for the rapid prototyping of efficient human activity-oriented applications. The effectiveness of the proposed framework has been demonstrated through the development of several prototypes related to physical activity monitoring, step counting, physical energy estimation, automatic fall detection, and smart wheelchair support. Finally, performance evaluation of the proposed framework at the Body-side of the activity classification has been carried out by analyzing processing load, data transmission time, CPU usage, memory footprint, and battery consumption using four heterogeneous mobile devices representing low, medium and high performance mobile platforms.

[1]  Davide Anguita,et al.  Human Activity Recognition on Smartphones Using a Multiclass Hardware-Friendly Support Vector Machine , 2012, IWAAL.

[2]  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).

[3]  Giancarlo Fortino,et al.  People-Centric Service for mHealth of Wheelchair Users in Smart Cities , 2014, Internet of Things Based on Smart Objects, Technology, Middleware and Applications.

[4]  Giancarlo Fortino,et al.  BodyCloud: A SaaS approach for community Body Sensor Networks , 2014, Future Gener. Comput. Syst..

[5]  Michael L. Littman,et al.  Activity Recognition from Accelerometer Data , 2005, AAAI.

[6]  Yacine Challal,et al.  Secure and Scalable Cloud-Based Architecture for e-Health Wireless Sensor Networks , 2012, 2012 21st International Conference on Computer Communications and Networks (ICCCN).

[7]  M. Brian Blake,et al.  Workshop Final Report , 2007, WETICE.

[8]  Michael B. Jones,et al.  The OAuth 2.0 Authorization Framework: Bearer Token Usage , 2012, RFC.

[9]  Peter E. Hart,et al.  Nearest neighbor pattern classification , 1967, IEEE Trans. Inf. Theory.

[10]  Daren C. Brabham,et al.  Crowdsourcing applications for public health. , 2014, American journal of preventive medicine.

[11]  David W. Mizell,et al.  Using gravity to estimate accelerometer orientation , 2003, Seventh IEEE International Symposium on Wearable Computers, 2003. Proceedings..

[12]  Giancarlo Fortino,et al.  Fall-MobileGuard: a Smart Real-Time Fall Detection System , 2015, BODYNETS.

[13]  Rajkumar Buyya,et al.  An autonomic cloud environment for hosting ECG data analysis services , 2012, Future Gener. Comput. Syst..

[14]  Giancarlo Fortino,et al.  A framework for collaborative computing and multi-sensor data fusion in body sensor networks , 2015, Inf. Fusion.

[15]  Josef Kittler,et al.  Floating search methods in feature selection , 1994, Pattern Recognit. Lett..

[16]  Giancarlo Fortino,et al.  Using Cloud-assisted Body Area Networks to Track People Physical Activity in Mobility , 2015, BODYNETS.

[17]  Giancarlo Fortino,et al.  Activity recognition and monitoring for smart wheelchair users , 2016, 2016 IEEE 20th International Conference on Computer Supported Cooperative Work in Design (CSCWD).

[18]  Kanav Kahol,et al.  Integrative Gaming: A Framework for Sustainable Game-Based Diabetes Management , 2011, Journal of diabetes science and technology.

[19]  Peter Brezany,et al.  Stream Management within the CloudMiner , 2011, ICA3PP.

[20]  Dick Hardt,et al.  The OAuth 2.0 Authorization Framework , 2012, RFC.

[21]  M. Sun,et al.  Improving energy expenditure estimation by using a triaxial accelerometer. , 1997, Journal of applied physiology.

[22]  Luca Benini,et al.  Activity Recognition from On-Body Sensors: Accuracy-Power Trade-Off by Dynamic Sensor Selection , 2008, EWSN.

[23]  Miguel A. Labrador,et al.  A Survey on Human Activity Recognition using Wearable Sensors , 2013, IEEE Communications Surveys & Tutorials.

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

[25]  Giancarlo Fortino,et al.  Agent-oriented smart objects development , 2012, Proceedings of the 2012 IEEE 16th International Conference on Computer Supported Cooperative Work in Design (CSCWD).

[26]  Fabio Bellifemine,et al.  SPINE: a domain‐specific framework for rapid prototyping of WBSN applications , 2011, Softw. Pract. Exp..

[27]  Hassan Ghasemzadeh,et al.  Power-Aware Activity Monitoring Using Distributed Wearable Sensors , 2014, IEEE Transactions on Human-Machine Systems.

[28]  Mohammad Mozumdar,et al.  BioMeSensi: a wearable multi-sensing platform for bio-medical applications , 2015, IPSN '15.

[29]  Athanasios V. Vasilakos,et al.  Cloud-assisted body area networks: state-of-the-art and future challenges , 2014, Wirel. Networks.

[30]  Jesse Hoey,et al.  Sensor-Based Activity Recognition , 2012, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[31]  Giancarlo Fortino,et al.  Enabling Multiple BSN Applications Using the SPINE Framework , 2010, 2010 International Conference on Body Sensor Networks.

[32]  Athanasios V. Vasilakos,et al.  Body Area Networks: A Survey , 2010, Mob. Networks Appl..

[33]  Muhammad Shoaib.  Human Activity Recognition Using Heterogeneous Sensors , 2013, UbiComp 2013.

[34]  Roozbeh Jafari,et al.  Enabling Effective Programming and Flexible Management of Efficient Body Sensor Network Applications , 2013, IEEE Transactions on Human-Machine Systems.

[35]  Lei Wu,et al.  A Fatigue Detect System Based on Activity Recognition , 2014, IDCS.