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

被引:74
作者
Gravina, Raffaele [1 ]
Ma, Congcong [3 ]
Pace, Pasquale [1 ]
Aloi, Gianluca [1 ]
Russo, Wilma [1 ]
Li, Wenfeng [3 ]
Fortino, Giancarlo [1 ,2 ]
机构
[1] Univ Calabria, DIMES, Via P Bucci, I-87036 Arcavacata Di Rende, CS, Italy
[2] CNR, Natl Res Council Italy, Inst High Performance Comp & Networking ICAR, Via P Bucci 7-11C, I-87036 Arcavacata Di Rende, CS, Italy
[3] Wuhan Univ Technol, Sch Logist Engn, Wuhan 430070, Peoples R China
来源
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE | 2017年 / 75卷
关键词
Cloud computing; Activity monitoring; Wearable sensors; Programming framework; Software as a service; ACTIVITY RECOGNITION;
D O I
10.1016/j.future.2016.09.006
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
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. (C) 2016 Elsevier B.V. All rights reserved.
引用
收藏
页码:158 / 171
页数:14
相关论文
共 37 条
[1]   BioMeSensi: a Wearable Multi-Sensing Platform for Bio-Medical Applications [J].
Ahmari, Sami ;
Ameri, Alireza ;
Padmanabhan, Sivasankar ;
Parameshwaran, Keerthi ;
Ragheb, Kareem ;
Mozumdar, Mohammad .
IPSN'15: PROCEEDINGS OF THE 14TH INTERNATIONAL SYMPOSIUM ON INFORMATION PROCESSING IN SENSOR NETWORKS, 2015, :372-373
[2]  
Anguita D., 2012, 4 INT C AMB ASS LIV
[3]  
[Anonymous], 2016, STREAM 2015 WORKSH A
[4]  
[Anonymous], 1996, Physical activity and health: A report of the Surgeon General
[5]  
[Anonymous], 2012, 6749 RFC
[6]   Activity recognition from user-annotated acceleration data [J].
Bao, L ;
Intille, SS .
PERVASIVE COMPUTING, PROCEEDINGS, 2004, 3001 :1-17
[7]   SPINE: A domain-specific framework for rapid prototyping of WBSN applications [J].
Bellifemine, Fabio ;
Fortino, Giancarlo ;
Giannantonio, Roberta ;
Gravina, Raffaele ;
Guerrieri, Antonio ;
Sgroi, Marco .
SOFTWARE-PRACTICE & EXPERIENCE, 2011, 41 (03) :237-265
[8]   Crowdsourcing Applications for Public Health [J].
Brabham, Daren C. ;
Ribisl, Kurt M. ;
Kirchner, Thomas R. ;
Bernhardt, Jay M. .
AMERICAN JOURNAL OF PREVENTIVE MEDICINE, 2014, 46 (02) :179-187
[9]   Improving energy expenditure estimation by using a triaxial accelerometer [J].
Chen, KY ;
Sun, M .
JOURNAL OF APPLIED PHYSIOLOGY, 1997, 83 (06) :2112-2122
[10]   Sensor-Based Activity Recognition [J].
Chen, Liming ;
Hoey, Jesse ;
Nugent, Chris D. ;
Cook, Diane J. ;
Yu, Zhiwen .
IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART C-APPLICATIONS AND REVIEWS, 2012, 42 (06) :790-808