Performance Evaluation of Wearable Computing Frameworks

• Michelle Cacais UFC
• Danielo G. Gomes UFC
• Paulo Armando C. Aguilar UFC
• Rossana M. C. Andrade UFC

DOI: https://doi.org/10.5753/wperformance.2017.3354

Resumo

Internet of Things (IoT) aims to connect multiple devices and enable communication on a global scale. In this context, wearable computing turns into one of the most imperative technologies for data capture and transfer. Even though many solutions exist for fast development of wearable applications, it is difficult to know which one is the best for each situation. In this paper, we evaluated the performance of three wearable computing frameworks: SPINE, BNSM and IBM Bluemix. We used performance metrics such as data accuracy, memory footprint and energy consumption in a movement recognition scenario. Results have shown that, among the analyzed frameworks, (i) BNSM is the best one concerning energy-efficiency; (ii) IBM Bluemix is the best one for data accuracy. Both frameworks presented interesting results in terms of memory footprint.

Referências

Bellifemine, F., Fortino, G., Giannantonio, R., Gravina, R., Guerrieri, A., and Sgroi, M. (2011). Spine: a domain-specific framework for rapid prototyping of wbsn applications. Software: Practice and Experience, 41(3):237–265.

Borgia, E., Gomes, D. G., Lagesse, B., Lea, R., and Puccinelli, D. (2016). Special issue on “internet of things: Research challenges and solutions. Computer Communications, 89–90:1 – 4.

Gheith, A., Rajamony, R., Bohrer, P., Agarwal, K., Kistler, M., Eagle, B. W., Hambridge, C., Carter, J., and Kaplinger, T. (2016). Ibm bluemix mobile cloud services. IBM Journal of Research and Development, 60(2-3):7–1.

Hussein, A. I. (2015). Wearable computing: Challenges of implementation and its future. In 12th Learning and Technology Conference, 2015. 35752 2015., pages 14–19. IEEE.

Iyengar, S. (2009). Framework for body sensor networks. Master’s thesis, EECS Department, University of California, Berkeley.