Advertisement

The Journal of Supercomputing

, Volume 72, Issue 12, pp 4810–4825 | Cite as

User-centric product recommendation on heterogeneous IoT device platform

  • Sang-Min Park
  • Young-Gab Kim
  • Doo-Kwon Baik
Article

Abstract

Interoperability and functional redundancy between devices are important issues on IoT device group management because an IoT device group consists of diverse devices on heterogeneous platform. However, previous approaches for IoT device management are conducted from the perspective of the manufacture such as usage-based design and pre-sales analytics. In addition, product-based device management has a limitation in dealing with multifunctional smart devices and feature-reconfigurable devices on heterogeneous IoT environment. In this paper, we propose a user-centric approach for proactive product recommendation on heterogeneous IoT device platform. For the user-centric device management on heterogeneous platform, user and user group device profiles are integrated with feature-level device profiles which are owned by user and user group, respectively. The user’s application usage of feature level is visualized to the comparison through a circular-coordinate diagram. For the recommendation of new supplement and substitute devices, the device scores are calculated with the interoperability score, redundancy score, and superior score.

Keywords

Device recommendation Heterogeneous platform Device group profile Application usage analysis User agent profile 

References

  1. 1.
    Manyika J, Chui M, Bisson P, Woetzel J, Dobbs R (2015) The internet of things: mapping the value beyond the hype. McKinsey & Company, London. http://www.mckinsey.com/
  2. 2.
    Zhong N, Ma JH, Huang RH, Liu JM, Yao YY, Zhang YX, Chen JH (2013) Research challenges and perspectives on Wisdom Web of Things (W2T). J Supercomput 64(3):862–882CrossRefGoogle Scholar
  3. 3.
    Saleemi MM, Lilius J (2014) Exploiting smart spaces for interactive TV applications development. J Supercomput 70(3):1200–1217CrossRefGoogle Scholar
  4. 4.
  5. 5.
  6. 6.
    Hsu IC (2013) Personalized web feeds based on profile technologies. Inf Syst Front 15(3):465–479CrossRefGoogle Scholar
  7. 7.
    Gibert K, Aïda V, Batet M (2013) Introducing semantic variables in mixed distance measures: Impact on hierarchical clustering. Knowl Inf Syst 40:1–35Google Scholar
  8. 8.
    Laborie S, Khallouki H, Roose P (2012) Bridging the gap between quantitative and qualitative constraints in profiles. 2012 Seventh International Workshop on semantic and social media adaptation and personalization (SMAP), IEEE, Luxembourg, pp 121–125Google Scholar
  9. 9.
    Bandara A et al (2014) An ontological framework for semantic description of devices. In: Proceedings of the Semantic WebGoogle Scholar
  10. 10.
    Skillen KL et al (2012) Ontological user profile modeling for context-aware application personalization. In: Bravo J, López-de-Ipiña D, Moya F (eds) Ubiquitous computing and ambient intelligence. Springer Berlin, Heidelberg, pp 261–268Google Scholar
  11. 11.
    Rosaci D, Sarné GML (2012) A multi-agent recommender system for supporting device adaptivity in e-commerce. J Intell Inf Syst 38(2):393–418CrossRefGoogle Scholar
  12. 12.
    Rosaci D, Sarné GML (2013) Recommending multimedia web services in a multi-device environment. Inf Syst 38(2):198–212CrossRefGoogle Scholar
  13. 13.
    Vrdoljak L et al (2009) The AMiGO-Mob: agent-based middleware for group-oriented mobile service provisioning. 10th International Conference on telecommunications, 2009. ConTEL 2009, IEEE, Zagreb, Croatia, pp 97–104Google Scholar
  14. 14.
    de Reuver M, Bouwman H (2012) Smartphone measurement: do people use mobile applications as they say they do?. International conference of mobile businessGoogle Scholar
  15. 15.
    Bolchini C et al (2011) Context modeling and context awareness: steps forward in the context-ADDICT project. IEEE Data Eng Bull 34(2):47–54Google Scholar
  16. 16.
    Zhang X et al (2013) Profile-based semantic retrieval for engineering domain knowledge. Neurocomputing 116:382–391CrossRefGoogle Scholar
  17. 17.
    Tennekes M, de Jonge E (2014) Tree colors: color schemes for tree-structured data. Vis Comput Graphics IEEE Trans 20(12):2072–2081CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2016

Authors and Affiliations

  1. 1.Department of Computer Science and EngineeringKorea UniversitySeoulKorea
  2. 2.Department of Computer and Information SecuritySejong UniversitySeoulKorea

Personalised recommendations