Personal and Ubiquitous Computing

, Volume 22, Issue 2, pp 245–257 | Cite as

Social recommendations for personalized fitness assistance

  • Saumil Dharia
  • Magdalini Eirinaki
  • Vijesh Jain
  • Jvalant Patel
  • Iraklis Varlamis
  • Jainikkumar Vora
  • Rizen Yamauchi
Original Article


Wearable technology allows users to monitor their activity and pursue a healthy lifestyle through the use of embedded sensors. Such wearables usually connect to a mobile application that allows them to set their profile and keep track of their goals. However, due to the relatively “high maintenance” of such applications, where a significant amount of user feedback is expected, users who are very busy, or not as self-motivated, stop using them after a while. It has been shown that accountability improves commitment to an exercise routine. In this work, we present the PRO-Fit framework, a personalized fitness assistant aiming at engaging users in fitness activities, incorporating a social element. The PRO-Fit architecture collects information from activity tracking devices and automatically classifies their activity type. Moreover, the framework incorporates a social recommender system. Using collaborative filtering on user profile and activity data, PRO-Fit generates personalized fitness schedules based on their availability and wellbeing goals. We also incorporate the social network community of the application’s users and identify different tie strengths based on the user’s connections and location. The output of the recommendation process is twofold, as both new activities, as well as fitness buddies, are being recommended to each user.


Wearable technology Activity tracking Social recommendation Collaborative filtering Personalized assistant 



This work was partially funded by San Jose State University’s Charles W. Davidson College of Engineering student research mini-grant.


  1. 1.
    Adomavicius G, Tuzhilin A (2005) Toward the next generation of recommender systems: a survey of the state-of-the-art and possible extensions. IEEE Trans Knowl Data Eng 17(6):734–749CrossRefGoogle Scholar
  2. 2.
    Ahtinen A, Isomursu M, Mukhtar M, Mäntyjärvi J, Häkkilä J, Blom J (2009) Designing social features for mobile and ubiquitous wellness applications. In: Proceedings of the 8th international conference on mobile and ubiquitous multimedia. ACM, p 12Google Scholar
  3. 3.
    Anderson I, Maitland J, Sherwood S, Barkhuus L, Chalmers M, Hall M, Brown B, Muller H (2007) Shakra: tracking and sharing daily activity levels with unaugmented mobile phones. Mobile Netw Appl 12 (2–3):185–199CrossRefGoogle Scholar
  4. 4.
    Anjum A, Ilyas M (2013) Activity recognition using smartphone sensors. In: Consumer communications and networking conference (CCNC), 2013 IEEE, pp 914–919Google Scholar
  5. 5.
    Ayu MA, Mantoro T, Matin AFA, Basamh SS (2011) Recognizing user activity based on accelerometer data from a mobile phone. In: 2011 IEEE symposium on computers & informatics (ISCI). IEEE, pp 617–621Google Scholar
  6. 6.
    Bajpai A, Jilla V, Tiwari V N, Venkatesan SM, Narayanan R (2015) Quantifiable fitness tracking using wearable devices. In: 2015 37th annual international conference of the IEEE engineering in medicine and biology society (EMBC). IEEE, pp 1633–1637Google Scholar
  7. 7.
    Bernardes D, Diaby M, Fournier R, FogelmanSoulié F, Viennet E (2015) A social formalism and survey for recommender systems. ACM SIGKDD Explorations Newsletter 16(2):20–37CrossRefGoogle Scholar
  8. 8.
    Centola D (2011) An experimental study of homophily in the adoption of health behavior. Science 334 (6060):1269–1272CrossRefGoogle Scholar
  9. 9.
    Chen Y, Pu P (2014) Healthytogether: exploring social incentives for mobile fitness applications. In: Proceedings of the second international symposium of chinese CHI. ACM, pp 25–34Google Scholar
  10. 10.
    Comstock J (2014) Mobihealthnews: half of mobile health app users are using fitness apps. [online; posted 21-february-2014]
  11. 11.
    Dharia S, Jain V, Patel J, Vora J, Chawla S, Eirinaki M (2016) Pro-Fit: a personalized fitness assistant framework. In: Proceedings of the 28th international conference on software engineering and knowledge engineering (SEKE 2016), Redwood City, CAGoogle Scholar
  12. 12.
    Dharia S, Jain V, Patel J, Vora J, Yamauchi R, Eirinaki M, Varlamis I (2016) Pro-Fit: exercise with friends. In: 2016 IEEE/ACM international conference on advances in social networks analysis and mining (ASONAM). IEEE, pp 1430–1433Google Scholar
  13. 13.
    Dishman R, Buckworth J (1996) Increasing physical activity: a quantitative synthesis. Med Sci Sports Exerc 28(6):706CrossRefGoogle Scholar
  14. 14.
    Feltz DL, Kerr NL, Irwin BC (2011) Buddy up: the Köhler effect applied to health games. J Sport Exerc Psychol 33(4):506–526CrossRefGoogle Scholar
  15. 15.
    Ghose S, Barua JJ (2013) A systematic approach with data mining for analyzing physical activity for an activity recognition system. In: 2013 international conference on advances in electrical engineering (ICAEE). IEEE, pp 415–420Google Scholar
  16. 16.
    Guiry JJ, van de Ven P, Nelson J (2012) Classification techniques for smartphone based activity detection. In: 2012 IEEE 11th international conference on cybernetic intelligent systems (CIS). IEEE, pp 154–158Google Scholar
  17. 17.
    Gupta N, Jilla S (2011) Digital fitness connector: smart wearable system. In: 2011 first international conference on informatics and computational intelligence (ICI). IEEE, pp 118–121Google Scholar
  18. 18.
    Guy I (2015) Social recommender systems. In: Recommender systems handbook. Springer, pp 511–543Google Scholar
  19. 19.
    Halko S, Kientz JA (2010) Personality and persuasive technology: an exploratory study on health-promoting mobile applications. In: International conference on persuasive technology. Springer, pp 150–161Google Scholar
  20. 20.
    Hong J-H, Ramos J, Dey AK (2016) Toward personalized activity recognition systems with a semipopulation approach. IEEE Trans Human-Mach Syst 46(1):101–112CrossRefGoogle Scholar
  21. 21.
    Koren Y, Bell R, Volinsky C (2009) Matrix factorization techniques for recommender systems. Computer 42(8):30–37CrossRefGoogle Scholar
  22. 22.
    Kwapisz JR, Weiss GM, Moore SA (2011) Activity recognition using cell phone accelerometers. ACM SigKDD Explorations Newsletter 12(2):74–82CrossRefGoogle Scholar
  23. 23.
    Lam XN, Vu T, Le TD, Duong AD (2008) Addressing cold-start problem in recommendation systems. In: Proceedings of the 2nd international conference on ubiquitous information management and communication. ACM, pp 208–211Google Scholar
  24. 24.
    Li Y, Zhang Y (2012) Application of data mining techniques in sports training. In: 2012 5th international conference on biomedical engineering and informatics (BMEI). IEEE, pp 954–958Google Scholar
  25. 25.
    Lockhart JW, Weiss GM, Xue JC, Gallagher ST, Grosner AB, Pulickal TT (2011) Design considerations for the wisdm smart phone-based sensor mining architecture. In: Proceedings of the fifth international workshop on knowledge discovery from sensor data. ACM, pp 25–33Google Scholar
  26. 26.
    Messé LA, Hertel G, Kerr NL, Lount Jr RB, Park ES (2002) Knowledge of partner’s ability as a moderator of group motivation gains: an exploration of the Köhler discrepancy effect. J Pers Soc Psychol 82(6):935CrossRefGoogle Scholar
  27. 27.
    Sarwar B, Karypis G, Konstan J, Riedl J (2001) Item-based collaborative filtering recommendation algorithms. In: Proceedings of the 10th international conference on world wide web. ACM, pp 285–295Google Scholar
  28. 28.
    Shani G, Gunawardana A (2011) Evaluating recommendation systems. In: Recommender systems handbook. Springer, pp 257–297Google Scholar
  29. 29.
    Silva PA, Holden K, Nii A (2014) Smartphones, smart seniors, but not-so-smart apps: a heuristic evaluation of fitness apps. In: International conference on augmented cognition. Springer, pp 347–358Google Scholar
  30. 30.
    Tang J, Hu X, Liu H (2013) Social recommendation: a review. Soc Netw Anal Min 3(4):1113–1133CrossRefGoogle Scholar
  31. 31.
    Uddin MT, Uddiny MA (2015) Human activity recognition from wearable sensors using extremely randomized trees. In: 2015 international conference on electrical engineering and information communication technology (ICEEICT). IEEE, pp 1–6Google Scholar
  32. 32.
    Wong FMF, Liu Z, Chiang M (2016) On the efficiency of social recommender networks. IEEE/ACM Trans Networking 24(4):2512–2524CrossRefGoogle Scholar
  33. 33.
    Zhang Y, Chen M, Huang D, Wu D, Li Y (2017) iDoctor: personalized and professionalized medical recommendations based on hybrid matrix factorization. Futur Gener Comput Syst 66:30–35CrossRefGoogle Scholar

Copyright information

© Springer-Verlag London Ltd. 2017

Authors and Affiliations

  • Saumil Dharia
    • 1
  • Magdalini Eirinaki
    • 1
  • Vijesh Jain
    • 1
  • Jvalant Patel
    • 1
  • Iraklis Varlamis
    • 2
  • Jainikkumar Vora
    • 1
  • Rizen Yamauchi
    • 1
  1. 1.Computer Engineering DepartmentSan Jose State UniversitySan JoseUSA
  2. 2.Department of Informatics and TelematicsHarokopio University of AthensAthensGreece

Personalised recommendations