Einstein International Journal Organization(EIJO)

ABSTRACT 

Recommendation systems have seen significant evolution in the field of knowledge engineering. Existing recommendation systems based their models on collaborative filtering approaches that make them simple to implement. However, performance of most of the existing collaborative filtering-based recommendation system suffers due to the challenges, such as: (a) cold start, (b) data sparseness, and (c) scalability. Moreover, recommendation problem is often characterized by the presence of many conflicting objectives or decision variables, such as users’ preferences and venue closeness. Here proposed Mobi Context, a hybrid cloud-based Bi-Objective Recommendation Framework (BORF) for mobile social networks. To address the issues pertaining to cold start and data sparseness, the BORF performs data pre-processing by using the Hub-Average (HA) inference model. Moreover, the Weighted Sum Approach (WSA) is implemented for scalar optimization and an evolutionary algorithm (NSGA-II) is applied for vector optimization to provide optimal suggestions to the users about a venue. Comprehensive experiments on a large-scale real dataset confirm the accuracy of the proposed recommendation framework.

Keywords: Cloud, System, Data, Mobi, NGSA, HA, WSA, BORF.

[1]. A.  Majid,  L.  Chen,  G.  Chen,  H.  Turab,  I.  Hussain,  and  J. Woodward,  “A  Context-aware  Personalized  Travel Recommendation  System  based  on  Geo-tagged  Social  Media Data  Mining,”  International  Journal  of  Geographical  Information Science, pp. 662-684, 2013.

[2]. M.  Ye,  P.  Yin,  and  W.  Lee,  “Location  recommendation  for location-based  social  networks,”  In  Proceedings  of  the  18th SIGSPATIAL  International  Conference  on  Advances  in  Geographic Information Systems, ACM, pp. 458-461, 2010.

[3]. Y. Zheng, L. Zhang, X. Xie, and W.Y. Ma, “Mining interesting locations  and  travel  sequences  from  gps  trajectories,”  In Proceedings of the 18th international conference on World wide web, ACM, pp. 791-800, 2009. IEEE Transactions on Cloud Computing, (Volume:PP , Issue: 99 ),17 June 2015.

[4]. C.  Chow,  J.  Bao,  and  M.  Mokbel,  “Towards  Location-Based Social  Networking  Services,”  In  Proceedings  of  the  2nd  ACM SIGSPATIAL  International  Workshop  on  Location  Based  Social Networks, ACM, pp. 31-38, 2010.

[5]. P. G. Campos, F. Díez, I. Cantador, “Time-aware Recommender Systems:  A  Comprehensive  Survey  and  Analysis  of  Existing Evaluation  Protocols,”  User  Modeling  and  User-Adapted Interaction, vol. 24, no.1-2, pp. 67-119, 2014.

[6]. A. Noulas, S. Scellato, N. Lathia,  and C. Mascolo, “A Random Walk  around  the  City:  New  Venue  Recommendation  in Location-Based Social Networks,” In  Proceedings of International Conference on Social Computing (SocialCom), pp.144-153, 2012.

[7].Y.  Doytsher,  B.  Galon,  and  Y.  Kanza,  “Storing  Routes  in Sociospatial  Networks  and  Supporting  Social-based  Route Recommendation,”  In  Proceedings  of  3rd  ACM  SIGSPATIAL International  Workshop  on  Location-Based  Social  Networks,  ACM, pp. 49-56, 2011.

[8]. S. Seema, and S. Alex, “Dynamic Bus Arrival Time Prediction, using  GPS  Data,”  In  Proceedings  of  the  Nat.  ConferenceTechnological Trends (NCTT), pp. 193-197, 2010.

[9]. B.  Chandra,  S.  Bhaskar,  “Patterned  Growth  Algorithm  using Hub-Averaging without Pre-assigned Weights,” In Proceeding of IEEE  International  Conference  on  Systems,  man,  and  Cybernetics(SMC), pp.3518-3523, 2010.

[10]. B.  Hidasi,  and  D.  Tikk,  “Initializing  Matrix  Factorization Methods  on  Implicit  Feedback  Database,”  Journal  of  Universal Computer Science, vol. 19, no. 12, pp. 1835-1853, 2013.

[11]. C.  Chitra and  P.  Subbaraj,  “A  Non-dominated  Sorting Genetic Algorithm  for  Shortest  Path  Routing  Problem  in  Computer Networks,”  Expert  Systems  with  Applications,  vol. 39, no. 1,  pp. 1518-1525, 2012.

[12]. Y.  Wang,  S.  Wang,  N.  Stash,  L.  Aroyo,  and  G.  Schreiber, “Enhancing  Content-Based  Recommendation  with  the  Task Model  of  Classification,”  In  Proceedings  of   the  Knowledge  and Management, pp. 431-440, 2010.

[13]. J.  Bobadilla,  F.  Ortega,  A.  Hernando,  A.  Gutiérrez, “Recommender Systems Survey,” Knowledge-Based Systems, vol.46, pp. 109-132, 2013.

[14]. J. Bao, Y. Zheng, M.F. Mokbel, “Location-based and  Preference Aware  Recommendation  using  Sparse  Geo-Social  Networking Data,” In  Proceeding of  20th International Conference on Advances in Geographic Information Systems, ACM New York, pp.199-208, 2012.

[15]. M.  Ribeiro,  A.  Lacerda,  A.  Veloso,  and  N.  Ziviani,  “ParetoEfficient  Hybridization  for  Multi-objective  Recommender Systems,” In  Proceeding of  6th ACM Conference on Recommender Systems, pp. 19-26, 2012.

[16]. K. Deb, A. Pratap, S. Agarwal, and T. Meyarivan, “A Fast and Elitist  Multi-objective  Genetic  Algorithm:  NSGA-II,”  IEEE Transaction on Evolutionary Computations, vol. 6, no. 2, pp. 182-197, 2002.

[17]. H.  Nasiri,  M.  Maghfoori,  “Multiobjective  Weighted  Sum Approach  Model  reduction  by  Routh-Pade  approximation using Harmony Search,” Turkish Journal of Electrical Engineering and Computer Science, vol. 21, no. 2, pp. 2283-2293, 2013.

[18]. J. Abimbola, “A  Non-linear Weights Selection in Weighted Sum Information, vol. 27, no. 3, 2012.

[19]. Paired t test. Wiley Encyclopedia of Clinical Trials, 2008.