Classification and prediction of routing nodes behavior in MANET using Fuzzy proximity relation and ordering with Bayesian classifier

Mobile Ad-hoc Network (MANET) is a technology that has been developed for real-world applications. The routing information system of MANET can be said to be the back bone for routing process which also represents the characteristics or behaviours of routing nodes. The performance of MANET can be improved if the routing is done based on nodes routing behaviours. Thus, classification and prediction of routing nodes behaviour could lead to proper data analysis and decision making through which an effective routing model can be developed. Association among the routing attributes could help us to predict the behaviour of routing nodes based on the similarity but it is also possible that some of the associations may be hidden due to uncertain behaviour of the routing nodes. Absence of unseen associations may possess some necessary information which should not be ignored when we build an effective routing model. Keeping this in view, we have proposed a prediction model based on the Bayesian approach with fuzzy proximity relation and ordering to predict the link-failure and hidden associations using routing information system of MANET. Since the values in the routing information system are almost identical, we have considered the almost indiscernibility relation to characterize the routing nodes based on fuzzy proximity relation. This result induces the almost equivalence class of routing nodes. On imposing order relation on this equivalence class, we have obtained ordered categorical classes of routing nodes through which we can compute the link-failure possibilities of each routing node. Finally, we use the Bayesian approach to predict the hidden associations of routing attributes which can provide useful information to build an effective routing model for MANET.

[1]  Yiyu Yao,et al.  An Analysis of Quantitative Measures Associated with Rules , 1999, PAKDD.

[2]  Eryk Dutkiewicz,et al.  A review of routing protocols for mobile ad hoc networks , 2004, Ad Hoc Networks.

[3]  D.P. Acharjya,et al.  Rough sets on fuzzy approximation spaces and applications to distributed knowledge systems , 2008, Int. J. Artif. Intell. Soft Comput..

[4]  Mohsen Guizani,et al.  A survey of secure mobile Ad Hoc routing protocols , 2008, IEEE Communications Surveys & Tutorials.

[5]  Andrzej Skowron,et al.  Tolerance Approximation Spaces , 1996, Fundam. Informaticae.

[6]  Yiyu Yao,et al.  Mining Ordering Rules Using Rough Set Theory , 2008 .

[7]  Z. Pawlak.  Granularity of knowledge, indiscernibility and rough sets , 1998, 1998 IEEE International Conference on Fuzzy Systems Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98CH36228).

[8]  Peter J. Haug,et al.  Exploiting missing clinical data in Bayesian network modeling for predicting medical problems , 2008, J. Biomed. Informatics.

[9]  Imrich Chlamtac,et al.  Mobile ad hoc networking: imperatives and challenges , 2003, Ad Hoc Networks.

[10]  Debi Prasanna Acharjya,et al.  Trust evaluation using fuzzy proximity relation with ordering for MANET , 2013, Int. J. Trust. Manag. Comput. Commun..

[11]  Elizabeth M. Belding-Royer,et al.  A review of current routing protocols for ad hoc mobile wireless networks , 1999, IEEE Wirel. Commun..

[12]  Zdzislaw Pawlak,et al.  Information systems theoretical foundations , 1981, Inf. Syst..

[13]  Azzedine Boukerche,et al.  Routing protocols in ad hoc networks: A survey , 2011, Comput. Networks.