{"references": ["Saida Benlarbi,Khaled El Emam, Nishith Geol (1999), \"Issues in\nValidating Object-Oriented Metrics for Early Risk Prediction\", by Cistel\nTechnology 210 Colonnade Road Suite 204 Nepean, Ontario Canada\nK2E 7L5.", "Lanubile F., Lonigro A., and Visaggio G. (1995) \"Comparing Models\nfor Identifying Fault-Prone Software Components\", Proceedings of\nSeventh International Conference on Software Engineering and\nKnowledge Engineering, June 1995, pp. 12-19.", "Fenton, N. E. and Neil, M. (1999), \"A Critique of Software Defect\nPrediction Models\", Bellini, I. Bruno, P. Nesi, D. Rogai, University of\nFlorence, IEEE Trans. Softw. Engineering, vol. 25, Issue no. 5, pp. 675-\n689.", "Giovanni Denaro (2000), \"Estimating Software Fault-Proneness for\nTuning Testing Activities\" Proceedings of the 22nd International\nConference on Software Engineering (ICSE2000), Limerick, Ireland,\nJune 2000.", "Manasi Deodhar (2002), \"Prediction Model and the Size Factor for\nFault-proneness of Object Oriented Systems\", MS Thesis, Michigan\nTech. University, Dec. 2002.", "Bellini, P. (2005), \"Comparing Fault-Proneness Estimation Models\",\n10th IEEE International Conference on Engineering of Complex\nComputer Systems (ICECCS'05), vol. 0, 2005, pp. 205-214.", "Khoshgoftaar, T.M., K. Gao and R. M. Szabo ( 2001), \"An Application\nof Zero-Inflated Poisson Regression for Software Fault Prediction.\nSoftware Reliability Engineering\", ISSRE 2001. Proceedings of 12th\nInternational Symposium on, 27-30 Nov. (2001), pp: 66 -73.", "Munson, J. and T. Khoshgoftaar, (1990) \"Regression Modeling of\nSoftware Quality: An Empirical Investigation\", Information and\nSoftware Technology, 32(2): 106 - 114.", "Khoshgoftaar, T. M. and J. C. Munson, (1990). \"Predicting Software\nDevelopment Errors using Complexity Metrics\", IEEE Journal on\nSelected Areas in Communications, 8(2): 253 -261.\n[10] Menzies, T., K. Ammar, A. Nikora, and S. Stefano, (2003), \"How\nSimple is Software Defect Prediction?\", Journal of Empirical Software\nEngineering, October (2003).\n[11] Eman, K., S. Benlarbi, N. Goel and S. Rai, (2001), \"Comparing casebased\nreasoning classifiers for predicting high risk software\ncomponents\", Journal of Systems Software, 55(3): 301 - 310.\n[12] Sandhu, Parvinder Singh, Sunil Kumar and Hardeep Singh, (2007),\n\"Intelligence System for Software Maintenance Severity Prediction\",\nJournal of Computer Science, Vol. 3 (5), pp. 281-288, 2007\n[13] Challagulla, V.U.B. , Bastani, F.B. , I-Ling Yen , Paul, (2005)\n\"Empirical assessment of machine learning based software defect\nprediction techniques\", 10th IEEE International Workshop on Object-\nOriented Real-Time Dependable Systems, WORDS 2005, 2-4 Feb 2005,\npp. 263-270."]}

As the majority of faults are found in a few of its modules so there is a need to investigate the modules that are affected severely as compared to other modules and proper maintenance need to be done in time especially for the critical applications. As, Neural networks, which have been already applied in software engineering applications to build reliability growth models predict the gross change or reusability metrics. Neural networks are non-linear sophisticated modeling techniques that are able to model complex functions. Neural network techniques are used when exact nature of input and outputs is not known. A key feature is that they learn the relationship between input and output through training. In this present work, various Neural Network Based techniques are explored and comparative analysis is performed for the prediction of level of need of maintenance by predicting level severity of faults present in NASA-s public domain defect dataset. The comparison of different algorithms is made on the basis of Mean Absolute Error, Root Mean Square Error and Accuracy Values. It is concluded that Generalized Regression Networks is the best algorithm for classification of the software components into different level of severity of impact of the faults. The algorithm can be used to develop model that can be used for identifying modules that are heavily affected by the faults.