The International Arab Journal of Information Technology (IAJIT)


Abductive Network Ensembles for Improved

Software systems are subject to a series of changes due to a variety of maintenance goals. Some parts of the software system are more prone to changes than others. These change-prone parts need to be identified so that maintenance resources can be allocated effectively. This paper proposes the use of Group Method of Data Handling (GMDH)-based abductive networks for modeling and predicting change proneness of classes in object-oriented software using both software structural properties (quantified by the C&K metrics) and software change history (quantified by a set of evolution-based metrics) as predictors. The empirical results derived from an experiment conducted on a case study of an open-source system show that the proposed approach improves the prediction accuracy as compared to statistical-based prediction models.

[1] Abdel-Aal R., Hourly temperature forecasting using abductive networks, Engineering Applications of Artificial Intelligence, vol. 17, no. 5, pp 543-556, 2004.

[2] Abdel-Aal R., Al-Garni A., and Al-Nassar Y., Modelling and Forecasting Monthly Electric Energy Consumption in Eastern Saudi Arabia using Abductive Networks, Energy, vol. 22, no. 9, pp. 911-921, 1997. 810 The International Arab Journal of Information Technology, Vol. 14, No. 6, November 2017

[3] Abdel-Aal R., Elhadidy M., and Shaahid S., Modeling and Forecasting the Mean Hourly Wind Speed Time Series using GMDH-Based Abductive Networks, Renewable Energy, vol. 34, no. 7, pp. 1686-1699, 2009.

[4] Aggarwal K., Singh Y., Kaur A., and Malhotra R., Application of Artificial Neural Network for Predicting Maintainability using Object-Oriented Metrics, Transactions on Engineering, Computing and Technology, vol. 15, pp. 285- 289, 2006.

[5] AIM Software User's Manual, AbTech Corporation, AIM Software User's Manual, Charlottesville, 1990.

[6] Baig Z., Sait S., and Shaheen A., GMDH-Based Networks for Intelligent Intrusion Detection, Engineering Applications of Artificial Intelligence, vol. 26, no. 7, pp. 1731-1740, 2013.

[7] Basili V., Briand L., and Melo W., A Validation of Object-Oriented Design Metrics as Quality Indicators, IEEE Transactions on Software Engineering, vol. 22, no. 10, pp. 751-761, 1996.

[8] Bayer J., Girard J., Wurthner M., DeBaud J., and Apel M., Transitioning Legacy Assets to a Product Line Architecture, in Proceeding of the 7th European software engineering conference held jointly with the 7th ACM SIGSOFT international symposium on Foundations of software engineering, Toulouse, pp. 446-463, 1999.

[9] Bernstein P., Halevy H., and Pottinger R., A Vision for Management of Complex Models, ACM Sigmod Record, vol. 29, no. 4, pp. 55-63, 2000.

[10] Boslaugh S. and Watters P., Statistics in a Nutshell: A Desktop Quick Reference, O Reilly Media, 2008.

[11] Brooks F., The Mythical Man-Month, Addison Wesley, 1995.

[12] Chidamber S. and Kemerer C., Towards a Metrics Suite for Object Oriented Design, in Proceeding of Object-oriented programming systems, languages, and applications, phoenix, pp. 197-211, 1991.

[13] Chidamber S. and Kemerer C., A Metrics Suite for Object Oriented Design, IEEE Transactions on Software Engineering, vol. 20, no. 6, pp. 476- 493, 1994.

[14] El-Alfy E. and Abdel-Aal R, Using GMDH- Based Networks for Improved Spam Detection and Email Feature Analysis, Applied Soft Computing, vol. 11, no. 1, pp. 477-488, 2011.

[15] El-Alfy E. and Abdel-Aal R., Abductive Learning Ensembles for Hand Shape Identification, Cognitive Computation, vol. 6, no. 3, pp. 321-330, 2014.

[16] Elish M. and Al-Khiaty M., A Suite of Metrics for Quantifying Historical Changes to Predict Future Change-Prone Classes in Object-Oriented Software, Journal of Software: Evolution and Process, vol. 25, no 5, pp. 407-437, 2012.

[17] Ellis D. and Morgan N., Size Matters: An Empirical Study of Neural Network Training for Large Vocabulary Continuous Speech Recognition, in Proceeding of IEEE International Conference on Acoustics, Speech, and Signal Processing, Phoenix , pp. 1013-1016, 1999.

[18] Eski S. and Buzluca F., An Empirical Study on Object-Oriented Metrics and Software Evolution in Order to Reduce Testing Costs by Predicting Change-Prone Classes, in Proceeding of Software Testing, Verification and Validation Workshops, honolulu, pp. 566-571, 2011.

[19] Farlow S., The GMDH algorithm. Self- organizing methods in modeling: GMDH Type Algorithms, Marcel Dekker, 1984.

[20] Fenton N. and Pfleeger S., Software Metrics: A Rigorous and Practical Approach, PWS Publishing Co., 1998.

[21] G ne -Koru A. and Liu H., Identifying and Characterizing Change-Prone Classes in Two Large-Scale Open-Source Products, Journal of Systems and Software, vol. 80, no. 1, pp. 63-73, 2007.

[22] Gyimothy T., Ferenc R., and Siket I., Empirical Validation of Object-Oriented Metrics on Open Source Software for Fault Prediction, IEEE Transactions on Software Engineering, vol 31, no. 10, pp. 897-910, 2005.

[23] Hippert H., Pedreira C., and Souza R., Neural Networks for Short-Term Load Forecasting: A Review and Evaluation, IEEE Transactions on Power Systems, vol. 16, no. 1, pp. 44-55, 2001.

[24] Ivakhnenko A., Polynomial Theory of Complex Systems, IEEE Transactions on Systems, Man and Cybernetics, vol. SMC-1, no. 4, pp. 64-378, 1971.

[25] Kagdi H. and Maletic J., Software-Change Prediction:Estimated+Actual, in Proceeding of Second International IEEE Workshop on Software Evolvability, Philadelphia, pp. 38-43, 2006.

[26] Kaur A., Kaur K., and Malhotra R., Soft Computing Approaches for Prediction of Software Maintenance Effort, International Journal of Computer Applications, vol. 1, no. 16, pp. 69-75, 2010.

[27] Kemerer C. and Slaughter S., An Empirical Approach To Studying Software Evolution, IEEE Transactions on Software Engineering, vol. 25, no. 4, pp. 493-509, 1999.

[28] Khoshgoftaar T., Allen E., Halstead R., Trio G., and Flass R., Process Measures for Predicting Software Quality, in Proceeding of High- Abductive Network Ensembles for Improved Prediction of Future Change-Prone Classes ... 811 Assurance Systems Engineering Workshop, Washington, pp. 155-160, 1997.

[29] Lawal I., Abdel-Aal R., and Mahmoud S., Recognition of Handwritten Arabic (Indian) Numerals Using Freeman's Chain Codes and Abductive Network Classifiers, in Proceeding of 20th International Conference on Pattern Recognition, Istanbul, pp. 1884-1887, 2010.

[30] Lehman M., Perry D., and Ramil J., Implications of Evolution Metrics on Software Maintenance, in Proceeding of International Conference on Software Maintenance, Bethesda, pp. 208-217, 1998.

[31] Li W. and Henry S., Object-Oriented Metrics that Predict Maintainability, Journal of Systems and Software, vol. 23, no. 2, pp. 111-122, 1993.

[32] Montgomery G. and Drake K., Abductive Reasoning Networks, Neurocomputing, vol. 2, no. 3, pp. 97-104, 1991.

[33] Nagappan N. and Ball T., Use of Relative Code Churn Measures to Predict System Defect Density, in Proceeding of 27th International Conference on Software Engineering, Louis, pp. 284-292, 2005.

[34] Parnas D., Software Aging, in Proceeding of 16th International Conference on Software Engineering, Sorrento, pp. 279-287, 1994.

[35] Porter A. and Selby R., Empirically Guided Software Development using Metric-Based Classification Trees, IEEE Software, vol. 7, no. 2, pp. 46-54, 1990.

[36] Romano D. and Pinzger M., Using Source Code Metrics to Predict Change-Prone Java Interfaces, in Proceeding of 27th IEEE International Conference on Software Maintenance, Williamsburg, pp. 303-312, 2011.

[37] Thwin M. and Quah T., Application of Neural Networks for Estimating Software Maintainability Using Object-Oriented Metrics, in Proceeding of International Conference on Software Engineering and Knowledge Engineering, San Francisco, pp. 69-73, 2003. Mojeeb AL-Khiaty received his BS degree in Mathematics and Computer from Sana a University, Yemen, in 1999, his MS degree in Computer Science from King Fahd University of Petroleum and Minerals (KFUPM), Saudi Arabia, in 2009, and his PhD degree in Computer Science and Engineering from KFUPM, Saudi Arabia, in 2015. His research interests include software engineering, software metrics, software reuse, and soft computing. Radwan Abdel-Aal received his BS in electrical engineering from Cairo University, Egypt, in 1972, his MS in aviation electronics from Cranfield University, UK in 1974, and his PhD from Strathclyde University, UK in 1983. Between 1985 and 2005 he was a research scientist at the Research Institute of King Fahd University of Petroleum and Minerals (KFUPM), Dhahran, Saudi Arabia. In 2005 he joined the Computer Engineering Department at KFUPM where he is currently a Professor. His research interests include nuclear physics instrumentation and machine learning and data mining applications. Mahmoud Elish is an Associate Professor in the Computer Science Department at Gulf University for Science and Technology (GUST), Kuwait. He has been an Associate Professor in the Information and Computer Science Department at King Fahd University of Petroleum and Minerals (KFUPM), Saudi Arabia. He received his PhD from George Mason University. His research interests include software metrics, design, quality and maintenance.