Abstract Software development effort estimation always remains a challenging task for project managers in a software industry. New techniques are applied to estimate effort. Evaluation of accuracy is a major activity as many methods are proposed in the literature. Here, we have developed a new algorithm called Real Time Extreme Learning Machine (RT-ELM) based on online sequential learning algorithm. The online sequential learning algorithm is modified so that the extreme learning machine learns continuously as new projects are developed in a software development organization. Performance of the real time extreme learning machine is compared with training and testing methodology. Studies were also conducted using radial basis function and additive hidden node. The accuracy of the Real time Extreme Learning machine with continuous learning is better than the conventional training and testing method. The results also indicate that the performance of radial basis function and additive hidden nodes is data dependent. The results are validated using data from academic setting and industry.

References

[1] Boehm B., Abts C., and Chulani S., “Software Development Cost Estimation Approaches: A Survey,” Annals of Software Engineering, vol. 10, no. 1-4, pp. 177-205, 2000.

[2] Dave V. and Dutta K., “Neural Network Based Models for Software Effort Estimation: A Review,” Artificial Intelligence Review, vol. 2, 22 The International Arab Journal of Information Technology, Vol. 16, No. 1, January 2019 no. 2, pp. 295-307, 2012.

[3] Dejaeger K., Verbeke W., Martens D., and Baesens B., “Data Mining Techniques for Software Effort Estimation: A Comparative Study,” IEEE Transactions on Software Engineering, vol. 38, no. 2, pp. 375-397, 2012.

[4] Huang G., Wang D., and Lan Y., “Extreme Learning Machines: A Survey,” International Journal, Machine Learning and Cybernetics, vol. 2, no. 2, pp. 107-122, 2011.

[5] Huang G., Zhou H., Ding X., and Zhang R., “Extreme Learning Machine for Regression and Multi-Class Classification,” IEEE Transactions on Systems, Man, and Cybernetics-Part b: Cybernetics, vol. 42, no. 2, pp. 513-529, 2012.

[6] Huang G., Zhu Q., and Siew C., “Extreme Learning Machine: Theory and Applications,” Neurocomputing, vol. 70, no. 1-3, pp. 489-501, 2006.

[7] Liang N., Huang G., Saratchandran P., and Sundararajan N., “A Fast and Accurate Online Sequential Learning Algorithm for Feed Forward Networks,” IEEE Transactions on Software Engineering, vol. 17, no. 6, pp. 141-1423, 2006.

[8] Lopez-Martin C., “A Fuzzy Logic Model for predicting the Development Effort of Short Scale Programs Based Upon Two Independent Variables,” Applied Soft Computing, vol. 11, no. 1, pp. 724-732, 2011.

[9] Mohammed Y., Analogy Based Software Project Effort Estimation, Ph.D. Thesis, University of Bradford, 2010.

[10] Nagpall G., Uddin M., and Kaur A., “Grey Relational Effort Analysis Technique Using Regression Methods for Software Estimation,” The International Arab Journal of Information Technology, vol. 11, no. 5, pp. 437-446, 2013.

[11] Olatunji S., Rasheed Z., Sattar K., Al-Mana A., Alshayeb M., and El-Sebakhy E., “Extreme Learning Machine as Maintainability Prediction Model for Object-Oriented Software Systems,” Journal of Computing, vol. 2, no. 8, pp. 49-56, 2010.

[12] PROMISEhttp://promise.site.uottawa.ca/SERepo sitory/datasets/desharnais.arff, Last Visited, 2012.

[13] PROMISEhttps://code.google.com/p/promisedata /source/browse/trunk/effort/maxwell/maxwell.arf f, Last Visited, 2012.

[14] Wen J., Li S., Lin Z., Hu Y., and Huang C., “Systematic Literature Review of Machine Learning Based Software Development Effort Estimation Models,” Information and Software Technology, vol. 54, no. 1, pp. 41-59, 2012. Kanakasabhapathi Pillai received B.E. in Electrical Engineering in 1971 from Madurai University, Madurai, Tamilnadu, India. He obtained M.Tech. from IIT Madras, Chennai, Tamilnadu, India, in 1973. After his masters, he joined Indian Space Research Organization and worked for 22 years. Then he joined NeST, Trivandrum, India as President and worked for eight years. Afterwards, he was Vice- President at HCL Technologies for six years. He was a Black Belt from American Society for quality and Master Black Belt from Indian Statistical Institute. Currently, he is working as Professor in the Department of Electrical and Electronics Engineering at K N S K College of Engineering, Nagercoil, India. He is also perusing his Ph.D. in Computer Science and Engineering. He has published more than 30 papers in peer reviewed journals and conferences. He is a senior member of IEEE and senior member of ACM. He is also a life member of Computer Society of India. He is Fellow of Institution of Engineers, India. His interests include soft computing and software engineering, Muthayyan Jeyakumar received his Post Graduation Degree in Master of Computer Applications from Bharathidasan University, Trichirappalli, Tamilnadu, India in 1993. He fetched his M.Tech degree in Computer Science and Engineering from Manonmaniam Sundarnar University, Tirunelveli, Tamilnadu, India in 2005. He completed his Ph.D degree in Computer Applications from Dr. M.G.R Educational and Research Institute University, Chennai, Tamilnadu, India in 2010. He is at present working as Professor in the Department of Computer Applications and Additional Controller of Examinations, Noorul Islam Centre for Higher Education, Kumaracoil, Tamilnadu, India and he has twenty years of teaching experience in this reputed institution. He has published Thirty Six research papers in International and National Journals. He has also presented more than twenty research papers in International and National Conferences conducted by esteemed organizations. His research interests are Mobile Computing, Software Engineering and Network Security.