SENSITIVITY-BASED LINEAR LEARNING METHOD AND EXTREME LEARNING MACHINES COMPARED FOR SOFTWARE MAINTAINABILITY PREDICTION OF OBJECT-ORIENTED SOFTWARE SYSTEMS

This paper presented two maintainability prediction models that are developed and compared for object-oriented software systems based on the recently introduced learning algorithm called Sensitivity Based Linear Learning Method (SBLLM) and extreme learning machines (ELM). As the number of object-oriented software systems increases, it becomes more important for organizations to maintain those systems effectively. However, currently only a small number of maintainability prediction models are available for object oriented systems. The model was constructed using popular object-oriented metric datasets, collected from different object-oriented systems. Prediction accuracy of the models were evaluated and compared with each other and with other commonly used regression-based models and also with Bayesian network based model which were earlier developed using the same datasets. Empirical results from simulation show that the proposed ELM and SBLLM based models produced promising results in term of prediction accuracy measures authorized in OO software maintainability literatures, better than most of the other earlier implemented models on the same datasets.