Search

Software testing (ST) is one of the most important software development life cycle (SDLC) phases and ST effort is often expressed as a percentage of SDLC effort. Unfortunately, in the literature ST effort percentage ranges from 10% to 60%. In the literature most of the machine learning algorithms and metaheuristics for optimizing them have looked at predicting overall SDLC effort without focusing on any specific SDLC phase, including testing. Therefore, this study investigates the application of the Software Testing Effort Prediction (STEP) of Gradient Boosting (GB) machine learning regression algorithm optimized through Differential Evolution (DE). Its prediction accuracy is compared with those obtained when the GB is also optimized through Particle Swarm Optimization (PSO) and Genetic Algorithms (GA). The performance of GB-DE, GB-PSO, and GB-GA was also compared to that of statistical regression (SR). Seven data sets of actual projects were selected from an international public repository for software projects. The results showed that GB-DE was statistically better than SR in all seven data sets at 95% confidence, whereas GB-PSO and GB-GA were better than SR in four and three data sets, respectively. Thus, we can conclude that GB-DE can be used for STEP of either new projects or enhancement projects developed in either the third or fourth programming language generation.

The Time-to-contact (TTC) estimate is mainly used in robotics navigation, in order to detect potential danger with obstacles in the environment. A key aspect in a robotic system is to perform its tasks promptly. Several approaches have been proposed to estimate reliable TTC in order to avoid collisions in real-time; nevertheless they are time consuming due to a calculation of scene characteristics in every frame. This paper presents an approach to estimate TTC using monocular vision based on the size change of the obstacles over time (); therefore, the robotic system may react promptly to its environment. Our approach collects information from few data of an obstacle, then the behavior of the movement is found through an online recursive modeling process, and finally, a forecasting of the upcoming positions is computed. We segment the obstacles using probabilistic hidden Markov chains. Our proposal is compared to a classical color segmentation approach using two real image sequences, each sequence is composed of 210 frames. Our results show that our proposal obtained smoother segmentations than a traditional color-based approach. [ABSTRACT FROM AUTHOR]