Nowadays, logistics for transportation and distribution of merchandise are a key element to increase the competitiveness of companies. However, the election of alternative routes outside the panned routes causes the logistic companies to provide a poor-quality service, with units that endanger the appropriate deliver of merchandise and impacting negatively the way in which the supply chain works. This paper aims to develop a module that allows the processing, analysis and deployment of satellite information oriented to the pattern analysis, to find anomalies in the paths of the operators by implementing the algorithm TODS, to be able to help in the decision making. The experimental results show that the algorithm detects optimally the abnormal routes using historical data as a base.

Albahli, S. (2020). A deep ensemble learning method for effort-aware Just-In-Time defect prediction. Applied Computer Science, 16(3), 5-15. doi:10.23743/acs-2020-17

Albahli, Saleh. "A Deep Ensemble Learning Method for Effort-Aware Just-in-Time Defect Prediction." Applied Computer Science 16, no. 3 (2020): 5-15.

S. Albahli, "A deep ensemble learning method for effort-aware Just-In-Time defect prediction," Applied Computer Science, vol. 16, no. 3, pp. 5-15, 2020, doi: 10.23743/acs-2020-17.

Albahli S. A deep ensemble learning method for effort-aware Just-In-Time defect prediction. Applied Computer Science. 2020;16(3):5-15.