Multi-Criteria Evaluation of Publication Impacts: Deep Learning in Autonomous Vehicles
Goshgar Can Ismayilov, Cansu Damla Yilmaz · 2021
Deep learning is the state-of-the-art approach that has been extensively used in the recent years to variety of real-world problems in the literature. The autonomous vehicles are among the applications where their integration with deep learning techniques has potential to disruptively change our daily lives. In this work, we have proposed a multi-criteria framework to evaluate the relative impacts of both publications and authors for deep learning in autonomous vehicles. For the framework, we have considered several criteria extracted from the metadata of the publications and the authors. The conflicts among the criteria are also justified through Pearson correlation. For the experiments, two comprehensive datasets for the publication and the author impacts have been constructed. The resulting pareto-fronts of the datasets after ranking are presented. Moreover, top 30 most impactful publications and authors in the literature are identified. We hope that our findings will be useful for researchers to accelerate the further technological advancements.