Decision Trees in Transportation Research

Summary

This chapter presents a bibliometric analysis of decision trees in transportation research, focusing on publication and citation counts, keyword analysis, and key contributors. The study examines 1107 publications from the Scopus database, spanning 2004–2024, to identify trends and significant contributions. The analysis shows a 20.18% annual growth rate in publications, highlighting the growing importance of decision trees in transportation. The average document age is 4.38 years, with an average of 25.95 citations per paper, indicating substantial impact and recognition. Strong collaboration among authors and institutions enhances research quality, with Southeast University and Beijing Jiaotong University leading in output. China is the most prolific country in this field. Key research categories include machine learning, algorithms, transportation and safety, data analysis, artificial intelligence and Inter of Things, health and safety, and environmental factors, reflecting the interdisciplinary nature of transportation research. This chapter identifies research gaps and provides recommendations for future studies, such as exploring machine learning techniques and optimizing intelligent transportation systems for autonomous vehicles. These insights aim to drive new discoveries and contribute to innovative solutions for complex challenges in transportation.