Rubén A. More Valencia, Juan M. Tume Ruíz, Antia Rangel Vega, Hoower A. Puicon Zapata, Moises D. Saavedra Arango

Proceedings of the 15th International Multi-Conference on Complexity, Informatics and Cybernetics: IMCIC 2024, pp. 139-144 (2024); https://doi.org/10.54808/IMCIC2024.01.139

Rubén A. More Valencia
Operations Research, National University of Piura, Piura, Peru

Juan M. Tume Ruíz
Engineering and Production, National University of Piura, Piura, Peru

Antia Rangel Vega
Engineering and Production, National University of Piura, Piura, Peru

Hoower A. Puicon Zapata
Informatics Engineering, National University of Piura, Piura, Peru

Moises D. Saavedra Arango
Informatics Engineering, National University of Piura, Piura, Peru

Cite this paper as:
More Valencia, R. A., Tume Ruíz, J. M., Rangel Vega, A., Puicon Zapata, H. A., Saavedra Arango, M. D. (2024). Exploring Programmatic Thinking: Efficient Code Generation in Programming Languages with Generative Artificial Intelligence for System Simulation. In N. Callaos, S. Hashimoto, N. Lace, B. Sánchez, M. Savoie (Eds.), Proceedings of the 15th International Multi-Conference on Complexity, Informatics and Cybernetics: IMCIC 2024, pp. 139-144. International Institute of Informatics and Cybernetics. https://doi.org/10.54808/IMCIC2024.01.139

The study on the application of artificial intelligence (AI) in education, specifically in computational programming languages and system simulation, proposes a procedure as part of a structured process to develop libraries in the R language. In the coding phase, students seek assistance from Generative AI, which generates code while students create instructions to assess its quality.
This iterative approach allows continuous improvements in the code. The evaluation phase involves students working on programming and simulation tasks validated by the instructor, establishing a structured evaluation framework.
During the simulation phase, students analyse the results, collaborating with the instructor to validate their findings. The final stage, reporting and presentation, emphasizes creating additional scenarios to compare and validate models, with students presenting reports to the instructor and showcasing results to the class.
Regarding results, the effectiveness of Generative AI in rapidly and efficiently generating code is highlighted, showing robust adaptability to different programming languages. Instructor evaluations suggest some diversity in the quality of students' work, particularly in code clarity and readability. Students demonstrate strengths in optimizing code efficiency and handling exceptions and errors, showcasing their ability to interact and scale algorithmic knowledge.
The study suggests areas for future research, such as exploring approaches to enhance the clarity and readability of code generated by Generative AI, as well as further optimizing efficiency in the practical application of programming and system simulation through artificial intelligence.