Research Article
VISTA ML - Visual Intelligence System for Teaching Algorithms with Machine Learning
@INPROCEEDINGS{10.4108/eai.28-4-2025.2358012, author={Revathy S and Atharva Ashish Patil and Anurag Haldar and Kavipriya V}, title={VISTA ML - Visual Intelligence System for Teaching Algorithms with Machine Learning}, proceedings={Proceedings of the 4th International Conference on Information Technology, Civil Innovation, Science, and Management, ICITSM 2025, 28-29 April 2025, Tiruchengode, Tamil Nadu, India, Part II}, publisher={EAI}, proceedings_a={ICITSM PART II}, year={2025}, month={10}, keywords={data structure interactive visualization large language model (llm) vista ml visualization}, doi={10.4108/eai.28-4-2025.2358012} }- Revathy S
Atharva Ashish Patil
Anurag Haldar
Kavipriya V
Year: 2025
VISTA ML - Visual Intelligence System for Teaching Algorithms with Machine Learning
ICITSM PART II
EAI
DOI: 10.4108/eai.28-4-2025.2358012
Abstract
VISTA ML (Visual Intelligence System for Teaching Algorithms with Machine Learning) is a learning system aimed at promoting the understanding of data structures with the help of NLP (Natural Language Processing) machine learning and real-time visualization. There exist many data visualization tools that can meet students’ needs and help them learn data structure, but these tools are based on the pattern of unidirectional information propagation, which is unable to provide interactive and communicative experiences, to well guide learners’ process of exploration and analysis. The main challenges of these visualization tools were large knowledge gaps, as well as less than desirable conceptual understanding and engagement. Meanwhile, VISTA ML is an innovative tool that encourages collaborative learning by deploying specialized AI models. Its chatbot, powered by Google Gemini 2.5, features smart query interpretation, and provides on-the-fly help by responding to student questions, explaining concepts, and working through complicated problems with incredible precision. What is more, the media's quiz upload option reduces to zero, thanks to the Mistral AI utilized for pre and post-assessment quizzes ensuring an extremely accurate assessment of learners' comprehension and progress.
