Utilization of RiceVision as Intelligent Learning Media to Support Smart Vocational Education in Quality Control at SMK SMTI Makassar

Purpose – This study aimed to develop RiceVision, an intelligent learning media based on computer vision and machine learning, to support the implementation of Smart Vocational Education in the Quality Control Department at SMK SMTI Makassar. Design/methods/approach – The study employed a research and development framework using the Plomp model, which consisted of design, validity, practicality, and effectiveness testing stages. In the effectiveness testing phase, a quasi-experimental design was implemented involving control and experimental groups. The control group consisted of 36 students who learned through conventional methods, while the experimental group consisted of 36 students who learned using RiceVision. Findings – The validity test by four experts resulted in a score of 0.94, categorized as valid, while practicality tests achieved 90.75% and 93.75% scores at the one-to-one and small-group stages. The effectiveness test showed significantly higher posttest scores in the experimental group (84.86 ± 6.74) compared to the control group (71.31 ± 8.21), with a significant difference (t(70)=7.64, p<.001) and a very large effect size (Cohen's d=1.80), indicating that RiceVision effectively improved students’ conceptual understanding, digital literacy, and practical competencies in rice quality identification and analysis. Research implications/limitations – These findings indicate that RiceVision effectively facilitates contextual and technology-enhanced vocational learning. Overall, the RiceVision-based intelligent learning media was proven to be valid, practical, and effective, indicating its potential as an innovative solution for integrating artificial intelligence into vocational learning environments. The implementation of RiceVision contributes to strengthening digital literacy, improving students’ learning engagement, and supporting the realization of Smart Vocational Education in vocational high schools. Originality/value – This study presents RiceVision as an innovative solution that integrates artificial intelligence, computer vision, and machine learning into vocational education, particularly in quality control learning. The development of intelligent visual recognition features combined with interactive learning modules and project-based activities demonstrates its potential value in supporting contextual technology-enhanced learning and strengthening Smart Vocational Education implementation.