From Traditional to AI-Enhanced Science Learning: Real-time Organ Recognition with YOLOv8
Canadian Journal of Science, Mathematics and Technology Education, cilt.26, sa.3, 2026 (ESCI, Scopus)
- Yayın Türü: Makale / Tam Makale
- Cilt numarası: 26 Sayı: 3
- Basım Tarihi: 2026
- Doi Numarası: 10.1007/s42330-026-00497-y
- Dergi Adı: Canadian Journal of Science, Mathematics and Technology Education
- Derginin Tarandığı İndeksler: Emerging Sources Citation Index (ESCI), Scopus, Aerospace Database, Agricultural & Environmental Science Database, EBSCO Education Source, ERIC (Education Resources Information Center), Academic Search Ultimate (EBSCO), Natural Science Collection (ProQuest), Social Science Premium Collection (ProQuest), Biological Science Database (ProQuest), Earth, Atmospheric, & Aquatic Science Collection (ProQuest), Education Collection (ProQuest), Education Source Ultimate (EBSCO), Materials Science & Engineering Collection (ProQuest), Technology Collection (ProQuest)
- Anahtar Kelimeler: Artificial intelligence, Object recognition, Roboflow, Science education, YOLO
- Yıldız Teknik Üniversitesi Adresli: Evet
Özet
This study was conducted using an adopted design-based research (DBR) approach to investigate the impact of artificial intelligence (AI)-supported object recognition technology on middle school students’ learning of the “Systems in Our Body” unit. A dataset capable of identifying human organs was developed using the YOLOv8 algorithm and the Roboflow platform, and this dataset was integrated into the instructional process. The research consisted of four main stages: initial design, pilot implementation, revision, and main implementation. During the pilot implementation, both technical and pedagogical issues were identified, leading to the redesign of the lesson scenario. The main implementation was carried out with 5th grade students. A quasi-experimental pretest–posttest control group design was used to measure the effectiveness of the intervention. In addition, qualitative data were collected through a focus group interview with the experimental group students. Quantitative findings revealed that the AI-supported dataset significantly improved students’ academic achievement. Qualitative findings indicated positive changes in students’ cognitive and affective development. The study suggests that AI-assisted instructional tools can enhance science learning processes and increase classroom engagement. These findings suggest that AI-supported image recognition can foster both conceptual understanding and motivation in science education.