인문학
사회과학
자연과학
공학
의약학
농수해양학
예술체육학
복합학
DBpia AI
AI 에이전트
AI 아이디어
AI 리더
AI 뷰어
Citeasy
크롬 서지관리 다운로드
지원사업
학술연구/단체지원/교육 등 연구자 활동을 지속하도록 DBpia가 지원하고 있어요.
커뮤니티
연구자들이 자신의 연구와 전문성을 널리 알리고, 새로운 협력의 기회를 만들 수 있는 네트워킹 공간이에요.
논문 기본 정보
- 저자정보
피인용 0
초록·키워드
Artificial intelligence has moved from an experimental aid to a standard component of digital learning: the global market for AI in education was valued at approximately USD 8.3 billion in 2025 and is projected to reach USD 57.2 billion by 2033, with personalized learning as its largest application segment [12]. Randomized evidence has also begun to appear, with a controlled trial of 194 undergraduates reporting that an AI tutor produced greater learning gains in less time than an active-learning class [11]. Learners preparing for certification examinations, however, are still served mainly by static question banks that do not adapt to individual weaknesses. This paper presents the design and implementation of an AI-based personalized learning system for certification exam preparation. The system integrates five modules: a problem-solving module offering level tests and difficulty-adaptive practice over a bank of 1,160 questions, an incorrect-answer note module, an Elasticsearch-based visualization module for proficiency dashboards, a real-time condition analysis module that classifies seven facial expressions from a webcam and converts them into a concentration state, and a similar-problem module that extracts text from an uploaded question image by OCR and retrieves questions from the same syllabus section using a fine-tuned BERT classifier. The system was evaluated at module level: OCR text extraction achieved 95.6% character accuracy, BERT section classification achieved 92.8% accuracy with an F1 score of 0.92, and the condition analysis model achieved 72.4% accuracy. A usability study with 20 learners returned a mean System Usability Scale score of 78.5.
본문·목차
인공지능 문자 인식 모델을 통해 추출된 텍스트로, 일부 오타나 오류가 포함될 수 있으나 지속적으로 개선 중입니다.
오류를 발견하셨다면 해당 부분을 드래그한 후 ' 를 통해 신고해주세요.
오류를 발견하셨다면 해당 부분을 드래그한 후 ' 를 통해 신고해주세요.
최근 본 자료 전체보기
