Semaphore is a communication method used to send and receive messages by utilizing flags, paddles, sticks, bare hands, or gloves. Semaphore signaling is commonly used in scouting activities (Pramuka). However, novice scouts often face difficulties in accurately recognizing semaphore gestures. Although guidebooks are available, errors may still occur, especially when learning independently. To address this issue, a gesture detection system using the Multi-Layer Perceptron (MLP) method and MediaPipe framework is proposed, which aims to evaluate the accuracy of MLP and MediaPipe in detecting semaphore poses. To assess the performance of the MLP model, a Confusion Matrix is used to analyze the number of correct and incorrect predictions and generate metrics such as accuracy, precision, recall, and F1-score. The evaluation results show that the system successfully recognized 122 poses correctly, achieving an accuracy of 93.84%, precision of 93.84%, recall of 100%, and an F1-score of 96.80%. Based on these results, the system is considered sufficiently accurate and can be used as an interactive learning tool to recognize semaphore codes, particularly in scouting activities.

Education is vital for human beings to develop and continue their lives. Although many of the tutor search apps are available, students in Eastern Sumba have difficulty enjoying this service because no private tutor is resident in East Sumba. A private lesson tutor is important for students who need more intensive learning outside of school, especially parents who are busy or do not have the opportunity or knowledge to help their children. The challenge often faced is the difficulty of finding a tutor that suits the needs of the student. The use of profile matching methods can help parents or student guardians find private tutors based on specific needs or preferences, such as subject, level of experience, location, or other criteria. Tutors that meet these criteria will appear as search results. Testing with the System Usability Scale (SUS) showed that the application is qualified for users, as it achieved an average score of 72.62.