Anomaly Detection in Classroom Using Convolutional Neural Networks

Anomaly detection is a task that involves identifying patterns or events that deviate significantly from the expected or normal behavior. In the context of classroom settings, it is essential to identify mischievous behavior exhibited by students to ensure a productive and conducive learning environment. This paper proposes a new method to identify abnormal behavior in a classroom setting using computer vision and deep learning techniques. This method uses convolutional neural networks (CNNs) and recurrent neural networks (RNN) algorithms to detect hand-raising, sleeping, talking, and fighting behaviors in the classroom with live video surveillance. It involves using the You Only Look Once (YOLO) algorithm to locate the position of students in the frame and an RNN algorithm to classify their behavior as normal or anomalous. RNN algorithm is trained on a labeled image and video dataset containing examples of normal and abnormal behaviors. This system can trigger real-time alerts, allowing teachers to act appropriately to maintain a conducive learning environment. It also helps to identify and address disruptive behaviors. Real-time, revolutionizing classroom monitoring: Our algorithm has the potential to improve student safety and well-being, as well as their academic performance. This research could lead to further developments in the field of the classroom.