Andi Saryoko, Faruq Aziz

YOLO MODEL DETECTION OF STUDENT NEATNESS BASED ON DEEP LEARNING: A SYSTEMTIC LITERATURE REVIEW

Introduction

Yolo model detection of student neatness based on deep learning: a systemtic literature review. Evaluate YOLO deep learning models for automated student neatness detection. This systematic review analyzes optimization techniques, challenges (occlusion, lighting), and future research, offering guidelines for educators and AI developers.

Abstract

Maintaining proper student neatness (uniform compliance, grooming standards, and posture) is essential for fostering disciplined learning environments. While traditional monitoring methods are labor-intensive and subjective, computer vision-based solutions leveraging You Only Look Once (YOLO) architectures offer promising alternatives. The objective of this study is to evaluate YOLO optimization techniques for student neatness detection, identify key challenges, and propose relevant future research directions. This systematic review evaluates 28 recent studies (2021-2024) to analyze optimization techniques for YOLO models in student neatness detection applications. Key findings demonstrate that attention-enhanced variants (e.g., YOLOv10-MSAM) achieve 87.0% mAP@0.5, while pruning and quantization methods enable real-time processing (50-130 FPS) on edge devices like Jetson Orin. The analysis reveals three critical challenges: (1) occlusion handling in crowded classrooms (10-15% false negatives), (2) lighting/background variability, and (3) ethical concerns regarding facial recognition. Emerging solutions include hybrid vision-language models for explainable detection and federated learning for privacy preservation. The review proposes a taxonomy of optimization approaches categorizing architectural modifications (attention mechanisms, lightweight backbones), data augmentation strategies (GAN-based synthesis), and deployment techniques (TensorRT acceleration). Future research directions emphasize multi-modal sensor fusion and domain adaptation for cross-institutional generalization. This work provides educators and AI developers with evidence-based guidelines for implementing automated neatness monitoring systems while addressing practical constraints in educational settings.

Review

This systematic literature review, "YOLO Model Detection of Student Neatness Based on Deep Learning," provides a timely and relevant examination of automated solutions for maintaining student neatness, encompassing uniform compliance, grooming, and posture. Recognizing the labor-intensive and subjective nature of traditional monitoring, the authors effectively position You Only Look Once (YOLO) architectures as a promising computer vision alternative. The study's clear objective is to evaluate YOLO optimization techniques for this specific application, identify key challenges encountered in practical deployments, and subsequently propose well-defined avenues for future research. By meticulously analyzing 28 recent studies published between 2021 and 2024, the review offers a current and comprehensive overview of the state-of-the-art in this emerging field. The review effectively distills crucial findings regarding YOLO model performance and optimization. It highlights that advanced attention-enhanced variants, such as YOLOv10-MSAM, demonstrate impressive accuracy, achieving up to 87.0% mAP@0.5. Furthermore, the analysis emphasizes the feasibility of real-time deployment on resource-constrained edge devices, like the Jetson Orin, with frame rates ranging from 50-130 FPS, attributed to optimization methods like pruning and quantization. Crucially, the study identifies three significant challenges: persistent issues with occlusion in crowded settings leading to 10-15% false negatives, variability in lighting and background conditions, and the critical ethical implications concerning facial recognition and student privacy. The authors also present a useful taxonomy of optimization approaches, categorizing them into architectural modifications, data augmentation strategies, and deployment techniques, while pointing to emerging solutions like hybrid vision-language models for explainability and federated learning for privacy. This systematic review serves as a valuable resource, offering evidence-based guidelines for both educators and AI developers keen on implementing automated neatness monitoring systems. By explicitly detailing the practical constraints and technical challenges inherent in educational environments, the work aids in developing more robust and ethically sound solutions. The proposed future research directions, particularly focusing on multi-modal sensor fusion, domain adaptation for cross-institutional generalization, explainable AI, and enhanced privacy preservation through federated learning, are critical for advancing the field. Overall, the paper makes a significant contribution by synthesizing current knowledge, identifying key gaps, and charting a clear path for future development in the application of deep learning for student neatness detection.

Full Text

Comments

You need to be logged in to post a comment.