Detection and Classification of Teacher-Rated Children’s Activity Levels Using Millimeter-Wave Radar and Machine Learning - A Pilot Study in a Real Primary School Environment

Aug 5, 2026

Upload by Miles

Traditional assessments of children’s health and behavioral concerns often depend on adult subjective ratings, creating substantial time and human-resource burdens for schools. This pilot study evaluates millimeter-wave radar with machine learning to objectively and semi-automatically detect and classify children’s activity levels (restlessness) in a real classroom. A nine-day observation uses two radar systems to monitor 14 children in a primary school and extracts radar features for detection and classification. Results show successful detection and 100% classification accuracy, highlighting privacy-protected, non-contact monitoring potential. Future work is needed to address limited duration and sample size.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages15

Reading Time38 min

AccessFree to download

Abstract

Introduction

Background and challenges of subjective evaluations

Need for objective, non-contact measurements

Received 1 December 2024, accepted 1 January 2025, date of publication 8 January 2025, date of current version 5 February 2025. Digital Object Identifier 10.1109/ACCESS.2025.3527037 Detection and Classification of Teacher-Rated Children’s Activity Levels Using Millimeter-Wave Radar and Machine Learning: A Pilot Study in a Real Primary School Environment TIANYI WANG1,(Member, IEEE), TAKUYA SAKAMOTO2,(Senior Member, IEEE), YU OSHIMA2, ITSUKI IWATA2, MASAYA KATO2, HARUTO KOBAYASHI2,(Graduate Student Member, IEEE), MANABU WAKUTA3, MASAKO MYOWA4, TOKOMO NISHIMURA5, AND ATSUSHI SENJU5 1Institute for Multidisciplinary Sciences, Yokohama National University, Yokohama, Kanagawa 240-8501, Japan 2Department of Electrical Engineering, Graduate School of Engineering, Kyoto University, Kyoto 615-8510, Japan 3Research Department, Institute of Child Developmental Science Research, Hamamatsu, Shizuoka 430-0929, Japan 4Graduate School of Education, Kyoto University, Kyoto 606-8501, Japan 5Research Center for Child Mental Development, Hamamatsu University School of Medicine, Hamamatsu, Shizuoka 431-3192, Japan Corresponding authors: Tianyi Wang ([gmwangtianyi@gmail.com](gmwangtianyi@gmail.com)) and Takuya Sakamoto ([sakamoto.takuya.8n@kyoto-u.ac.jp](sakamoto.takuya.8n@kyoto-u.ac.jp)) This work was supported in part by Japan Science and Technology Agency (JST)-Mirai Program under Grant JPMJMI22J2 . This work involved human subjects or animals in its research. Approval of all ethical and experimental procedures and protocols was granted by the Ethics Committee of the Graduate School of Engineering, Kyoto University, under Approval No. 202219. ABSTRACT Traditional assessments of children’s health and behavioral issues primarily rely on subjective evaluation by adult raters, which imposes major costs in time and human resource to the school system. This pilot study investigates the utilization of millimeter-wave radar coupled with machine learning for the objective and semi-automatic detection and classification of children’s activity levels, defined as restlessness, within a real classroom environment. Two objectives are pursued: confirming the feasibility of restlessness detection using millimeter-wave radar and applying standard machine learning method for restlessness classification. The experiment involves a nine-day observational study, using two radar systems to monitor the activities of 14 children in a primary school. Radar data analysis involves the extraction of distinctive features for restlessness detection and classification. Results indicate the successful detection of restlessness using millimeter-wave radar, demonstrating its potential to capture nuanced body movements in a privacyprotected manner. Machine learning models trained on radar data achieve a classification accuracy of 100%, outperforming other methods in terms of non-invasiveness, lack of body restraint, multi-target applications, and privacy protection. The study’s contributions extend to children, parents, and educational practitioners, emphasizing non-invasiveness, privacy protection, and evidence-based support. Despite limitations such as a short monitoring duration and a small sample size, this pilot study lays the foundation for future research in non-invasive restlessness detection using non-contact monitoring technologies. The integration of millimeter-wave radar and machine learning offers a promising avenue for efficient and ethical trait assessments in real-world educational environments, contributing to the advancement of child psychology and education. This work supports efforts for non-contact monitoring of children’s activity holding promise such as non-invasive, privacy protection, multi-targets, objective evaluation, and computer-aided screening. The associate editor coordinating the review of this manuscript and approving it for publication was Luyu Zhao . 􀀊 2025 The Authors. This work is licensed under a Creative Commons Att

FAQs

What problem does the pilot study address in assessing children’s activity levels?

It targets the heavy time and human-resource burden of subjective, adult-rated assessments used for children’s health and behavioral concerns in schools.

How does the study measure restlessness in a real classroom?

It uses millimeter-wave radar coupled with machine learning to detect and classify restlessness by extracting distinctive features from radar data.

What were the main findings and limitations of the pilot study?

The radar system successfully detected restlessness and achieved 100% classification accuracy with privacy-protective, non-contact monitoring, though the study used a short monitoring period and a small sample size.

Aug 5, 2026

Upload by Miles