DESIGN AND IMPLEMENTATION OF AN INTELLIGENT CHILD FALL PREVENTION SYSTEM FOR PARALLEL-PUSH WINDOWS

Authors

  • YuanJu Zhou (Corresponding Author) School of Artificial Intelligence and Electronic Engineering, Sichuan Technology and Business University, Chengdu 611745, Sichuan, China.
  • YongKang Nie School of Artificial Intelligence and Electronic Engineering, Sichuan Technology and Business University, Chengdu 611745, Sichuan, China.
  • XiaoSong Nie School of Artificial Intelligence and Electronic Engineering, Sichuan Technology and Business University, Chengdu 611745, Sichuan, China.
  • JiangLin Huang School of Artificial Intelligence and Electronic Engineering, Sichuan Technology and Business University, Chengdu 611745, Sichuan, China.

Keywords:

Intelligent parallel-push window, Child fall prevention, STM32F407, K230 visual module, YOLO object detection

Abstract

Traditional parallel-push windows employ simple handle-locking mechanisms that young children can easily unlock, whereas permanently locking these windows restricts ventilation and obstructs emergency egress. To address these issues, a dual-controller intelligent parallel-push window system based on the STM32F407ZGT6 microcontroller and the K230 visual AI module is designed and implemented. The K230 module runs a YOLO-based object detection model to recognize children approaching the window frame and estimate their distance, transmitting a window-closing command to the STM32 microcontroller upon detecting a potential hazard. Serving as the central hub, the STM32 manages multi-source environmental sensor data acquisition and actuation mechanism control, forming a closed-loop control system in conjunction with limit switches. The software architecture adopts a hybrid approach, combining external interrupts for immediate response to emergency events with dynamic polling within the main loop for routine monitoring. Furthermore, the system supports dual-channel operation via 4G remote control and a local touchscreen interface; in the event of a network outage, the STM32 can execute safety protocols independently. Performance tests demonstrate that the system automatically closes and locks the window when a child approaches, and responds similarly to environmental anomalies such as strong winds, heavy rain, or combustible gas leaks. The system effectively meets domestic fall-prevention requirements, exhibiting significant practical value and potential for widespread application.

References

[1] Lindaman F C, Spiegel C N. Children can't fly: a program to prevent childhood morbidity and mortality from window falls. American Journal of Public Health, 1978, 67(12): 1143-1147. DOI: 10.1136/ip.1.3.194.

[2] Istre G R. Childhood injuries due to falls from apartment balconies and windows. Injury Prevention Journal of the International Society for Child & Adolescent Injury Prevention, 2003, 9(4): 349-352. DOI: 10.1136/ip.9.4.349.

[3] Vish N L. Pediatric window falls: not just a problem for children in high rises. Injury Prevention Journal of the International Society for Child & Adolescent Injury Prevention, 2005, 11(5): 300. DOI: 10.1136/ip.2005.008664.

[4] Rajashree Koppolu M R C V. Pediatric Falls From Windows: A Health Policy Model for Prevention. Journal of Pediatric Health Care, 2014, 28(2): 182-185.

[5] Toprani A, Robinson M, III J K M, et al. New York City's window guard policy: four decades of success. Injury Prevention, 2018, 24: i14-i18. DOI: 10.1136/injuryprev-2017-042649.

[6] Zhao H, Zhu Y, Qu F, et al. Design of intelligent window system based on OneNET cloud platform. Proceedings of SPIE, Design of intelligent window system based on OneNET cloud platform, 2022, 12258: 8. DOI: 10.1117/12.2639277.

[7] Lei S, Yan H, Li Z, et al. Automatic switching window ventilation system based on STM32 microcontroller. Proceedings of SPIE, Second International Conference on Electronic Information Engineering, Big Data, and Computer Technology (EIBDCT 2023), 126422V, 2023. DOI: 10.1117/12.2674867.

[8] Gunasegran S, Abdulla R, Vinesh T, et al. IoT-based smart window and temperature control system for optimized thermal comfort. AIP Conference Proceedings, 2024, 3161: 020018. DOI: 10.1063/5.0230083.

[9] Rios Moreno J G, Trejo Perea M, Ronquillo Lomeli G, et al. Smart window with an embedded control system for thermal comfort in buildings in Mexico. Proceedings of the institution of civil engineers, 2019, 172(ES8): 424-437.

[10] Xie X, Ji H, Wang L, et al. Design and Implementation of Electrochromic Smart Windows with Self-Driven Thermoelectric Power Generation. Nanomaterials, 2024, 14(12): 1027. DOI: 10.3390/nano14121027.

[11] Bochkovskiy A, Wang C Y, Liao H Y M. YOLOv4: Optimal Speed and Accuracy of Object Detection. arXiv e-prints, 2020. DOI: 10.48550/arXiv.2004.10934.

[12] Wang C Y, Bochkovskiy A, Liao H Y M. YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. arXiv e-prints, 2022. DOI: 10.48550/arXiv.2207.02696.

[13] Ge Z, Liu S, Wang F, et al. YOLOX: Exceeding YOLO Series in 2021. arXiv e-prints, 2021. DOI: 10.48550/arXiv.2107.08430.

[14] Ren S, He K, Girshick R, et al. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2017, 39(6): 1137-1149. DOI: 10.1109/TPAMI.2016.2577031.

[15] Sandler M, Howard A, Zhu M, et al. MobileNetV2: Inverted Residuals and Linear Bottlenecks. IEEE, 2018. DOI: 10.1109/CVPR.2018.00474.

Downloads

Published

2026-06-17

Issue

Vol. 8 No. 3 (2026)

Section

Articles

DOI:

https://doi.org/10.61784/ejst3152

How to Cite

YuanJu Zhou, YongKang Nie, XiaoSong Nie, JiangLin Huang. Design And Implementation Of An Intelligent Child Fall Prevention System For Parallel-Push Windows. Eurasia Journal of Science and Technology. 2026, 8(3): 52-59. DOI: https://doi.org/10.61784/ejst3152.