Skip to content
Log in
Sponsored AI Networking Cookbook: Practical recipes for AI-assisted network automation and development AI Networking Cookbook: Practical recipes for AI-assisted network automation and development
Open access

A Deep Learning Approach To Human Fall Detection With YOLOv12 Versi Nano

Florensce Sumarauw Febriyanti Ludja Robby Moody Lintong
Oct 2026 · International Journal of Informatics, Data, and Emerging Applications · 0 citations

TL;DR

The original YOLOv12-nano model, known for its lightweight architecture, low latency, and efficiency on edge devices, was implemented on the Le2i dataset and achieved an mAP50 of 0.866 and an mAP50-95 of 0.555, providing a strong foundation for further improvement in elderly fall detection systems.

Abstract

The growing elderly population faces a heightened risk of falls. Current monitoring solutions, such as in-person observation by caregivers or wearable sensors, suffer from several drawbacks. These include low accuracy, user discomfort, and a constant need for human oversight. To overcome these issues, automated approaches using Convolutional Neural Networks (CNNs), especially the YOLO algorithm, have been applied for fast and real-time fall detection. In this study, the original YOLOv12-nano model, which is known for its lightweight architecture, low latency, and efficiency on edge devices, was implemented on the Le2i dataset. The model achieved an mAP50 of 0.866 and an mAP50-95 of 0.555, with only 2.52 M parameters and 6.0 GFLOPs. These provide a strong foundation for further improvement in elderly fall detection systems

DOI Semantic Scholar
Read PDF

Similar papers

Open access Sep 2026

A Comparative Study of Fall Detection Device for Elderly People Using Machine Learning

A comparative evaluation of existing fall detection methodologies is presented, demonstrating that the proposed approach effectively overcomes the limitations of traditional threshold-based and resource-intensive deep learning methods, offering a scalable and reliable solution for elderly safety and remote health monit...

Dileep J, J. G, K. Pallavi et al. · 0 citations
Open access Sep 2026

A Lightweight CNN-GRU Model for Human Activity Recognition with Efficient Edge Deployment Using TFLite

A resource-constrained CNN-GRU hybrid model for HAR on the WISDM dataset that uses convolutional layers for spatial learning and gated recurrent units (GRU) for sequence learning, enabling real-time HAR on edge devices.

H. S. Ganesha, K. G. Harsha, Roshini P et al. · 0 citations
Open access 2026

Evaluation of Deep Learning Architectures on Synthetic LiDAR Sequences for Fall Detection

The study evaluates four temporal deep learning models including LSTM, GRU, CNN1D and Transformer Lite to analyze spatio temporal motion patterns from 3D LiDAR point sequences and identify the most suitable approach for accurate fall detection.

Amir Ali, Teodoro Montanaro, Ahmad Alsharoa et al. · 0 citations
Conference Aug 2026

Vision-Based Fall Detection in Hospitals Using a Dual-YOLO Deep Learning Framework

Each year, an estimated 700,000 to 1,000,000 patients experience falls in hospitals across the United States [1], and inpatient falls are similarly rising in Indian healthcare settings [25]. Manual CCTV surveillance remains the norm but cannot reliably cover multiple feeds, especially during understaffed night shifts,...

G. Kiran, A. Usha, P. R. Reddy et al. · 0 citations
Sep 2026

Humcareadl: A diverse multimodal dataset and HyMCL-Net for robust human activity recognition

A hybrid multi-branch CNN-LSTM architecture, termed HyMCL-Net, is proposed, which leverages the complementary strengths of Convolutional Neural Networks (CNNs) for spatial feature extraction and Long Short-Term Memory (LSTM) networks for temporal dependency modeling.

Ayesha Ashraf, Malik Haider Ali, Nazish Ashfaq et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.