Back to Search
Start Over
Human Action Recognition-Based IoT Services for Emergency Response Management
- Source :
- Machine Learning and Knowledge Extraction, Vol 5, Iss 1, Pp 330-345 (2023)
- Publication Year :
- 2023
- Publisher :
- MDPI AG, 2023.
-
Abstract
- Emergency incidents can appear anytime and any place, which makes it very challenging for emergency medical services practitioners to predict the location and the time of such emergencies. The dynamic nature of the appearance of emergency incidents can cause delays in emergency medical services, which can sometimes lead to vital injury complications or even death, in some cases. The delay of emergency medical services may occur as a result of a call that was made too late or because no one was present to make the call. With the emergence of smart cities and promising technologies, such as the Internet of Things (IoT) and computer vision techniques, such issues can be tackled. This article proposes a human action recognition-based IoT services architecture for emergency response management. In particular, the architecture exploits IoT devices (e.g., surveillance cameras) that are distributed in public areas to detect emergency incidents, make a request for the nearest emergency medical services, and send emergency location information. Moreover, this article proposes an emergency incidents detection model, based on human action recognition and object tracking, using image processing and classifying the collected images, based on action modeling. The primary notion of the proposed model is to classify human activity, whether it is an emergency incident or other daily activities, using a Convolutional Neural Network (CNN) and Support Vector Machine (SVM). To demonstrate the feasibility of the proposed emergency detection model, several experiments were conducted using the UR fall detection dataset, which consists of emergency and other daily activities footage. The results of the conducted experiments were promising, with the proposed model scoring 0.99, 0.97, 0.97, and 0.98 in terms of sensitivity, specificity, precision, and accuracy, respectively.
Details
- Language :
- English
- ISSN :
- 25044990
- Volume :
- 5
- Issue :
- 1
- Database :
- Directory of Open Access Journals
- Journal :
- Machine Learning and Knowledge Extraction
- Publication Type :
- Academic Journal
- Accession number :
- edsdoj.329fe939be1c44a7b47edf3bd0ce7bda
- Document Type :
- article
- Full Text :
- https://doi.org/10.3390/make5010020