Real-time personal protective equipment monitoring system

doi:10.1016/j.comcom.2012.01.005

Computer Communications

Volume 36, Issue 1, 1 December 2012, Pages 42-50

https://doi.org/10.1016/j.comcom.2012.01.005 Get rights and content

Abstract

The use of personal protective equipment (PPEs) in the construction industry is necessary to guarantee the safety of the workers. However, this equipment is not usually worn properly. Nowadays, the only control performed over the use of PPEs consists of a visual inspection. This paper introduces a novel cyber-physical system (CPS) to check in real time how the PPEs are worn by the workers. In order to perform such a control, an architecture composed of a wireless local area network and a body area network is considered. A system prototype was developed by using Zigbee and RFID technologies that support the deployment of both kinds of networks. The worker carries a microcontroller-based device that detects the presence of the PPEs and sends a report to a central unit where alerts and historical data are generated. This paper is basically aimed at introducing the monitoring system, describing its hardware and software components, and analyzing the coverage and consumption of the worker’s device.

Introduction

In recent years society has been demanding enhanced mechanisms to prevent occupational hazards. The construction industry is a field with a particular interest in this topic. In this industry workers have to follow several working rules. If they are not followed, the responsibility lies with the construction company. Some of the most important rules on a building site are related to the use of protective elements, such as helmets, gloves, boots, goggles, harness, etc. These elements are collectively known as personal protective equipment (PPE).

To reduce the accident rate in this type of work, it is required the application of technical and organizational actions. Among these actions, there are several that involve the use of PPEs to prevent harm from uncontrollable risks. Hence, PPEs are the last line of defense for the protection of workers and, therefore, one of the elements an organization should pay attention to, since if they fail, the worker can suffer serious consequences.

The main problem of a PPE-based protection policy arises when workers do not use PPEs (on purpose or not) or when they use them inappropriately. The only current way to avoid this situation is through a visual inspection by a technician. However, this solution is ineffective, since such control is performed only at specific times and it does not allow the performance of PPE traceability or real-time monitoring.

One of the solutions to this problem consists in using smart devices that are embedded in clothing, which lie in the areas of wearable computing [1] and cyber-physical systems (CPS). This paper introduces a novel system that provides real-time information on the use of PPEs. This system is able to determine whether each worker is wearing the required PPEs, monitoring their presence and warning the worker if they are not properly used. The result of the monitoring process is collected at a central server which generates historical records, alerts and any other type of events required for the proper use of the PPEs. In the system proposed each worker wears a body area network (BAN) of sensors that is able to detect the presence of a PPE adjacent to certain parts of the body.

Although the implementation presented is innovative, similar developments have been used in other wearable computing applications: healthcare, games, context awareness and ubiquitous solutions, human activity analysis [2], energy efficiency [3], wearable gestural interfacing [4] and even for monitoring everyday activities [5].

As discussed in this paper, the system introduced integrates different types of networks and technologies. On the one hand there is a mesh network that provides communications support for a real-time view of the status of workers and their PPEs. Moreover, each worker needs to carry a personal network or body area network (BAN) device able to analyze the presence and location of the PPEs used.

Given this scenario, we will show a prototype that uses RFID technology to determine when an employee makes use of a PPE, and that performs mesh network communications using Zigbee. The rest of this paper is structured as follows. Section 2 describes the problem to be solved. Section 3 shows the system architecture. Sections 4 Hardware components, 5 Software components detail the hardware and software components of the system. Section 6 explains the communications protocol and Section 7 shows the results from several performance tests. Finally, Section 8 is devoted to conclusions.

Section snippets

Problem statement

As we mentioned before, our objective is to design and develop a system to check in real time the use of PPEs in the field of construction. Since this system is going to be included in the topic of wearable computing, and taking into account the environment where it is going to be used, the new system has to cover the following goals:

•
Low cost. The system is used in an environment with several workers where each one will wear a device to monitor their PPEs. Thus, the price of each worker’s unit

System architecture

In order to have centralized information of the workers in real time, the system requires two kinds of network: a mesh network and a BAN.

Fig. 1 shows a typical structure of a mesh network where we can see three kinds of devices¹:

Coordinator
This device collects the information coming from the worker’s device, which is called “End node”. The coordinator has the following capabilities:
- •

Hardware components

In order to develop a prototype and satisfy the requirements of the system, we have decided to use standard technologies. In particular, we have used RFID for detecting tags attached to PPEs and Zigbee as the technology for the mesh network. The following subsections provide the specific details of the system components are exposed.

Microcontroller software

It is important to note that thanks to the use of an ATmega1280, the software of the microcontroller can be developed with the IDE from the Arduino project [9], which uses a programming language very similar to C/C++. The microcontroller software performs the following main tasks:

•
Initialization of the serial ports to communicate through the Zigbee module and with the RFID reader.
•
Periodical detection and validation of the RFID UIDs.
•
Reception of the configuration from the coordination node

Protocol

The system needs a protocol to enable the mesh network interaction between the end nodes and the coordinator to take place. The control flow must be very clear and precise, in order to prevent any data loss caused by typical situations that commonly occur in wireless systems, such as power failure, coverage loss, packet loss, etc. With this objective, timeout-acknowledgement mechanisms are implicitly assumed in communications, although they have not been represented in the following diagram.

Prototype tests

Several tests dealing with coverage and power consumption were done in order to evaluate prototype performance.

Conclusions

This paper has introduced a novel system to control the use of PPEs (personal protective equipment) in the construction industry, allowing the checking in real time of how workers use the PPEs.

An architecture composed of two kinds of network, a mesh network and a BAN, was presented. The mesh network is needed to transmit information gathered from devices worn by the workers. These devices, called end nodes, make use of a BAN in order to distribute several PPE detectors (readers) in the

Acknowledgment

This work has been supported by 09TMT005CT (Xunta de Galicia, Spain) and IPT-020000-2010-35 (Ministerio de Ciencia e Innovación, Spain with FEDER funds of the European Union).

References (26)

O. Amft, P. Lukowicz, From backpacks to smartphones: past, present, and future of wearable computers, in: IEEE...
Andreas Krause, Daniel P. Siewiorek, Asim Smailagic, Jonny Farringdon, “Unsupervised, Dynamic identification of...
T. Starner
Human-powered wearable computing
IBM Systems Journal
(2010)
Pranav Mistry, Pattie Maes, “SixthSense: a wearable gestural interface”, in: ACM SIGGRAPH ASIA 2009 sketches (SIGGRAPH...
C. Kidd et al.
(1999)
J. Rodas, C.J. Escudero, “Plataforma Hardware de Alta Conectividad y Muy Bajo Consumo Energético”, Patent pending...
Digi International, Last access: February 2011,...
ID Innovations, Last Access: February 2011,...
Arduino project, Last Access: February 2011,...
JSON, Last access: february 2011,...

A. Goldsmith

Wireless Communications

(2005)

A. Borrelli, C. Monti, M. Vari, F. Mazzenga, “Channel models for IEEE 802.11b indoor system design, in: IEEE...

A. Rahmati et al., “Reliability techniques for RFID-based object tracking applications”, in: Proceedings of the 37th...

Cited by (115)

In the name of safety - safety monitoring and the development of the Duty, Utility, Virtue framework for ethical consideration
2024, Safety Science
New safety monitoring technologies have begun to emerge in both research and practice. This may improve safety and health at the workplace, but may also cause worries about the implications for people exposed to the technologies. This calls for ethical considerations concerning the monitoring technologies. A need, which is not currently fulfilled. The lack of ethical considerations means that potential negative consequences of the technologies are never brought into the light of day, which means that potentially problematic technologies are developed and implemented at workplaces at the cost of worker health and safety. In order to address this issue, we revisit existing literature on monitoring technologies at work and develop the Duty, Utility, Virtue (DUV) framework for considering ethical implications of OSH technologies. We then examine nine safety monitoring studies, in order to illustrate the use of the DUV framework and show the character of ethical considerations currently taking place in this field of research.
The analysis of the nine safety monitoring studies shows that all studies had severe shortcomings in their ethical considerations and that the development and implementation of safety monitoring technologies inadvertently risk affecting both workers overview of work, their influence, their skill discretion, their safety and their physical and mental wellbeing in negative ways. All, in the name of safety.
To remedy this, we suggest employing the DUV framework may be a way for researchers and organizations to reflect on the technologies they develop, implement and study. This may help research communities and organizations/managers provide ethically well-grounded recommendations for technology implementation to the audiences and people they engage with.
Enhancing workplace safety: A flexible approach for personal protective equipment monitoring
2024, Expert Systems with Applications
Workplace safety is a prominent concern, motivating researchers across diverse disciplines to investigate valuable ways to address its challenges. However, creating an efficient system to address this issue remains a significant challenge. Since many accidents happen due to improper usage or complete removal of Personal Protective Equipment (PPE), one straightforward method for enhancing workplace security involves monitoring their usage This paper introduces an Operator Area Network (OAN) system which improves the existing solutions by increasing portability across different users and environments, non-intrusiveness and privacy. To enhance robustness in detecting the situations in which PPEs are not used correctly, we take advantage of Machine Learning to analyse the received signal strength indicator (RSSI) between PPEs in the same OAN The novelty of this work is that it does not exploit RSSI as a proxy of the distance but instead recognizes a signature of the correct wearing of the PPE By employing this system, employers can effectively ensure the proper usage of PPE devices at their worksites while also minimizing any adverse effects on workers’ comfort and reducing the setup burden for employers. The system runs a Support Vector Machine (SVM) model several times per second and employs a post-processing algorithm to enhance its initial accuracy further As a result, the system effectively reduces false positives by about 80% and swiftly detects instances of improper usage of the worker’s PPE, raising the alarm in less than seven seconds. Moreover, the post-processing algorithm can be customized to meet the specific needs of different use cases, allowing for a flexible trade-off between the detection time interval and the overall accuracy of the detection system.
Precast concrete project image dataset for deep learning object detection
2024, Developments in the Built Environment
Computer vision technology in precast concrete (PC) projects has the potential to enhance site management but faces challenges due to the lack of specialized datasets for this field. This study developed a PC components dataset for object detection (PCCODA) in four steps: component range selection, image collection, image preprocessing, and labeling. The performance of PCCODA was assessed using multiple algorithms, including You Only Look Once (YOLO), YOLO X, faster region-based convolutional neural networks (Faster R-CNN), and Double Head R-CNN. The dataset resulted in average accuracies of 0.88–0.97, average robustness of 0.84–0.96, and average detection speed of 3.64–23.3 frames per second. This performance fulfills the level required by most studies on construction automation. The applicability of the dataset was tested at a real site. This study contributes to the off-site construction project management theory and enhances productivity in PC projects by automating object detection-related tasks.
Identification of the normative use of medical protective equipment by fusion of object detection and keypoints detection
2024, Computer Methods and Programs in Biomedicine
Irregular use of personal protective equipment (PPE) seriously affects the occupational health and safety of healthcare workers, especially in large public health emergencies such as COVID-19. The danger often occurs in some complex scenarios where the use of certain equipment does not comply with the spatial rules it specifies. The single object detection-based method is difficult to effectively verify whether the worker's use of PPE is normative. Also detecting the use of six classes of PPE brings a large computational load to the task.
In this paper, we proposed an identification approach that combined human keypoints detection with deep learning object detection to help facilitate the monitoring of healthcare workers' standard PPE use. We used YOLOv4 as the baseline model for PPE detection and MobileNetv3 as the backbone of the detector to reduce the computational effort. In addition, High-Resolution Net (HRNet) was the benchmark for keypoints detection, characterizing the coordinates of 25 key points in the human body. Generalized Intersection over Union (GIoU) was used to establish the association between PPEs and key points, and by calculating the matching score between a PPE and the corresponding body bounding boxes, the authenticity of the PPE specification could be effectively inferred.
The proposed detector is able to identify whether a healthcare worker is normatively using multiple equipment with a higher precision (95.81 %), recall (96.38 %), and F1-score (96.09 %). Meanwhile, the number of parameters (2.87 M) and the size of the model (6.4 MB) are also more lightweight than other comparative detectors.
Our approach is more reliable for reasoning about the normality of personal protection for healthcare workers in some complex scenarios than a single object detection-based approach. The developed identification framework provides a new automated monitoring solution for protection management in healthcare, and the modular design brings more flexible applications for different medical operation scenarios.
Smart Personal Protective Equipment (PPE) for construction safety: A literature review
2024, Safety Science
Construction projects are risky environments which can increase the number of fatal and non-fatal accidents. The development of Personal Protective Equipment (PPE) is one of the beneficial endeavors to control the number of accidents. Since traditional PPEs have not reached full success in controlling occupational injuries, the collection and analysis of safety data were introduced as a vital factor in comprehensive safety management of construction sites. With the widespread use of advanced technologies in this industry, questions have arisen about impacts of the smart PPE on construction safety. This study thus reviews high-tech PPEs for the construction industry and discusses possible benefits, challenges, and structures to explore their capacity for data collection from personnel and construction sites to reduce the risks and hazards.
Computer vision applications in offsite construction
2023, Automation in Construction
The field of computer vision has undergone rapid growth in recent years, yet the use of computer vision in offsite construction remains an under-researched area of study. Given the current momentum around the adoption of this technology, this article presents a scoping review of computer vision applications in offsite construction. It provides (1) summaries of and discussions on the research areas in which computer vision is used in offsite construction, the computer vision tasks undertaken, the algorithms used, and related performance evaluation results and limitations, (2) a tabulated summary of performance-related terms commonly used in computer vision applications (to facilitate understanding of the performance evaluation results reported in the review), and (3) potential avenues of future research. The review provides a useful point of reference for practitioners and researchers in the offsite construction industry, aiding their understanding of current practice, limitations, research gaps, and potential opportunities to apply computer vision.

View all citing articles on Scopus

View full text