Full metadata record
| DC Field | Value | Language |
|---|---|---|
| dc.contributor | Department of Building and Real Estate | en_US |
| dc.contributor.advisor | Li, Heng (BRE) | en_US |
| dc.creator | Guo, Runhao | - |
| dc.identifier.uri | https://theses.lib.polyu.edu.hk/handle/200/13207 | - |
| dc.language | English | en_US |
| dc.publisher | Hong Kong Polytechnic University | en_US |
| dc.rights | All rights reserved | en_US |
| dc.title | Sensor-based data collection and analysis of construction worker activities | en_US |
| dcterms.abstract | The activity data derived from construction workers not only indicates their physical health and safety status but also provides indirect insights into the efficiency and quality defects of construction projects. Activity data encompasses both kinematic and physiological data. Kinematic data primarily involves the spatial and temporal relationships within body movements, including position, velocity, acceleration, and angles. Simultaneously, physiological data encompass vital aspects such as heart rate, oxygen consumption, and electromyographic activity. The deployment of sensors for real-time, high-precision data collection of construction worker activity holds the potential to greatly enhance productivity, quality, and safety within the construction sector. | en_US |
| dcterms.abstract | However, previous research focused on monitoring the activities of construction workers has predominantly depended on the subjective assessments of supervision engineers, leading to low accuracy and high costs. Those approaches prove inadequate in satisfying the increasing regulatory demands in the dynamic and intricate construction environments. Although the adoption of sensor-based data collection holds promise, it is beset by numerous limitations. Apart from its insufficient accuracy and stability in use on intricate construction sites, it rarely delves into the hidden information reflected in the behavior of construction workers. | en_US |
| dcterms.abstract | This thesis aims to explore intelligent sensor-based methods for monitoring the activities of construction workers, and then seek valuable insights into worker behavior to improve the construction management level. The ultimate goal is to enhance labor productivity, improve construction quality, and ensure worker safety. Specifically, this study begins with a comprehensive literature review of previous research. Then, three intelligent sensing scenarios are proposed to illustrate the conversion of real-time and precise information regarding worker activities into actionable construction guidance. The first scenario focuses on labor input assessment, employing the inertial measurement unit (IMU) for counting construction activity motions and measuring labor input. The second scenario targets construction quality management, utilizing cameras installed on the site. It formulates a computer vision (CV) based approach to discern the sequence of worker activities, ensuring the quality of construction projects by verifying the accuracy of construction procedures. The third scenario prioritizes worker safety, initially employing non-intrusive wireless sensing methods that utilize channel state information (CSI) to detect hazardous behaviors. Subsequently, a project is conducted to identify the common issue of data artifacts in physiological data collected using wearable sensing devices (WSDs), aiming to improve the quality of activity data. | en_US |
| dcterms.abstract | Based on a series of experiments and field tests, this thesis has made several significant contributions. Firstly, it innovatively introduces a novel labor measurement method based on IMU and hand tools. This approach facilitates the quantification of labor inputs from workers while respecting their privacy. Secondly, the thesis proposed a CV-based activity sequence recognition method that ensures the quality of concealed work with higher activity recognition accuracy than previous methods. Thirdly, a new low-cost CSI-based wireless sensing approach has been developed to identify hazardous behaviors among construction workers. Fourthly, the thesis provides an in-depth evaluation of the current approaches used to evaluate data and remove artifacts from physiological measurements obtained by WSDs during construction-related tasks. In summary, this thesis contributes to the construction field by advancing the collection and evaluation of construction worker activity data through sensor technology, thereby improving labor productivity, construction quality, and worker safety. | en_US |
| dcterms.extent | 177 pages : color illustrations | en_US |
| dcterms.isPartOf | PolyU Electronic Theses | en_US |
| dcterms.issued | 2024 | en_US |
| dcterms.educationalLevel | Ph.D. | en_US |
| dcterms.educationalLevel | All Doctorate | en_US |
| dcterms.LCSH | Construction industry -- Data processing | en_US |
| dcterms.LCSH | Construction workers -- Health and hygiene | en_US |
| dcterms.LCSH | Building -- Safety measures | en_US |
| dcterms.LCSH | Hong Kong Polytechnic University -- Dissertations | en_US |
| dcterms.accessRights | open access | en_US |
Copyright Undertaking
As a bona fide Library user, I declare that:
- I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
- I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
- I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.
By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.
Please use this identifier to cite or link to this item:
https://theses.lib.polyu.edu.hk/handle/200/13207