event

PhD Defense by Kinam Kim

Primary tabs

School of Civil and Environmental Engineering 

 

Ph.D. Thesis Defense Announcement 

Title of defense 

By 

Kinam Kim

Advisor: 

Dr. Yong K. Cho (CEE)

Committee Members: 

Dr. Yang Wang (CEE), Dr. Eric Marks (CEE), Dr. Jun Ueda (ME), and Dr. Inbae Jeong (ME - NDSU)
 

Date & Time: Tuesday May 3, 2022, at 10 am

Location: https://bluejeans.com/509321684/0991?src=calendarLink

 

Construction tasks involve various activities composed of one or more body motions. As construction projects are labor-intensive and heavily rely on manual tasks, understanding the ever-changing behavior and activities is essential to manage construction workers effectively regarding their safety and productivity. While several research efforts have shown promising results in automated motion and activity recognition of the workers using motion sensors, there is still a lack of understanding about how motion sensors' quantity and their locations affect the performance of the recognition, which can contribute to improving the recognition performance and reducing the implementation cost. Moreover, further research is necessary to seek a motion recognition model that accurately identifies various motions using motion sensors attached to the workers' bodies. Furthermore, although detection-based approaches have shown a noticeable performance in identifying posture-related safety hazards, few efforts have been made to directly obtain labor productivity from workers' behavior because this requires the discretization of continuous movements to estimate a production amount. 
To address these challenges, this study proposes artificial intelligence (AI)-based methods for effectively and efficiently recognizing various motions of individual construction workers and predicting their labor productivity by using wearable motion sensors and deep learning approaches. The development of the motion recognition method using a deep learning approach includes the evaluation of the effectiveness of the quantity and locations of motion sensors to maximize the AI-based motion recognition methods and sensor implementation efficiency. The evaluation is conducted by generating different datasets containing motion sensor data collected from the wearable motion sensors located on different body parts. By using the performance of five machine learning models trained using the datasets, the evaluation formula is provided to obtain quantitative contribution scores of each node, which indicates the relative impacts of using different nodes on the performance of AI-based motion recognition algorithms. With the formula, the desired quantity and locations of motion sensors are identified. Based on the findings, the long short-term memory (LSTM) network for recognizing construction workers' motions is developed. The LSTM network classifies various motions of the workers that can be utilized as primitive elements for monitoring the workers regarding safety and productivity. Multiple case studies are conducted to validate the technical and practical feasibility of the developed network. Furthermore, this study presents an automated labor productivity prediction method that estimates the production amount of individual workers and predicts their labor productivity. The production amount is derived by discretizing activities classified using an LSTM network and a dynamic time warping (DTW) technique. With the proposed methods, it is expected that the individual workers' behavior and working conditions can be automatically monitored and managed without excessive manual observation. Thus, this study contributes to building the theoretical and practical

Status

  • Workflow Status:Published
  • Created By:Tatianna Richardson
  • Created:04/22/2022
  • Modified By:Tatianna Richardson
  • Modified:04/22/2022

Categories

Keywords