• 국제학술발표논문집
• /
• The 6th International Conference on Construction Engineering and Project Management
• /
• pp.612-613
• /
• 2015

As a construction project is recently becoming large-scaled and complex, construction process plan and management for successful performance of a construction project has become more important. Especially a reasonable estimation plan of activity duration is required because the activity duration is directly related to the determination of the entire project duration and budget. However, the activity duration is used to estimate by the experience of a construction manager and past construction records. Furthermore, the prediction of activity duration is more difficult because there is some uncertainty caused by various influencing factors in a construction project. This study suggests an estimation model of construction activity duration using neural network theory for a more systematic and objective estimation of each activity duration. Because suggested model estimates the activity duration by a reasonable schedule plan, it is expected to reduce the error between planning duration and actual duration in a construction project. And it can be a more systematic estimation method of activity duration comparing to the estimation method by experience of project manager.

• 국제학술발표논문집
• /
• The 8th International Conference on Construction Engineering and Project Management
• /
• pp.41-49
• /
• 2020

Concurrent construction offers considerable improvement for shorten the project duration of its production process. Therefore, standardized concurrent construction is widely applied in building construction projects. However, resources planning for standardized concurrent construction project is manually developed by construction manager. This practice is not effective since it is time-consuming and error-prone for managers to identify all project-specific information, distinguish different activity-resource types, interpret these types and analyze how they affect resource allocated on an ad hoc basis. Therefore, this research investigates the opportunity for leveraging activity modeling to enable automated resource planning for standardized concurrent construction during project development, with identifying the characteristics of construction activities under standardized concurrent planning and determining the activity-resources types that affects resource planning. Both will function as a basis for modeling these construction activities in a computer-interpretable manner and for automation in resource planning.

• 국제학술발표논문집
• /
• The 3th International Conference on Construction Engineering and Project Management
• /
• pp.1100-1106
• /
• 2009

General contractors' overhead costs are increasing relative to direct costs. However, it is difficult to apply the traditional activity-based costing directly to the construction site overhead costing because the resource consumption rate per each activity is varied depending on the attributes of activities. The research develops a methodology of hybrid cost allocation system when resources are assigned to cost objects unlike the traditional activity-based costing. The study also develops a database program and demonstrates how it can be applied to the construction projects using a case study.

• 국제학술발표논문집
• /
• The 8th International Conference on Construction Engineering and Project Management
• /
• pp.443-452
• /
• 2020

Worker's awkward postures and unreasonable physical load can be corrected by monitoring construction activities, thereby increasing the safety and productivity of construction workers and projects. However, manual identification is time-consuming and contains high human variance. In this regard, an automated activity recognition system based on inertial measurement unit can help in rapidly and precisely collecting motion data. With the acceleration data, the machine learning algorithm will be used to train classifiers for automatically categorizing activities. However, input acceleration data are extracted either from designed experiments or simple construction work in previous studies. Thus, collected data series are discontinuous and activity categories are insufficient for real construction circumstances. This study aims to collect acceleration data during long-term continuous work in a construction project and validate the feasibility of activity recognition algorithm with the continuous motion data. The data collection covers two different workers performing formwork at the same site. An accelerator, as well as portable camera, is attached to the worker during the entire working session for simultaneously recording motion data and working activity. The supervised machine learning-based models are trained to classify activity in hierarchical levels, which reaches a 96.9% testing accuracy of recognizing rest and work and 85.6% testing accuracy of identifying stationary, traveling, and rebar installation actions.

• 국제학술발표논문집
• /
• The 1th International Conference on Construction Engineering and Project Management
• /
• pp.917-923
• /
• 2005

Scheduling is one of the main functions in construction project to determine the sequence of activities necessary to complete a project. The scheduling techniques provide important information crucial to a project's success. Highway construction project the paving activity can be considered a linear activity. Linear scheduling technique may be better suited for linear projects than other scheduling techniques. A new type of scheduling in linear project is calling Linear Scheduling Model (LSM). The Project monitoring and controlling is very ease to identify that all the stage of linear project and have more advantages.

• 국제학술발표논문집
• /
• The 9th International Conference on Construction Engineering and Project Management
• /
• pp.877-885
• /
• 2022

Vision-based activity recognition has been widely attempted at construction sites to estimate productivity and enhance workers' health and safety. Previous studies have focused on extracting an individual worker's postural information from sequential image frames for activity recognition. However, various trades of workers perform different tasks with similar postural patterns, which degrades the performance of activity recognition based on postural information. To this end, this research exploited a concept of human-object interaction, the interaction between a worker and their surrounding objects, considering the fact that trade workers interact with a specific object (e.g., working tools or construction materials) relevant to their trades. This research developed an approach to understand the context from sequential image frames based on four features: posture, object, spatial features, and temporal feature. Both posture and object features were used to analyze the interaction between the worker and the target object, and the other two features were used to detect movements from the entire region of image frames in both temporal and spatial domains. The developed approach used convolutional neural networks (CNN) for feature extractors and activity classifiers and long short-term memory (LSTM) was also used as an activity classifier. The developed approach provided an average accuracy of 85.96% for classifying 12 target construction tasks performed by two trades of workers, which was higher than two benchmark models. This experimental result indicated that integrating a concept of the human-object interaction offers great benefits in activity recognition when various trade workers coexist in a scene.

• 국제학술발표논문집
• /
• The 7th International Conference on Construction Engineering and Project Management Summit Forum on Sustainable Construction and Management
• /
• pp.80-88
• /
• 2017

Although hazard identification is one of the most important steps of safety management process, numerous hazards remain unidentified in the construction workplace due to the dynamic environment of the construction site and the lack of available resource for visual inspection. To this end, our previous study proposed the collective sensing approach for safety hazard identification and showed the feasibility of identifying hazards by capturing collective abnormalities in workers' walking patterns. However, workers generally performed different activities during the construction task in the workplace. Thereby, an additional process that can identify the worker's walking activity is necessary to utilize the proposed hazard identification approach in real world settings. In this context, this study investigated the feasibility of identifying walking activities during construction task using Wearable Inertial Measurement Units (WIMU) attached to the worker's ankle. This study simulated the indoor masonry work for data collection and investigated the classification performance with three different machine learning algorithms (i.e., Decision Tree, Neural Network, and Support Vector Machine). The analysis results showed the feasibility of identifying worker's activities including walking activity using an ankle-attached WIMU. Moreover, the finding of this study will help to enhance the performance of activity recognition and hazard identification in construction.

• 국제학술발표논문집
• /
• The 5th International Conference on Construction Engineering and Project Management
• /
• pp.111-114
• /
• 2013

Underground construction requires long construction duration and a variety of equipment, and environmental management and improvement of its activities are considered necessary. For the purpose of the environmental improvement of underground construction activities, the appropriate development of technologies to reduce generated pollutants is mandatory. However, the analysis of the needs of technology development and the evaluation of development priorities should take precedence. In this research, the needs for the improvement of each construction activity are analyzed as a preliminary study for a proposed technology development plan to improve the environmental performance of underground construction. Firstly, environmental problem factors caused by underground construction activities are determined while underground construction types, methods, and activities are classified. A questionnaire survey to determine the needs for the improvement of each activity is then carried out. The survey indicated that the most urgent activity to be improved is that of cutting excavation, which causes environmental problems associated with flying dust. This study could be used as a basis for a technology development plan for the environmental improvement of underground construction activities. The result of this study, the priority of improvement needs, contributes to the effective allocation of a limited Research and Development (R&D) budget.

• 국제학술발표논문집
• /
• The 4th International Conference on Construction Engineering and Project Management Organized by the University of New South Wales
• /
• pp.504-509
• /
• 2011

Recently, construction projects are very complicated and diverse such as high-rise buildings and big bridges, etc. These complicated projects call for a system which can effectively generate productive ideas and activities. Value Engineering (V.E.) activity within construction projects is a necessity for systematic design management and to improve construction ability. This need in the construction industry has required a regular implementation of VE into construction projects. For this reason; America, South Korea, and some other nations have adopted VE applications which control the baseline investments of the construction projects. The process of VE activity is a preferred system and a reasonable alternative. In particular, idea generation within these projects is an important stage in the VE job plan. In this study, VE idea patterns are extracted through best practice analysis from VE cases of road construction projects. Next, we suggest an idea hierarchy model to be used in conjunction with VE idea patterns. This model is supported by reasonable idea generation in VE activity of construction projects. Finally, this model could possibly be the outcome of successful VE results.

• 대한건축학회논문집:구조계
• /
• 제36권3호
• /
• pp.135-145
• /
• 2020

Recently, the disaster rate of the construction industry has increased with high-rise, and complexity of the building, unlike the decrease in the disaster rate in other industries. Although risk assessment is performed to reduce the occurrence of disasters, it is difficult to estimate the risks accurately due to activity in which no disaster has occurred, and inconsistencies in the level of details of work. In this study, in order to evaluate the risk of the major activity for the apartment construction work, the activity was identified by referring to the risk assessment model of construction industry type by the KOSHA. The construction work types and activities were consistently organized in level of work into nine work types and 82 activities were through experts consultation. Analyzing the disaster types that occurred during work through KOSHA disaster cases, calculating the probability of disaster occurrence according to the type of disaster, and combining the probability of disaster with the severity of disaster to estimate the risk assessment method was presented. Using the daily report of the construction site of the apartment, the results of a case study confirmed the validity of the risk calculation method presented in this study.