Jaeho Son

Dr. Jaeho Son

Hongik University, Sejong City, 30016, Korea.

Research Focus & Metrics

Academic Career Length

17Years (2010-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
28 September 2022 in Applied Sciences
Verified
Journal Article
Open access
PDF file
JSJaeho Son
Jaeho Son
SYSungchul Yang
Sungchul Yang
The goal of this work is to show how machine learning models, such as the random forest, neural network, gradient boosting, and AdaBoost models, can be used to forecast the fatigue life (N) of plain concrete under uniaxial compression. Here, we developed our final machine learning model by generating the following three data files from the original data used in the work of Zhang et al.: (a) grouped data with the same input variable value and different output variable logN value, (b) data excluding outliers selected by three or more outlier detection methods; (c) average data excluding outliers, created by averaging the grouped data after excluding outliers from among the grouped data. Excluding the sustained strength of the concrete variable, originally treated as the seventh input variable in the work of Zhang et al., resulted in improving the determination coefficient (R2) values. Moreover, the gradient boosting model showed a high R2 value at 0.753, indicating a high accuracy in predicting outcomes. Further analysis using data excluding outliers shows that the R2 value increased to 0.803. Moreover, the average data excluding outliers provided the best R2 value at 0.915. Finally, a permutation feature importance (PFI) analysis was carried out to determine the strength of the relationship between the feature and the target value for the gradient boosting model. The analysis results showed that the maximum stress level (Smax) and loading frequency (f) were the most significant input variables, followed by compressive strength (f′c) and maximum to minimum stress ratio (R). Shape and height to width ratio (h/w) were the features with a non-significant influence on the model. This trend was previously confirmed by a Pearson and Spearman correlation analysis.

1 March 2013 in KSCE Journal of Civil Engineering
Verified
Journal Article
Open access
PDF file
JSJaeho Son
Jaeho Son
Taehoon HongTaehoon Hong
Taehoon Hong
SLSangyoub Lee
Sangyoub Lee
Numerous Time-Cost Trade-Off (TCTO) models have been developed to identify the best combination of time and cost in a critical path network. Although there are four relationships in the critical path network, most of the models developed so far have considered only the Finish-Start (F-S) relationship. Thus, an advanced TCTO model that considers all four relationships between activities was developed in this study to accurately present a project, and is presented in this paper. The model also takes into account the lag time between activities. Previous TCTO models minimize the total project cost based on the given crash scenario. Moreover, to enhance the practicality, the model was developed to work with various TCTO scenarios such as continuous, discrete, and even mixed (continuous + discrete). The combined scenario reflects the most realistic situation. Two independent scenarios cannot be combined without mathematical modifications since a rudimentary mixing of two scenarios may provide an incorrect solution. A new formulation technique is introduced to merge the two independent scenarios mathematically and it guarantees the optimal solution.

1 September 2014 in KSCE Journal of Civil Engineering
Verified
Journal Article
Open access
PDF file
SHSe-In Hwang
Se-In Hwang
JSJaeho Son
Jaeho Son
SLSeung-Hyun Lee
Seung-Hyun Lee
Due to the large sizes and repetitive processes of an Earthwork operation, it is important to acquire an efficient plan starting from the early stages of operation. In order to have an efficient earthwork plan, the minimization of the earthmoving distance and the optimization of the required equipment must be included in the model. This study develops a planning model for earth work and considers them comprehensively. First, the optimized route is chosen in the form of the vector diagram by the developed software POEM while the possible equipment combinations are found by Web-Cyclone’s sensitivity analysis. Then, the data of the optimized route and the possible combinations are input to the proposed planning model for earth work. Genetic Algorithm is used to develop the model since the size of the search space is exponentially growing. The model gives a viable schedule and the field engineer can utilize the schedule to manage the earthwork operation with more efficiency.

3 February 2021 in Applied Sciences
Verified
Journal Article
Open access
PDF file
SLSeung-Hyun Lee
Seung-Hyun Lee
JSJaeho Son
Jaeho Son
It has been pointed out that the act of carrying a heavy object that exceeds a certain weight by a worker at a construction site is a major factor that puts physical burden on the worker’s musculoskeletal system. However, due to the nature of the construction site, where there are a large number of workers simultaneously working in an irregular space, it is difficult to figure out the weight of the object carried by the worker in real time or keep track of the worker who carries the excess weight. This paper proposes a prototype system to track the weight of heavy objects carried by construction workers by developing smart safety shoes with FSR (Force Sensitive Resistor) sensors. The system consists of smart safety shoes with sensors attached, a mobile device for collecting initial sensing data, and a web-based server computer for storing, preprocessing and analyzing such data. The effectiveness and accuracy of the weight tracking system was verified through the experiments where a weight was lifted by each experimenter from +0 kg to +20 kg in 5 kg increments. The results of the experiment were analyzed by a newly developed machine learning based model, which adopts effective classification algorithms such as decision tree, random forest, gradient boosting algorithm (GBM), and light GBM. The average accuracy classifying the weight by each classification algorithm showed similar, but high accuracy in the following order: random forest (90.9%), light GBM (90.5%), decision tree (90.3%), and GBM (89%). Overall, the proposed weight tracking system has a significant 90.2% average accuracy in classifying how much weight each experimenter carries.

20 December 2010 in Journal of the Korea Institute of Building Construction
Verified
Journal Article
Closed access
OKO-Bin Kwon
O-Bin Kwon
JSJaeho Son
Jaeho Son
SLSeung-Hyun Lee
Seung-Hyun Lee

7 January 2017 in Sustainability
Verified
Journal Article
Open access
PDF file
SLSeung Hak Lee
Seung Hak Lee
JSJaeho Son
Jaeho Son
SLSeung-Hyun Lee
Seung-Hyun Lee
Earthwork in road construction projects is the major activity that accounts for about 20%–30% of the total construction cost, and the internal/external hauling plan is the key factor for determining the successful completion of the project. However, the hauling plan at the site, which includes the selection of the dump site and borrow pit, is usually determined by the site manager’s subjective and empirical discretion alone. Therefore, this study has developed a prototype model that provides the optimal internal/external hauling plan. It includes the determination of the most economical dump sites and borrow pits (location and number) among other candidate sites as well. The transshipment problem theory is incorporated into the optimized algorithm with the consideration of various factors affecting earthwork cost. Direct costs from an optimized transport based on an existing model against another from this model were compared to prove its feasibility. As a result, the reduction of earthwork cost including the dump site/borrow pits reached 4%–8%. This result implies that this prototype model would also be useful in reducing both the earthwork cost and the occurrence of exhaust gas from earthwork equipment by providing optimized transportation paths.