• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.248-248
• /
• 2023

In recent years, the number of landslides in Korea has been increasing due to extreme weather events such as localized heavy rainfall and typhoons. Landslides often occur with debris flows, land subsidence, and earthquakes. They cause significant damage to life and property. 64% of Korea's land area is made up of mountains, the government wanted to predict landslides to reduce damage. In response, the Korea Forest Service has established a 'Landslide Information System' to predict the likelihood of landslides. This system selects a total of 13 landslide factors based on past landslide events. Using the LR technique (Logistic Regression) to predict the possibility of a landslide occurrence and the accuracy is known to be 0.75. However, most of the data used for learning in the current system is on landslides that occurred from 2005 to 2011, and it does not reflect recent typhoons or heavy rain. Therefore, in this study, we will apply a total of six machine learning techniques (KNN, LR, SVM, XGB, RF, GNB) to predict the occurrence of landslides based on the data of Inje, Gangwon-do, which was recently produced by the National Institute of Forest. To predict the occurrence of landslides, it is necessary to process converting landslide events and factors data into a suitable form for machine learning techniques through ArcGIS and Python. In addition, there is a large difference in the number of data between areas where landslides occurred or not. Therefore, the prediction was performed after correcting the unbalanced data using Tomek Links and Near Miss techniques. Moreover, to control unbalanced data, a model that reflects soil properties will use to remove absolute safe areas.

• Computers and Concrete
• /
• v.32 no.2
• /
• pp.119-138
• /
• 2023

Concrete carbonation is a prevalent phenomenon that leads to steel reinforcement corrosion in reinforced concrete (RC) structures, thereby decreasing their service life as well as durability. The process of carbonation results in a lower pH level of concrete, resulting in an acidic environment with a pH value below 12. This acidic environment initiates and accelerates the corrosion of steel reinforcement in concrete, rendering it more susceptible to damage and ultimately weakening the overall structural integrity of the RC system. Lower pH values might cause damage to the protective coating of steel, also known as the passive film, thus speeding up the process of corrosion. It is essential to estimate the carbonation factor to reduce the deterioration in concrete structures. A lot of work has gone into developing a carbonation model that is precise and efficient that takes both internal and external factors into account. This study presents an ML-based adaptive-neuro fuzzy inference system (ANFIS) approach to predict the carbonation depth of fly ash (FA)-based concrete structures. Cement content, FA, water-cement ratio, relative humidity, duration, and CO2 level have been used as input parameters to develop the ANFIS model. Six performance indices have been used for finding the accuracy of the developed model and two analytical models. The outcome of the ANFIS model has also been compared with the other models used in this study. The prediction results show that the ANFIS model outperforms analytical models with R-value, MAE, RMSE, and Nash-Sutcliffe efficiency index values of 0.9951, 0.7255 mm, 1.2346 mm, and 0.9957, respectively. Surface plots and sensitivity analysis have also been performed to identify the repercussion of individual features on the carbonation depth of FA-based concrete structures. The developed ANFIS-based model is simple, easy to use, and cost-effective with good accuracy as compared to existing models.

• Steel and Composite Structures
• /
• v.46 no.3
• /
• pp.385-401
• /
• 2023

Steel is becoming increasingly popular due to its high strength, excellent ductility, great assembly performance, and recyclability. In reality, steel structures serving for a long time in atmospheric, industrial, and marine environments inevitably suffer from corrosion, which significantly decreases the durability and the service life with the exposure time. For the mechanical properties of corroded steel, experimental studies are mainly conducted. The existing numerical analyses only evaluate the mechanical properties based on corroded morphology at the isolated time-in-point, ignoring that this morphology varies continuously with corrosion time. To solve this problem, the relationships between pit depth expectation, standard deviation, and corrosion time are initially constructed based on a large amount of wet-dry cyclic accelerated test data. Successively, based on that, an in-situ pitting evolution method for evaluating the residual tensile strength of corroded steel is proposed. To verify the method, 20 repeated simulations of mass loss rates and mechanical properties are adopted against the test results. Then, numerical analyses are conducted on 135 models of corrosion pits with different aspect ratios and uneven corrosion degree on two corroded surfaces. Results show that the power function with exponents of 1.483 and 1.091 can well describe the increase in pit depth expectation and standard deviation with corrosion time, respectively. The effect of the commonly used pit aspect ratios of 0.10-0.25 on yield strength and ultimate strength is negligible. Besides, pit number ratio α equating to 0.6 is the critical value for the strength degradation. When α is less than 0.6, the pit number increases with α, accelerating the degradation of strength. Otherwise, the strength degradation is weakened. In addition, a power function model is adopted to characterize the degradation of yield strength and ultimate strength with corrosion time, which is revised by initial steel plate thickness.

• Computers and Concrete
• /
• v.30 no.5
• /
• pp.301-310
• /
• 2022

Cement-based sensors have been widely used as structural health monitoring systems, however, their long-term sensing performance have not actively investigated. In this study, a deep learning-based methodology is adopted to predict the long-term piezoresistive properties of cement-based sensors. Samples with different multi-walled carbon nanotube contents (0.1, 0.3, and 0.5 wt.%) are fabricated, and piezoresistive tests are conducted over 10,000 loading cycles to obtain the training data. Time-dependent degradation is predicted using a modified long short-term memory (LSTM) model. The effects of different model variables including the amount of training data, number of epochs, and dropout ratio on the accuracy of predictions are analyzed. Finally, the effectiveness of the proposed approach is evaluated by comparing the predictions for long-term piezoresistive sensing performance with untrained experimental data. A sensitivity of 6% is experimentally examined in the sample containing 0.1 wt.% of MWCNTs, and predictions with accuracy up to 98% are found using the proposed LSTM model. Based on the experimental results, the proposed model is expected to be applied in the structural health monitoring systems to predict their long-term piezoresistice sensing performances during their service life.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.13 no.6
• /
• pp.2641-2647
• /
• 2012

Quality and sensory characteristics such as microbial count, pH, acidity, flavor, taste, color and overall acceptance of bamboo shoot pickle cured with red pepper paste and bamboo shoot pickle cured with soy sauce paste made of Maengjong bamboo shoots were investigated during a long-term storage at different temperature (at $25^{\circ}C$, $35^{\circ}C$ and $45^{\circ}C$). Microbial contamination was not observed, and water content did not showed significant change in all samples of both pickles during the whole storage period of 30 days, regardless of storage temperature. At $25^{\circ}C$, all sensory characteristics of bamboo shoot-red pepper paste pickle did not show a significant change for 30 d. However, at $35^{\circ}C$ and $45^{\circ}C$, the flavor, taste and color of bamboo shoot-red pepper paste pickle did not change remarkably, but the overall acceptance significantly changed from the beginning of storage. Bamboo shoot-soy sauce pickle did not give a significant change in flavor, taste and overall acceptance at $25^{\circ}C$, $35^{\circ}C$ and $45^{\circ}C$. However a remarkable change in color started to be shown at 25 d in case of storage at $45^{\circ}C$. Overall acceptance and color were selected as indicating parameters for the shelf-life estimation of bamboo shoot-red pepper paste pickle and bamboo shoot-soy sauce pickle, respectively. Based on room temperature storage and delivery at $20^{\circ}C$, the shelf-life of bamboo shoot-red pepper paste pickle and bamboo shoot-soy sauce pickle were determined as 308 d (about 10 month) and 447 d (about 14 month), respectively.

• Journal of the Korea Concrete Institute
• /
• v.16 no.5 s.83
• /
• pp.621-626
• /
• 2004

The use of blast-furnace slag (BFS) in making not only normal concrete but also high-performance concrete has several advantages with respect to workability, long-term strength and durability. However, slag concrete tends to show more shrinkage than normal concrete, especially autogenous shrinkage. High autogenous shrinkage would result in severe cracking if they are not controlled properly. Therefore, in order to minimize the shrinkage stress and to ensure the service life of concrete structures, the autogenous shrinkage behavior of concrete containing BFS should be understood. In this study, small prisms made of concrete with water-binder (cement+BFS) ratio (W/B) ranging from 0.27 to 0.42 and BFS replacement level of $0\%$, $30\%$, and $50\%$, were prepared to measure the autogenous shrinkage. Based on the test results, thereafter, material constants in autogenous shrinkage prediction model were determined. In particular, an effective autogenous shrinkage defined as the shrinkage that contributes to the stress development was introduced. Moreover, an estimation formula of the 28-day effective autogenous shrinkage was proposed by considering various W/B's. Test results showed that autogenous shrinkage increased with replacement level of BFS at the same W/B. Interestingly, the increase of autogenous shrinkage is dependent on the W/B at the same content of BFS; the lower W/B, the smaller increasing rate. In concluding, it is necessary to use the combination of other mineral admixtures such as shrinkage reducing admixture or to perform sufficient moisture curing on the construction site in order to reduce the autogenous shrinkage of BFS concrete.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.24 no.1
• /
• pp.92-111
• /
• 2021

As fine dust negatively affects disease, industry and economy, the people are sensitive to fine dust. Therefore, if the occurrence of fine dust can be predicted, countermeasures can be prepared in advance, which can be helpful for life and economy. Fine dust is affected by the weather and the degree of concentration of fine dust emission sources. The industrial sector has the largest amount of fine dust emissions, and in industrial complexes, factories emit a lot of fine dust as fine dust emission sources. This study targets regions with old industrial complexes in local cities. The purpose of this study is to explore the factors that cause fine dust and develop a predictive model that can predict the occurrence of fine dust. weather data and fine dust data were used, and variables that influence the generation of fine dust were extracted through multiple regression analysis. Based on the results of multiple regression analysis, a model with high predictive power was extracted by learning with a machine learning regression learner model. The performance of the model was confirmed using test data. As a result, the models with high predictive power were linear regression model, Gaussian process regression model, and support vector machine. The proportion of training data and predictive power were not proportional. In addition, the average value of the difference between the predicted value and the measured value was not large, but when the measured value was high, the predictive power was decreased. The results of this study can be developed as a more systematic and precise fine dust prediction service by combining meteorological data and urban big data through local government data hubs. Lastly, it will be an opportunity to promote the development of smart industrial complexes.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.16 no.6
• /
• pp.295-303
• /
• 2016

The purposes of this study are to describe the process for the instrument construction and the development of scales on rating college students' adaptability and to analyze the technical qualities of the test. The primary goal of this study is to inform students and institutions what is needed to college student's adjustment process into university and college life. The scales are tested by specialty group and statistical methods, and finally composed of 142 items, which measures 8 scales, the academic integration, the social integration into college, career identity, emotional stability, learning condition's stability, relationship with professors, satisfaction degree of educational service, satisfaction degree of college education. This study analyzed 1,959 students' responses from 4 colleges and universities. This study confirms that the scales which this study developed show high concurrent evidence with the college student's adaptability inventory for Korean university and college students based on various development process, specially rapid great change of college. The result of factor analysis shows the evidence based on internal structures of the scales. The Cronbach's ${\alpha}$ of the subscales is .965, from 742 to .937. The prediction model to determine the possibility of dropout by 7 scales is statistically significant in .05, except learning condition's stability. According to CFA Model, RMSEA= .08~.09. dependence factor variance are explained by this study's CFA model. In conclusion, this study confirms that the scales which this study developed are valid and reliable instrument for Korean university and college students to predict their adaptability to college.

• Fire Science and Engineering
• /
• v.27 no.3
• /
• pp.85-93
• /
• 2013

Modern fire fighting jobs have been expanded to include areas of rescue, emergency medical service as well as conventional fire suppression, so that load for fire fighting jobs has been increased. Specifically, musculoskeletal disorders (MSDs) such as low back injury have been considered as one of major industrial hazards in heavy manual material handling during fire fighting jobs. This study tried to evaluate risk levels and to prepare background for reducing risk levels associated with heavy manual material handling during fire fighting jobs. This study applied two major tools in evaluating heavy manual material handling jobs which were NLE (NIOSH Lifting Equation) and 3DSSPP (3D Static Strength Prediction Program). A risk index in terms of heavy manual material handling during fire fighting jobs was identified. This index consisted of seven risk levels ranged from nine points (the first level) to three points (the seventh level). There was no job associated with the first level (the highest risk level) of index. There was only one job (life saving job) belonging to the second level (the second highest risk level) of index. The third level had jobs such as usage of destruction equipment and lifting patient. A total of basic eighteen jobs was categorized into six different levels (2nd-7th levels) of index. The outcome of the study could provide a good basis for conducting job intervention, preparing good equipment and developing good education program in order to prevent and reduce MSDs including low back injury of fire fighting jobs.

• Journal of the Korea Concrete Institute
• /
• v.17 no.2 s.86
• /
• pp.179-189
• /
• 2005

Corrosion of steel due to chloride attack is a major concern in reinforced concrete structures which are located in the marine environments. In this case, Fick's 2nd law has been used for the prediction of chloride diffusion related with service life of concrete structures. However, those studies were confined mostly to the single deterioration due to chloride only, although actual environment is rather of combined type. The purpose of the present study is, therefore, to explore the influences of carbonation to chloride attack in concrete structures and to investigate the validity of Fick's law to chloride attack combined carbonation. The test results indicate that the chloride ion profiles from Fick's law using the diffusion coefficient of immersion tests is not reflected the effect of separation of chloride ions in carbonation region but valid in sound region in case of combined action. On the other hand, the chloride ion profiles from Fick's law using the diffusion coefficient of Tang and Nilsson's method coincide with test results under dry-wet condition but not under combined condition. The results of present study may Imply that the new method for the measurement of diffusion coefficient is required to predict the chloride ion profiles in case of combined action at early.