• Proceedings of the Korean Geotechical Society Conference
• /
• 2002.10a
• /
• pp.499-506
• /
• 2002

The purpose of this study is to develop landslide susceptibility analysis techniques using artificial neural networks and to apply the newly developed techniques for assessment of landslide susceptibility to the study area of Yongin in Korea. Landslide locations were identified in the study area from interpretation of aerial Photographs and field survey data, and a spatial database of the topography, soil type and timber cover were constructed. The landslide-related factors such as topographic slope, topographic curvature, soil texture, soil drainage, soil effective thickness, timber age, and timber diameter were extracted from the spatial database. Using those factors, landslide susceptibility and weights of each factor were analyzed by two artificial neural network methods. In the first method, the landslide susceptibility index was calculated by the back propagation method, which is a type of artificial neural network method. Then, the susceptibility map was made with a GIS program. The results of the landslide susceptibility analysis were verified using landslide location data. The verification results show satisfactory agreement between the susceptibility index and existing landslide location data. In the second method, weights of each factor were determinated. The weights, relative importance of each factor, were calculated using importance-free characteristics method of artificial neural networks.

• Computers and Concrete
• /
• v.32 no.3
• /
• pp.327-337
• /
• 2023

Concrete is the most widely used building material, with various types including high- and ultra-high-strength, reinforced, normal, and lightweight concretes. However, accurately predicting concrete properties is challenging due to the geotechnical design code's requirement for specific characteristics. To overcome this issue, researchers have turned to new technologies like machine learning to develop proper methodologies for concrete specification. In this study, we propose a highly accurate deep learning-based predictive model to investigate the compressive strength (UCS) of lightweight concrete with natural aggregates (pumice). Our model was implemented on a database containing 249 experimental records and revealed that water, cement, water-cement ratio, fine-coarse aggregate, aggregate substitution rate, fine aggregate replacement, and superplasticizer are the most influential covariates on UCS. To validate our model, we trained and tested it on random subsets of the database, and its performance was evaluated using a confusion matrix and receiver operating characteristic (ROC) overall accuracy. The proposed model was compared with widely known machine learning methods such as MLP, SVM, and DT classifiers to assess its capability. In addition, the model was tested on 25 laboratory UCS tests to evaluate its predictability. Our findings showed that the proposed model achieved the highest accuracy (accuracy=0.97, precision=0.97) and the lowest error rate with a high learning rate (R2=0.914), as confirmed by ROC (AUC=0.971), which is higher than other classifiers. Therefore, the proposed method demonstrates a high level of performance and capability for UCS predictions.

• Journal of the Korean Geosynthetics Society
• /
• v.17 no.2
• /
• pp.33-40
• /
• 2018

Characteristics of interface friction between cohesionless soils and geotechnical structure surfaces play an important role in the analysis of earth load and resistance on the structure. In general, geotechnical structures are mainly composed of either steel or concrete, and their surface roughnesses with respect to soil particle sizes influence the interface characteristics between soils and the structures. Accurate assessment of the interface friction characteristics between soils and structures is important to ensure the safety of geotechnical structures, such as mechanically stabilized earth walls reinforced with inextensible reinforcements, piles embedded into soils, retaining wall backfilled with soils. In this study, based on the database of high quality interface friction tests between frictional soils and solid surfaces from literature, equation representing peak interface friction angle is proposed. The influential factors of the peak interface friction angle are relative roughness between soil and solid surface, relative density of frictional soil, and residual (constant volume) interface friction angle. Futhermore, for the developed equation of the interface friction angle, its uncertainty was assessed statistically based on Goodness-of-fit test results.

• Journal of the Korean Geotechnical Society
• /
• v.31 no.10
• /
• pp.5-16
• /
• 2015

Considering the conversion of the Korea Construction Standards to Limit State Design (LSD), we analyzed the resistance bias factor for pullout resistance, as a part of the development of the Load and Resistance Factor Design (LRFD) for soil nailing; very few studies have been conducted on soil nailing. In order to reflect the local characteristics of soil nailing, such as the design and construction level, we collected statistics on pullout tests conducted on slopes and excavation construction sites around the country. In this study a database was built based on the geotechnical properties, soil nailing specifications, and pullout test results. The resistance bias factors are calculated to determine the resistance factor of the pullout resistance for gravity and pressurized grouting method, which are the most commonly used methods in Korea; moreover, we have relatively sufficient data on these methods. We found the resistance bias factors to be 1.144 and 1.325, which are relatively conservative values for predicting the actual ultimate pullout resistance. It showed that our designs are safer than those found in a research case in the United States (NCHRP Report); however, there was an uncertainty, $COV_R$, of 0.27-0.43 in the pullout resistance, which is relatively high. In addition, the pressurized grouting method has a greater margin of safety than the gravity grouting method, and the actual ultimate pullout resistance determined using the pressurized grouting method has low uncertainty.

• Proceedings of the Korean Geotechical Society Conference
• /
• 2010.03a
• /
• pp.891-894
• /
• 2010

Steep slope disasters accompany economic loss along with casualties, so the evaluation and the systematic management on the regions with slope collapse danger are required. A lot of manpower, time, and economic cost are needed to accumulate disaster history of steep slope areas by the national and small-sized region. As the method for this, it construed location data about each area with disaster occurrence by maknd elocation data of collapsed steep areas through high-resolution satellite image and collectnd edata on the regions with disasters through media and literature data such as a disaster annual report and a disaster comprehensive report. The study selected three shortest routes includnd ethe area with disaster in Jeolla province on literature and the collapsed area found by the image data, and constructed the results of the field survey as database.

• Proceedings of the Korean Geotechical Society Conference
• /
• 2006.03a
• /
• pp.1287-1294
• /
• 2006

A pile is compressed with settlements when loading and bearing capacity is altered along relative displacement of pile/soil on settlement and compression. Settlements of pile displaying limit skin friction is different from displaying tip resistance. Therefore, it is an error in traditional method that bearing capacity of pile is estimated from the sum of limit skin fraction and tip resistance. Accordingly, development of design method considering behavior of load-settlement is needed. In this study, we would like to establish the base for development of design method considering bearing capacity altering along displacement on settlement and compression. For this, we established system and substance of design method. And in order to establish relationship of load-settlement of pile on the type of soil, we analyzed and arranged existing database and pile loading test. On design method, settlement is assumed gradually on each capacity level being assumed gradually. Bearing capacity developing on the pile is obtained on each settlement level. Until the obtained bearing capacity will be equal to assumed capacity, this process is continued with increasing settlement. Load-settlement curve for soil classification is sketched in the process computing settlement on assumed capacity. This design method will be materialized by computation program.

• Proceedings of the Korean Geotechical Society Conference
• /
• 2005.03a
• /
• pp.603-610
• /
• 2005

The end bearing behavior of piles socketed in weathered/soft rock is generally dependent upon the mass conditions of rock with fractures rather than the strength of intact rock. However, there are few available data and little guidance in the prediction of the end bearing capacity of drilled shafts socketed in weathered/soft rock, considering rock mass weathering. Therefore, a database of 13 load tests was constructed first, and new empirical relationships between the base reaction modulus of piles in rock and rock mass properties were developed. No correlation was found between the compressive strengths of intact rock and the base reaction modulus of weathered/soft rock. The ground investigation data regarding the rock mass conditions(e.g. Em, Eur, RMR, RQD) was found to be highly correlated with the base reaction modulus, showing the coefficients of correlation greather than 0.7 in most cases. Additionally, the applicability of existing methods for the end bearing capacity of piles in rock was verified by comparison with the field test data.

• Proceedings of the Korean Geotechical Society Conference
• /
• 2005.03a
• /
• pp.191-198
• /
• 2005

Slope failures during heavy rainfall have resulted in death of life and economic loss. In recent years, the research on slope damage assessment using Geographical Information System(GIS) has been actively carried out by researchers of several goverment organizations and schools. The researchers in Highway and Transportation Technology Institute (HTTI) of Korea Highway Corporation has developed the GIS database(DB), including highway, rainfalls, soil or rock geometry, types of damage, etc. and have been working on the damage assessment of highway slopes. The DB has been established and summarized in two different ways, such as highway routes and administrative districts. Grid of rainfall intensity generated by maximum rainfalls of each administrative district has been devloped. It shows good correlation of slope damage with heavy rainfalls. Most of damaged slopes were found in the amount of 100 mm to 300 mm rainfalls.

• Proceedings of the Korean Geotechical Society Conference
• /
• 2009.03a
• /
• pp.667-672
• /
• 2009

Gathering information and systemization of infrastructure disaster management is to reduce uncertainties in making decisions and maximize the number of alternations. The key objects of a sensor-based progress report and propagation automation systems are to provide objective data, realize and support decision making and deliver them to a certain area, department, manager and other people rapidly. The major findings and results of this study are as follows. 1) Application of international standard-based alerting protocol(CAP; Common Alerting Protocol). 2) Development of database of existing progress report and propagation manual in order to achieve networking of safety management on major social infrastructure of the nation. 3) Development middleware application programs to progress report and propagation data using SMS, FAX, EMS, VMS, MMS.

• Proceedings of the Korean Geotechical Society Conference
• /
• 2009.03a
• /
• pp.456-463
• /
• 2009

The preconsolidation pressure has been commonly determined by oedometer test. However, it can also be determined by in-situ test, such as piezocone test with theoretical and(or) empirical correlations. Recently, Neural Network(NN) theory was applied and some models were proposed to estimate the preconsolidation pressure or OCR. However, since the optimization process of synaptic weights of NN model is dependent on the initial synaptic weights, NN models which are trained with different initial weights can't avoid the variability on prediction result for new database even though they have same structure and use same transfer function. In this study, Committee Neural Network(CNN) model is proposed to improve the initial weight dependency of multi-layered neural network model on the prediction of preconsolidation pressure of soft clay from piezocone test result. It was found that even though the NN model has the optimized structure for given training data set, it still has the initial weight dependency, while the proposed CNN model can improve the initial weight dependency of the NN model and provide a consistent and precise inference result than existing NN models.