• Journal of Korean Society of Disaster and Security
• /
• v.14 no.3
• /
• pp.17-27
• /
• 2021

In this study, classification models were built using machine learning techniques that can classify the soil creep risk into three classes from A to C (A: risk, B: moderate, C: good). A total of six machine learning techniques were used: K-Nearest Neighbor, Support Vector Machine, Logistic Regression, Decision Tree, Random Forest, and Extreme Gradient Boosting and then their classification accuracy was analyzed using the nationwide soil creep field survey data in 2019 and 2020. As a result of classification accuracy analysis, all six methods showed excellent accuracy of 0.9 or more. The methods where numerical data were applied for data training showed better performance than the methods based on character data of field survey evaluation table. Moreover, the methods learned with the data group (R1~R4) reflecting the expert opinion had higher accuracy than the field survey evaluation score data group (C1~C4). The machine learning can be used as a tool for prediction of soil creep if high-quality data are continuously secured and updated in the future.

• The Journal of the Korea Contents Association
• /
• v.19 no.1
• /
• pp.1-15
• /
• 2019

One of the biggest difficulties in the vocational training field is the dropout problem. A large number of students drop out during the training process, which hampers the waste of the state budget and the improvement of the youth employment rate. Previous studies have mainly analyzed the cause of dropouts. The purpose of this study is to propose a machine learning based model that predicts dropout in advance by using various information of learners. In particular, this study aimed to improve the accuracy of the prediction model by taking into consideration not only structured data but also unstructured data. Analysis of unstructured data was performed using Word2vec and Convolutional Neural Network(CNN), which are the most popular text analysis technologies. We could find that application of the proposed model to the actual data of a domestic vocational training institute improved the prediction accuracy by up to 20%. In addition, the support vector machine-based prediction model using both structured and unstructured data showed high prediction accuracy of the latter half of 90%.

• International Journal of Highway Engineering
• /
• v.20 no.2
• /
• pp.127-135
• /
• 2018

PURPOSES : This study develops various models that can estimate the pattern of road surface temperature changes using machine learning methods. METHODS : Both a thermal mapping system and weather forecast information were employed in order to collect data for developing the models. In previous studies, the authors defined road surface temperature data as a response, while vehicular ambient temperature, air temperature, and humidity were considered as predictors. In this research, two additional factors-road type and weather forecasts-were considered for the estimation of the road surface temperature change pattern. Finally, a total of six models for estimating the pattern of road surface temperature changes were developed using the MATLAB program, which provides the classification learner as a machine learning tool. RESULTS : Model 5 was considered the most superior owing to its high accuracy. It was seen that the accuracy of the model could increase when weather forecasts (e.g., Sky Status) were applied. A comparison between Models 4 and 5 showed that the influence of humidity on road surface temperature changes is negligible. CONCLUSIONS : Even though Models 4, 5, and 6 demonstrated the same performance in terms of average absolute error (AAE), Model 5 can be considered the optimal one from the point of view of accuracy.

• IEIE Transactions on Smart Processing and Computing
• /
• v.5 no.6
• /
• pp.430-439
• /
• 2016

Estimation and analysis of traffic jams plays a vital role in an intelligent transportation system and advances safety in the transportation system as well as mobility and optimization of environmental impact. For these reasons, many researchers currently mainly focus on the brilliant machine learning-based prediction approaches for traffic prediction systems. This paper primarily addresses the analysis and comparison of prediction accuracy between two machine learning algorithms: Naïve Bayes and K-Nearest Neighbor (K-NN). Based on the fact that optimized estimation accuracy of these methods mainly depends on a large amount of recounted data and that they require much time to compute the same function heuristically for each action, we propose an approach that applies multi-threading to these heuristic methods. It is obvious that the greater the amount of historical data, the more processing time is necessary. For a real-time system, operational response time is vital, and the proposed system also focuses on the time complexity cost as well as computational complexity. It is experimentally confirmed that K-NN does much better than Naïve Bayes, not only in prediction accuracy but also in processing time. Multi-threading-based K-NN could compute four times faster than classical K-NN, whereas multi-threading-based Naïve Bayes could process only twice as fast as classical Bayes.

• Journal of the Korean Society for Precision Engineering
• /
• v.20 no.6
• /
• pp.88-95
• /
• 2003

This paper presents the measurement and correction method of PCB alignment errors for PCB screen printer. Electronic equipment is getting smaller and yet must satisfy high performance standard. Therefore, there is a great demand for PCB with high density. However conventional PCB screen printer doesn't have enough accuracy to accommodate the demand fur high-resolution circuit pattern and high-density mounting capacity of electronic chips. It is because the alignment errors of PCB occur when it is loaded to the screen printer. Therefore, this study focuses on the development of the system which is able to measure and correct alignment errors with high-accuracy. An automatic optical inspection part measures the PCB alignment errors using machine vision, and the high-accuracy 3-axis stage makes correction for these errors. This system used two CCD cameras to get images of two fiducial marks of PCB. The geometrical relationship between PCB, cameras, and xy$\theta$ stage is derived, and analytical equations for alignment errors are also obtained. The unknown parameters including camera declining angles and etc. can be obtained by initialization process. Finally, the proposed algorithm is verified by experiments by using test bench.

• Journal of the Korean Society for Precision Engineering
• /
• v.20 no.6
• /
• pp.96-104
• /
• 2003

This paper presents the measurement and correction method of PCB alignment errors for PCB screen printer. Electronic equipment is getting smaller and yet must satisfy high performance standard. Therefore, there is a great demand for PCB with high density. However conventional PCB screen printer doesn't have enough accuracy to accommodate the demand for high-resolution circuit pattern and high-density mounting capacity of electronic chips. It is because the alignment errors of PCB occur when it is loaded to the screen printer. Therefore, this study focuses on the development of the system which is able to measure and correct alignment errors with high-accuracy. An automatic optical inspection part measures the PCB alignment errors using machine vision, and the high-accuracy 3-axis stage makes correction for these errors. This system used two CCD cameras to get images of two fiducial marks of PCB. The centers of fiducial marks are obtained by using moment, gradient method. The first method is calculating the centroid by using first moment of blob, and the latter method is calculating the center of the circle whose equation is obtained by curve-fitting the boundaries of fiducial mark. The operating system used to implement the whole set-up is carried in Window 98 (or NT) environment. Finally we implemented this system to PCB screen printer.

• Computers and Concrete
• /
• v.20 no.5
• /
• pp.555-562
• /
• 2017

The accuracy and integrity of stress data acquired by bridge heath monitoring system is of significant importance for bridge safety assessment. However, the missing and abnormal data are inevitably existed in a realistic monitoring system. This paper presents a data reconstruction approach for bridge heath monitoring based on the wavelet multi-resolution analysis and support vector machine (SVM). The proposed method has been applied for data imputation based on the recorded data by the structural health monitoring (SHM) system instrumented on a prestressed concrete cable-stayed bridge. The effectiveness and accuracy of the proposed wavelet-based SVM prediction method is examined by comparing with the traditional autoregression moving average (ARMA) method and SVM prediction method without wavelet multi-resolution analysis in accordance with the prediction errors. The data reconstruction analysis based on 5-day and 1-day continuous stress history data with obvious preternatural signals is performed to examine the effect of sample size on the accuracy of data reconstruction. The results indicate that the proposed data reconstruction approach based on wavelet multi-resolution analysis and SVM is an effective tool for missing data imputation or preternatural signal replacement, which can serve as a solid foundation for the purpose of accurately evaluating the safety of bridge structures.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2002.10a
• /
• pp.158-163
• /
• 2002

This paper presents a multiple sensor system for rapid and high-precision coordinate data acquisition in the OMM (On-machine measurement) process. In this research, three sensors (touch probe, laser, and vision sensor) are integrated to obtain more accurate measuring results. The touch-type probe has high accuracy, but is time-consuming. Vision sensor can acquire many point data rapidly over a spatial range but its accuracy is less than other sensors. Also, it is not possible to acquire data for invisible areas. Laser sensor has medium accuracy and measuring speed among the sensors, and can acquire data for sharp or rounded edge and the features with very small holes and/or grooves. However, it has range- constraints to use because of its system structure. In this research, a new optimum sensor integration method for OMM is proposed by integrating the multiple-sensor to accomplish mote effective inspection planning. To verify the effectiveness of the proposed method, simulation and experimental works are performed, and the results are analyzed.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 1999.05a
• /
• pp.75-80
• /
• 1999

As current manufacturing processes require high spindle speed and precise machining, increasing accuracy by reducing volumetric errors of the machine itself, particularly thermal errors, is very important. Thermal errors can be estimated by many empirical models, for example, an FEM model, a neural network model, a linear regression model, an engineering judgment model etc. This paper discusses to make a modeling of thermal errors efficiently through backward elimination and fuzzy logic strategy. The model of a thermal error using fuzzy logic strategy overcome limitation of accuracy in the linear regression model or the engineering judgment model. And this model is compared with the engineering judgment model. It is not necessary complex process such like multi-regression analysis of the engineering judgment model. A fuzzy model does not need to know the characteristics of the plant, and the parameters of the model can be mathematically calculated. Like a regression model, this model can be applied to any machine, but it delivers greater accuracy and robustness.

• Structural Engineering and Mechanics
• /
• v.84 no.1
• /
• pp.1-16
• /
• 2022

An efficient and accurate classification method for failure modes of reinforced concrete (RC) columns was proposed based on key characteristic parameters. The weight coefficients of seven characteristic parameters for failure modes of RC columns were determined first based on the support vector machine-recursive feature elimination. Then key characteristic parameters for classifying flexure, flexure-shear and shear failure modes of RC columns were selected respectively. Subsequently, a support vector machine with key characteristic parameters (SVM-K) was proposed to classify three types of failure modes of RC columns. The optimal parameters of SVM-K were determined by using the ten-fold cross-validation and the grid-search algorithm based on 270 sets of available experimental data. Results indicate that the proposed SVM-K has high overall accuracy, recall and precision (e.g., accuracy>95%, recall>90%, precision>90%), which means that the proposed SVM-K has superior performance for classification of failure modes of RC columns. Based on the selected key characteristic parameters for different types of failure modes of RC columns, the accuracy of SVM-K is improved and the decision function of SVM-K is simplified by reducing the dimensions and number of support vectors.