• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.11 no.9
• /
• pp.1786-1792
• /
• 2007

In this paper, we proposed a recognition system for resident registration cards using ART-1 and PCA algorithm. To extract registration numbers and issue date, Sobel mask and median filter are applied first and noise removal follows. From the noise-removed image, horizontal smearing is used to extract the regions, which are binarized with recursive binarization algorithm. After that vortical smearing is applied to restore corrupted lesions, which are mainly due to the horizontal smearing. from the restored image, areas of individual codes are extracted using 4-directional edge following algorithm and face area is extracted by the morphologic characteristics of a registration card. Extracted codes are recognized using ART-1 algorithm and PCA algorithm is used to verify the face. When the proposed method was applied to 25 real registration card images, 323 characters from 325 registration numbers and 166 characters from 167 issue date numbers, were correctly recognized. The verification test with 25 forged images showed that the proposed verification algorithm is robust to detect forgery.

• Geomechanics and Engineering
• /
• v.25 no.1
• /
• pp.1-16
• /
• 2021

Machine learning models have been widely used for landslide susceptibility assessment (LSA) in recent years. The large number of inputs or conditioning factors for these models, however, can reduce the computation efficiency and increase the difficulty in collecting data. Feature selection is a good tool to address this problem by selecting the most important features among all factors to reduce the size of the input variables. However, two important questions need to be solved: (1) how do feature selection methods affect the performance of machine learning models? and (2) which feature selection method is the most suitable for a given machine learning model? This paper aims to address these two questions by comparing the predictive performance of 13 feature selection-based machine learning (FS-ML) models and 5 ordinary machine learning models on LSA. First, five commonly used machine learning models (i.e., logistic regression, support vector machine, artificial neural network, Gaussian process and random forest) and six typical feature selection methods in the literature are adopted to constitute the proposed models. Then, fifteen conditioning factors are chosen as input variables and 1,017 landslides are used as recorded data. Next, feature selection methods are used to obtain the importance of the conditioning factors to create feature subsets, based on which 13 FS-ML models are constructed. For each of the machine learning models, a best optimized FS-ML model is selected according to the area under curve value. Finally, five optimal FS-ML models are obtained and applied to the LSA of the studied area. The predictive abilities of the FS-ML models on LSA are verified and compared through the receive operating characteristic curve and statistical indicators such as sensitivity, specificity and accuracy. The results showed that different feature selection methods have different effects on the performance of LSA machine learning models. FS-ML models generally outperform the ordinary machine learning models. The best FS-ML model is the recursive feature elimination (RFE) optimized RF, and RFE is an optimal method for feature selection.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.43 no.4
• /
• pp.23-32
• /
• 2020

Many small and medium-sized manufacturing companies process various product types to respond different customer orders in a single production line. To improve their productivity, they often apply batch processing while considering various product types, constraints on batch sizes and setups, and due date of each order. This study introduces a batch scheduling heuristic for a production line with multiple product types and different due dates of each order. As the process times vary due to the different batch sizes and product types, a recursive equation is developed based on a flow line model to obtain the upper bound on the completion times with less computational complexity than full computation. The batch scheduling algorithm combines and schedules the orders with same product types into a batch to improve productivity, but within the constraints to match the due dates of the orders. The algorithm incorporates simple and intuitive principles for the purpose of being applied to small and medium companies. To test the algorithm, two case studies are introduced; a high pressure coolant (HPC) manufacturing line and a press process at a plate-type heat exchanger manufacturer. From the case studies, the developed algorithm provides significant improvements in setup frequency and thus convenience of workers and productivity, without violating due dates of each order.

• Journal of the Korean Society for Precision Engineering
• /
• v.13 no.10
• /
• pp.154-160
• /
• 1996

The control of diamond turning is usually achieved through a laser-interferometer feedback of slide position. The limitation of this control scheme is that the feedback signal does not account for additional dynamics of the tool post and the material removal process. If the tool post is rigid and the material removal process is relatively static, then such a non-collocated position feedback control scheme may surfice. However, as the accuracy requirement gets tighter and desired surface cnotours become more complex, the need for a direct tool-tip sensing becomes inevitable. The physical constraints of the machining process prohibit any reasonable implementation of a tool-tip motion measurement. It is proposed that the measured force normal to the face of the workpiece can be filtered through an appropriate admittance transfer function to result in the estimated dapth of cut. This can be compared to the desired depth of cut to generate the adjustment control action in additn to position feedback control. In this work, the design methodology on the admittance model-based control with a conventional controller is presented. The recursive least-squares algorithm with forgetting factor is proposed to identify the parameters and update the cutting process in real time. The normal cutting forces are measured to identify the cutting dynamics in the real diamond turning process using the precision dynamoneter. Based on the parameter estimation of cutting dynamics and the admitance model-based nanodynamic control scheme, simulation results are shown.

• Journal of Advanced Navigation Technology
• /
• v.26 no.6
• /
• pp.522-527
• /
• 2022

Object tracking is a field of signal processing that sequentially tracks the location of an object based on the previous-time location estimations and the present-time observation data. In this paper, we propose an adaptive scaling neural network that can track and adjust the scale of the input data with three recursive neural network (RNN) submodules. To evaluate object tracking performance, we compare the proposed system with the Kalman filter and the maximum likelihood object tracking scheme under an one-dimensional object movement model in which the object moves with piecewise constant acceleration. We show that the proposed scheme is generally better, in terms of root mean square error (RMSE) performance, than maximum likelihood scheme and Kalman filter and that the performance gaps grow with increased observation noise.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.23 no.1
• /
• pp.21-29
• /
• 2003

It is very important to reduce the computational time in estimating the parameters of vision control algorithm for robot's position control in real time. Unfortunately, the batch estimation commonly used requires too murk computational time because it is iteration method. So, the batch estimation has difficulty for robot's position control in real time. On the other hand, the Extended Kalman Filtering(EKF) has many advantages to calculate the parameters of vision system in that it is a simple and efficient recursive procedures. Thus, this study is to develop the EKF algorithm for the robot's vision control in real time. The vision system model used in this study involves six parameters to account for the inner(orientation, focal length etc) and outer (the relative location between robot and camera) parameters of camera. Then, EKF has been first applied to estimate these parameters, and then with these estimated parameters, also to estimate the robot's joint angles used for robot's operation. finally, the practicality of vision control scheme based on the EKF has been experimentally verified by performing the robot's position control.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.43 no.3
• /
• pp.321-335
• /
• 2023

Monitoring sediment loads in natural rivers is the key process in river engineering, but it is costly and dangerous. In practice, suspended loads are directly measured, and total loads, which is a summation of suspended loads and bed loads, are estimated. This study proposes a real-time sediment discharge monitoring system using the horizontal acoustic Doppler current profiler (H-ADCP) and support vector regression (SVR). The proposed system is comprised of the SVR model for suspended sediment concentration (SVR-SSC) and for total loads (SVR-Q_TL), respectively. SVR-SSC estimates SSC and SVR-Q_TL mimics the modified Einstein procedure. The grid search with K-fold cross validation (Grid-CV) and the recursive feature elimination (RFE) were employed to determine SVR's hyperparameters and input variables. The two SVR models showed reasonable cross-validation scores (R²) with 0.885 (SVR-SSC) and 0.860 (SVR-Q_TL). During the time-series sediment load monitoring period, we successfully detected various sediment transport phenomena in natural streams, such as hysteresis loops and sensitive sediment fluctuations. The newly proposed sediment monitoring system depends only on the gauged features by H-ADCP without additional assumptions in hydraulic variables (e.g., friction slope and suspended sediment size distribution). This method can be applied to any ADCP-installed discharge monitoring station economically and is expected to enhance temporal resolution in sediment monitoring.

• Journal of Intelligence and Information Systems
• /
• v.26 no.4
• /
• pp.173-198
• /
• 2020

For a long time, many studies have been conducted on predicting the success of campaigns for customers in academia, and prediction models applying various techniques are still being studied. Recently, as campaign channels have been expanded in various ways due to the rapid revitalization of online, various types of campaigns are being carried out by companies at a level that cannot be compared to the past. However, customers tend to perceive it as spam as the fatigue of campaigns due to duplicate exposure increases. Also, from a corporate standpoint, there is a problem that the effectiveness of the campaign itself is decreasing, such as increasing the cost of investing in the campaign, which leads to the low actual campaign success rate. Accordingly, various studies are ongoing to improve the effectiveness of the campaign in practice. This campaign system has the ultimate purpose to increase the success rate of various campaigns by collecting and analyzing various data related to customers and using them for campaigns. In particular, recent attempts to make various predictions related to the response of campaigns using machine learning have been made. It is very important to select appropriate features due to the various features of campaign data. If all of the input data are used in the process of classifying a large amount of data, it takes a lot of learning time as the classification class expands, so the minimum input data set must be extracted and used from the entire data. In addition, when a trained model is generated by using too many features, prediction accuracy may be degraded due to overfitting or correlation between features. Therefore, in order to improve accuracy, a feature selection technique that removes features close to noise should be applied, and feature selection is a necessary process in order to analyze a high-dimensional data set. Among the greedy algorithms, SFS (Sequential Forward Selection), SBS (Sequential Backward Selection), SFFS (Sequential Floating Forward Selection), etc. are widely used as traditional feature selection techniques. It is also true that if there are many risks and many features, there is a limitation in that the performance for classification prediction is poor and it takes a lot of learning time. Therefore, in this study, we propose an improved feature selection algorithm to enhance the effectiveness of the existing campaign. The purpose of this study is to improve the existing SFFS sequential method in the process of searching for feature subsets that are the basis for improving machine learning model performance using statistical characteristics of the data to be processed in the campaign system. Through this, features that have a lot of influence on performance are first derived, features that have a negative effect are removed, and then the sequential method is applied to increase the efficiency for search performance and to apply an improved algorithm to enable generalized prediction. Through this, it was confirmed that the proposed model showed better search and prediction performance than the traditional greed algorithm. Compared with the original data set, greed algorithm, genetic algorithm (GA), and recursive feature elimination (RFE), the campaign success prediction was higher. In addition, when performing campaign success prediction, the improved feature selection algorithm was found to be helpful in analyzing and interpreting the prediction results by providing the importance of the derived features. This is important features such as age, customer rating, and sales, which were previously known statistically. Unlike the previous campaign planners, features such as the combined product name, average 3-month data consumption rate, and the last 3-month wireless data usage were unexpectedly selected as important features for the campaign response, which they rarely used to select campaign targets. It was confirmed that base attributes can also be very important features depending on the type of campaign. Through this, it is possible to analyze and understand the important characteristics of each campaign type.

• Journal of Science Education
• /
• v.33 no.1
• /
• pp.12-30
• /
• 2009

The purpose of this study was to analyze recognition characteristics of science gifted students on the earth system based on their thinking style. The subjects were 24 science gifted students at the Science Institute for Gifted Students of a university located in metropolitan city in Korea. The students' thinking styles were firstly examined on the basis of the Sternberg's theory of mental self-government. And then, the students were divided into two groups: Type I group(legislative, judicial, global, liberal) and Type II group(executive, local, conservative) based on Sternberg's theory. Data was collected from three different type of questionnaires(A, B, C types), interview, word association method, drawing analyses, concept map, hidden dimension inventory, and in-depth interviews. The findings of analysis indicated that their thinking styles were characterized by 'Legislative', 'Executive', 'Anarchic', 'Global', 'External', 'Liberal' styles. Their preference were conducting new projects and using creative problem solving processes. The results of students' recognition characteristics on earth system were as follows: First, though the two groups' quantitative value on 'System Understanding' was very similar, there were considerable distinctions in details. Second, 'Understanding the Relationship in the System' was closely connected to thinking styles. Type I group was more advantageous with multiple, dynamic, and recursive approach. Third, in the relation to 'System Generalization' both of the groups had similar simple interpretational ability of the system, but Type I group was better on generalization when 'hidden dimension inventory' factor was added. On the system prediction factor, however, students' ability was weak regardless of the type. Consequently, more specific development strategies on various objects are needed for the development and application of the system learning program. Furthermore, it is expected that this study could be practically and effectively used on various fields related to system recognition.

• Korean Journal of Cognitive Science
• /
• v.22 no.3
• /
• pp.271-298
• /
• 2011

The lexical semantic system should be built to grasp lexical semantic information more clearly. In this paper, we studied a semantic clustering of predicates that is one of the steps in building the lexical semantic system. Unlike previous studies that used argument of subcategorization(subject and object), selectional restrictions and interaction information of adverb, we used sense tagged definition in dictionary for the semantic clustering of predicate, and also attempted hierarchical clustering of predicate using the relationship between the generic concept and the specific concept. Most of the predicates in the dictionary were used for clustering. Total of 106,501 predicates(85,754 verbs, 20,747 adjectives) were used for the test. We got results of clustering which is 2,748 clusters of predicate and 130 recursive definition clusters and 261 sub-clusters. The maximum depth of cluster was 16 depth. We compared results of clustering with the Sejong semantic classes for evaluation. The results showed 70.14% of the cohesion.