• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.12
• /
• pp.889-898
• /
• 2013

Due to the popularization of high-performance capturing equipments and the emergence of powerful image-editing softwares, it is easy to make high-quality counterfeit money. However, the probability of detecting counterfeit money to the general public is extremely low and the detection device is expensive. In this paper, a counterfeit money detection algorithm using a general purpose scanner and computer system is proposed. First, the printing features of color printers are calculated using morphological operations and gray-level co-occurrence matrix. Then, these features are used to train a support vector machine classifier. This trained classifier is applied for identifying either original or counterfeit money. In the experiment, we measured the detection rate between the original and counterfeit money. Also, the printing source was identified. The proposed algorithm was compared with the algorithm using wiener filter to identify color printing source. The accuracy for identifying counterfeit money was 91.92%. The accuracy for identifying the printing source was over 94.5%. The results support that the proposed algorithm performs better than previous researches.

• The Korean Journal of Applied Statistics
• /
• v.21 no.1
• /
• pp.141-149
• /
• 2008

Recently we frequently analyze multivariate data with quite large number of variables. In such data sets, virtually duplicated variables may exist simultaneously even though they are conceptually distinguishable. Duplicate variables may cause problems such as the distortion of principal axes in principal component analysis and factor analysis and the distortion of the distances between observations, i.e. the input for cluster analysis. Also in supervised learning or regression analysis, duplicated explanatory variables often cause the instability of fitted models. Since real data analyses are aimed often at multiple purposes, it is necessary to reduce the number of variables to a parsimonious level. The aim of this paper is to propose a practical algorithm for selection of a subset of variables from a given set of p input variables, by the criterion of minimum trace of partial variances of unselected variables unexplained by selected variables. The usefulness of proposed method is demonstrated in visualizing the relationship between selected and unselected variables, in building a predictive model with very large number of independent variables, and in reducing the number of variables and purging/merging categories in categorical data.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.15 no.3
• /
• pp.134-141
• /
• 2011

There have been increased economic and societal demands to continuously monitor the integrity and long-term deterioration of civil infrastructures to ensure their safety and adequate performance throughout their life span. However, it is very difficult to continuously monitor the structural condition of the pipeline structures because those are placed underground and connected each other complexly, although pipeline structures are core underground infrastructures which transport primary sources. Moreover, damage can occur at several scales from micro-cracking to buckling or loose bolts in the pipeline structures. In this study, guided wave measurement can be achieved with a self-sensing circuit using a piezoelectric active sensor. In this self sensing system, a specific frequency-induced structural wavelet response is obtained from the self-sensed guided wave measurement. To classify the multiple types of structural damage, supervised learning-based statistical pattern recognition was implemented using the damage indices extracted from the guided wave features. Different types of structural damage artificially inflicted on a pipeline system were investigated to verify the effectiveness of the proposed SHM approach.

• Journal of Cadastre & Land InformatiX
• /
• v.50 no.1
• /
• pp.75-85
• /
• 2020

This study examines machine learning cross-validation to utilized create ROI for classification of land cover. The study area located in Sejong and one KOMPSAT-3A image was used in this analysis: procedure on October 28, 2019. We used four bands(Red, Green, Blue, Near infra-red) for learning cross validation process. In this study, we used K-fold method in cross validation and used SVM kernel type with cross validation result. In addition, we used 4 kernels of SVM(Linear, Polynomial, RBF, Sigmoid) for supervised classification land cover map using extracted ROI. During the cross validation process, 1,813 data extracted from 3,500 data, and the most of the building, road and grass class data were removed about 60% during cross validation process. Based on this, the supervised SVM linear technique showed the highest classification accuracy of 91.77% compared to other kernel methods. The grass' producer accuracy showed 79.43% and identified a large mis-classification in forests. Depending on the results of the study, extraction ROI using cross validation may be effective in forest, water and agriculture areas, but it is deemed necessary to improve the distinction of built-up, grass and bare-soil area.

• The Journal of the Korea Contents Association
• /
• v.21 no.10
• /
• pp.59-66
• /
• 2021

In this paper, an improved integrated security control procedure is newly proposed by applying artificial intelligence technology to integrated security control and unifying the existing security control and AI security control response procedures. Current cyber security control is highly dependent on the level of human ability. In other words, it is practically unreasonable to analyze various logs generated by people from different types of equipment and analyze and process all of the security events that are rapidly increasing. And, the signature-based security equipment that detects by matching a string and a pattern has insufficient functions to accurately detect advanced and advanced cyberattacks such as APT (Advanced Persistent Threat). As one way to solve these pending problems, the artificial intelligence technology of supervised and unsupervised learning is applied to the detection and analysis of cyber attacks, and through this, the analysis of logs and events that occur innumerable times is automated and intelligent through this. The level of response has been raised in the overall aspect by making it possible to predict and block the continuous occurrence of cyberattacks. And after applying AI security control technology, an improved integrated security control service model was newly proposed by integrating and solving the problem of overlapping detection of AI and SIEM into a unified breach response process(procedure).

• Information Systems Review
• /
• v.25 no.1
• /
• pp.93-110
• /
• 2023

Recently, attempts have been made to convert unstructured text into vectors and to analyze vast amounts of natural language for various purposes. In particular, the demand for analyzing texts in specialized domains is rapidly increasing. Therefore, studies are being conducted to analyze specialized and general-purpose documents simultaneously. To analyze specific terms with general terms, it is necessary to align the embedding space of the specific terms with the embedding space of the general terms. So far, attempts have been made to align the embedding of specific terms into the embedding space of general terms through a transformation matrix or mapping function. However, the linear transformation based on the transformation matrix showed a limitation in that it only works well in a local range. To overcome this limitation, various types of nonlinear vector alignment methods have been recently proposed. We propose a vector alignment model that matches the embedding space of specific terms to the embedding space of general terms through end-to-end learning that simultaneously learns the autoencoder and regression model. As a result of experiments with R&D documents in the "Healthcare" field, we confirmed the proposed methodology showed superior performance in terms of accuracy compared to the traditional model.

• Journal of KIISE:Software and Applications
• /
• v.36 no.11
• /
• pp.960-966
• /
• 2009

A manifold is used to represent a relationship between high-dimensional data samples in low-dimensional space. In human pose estimation, it is created in low-dimensional space for processing image and 3D body configuration data. Manifold learning is to build a manifold. But it is vulnerable to silhouette variations. Such silhouette variations are occurred due to view-change, person-change, distance-change, and noises. Representing silhouette variations in a single manifold is impossible. In this paper, we focus a silhouette variation problem occurred by view-change. In previous view invariant pose estimation methods based on manifold learning, there were two ways. One is modeling manifolds for all view points. The other is to extract view factors from mapping functions. But these methods do not support one by one mapping for silhouettes and corresponding body configurations because of unsupervised learning. Modeling manifold and extracting view factors are very complex. So we propose a method based on triple manifolds. These are view manifold, pose manifold, and body configuration manifold. In order to build manifolds, we employ biased manifold learning. After building manifolds, we learn mapping functions among spaces (2D image space, pose manifold space, view manifold space, body configuration manifold space, 3D body configuration space). In our experiments, we could estimate various body poses from 24 view points.

• The Journal of Korean Philosophical History
• /
• no.58
• /
• pp.307-336
• /
• 2018

This paper traces the historical genealogy of the subjectivity and the silsim (實心, true mind) that appear in Jeong In-Bo's "gukhak" (國學, the national learning) thought and illuminates its characteristics. In the modern East Asian history of thought, the beginning of the emergence of subjectivity and the silsim as the main philosophical topic comes from the Neo-Confucianism of Song Dynasty in China. Cheng Yi is the first thinker to emphasize subjectivity and consciousness. Zhu Xi and Wang Yang-ming inherit the Neo-Confucian thought based on Cheng Yi's principle of subjectivity, but only show difference in methodology. In the Chosun Dynasty, Jeong Je-Doo and his School were one example of the Neo-Confucian spirit of subjectivity and the silsim. Although Jeong In-Bo (鄭寅普) belongs to Jeong Je-Doo's school of Ganghwa in the school curriculum, he has only used it methodologically since he believed that Yangming's learning is more effective in the awareness and practice of the silsim. Especially noteworthy is that the principle of subjectivity led Jeong In-Bo to follow the frame of Zhu Xi's moral theory. Jeong's claim that selfish desire (jasasim 自私心) should be controlled by a conscious mind (silsim) being aware of the right and 'ought to do' corresponds to Zhu Xi's view that the moral mind (dosim 道心) should be selected in the conflict situation between sensual desire (insim 人心) and moral consciousness so that the insim should be supervised by the dosim. Such ethics is a position to emphasize the inner motive and the sense of duty of conduct, and there is no fundamental difference in Zhu Xi and Wang Yang-ming. At least on this point, it is necessary to look at modern and contemporary Korean studies from the perspective of continuity, not discontinuity from Confucian tradition.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.12
• /
• pp.25-34
• /
• 2020

In this paper, we empirically compare the effectiveness of training models to recognize beauty-related skin disease using supervised deep learning algorithms. Recently, deep learning algorithms are being actively applied for various fields such as industry, education, and medical. For instance, in the medical field, the ability to diagnose cutaneous cancer using deep learning based artificial intelligence has improved to the experts level. However, there are still insufficient cases applied to disease related to skin beauty. This study experimentally compares the effectiveness of identifying beauty-related skin disease by applying deep learning algorithms, considering CNN, ResNet, and SE-ResNet. The experimental results using these training models show that the accuracy of CNN is 71.5% on average, ResNet is 90.6% on average, and SE-ResNet is 95.3% on average. In particular, the SE-ResNet-50 model, which is a SE-ResNet algorithm with 50 hierarchical structures, showed the most effective result for identifying beauty-related skin diseases with an average accuracy of 96.2%. The purpose of this paper is to study effective training and methods of deep learning algorithms in consideration of the identification for beauty-related skin disease. Thus, it will be able to contribute to the development of services used to treat and easy the skin disease.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.10
• /
• pp.461-470
• /
• 2023

While speech animation generation employing deep learning has been actively researched for English, there has been no prior work for Korean. Given the fact, this paper for the very first time employs supervised deep learning to generate Korean speech animation. By doing so, we find out the significant effect of deep learning being able to make speech animation research come down to speech recognition research which is the predominating technique. Also, we study the way to make best use of the effect for Korean speech animation generation. The effect can contribute to efficiently and efficaciously revitalizing the recently inactive Korean speech animation research, by clarifying the top priority research target. This paper performs this process: (i) it chooses blendshape animation technique, (ii) implements the deep-learning model in the master-servant pipeline of the automatic speech recognition (ASR) module and the facial action coding (FAC) module, (iii) makes Korean speech facial motion capture dataset, (iv) prepares two comparison deep learning models (one model adopts the English ASR module, the other model adopts the Korean ASR module, however both models adopt the same basic structure for their FAC modules), and (v) train the FAC modules of both models dependently on their ASR modules. The user study demonstrates that the model which adopts the Korean ASR module and dependently trains its FAC module (getting 4.2/5.0 points) generates decisively much more natural Korean speech animations than the model which adopts the English ASR module and dependently trains its FAC module (getting 2.7/5.0 points). The result confirms the aforementioned effect showing that the quality of the Korean speech animation comes down to the accuracy of Korean ASR.