• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.13 no.3
• /
• pp.197-205
• /
• 2020

Korean language has the characteristics that the pronunciation of phoneme units such as vowels and consonants are fixed and the pronunciation associated with a notation does not change, so that foreign learners can approach rather easily Korean language. However, when one pronounces words, phrases, or sentences, the pronunciation changes in a manner of a wide variation and complexity at the boundaries of syllables, and the association of notation and pronunciation does not hold any more. Consequently, it is very difficult for foreign learners to study Korean standard pronunciations. Despite these difficulties, it is believed that systematic analysis of pronunciation errors for Korean words is possible according to the advantageous observations that the relationship between Korean notations and pronunciations can be described as a set of firm rules without exceptions unlike other languages including English. In this paper, we propose a visualization framework which shows the differences between standard pronunciations and erratic ones as quantitative measures on the computer screen. Previous researches only show color representation and 3D graphics of speech properties, or an animated view of changing shapes of lips and mouth cavity. Moreover, the features used in the analysis are only point data such as the average of a speech range. In this study, we propose a method which can directly use the time-series data instead of using summary or distorted data. This was realized by using the deep learning-based technique which combines Self-organizing map, variational autoencoder model, and Markov model, and we achieved a superior performance enhancement compared to the method using the point-based data.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.32 no.2C
• /
• pp.141-149
• /
• 2007

Associating the shoulder line with head location of the human body is useful in verifying, localizing and tracking persons in an image. Since the head line and the shoulder line, what we call ${\Omega}$-shape, move together in a consistent way within a limited range of deformation, we can build a statistical shape model using Active Shape Model (ASM). However, when the conventional ASM is applied to ${\Omega}$-shape fitting, it is very sensitive to background edges and clutter because it relies only on the local edge or gradient. Even though appearance is a good alternative feature for matching the target object to image, it is difficult to learn the appearance of the ${\Omega}$-shape because of the significant difference between people's skin, hair and clothes, and because appearance does not remain the same throughout the entire video. Therefore, instead of teaming appearance or updating appearance as it changes, we model the discriminative appearance where each pixel is classified into head, torso and background classes, and update the classifier to obtain the appropriate discriminative appearance in the current frame. Accordingly, we make use of two features in fitting ${\Omega}$-shape, edge gradient which is used for localization, and discriminative appearance which contributes to stability of the tracker. The simulation results show that the proposed method is very robust to pose change, occlusion, and illumination change in tracking the head and shoulder line of people. Another advantage is that the proposed method operates in real time.

• Smart Media Journal
• /
• v.5 no.2
• /
• pp.15-23
• /
• 2016

In this paper we propose the depth-poselets using body-part-poses and also propose the method to recognize the gesture. Since the gestures are composed of sequential poses, in order to recognize a gesture, it should emphasize to obtain the time series pose. Because of distortion and high degree of freedom, it is difficult to recognize pose correctly. So, in this paper we used partial pose for obtaining a feature of the pose correctly without full-body-pose. In this paper, we define the 16 gestures, a depth image using a learning image was generated based on the defined gestures. The depth poselets that were proposed in this paper consists of principal three-dimensional coordinates of the depth image and its depth image of the body part. In the training process after receiving the input defined gesture by using a depth camera in order to train the gesture, the depth poselets were generated by obtaining 3D joint coordinates. And part-gesture HMM were constructed using the depth poselets. In the testing process after receiving the input test image by using a depth camera in order to test, it extracts foreground and extracts the body part of the input image by comparing depth poselets. And we check part gestures for recognizing gesture by using result of applying HMM. We can recognize the gestures efficiently by using HMM, and the recognition rates could be confirmed about 89%.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.27 no.5
• /
• pp.1087-1097
• /
• 2017

As the penetration rate of smartphones increases, the number of malicious codes targeting smartphones is increasing. I 360 Security 's smartphone malware statistics show that malicious code increased 437 percent in the first quarter of 2016 compared to the fourth quarter of 2015. In particular, malicious applications, which are the main means of distributing malicious code on smartphones, are aimed at leakage of user information, data destruction, and money withdrawal. Often, it is operated by an API, which is an interface that allows you to control the functions provided by the operating system or programming language. In this paper, we propose a mechanism to detect malicious application based on the similarity of API pattern in normal application and malicious application by learning pattern of API in application derived from static analysis. In addition, we show a technique for improving the detection rate and detection rate for each label derived by using the corresponding mechanism for the sample data. In particular, in the case of the proposed mechanism, it is possible to detect when the API pattern of the new malicious application is similar to the previously learned patterns at a certain level. Future researches of various features of the application and applying them to this mechanism are expected to be able to detect new malicious applications of anti-malware system.

• Journal of Korean Home Economics Education Association
• /
• v.20 no.3
• /
• pp.215-230
• /
• 2008

Activity materials in textbook could facilitate students' oriented self-help learning. The purpose of this paper is to find out characteristics of activity materials in the housing area of middle school Technology and Home Economics and teacher's perception of them. The data were collected from 253 middle school teachers who had ever taught the housing unit in any of 6 textbooks. The results showed that the number of activity materials were differed by the characteristics of the materials such as type of materials, feature of non sentence materials, and type of activity, depend on authors as well as textbooks. In general, teachers interests in the materials were higher than those of students even the trends of the interests were the same. Adequacy of activity contents and related knowledge of teachers were higher than adequacy of level. Teachers thought time and extra search beyond class were barrier to full the interests of students. Further research is suggested to find out whether higher interests in the materials are related to the higher activating rate of them.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.38 no.6
• /
• pp.839-850
• /
• 2018

The flood damage in urban areas due to torrential rain is increasing with urbanization. For this reason, accurate and rapid flooding forecasting and expected inundation maps are needed. Predicting the extent of flooding for certain rainfalls is a very important issue in preparing flood in advance. Recently, government agencies are trying to provide expected inundation maps to the public. However, there is a lack of quantifying the extent of inundation caused by a particular rainfall scenario and the real-time prediction method for flood extent within a short time. Therefore the real-time prediction of flood extent is needed based on rainfall-runoff-inundation analysis. One/two dimensional model are continued to analyize drainage network, manhole overflow and inundation propagation by rainfall condition. By applying the various rainfall scenarios considering rainfall duration/distribution and return periods, the inundation volume and depth can be estimated and stored on a database. The Rainfall-Duration-Flooding Quantity (RDF) relationship curve based on the hydraulic analysis results and the Self-Organizing Map (SOM) that conducts unsupervised learning are applied to predict flooded area with particular rainfall condition. The validity of the proposed methodology was examined by comparing the results of the expected flood map with the 2-dimensional hydraulic model. Based on the result of the study, it is judged that this methodology will be useful to provide an unknown flood map according to medium-sized rainfall or frequency scenario. Furthermore, it will be used as a fundamental data for flood forecast by establishing the RDF curve which the relationship of rainfall-outflow-flood is considered and the database of expected inundation maps.

• Asian-Australasian Journal of Animal Sciences
• /
• v.32 no.7
• /
• pp.1015-1026
• /
• 2019

Objective: The objective of this study was to evaluate three different degrees of white striping (WS) addressing their automatic assessment and customer acceptance. The WS classification was performed based on a computer vision system (CVS), exploring different machine learning (ML) algorithms and the most important image features. Moreover, it was verified by consumer acceptance and purchase intent. Methods: The samples for image analysis were classified by trained specialists, according to severity degrees regarding visual and firmness aspects. Samples were obtained with a digital camera, and 25 features were extracted from these images. ML algorithms were applied aiming to induce a model capable of classifying the samples into three severity degrees. In addition, two sensory analyses were performed: 75 samples properly grilled were used for the first sensory test, and 9 photos for the second. All tests were performed using a 10-cm hybrid hedonic scale (acceptance test) and a 5-point scale (purchase intention). Results: The information gain metric ranked 13 attributes. However, just one type of image feature was not enough to describe the phenomenon. The classification models support vector machine, fuzzy-W, and random forest showed the best results with similar general accuracy (86.4%). The worst performance was obtained by multilayer perceptron (70.9%) with the high error rate in normal (NORM) sample predictions. The sensory analysis of acceptance verified that WS myopathy negatively affects the texture of the broiler breast fillets when grilled and the appearance attribute of the raw samples, which influenced the purchase intention scores of raw samples. Conclusion: The proposed system has proved to be adequate (fast and accurate) for the classification of WS samples. The sensory analysis of acceptance showed that WS myopathy negatively affects the tenderness of the broiler breast fillets when grilled, while the appearance attribute of the raw samples eventually influenced purchase intentions.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.23 no.4
• /
• pp.52-67
• /
• 2020

Recently, the Arctic has been exposed to snow-covered land due to melting permafrost every year, and the Korea Geographic Information Institute(NGII) provides polar spatial information service by establishing spatial information of the polar region. However, there is a lack of spatial information on vegetation sensitive to climate change. This research used a multi-temporal Sentinel-2 image to perform land cover classification of the Ny-Ålesund in Arctic Svalbard. In the pre-processing step, 10 bands and 6 vegetation spectral index were generated from multi-temporal Sentinel-2 images. In image-classification step is consisted of extracting the vegetation area through 8-class land cover classification and performing the vegetation species classification. The image classification algorithm used Random Forest to evaluate the accuracy and calculate feature importance through Out-Of-Bag(OOB). To identify the advantages of multi- temporary Sentinel-2 for vegetation classification, the overall accuracy was compared according to the number of images stacked and vegetation spectral index. Overall accuracy was 77% when using single-time Sentinel-2 images, but improved to 81% when using multi-time Sentinel-2 images. In addition, the overall accuracy improved to about 83% in learning when the vegetation index was used additionally. The most important spectral variables to distinguish between vegetation classes are located in the Red, Green, and short wave infrared-1(SWIR1). This research can be used as a basic study that optimizes input characteristics in performing the classification of vegetation in the polar regions.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.34 no.1
• /
• pp.25-33
• /
• 2021

With the development of machine learning techniques, various types of data such as vibration, temperature, and flow rate can be used to detect and diagnose abnormalities in machine conditions. In particular, in the field of the state monitoring of rotating machines, the fault diagnosis of machines using vibration data has long been carried out, and the methods are also very diverse. In this study, an experiment was conducted to collect vibration data from normal and abnormal compressors by installing accelerometers directly on rotary compressors used in household air conditioners. Data segmentation was performed to solve the data shortage problem, and the main features for the fault classification model were extracted through the chi-square test after statistical and physical features were extracted from the vibration data in the time domain. The support vector machine (SVM) model was developed to classify the normal or abnormal conditions of compressors and improve the classification accuracy through the hyperparameter optimization of the SVM.

• Journal of Intelligence and Information Systems
• /
• v.28 no.2
• /
• pp.307-332
• /
• 2022

One of the most intensively conducted research areas in business application study is a bankruptcy prediction model, a representative classification problem related to loan lending, investment decision making, and profitability to financial institutions. Many research demonstrated outstanding performance for bankruptcy prediction models using artificial intelligence techniques. However, since most machine learning algorithms are "black-box," AI has been identified as a prominent research topic for providing users with an explanation. Although there are many different approaches for explanations, this study focuses on explaining a bankruptcy prediction model using a counterfactual example. Users can obtain desired output from the model by using a counterfactual-based explanation, which provides an alternative case. This study introduces a counterfactual generation technique based on a genetic algorithm (GA) that leverages both domain knowledge (i.e., causal feasibility) and feature importance from a black-box model along with other critical counterfactual variables, including proximity, distribution, and sparsity. The proposed method was evaluated quantitatively and qualitatively to measure the quality and the validity.