• Journal of the HCI Society of Korea
• /
• v.2 no.2
• /
• pp.35-43
• /
• 2007

This paper presents a system for image matching and recognition based on image feature detection and description techniques from artificial satellite photographs. We propose some kind of parameters from the varied environmental elements happen by image handling process. The essential point of this experiment is analyzes that affects match rate and recognition accuracy when to change of state of each parameter. The proposed system is basically inspired by Lowe's SIFT(Scale-Invariant Transform Feature) algorithm. The descriptors extracted from local affine invariant regions are saved into database, which are defined by k-means performed on the 128-dimensional descriptor vectors on an artificial satellite photographs from Google earth. And then, a label is attached to each cluster of the feature database and acts as guidance for an appeared building's information in the scene from camera. This experiment shows the various parameters and compares the affected results by changing parameters for the process of image matching and recognition. Finally, the implementation and the experimental results for several requests are shown.

• Journal of the Korean Society of Costume
• /
• v.50 no.7
• /
• pp.97-111
• /
• 2000

The purpose of this study were to segment the hair care cosmetics market according to the benefits sought, to categorize the information sources on the hair care cosmetics, and to characterize the profiles of the segmentized groups of university students. Self-administered questionnaires were distributed to 457 university students in Chonbuk province from Jul. 10 to Jul. 21, 1999. Frequencies and percentages were calculated, and factor analysis, cluster analysis, one-way ANOVA, and $\chi$$^2$-test were used. The results were: 1. University student's benefit variables on hair care cosmetics were classified into special function, fashion, practicality, brand, fragrance, styling, nutritional reinforcement, and economy. And they were segmentized into the feeling pursuit, the multi-benefit pursuit, the practicality pursuit, the benefit unconscious, and the function pursuit. The information sources were classified into marketer-dominated sources, neutral sources and consumer -dominated sources. 2. The feeling pursuit strongly sought for fashion, brand and fragrance pursuit, but considered economy less, chiefly used the marketer-dominated and neutral information sources, and showed much interests in hair care cosmetics, and were consisted of women dominantly. The multi-benefits pursuit sought for various kinds of benefits from hair care cosmetics, depended heavily on various kinds of information sources, were well aware of their hair types and instructions on the hair care cosmetics label, and were consisted of women dominantly. The practicality pursuit highly sought for practicality, but low on the fashion, were not aware of their hair style, haler care, hair health status and hair type, and almost half of them are men. The benefit unconscious showed low concern about, all kinds of benefits and hair care cosmetics, and were consisted of more men than women. The function pursuit highly sought for special function and nutritional reinforcement, mainly depended on the consumer-dominated sources. and showed low concern about their hair style and hair care.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.5
• /
• pp.155-164
• /
• 2024

This study proposes an unsupervised learning-based clustering model to estimate the ESG ratings of domestic public institutions. To achieve this, the optimal number of clusters was determined by comparing spectral clustering and k-means clustering. These results are guaranteed by calculating the Davies-Bouldin Index (DBI), a model performance index. The DBI values were 0.734 for spectral clustering and 1.715 for k-means clustering, indicating lower values showed better performance. Thus, the superiority of spectral clustering was confirmed. Furthermore, T-test and ANOVA were used to reveal statistically significant differences between ESG non-financial data, and correlation coefficients were used to confirm the relationships between ESG indicators. Based on these results, this study suggests the possibility of estimating the ESG performance ranking of each public institution without existing ESG ratings. This is achieved by calculating the optimal number of clusters, and then determining the sum of averages of the ESG data within each cluster. Therefore, the proposed model can be employed to evaluate the ESG ratings of various domestic public institutions, and it is expected to be useful in domestic sustainable management practice and performance management.

• The KIPS Transactions:PartC
• /
• v.12C no.5 s.101
• /
• pp.649-658
• /
• 2005

Since the Network based attack Is extensive in the real state of damage, It is very important to detect intrusion quickly at the beginning. But the intrusion detection using supervised learning needs either the preprocessing enormous data or the manager's analysis. Also it has two difficulties to detect abnormal traffic that the manager's analysis might be incorrect and would miss the real time detection. In this paper, we propose a traffic attributes correlation analysis mechanism based on self-organizing maps(SOM) for the real-time intrusion detection. The proposed mechanism has three steps. First, with unsupervised learning build a map cluster composed of similar traffic. Second, label each map cluster to divide the map into normal traffic and abnormal traffic. In this step there is a rule which is created through the correlation analysis with SOM. At last, the mechanism would the process real-time detecting and updating gradually. During a lot of experiments the proposed mechanism has good performance in real-time intrusion to combine of unsupervised learning and supervised learning than that of supervised learning.

• Journal of Nutrition and Health
• /
• v.44 no.6
• /
• pp.527-536
• /
• 2011

This study was performed to analyze children's perceptions and practice levels according to gender and obesity status using a dietary life safety index. A national survey was conducted on fifth grade children (n = 2,400), who were selected using three-stage stratified cluster sampling from 16 provinces. The average height was 144.8 cm, and weight was 38.8 kg. The average body mass index was 18.4 kg/$m^2$ and underweight, overweight, and obese children were identified using the 2009 KHNANES cutoff values, which were 5.3%, 10%, and 5.9%, respectively. The perception and practice scores for hand-washing prior to eating were high and the score for willing to buy at a clean store was also high. However, students answered that the hygiene level of food stores near the school was poor. More students skipped breakfast than lunch or dinner. The frequency scores for fruit and vegetables were significantly higher for girls than those for boys. Students had a good understanding of nutrition labeling but did not frequently check the label. Seventy-five percent of the students tried to avoid high calorie foods with low nutritional value, but only 40% had the appropriate knowledge about high calorie foods with low nutritional value. Girls had better dietary life perception and practice levels than those of boys. No differences in perception or practice levels were observed based on obesity status. Nutrition education on the importance of eating breakfast and having accurate knowledge on nutrition labeling and high calorie foods with low nutritional value is needed. Behavior-centered education should be implemented to improve the perceptions and practice level of student's dietary life.

• Journal of Advanced Navigation Technology
• /
• v.22 no.1
• /
• pp.20-26
• /
• 2018

In this paper, we propose a moving object detection and tracking algorithm based on multi-frame feature point tracking information to reduce false positives. However, there are problems of detection error and tracking speed in existing studies. In order to compensate for this, we first calculate the corner feature points and the optical flow of multiple frames for camera movement compensation and object tracking. Next, the tracking error of the optical flow is reduced by the multi-frame forward-backward tracking, and the traced feature points are divided into the background and the moving object candidate based on homography and RANSAC algorithm for camera movement compensation. Among the transformed corner feature points, the outlier points removed by the RANSAC are clustered and the outlier cluster of a certain size is classified as the moving object candidate. Objects classified as moving object candidates are tracked according to label tracking based data association analysis. In this paper, we prove that the proposed algorithm improves both precision and recall compared with existing algorithms by using quadrotor image - based detection and tracking performance experiments.

• Journal of Distribution Science
• /
• v.9 no.1
• /
• pp.49-59
• /
• 2011

Although the South Korean organic food market is in the infancy compared to other industrialized countries, Korean consumers'interest in organic food and retail stores devoting space to organic products have been rapidly increasing. Despite the fact of organic food popularity, the term "organic" is interpreted differently by individuals. As opposed to the US, Japan and the EU where have operated an integrated organic food labelling system, Korea has adopted complex organic labelling systems regulated by several different government bodies. As a result, complicated food labelling standards make consumers confused when purchasing organic foods. Furthermore, in terms of country of origin (COO), it is argued by a lot of researchers that COO effects vary from product to product and from country to country; moreover, other informational cues such as brand and price can influence COO effects. In modern society, COO labelling has been complicated, due to the sourcing, manufacturing and market locations of merchandise spread over the world. Accordingly, the evaluation of COO effects has become complex. In order to examine these issues, a quantitative research was selected to classify the commonfeatures of organic food consumers and construct statistics such as the extent to which people are aware of organic food and COO labellingvia a questionnaire which took place in two cities in Korea with a cluster sample of 161 organic food purchasers. As for the data analysis, one-way analysis of variance (ANOVA), T-tests, bivariate crosstatulations with Cramer's V were conducted,depending on the characteristics of variables and the assumptions the research data need to fit. It has been concluded that in general, Korean organic consumers comprehend the term "organic"in a closer way to the general concept rather than technical term, thus people do not appreciate environmentally labels which include organic food labels, although marital status influence the degree of label awareness, regardless of gender, age, education level and so on. Regarding COO effects on organic food, home organic products were Korean consumers'first choice over those from industrialized countries and developing nations. Specifically, in processed organic product category, domestically cultivated and processed organic products were absolutely preferred to leading national brands produced with imported ingredients and international brands. However, due to a lack of checks of ingredients' COO, consumers tend to purchase a leading national organic food brand, believing that it is a pure organic food sourced domestically. As a consequence, this research has suggested some important managerial implications and future research directions. In order to prevent consumer confusion when buying organic foods, it should be noted that consumers do not comprehend the organic food certifications, due to complicated labelling systems for organic produce and processed organic foods. Therefore, government bodies related to organic food distribution have to know consumers' perception of organic food labels and the significance of customer-oriented labels and reestablish labelling standards. Similarly, public advertising should be followed to raise public awareness of the labelling to enable customers to have the correct information. In addition, not only international marketers but also domestic marketers need to understand COO images and also the influence COO of ingredients has on the image of an organic product.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.36 no.12B
• /
• pp.1450-1458
• /
• 2011

The HPcN (Hybrid & high Performance Convergence Network) in research networks means environment which can provide both computing resource such as supercomputer, cluster and network resource to application researchers in the field of medical, bio, aerospace and e-science. The most representative research network in Korea, KREONET has been developing following technologies through the HERO (Hybrid Networking project for research oriented infrastructure) from 200S. First, we have constructed and deployed a control plane technology which can provide a connection oriented network dynamically. Second, the integrated resource management system technology has been developing for reservation and allocation of both computing and network resources, whenever users want to utilize them. In this paper, a testbed network is presented, which is possible to reserve and allocate network resource using the integrated resource management system. We reserve network resource through GNSI (Grid Network Service Interface) messages between GRS (Global Resource Scheduler) and NRM (Network Resource Manager) and allocate network resource through GUNI (Grid User Network Interface) messages between the NRM (network resource manager) and routers, based on reservation information provided from a user on the web portal. It is confirmed that GUNI interface messages are delivered from the NRM to each router at the starting of reservation time and traffic is transmitted through LSP allocated by the NRM.

• Journal of Intelligence and Information Systems
• /
• v.27 no.3
• /
• pp.57-73
• /
• 2021

Maintenance and prevention of failure through anomaly detection of ICT infrastructure is becoming important. System monitoring data is multidimensional time series data. When we deal with multidimensional time series data, we have difficulty in considering both characteristics of multidimensional data and characteristics of time series data. When dealing with multidimensional data, correlation between variables should be considered. Existing methods such as probability and linear base, distance base, etc. are degraded due to limitations called the curse of dimensions. In addition, time series data is preprocessed by applying sliding window technique and time series decomposition for self-correlation analysis. These techniques are the cause of increasing the dimension of data, so it is necessary to supplement them. The anomaly detection field is an old research field, and statistical methods and regression analysis were used in the early days. Currently, there are active studies to apply machine learning and artificial neural network technology to this field. Statistically based methods are difficult to apply when data is non-homogeneous, and do not detect local outliers well. The regression analysis method compares the predictive value and the actual value after learning the regression formula based on the parametric statistics and it detects abnormality. Anomaly detection using regression analysis has the disadvantage that the performance is lowered when the model is not solid and the noise or outliers of the data are included. There is a restriction that learning data with noise or outliers should be used. The autoencoder using artificial neural networks is learned to output as similar as possible to input data. It has many advantages compared to existing probability and linear model, cluster analysis, and map learning. It can be applied to data that does not satisfy probability distribution or linear assumption. In addition, it is possible to learn non-mapping without label data for teaching. However, there is a limitation of local outlier identification of multidimensional data in anomaly detection, and there is a problem that the dimension of data is greatly increased due to the characteristics of time series data. In this study, we propose a CMAE (Conditional Multimodal Autoencoder) that enhances the performance of anomaly detection by considering local outliers and time series characteristics. First, we applied Multimodal Autoencoder (MAE) to improve the limitations of local outlier identification of multidimensional data. Multimodals are commonly used to learn different types of inputs, such as voice and image. The different modal shares the bottleneck effect of Autoencoder and it learns correlation. In addition, CAE (Conditional Autoencoder) was used to learn the characteristics of time series data effectively without increasing the dimension of data. In general, conditional input mainly uses category variables, but in this study, time was used as a condition to learn periodicity. The CMAE model proposed in this paper was verified by comparing with the Unimodal Autoencoder (UAE) and Multi-modal Autoencoder (MAE). The restoration performance of Autoencoder for 41 variables was confirmed in the proposed model and the comparison model. The restoration performance is different by variables, and the restoration is normally well operated because the loss value is small for Memory, Disk, and Network modals in all three Autoencoder models. The process modal did not show a significant difference in all three models, and the CPU modal showed excellent performance in CMAE. ROC curve was prepared for the evaluation of anomaly detection performance in the proposed model and the comparison model, and AUC, accuracy, precision, recall, and F1-score were compared. In all indicators, the performance was shown in the order of CMAE, MAE, and AE. Especially, the reproduction rate was 0.9828 for CMAE, which can be confirmed to detect almost most of the abnormalities. The accuracy of the model was also improved and 87.12%, and the F1-score was 0.8883, which is considered to be suitable for anomaly detection. In practical aspect, the proposed model has an additional advantage in addition to performance improvement. The use of techniques such as time series decomposition and sliding windows has the disadvantage of managing unnecessary procedures; and their dimensional increase can cause a decrease in the computational speed in inference.The proposed model has characteristics that are easy to apply to practical tasks such as inference speed and model management.

• Journal of Intelligence and Information Systems
• /
• v.19 no.3
• /
• pp.1-23
• /
• 2013

To discover significant social issues such as unemployment, economy crisis, social welfare etc. that are urgent issues to be solved in a modern society, in the existing approach, researchers usually collect opinions from professional experts and scholars through either online or offline surveys. However, such a method does not seem to be effective from time to time. As usual, due to the problem of expense, a large number of survey replies are seldom gathered. In some cases, it is also hard to find out professional persons dealing with specific social issues. Thus, the sample set is often small and may have some bias. Furthermore, regarding a social issue, several experts may make totally different conclusions because each expert has his subjective point of view and different background. In this case, it is considerably hard to figure out what current social issues are and which social issues are really important. To surmount the shortcomings of the current approach, in this paper, we develop a prototype system that semi-automatically detects social issue keywords representing social issues and problems from about 1.3 million news articles issued by about 10 major domestic presses in Korea from June 2009 until July 2012. Our proposed system consists of (1) collecting and extracting texts from the collected news articles, (2) identifying only news articles related to social issues, (3) analyzing the lexical items of Korean sentences, (4) finding a set of topics regarding social keywords over time based on probabilistic topic modeling, (5) matching relevant paragraphs to a given topic, and (6) visualizing social keywords for easy understanding. In particular, we propose a novel matching algorithm relying on generative models. The goal of our proposed matching algorithm is to best match paragraphs to each topic. Technically, using a topic model such as Latent Dirichlet Allocation (LDA), we can obtain a set of topics, each of which has relevant terms and their probability values. In our problem, given a set of text documents (e.g., news articles), LDA shows a set of topic clusters, and then each topic cluster is labeled by human annotators, where each topic label stands for a social keyword. For example, suppose there is a topic (e.g., Topic1 = {(unemployment, 0.4), (layoff, 0.3), (business, 0.3)}) and then a human annotator labels "Unemployment Problem" on Topic1. In this example, it is non-trivial to understand what happened to the unemployment problem in our society. In other words, taking a look at only social keywords, we have no idea of the detailed events occurring in our society. To tackle this matter, we develop the matching algorithm that computes the probability value of a paragraph given a topic, relying on (i) topic terms and (ii) their probability values. For instance, given a set of text documents, we segment each text document to paragraphs. In the meantime, using LDA, we can extract a set of topics from the text documents. Based on our matching process, each paragraph is assigned to a topic, indicating that the paragraph best matches the topic. Finally, each topic has several best matched paragraphs. Furthermore, assuming there are a topic (e.g., Unemployment Problem) and the best matched paragraph (e.g., Up to 300 workers lost their jobs in XXX company at Seoul). In this case, we can grasp the detailed information of the social keyword such as "300 workers", "unemployment", "XXX company", and "Seoul". In addition, our system visualizes social keywords over time. Therefore, through our matching process and keyword visualization, most researchers will be able to detect social issues easily and quickly. Through this prototype system, we have detected various social issues appearing in our society and also showed effectiveness of our proposed methods according to our experimental results. Note that you can also use our proof-of-concept system in http://dslab.snu.ac.kr/demo.html.