• Proceedings of the KAIS Fall Conference
• /
• 2003.11a
• /
• pp.223-230
• /
• 2003

Feature-based similarity retrieval has become an important research issue in multimedia database systems. The features of multimedia data are useful for discriminating between multimedia objects (e 'g', documents, images, video, music score, etc.). For example, images are represented by their color histograms, texture vectors, and shape descriptors, and are usually high-dimensional data. The performance of conventional multidimensional data structures(e'g', R- Tree family, K-D-B tree, grid file, TV-tree) tends to deteriorate as the number of dimensions of feature vectors increases. The R＊-tree is the most successful variant of the R-tree. In this paper, we propose a SOM-based R＊-tree as a new indexing method for high-dimensional feature vectors.The SOM-based R＊-tree combines SOM and R＊-tree to achieve search performance more scalable to high dimensionalities. Self-Organizing Maps (SOMs) provide mapping from high-dimensional feature vectors onto a two dimensional space. The mapping preserves the topology of the feature vectors. The map is called a topological of the feature map, and preserves the mutual relationship (similarity) in the feature spaces of input data, clustering mutually similar feature vectors in neighboring nodes. Each node of the topological feature map holds a codebook vector. A best-matching-image-list. (BMIL) holds similar images that are closest to each codebook vector. In a topological feature map, there are empty nodes in which no image is classified. When we build an R＊-tree, we use codebook vectors of topological feature map which eliminates the empty nodes that cause unnecessary disk access and degrade retrieval performance. We experimentally compare the retrieval time cost of a SOM-based R＊-tree with that of an SOM and an R＊-tree using color feature vectors extracted from 40, 000 images. The result show that the SOM-based R＊-tree outperforms both the SOM and R＊-tree due to the reduction of the number of nodes required to build R＊-tree and retrieval time cost.

• Journal of the Korean Institute of Electrical and Electronic Material Engineers
• /
• v.33 no.4
• /
• pp.303-309
• /
• 2020

This study proposes a crack identification algorithm to analyze the surface condition of porcelain insulators and to efficiently visualize cracks. The proposed image processing algorithm for crack identification consists of two primary steps. In the first step, the brightness is eliminated by converting the image to the lab color space. Then, the background is removed by the K-means clustering method. After that, the optimum image treatment is applied using morphological image processing and median filtering to remove unnecessary noise, such as blobs. In the second step, the preprocessed image is converted to grayscale, and any cracks present in the image are identified. Next, the region properties, such as the number of pixels and the ratio of the major to the minor axis, are used to separate the cracks from the noise. Using this image processing algorithm, the precision of crack identification for all the sample images was approximately 80%, and the F1 score was approximately 70. Thus, this method can be helpful for efficient crack monitoring.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.19 no.5
• /
• pp.730-736
• /
• 2009

It is more important to analysis of huge gemonics data in Bioinformatics. Here we present a novel datamining approach to predict structure and function using protein's primnary structure only. We propose not also to develope n-Block substring search algorithm in reducing enormous search space effectively in relation to feature selection, but to formulate weighted linear algorithm in a prediction of structure and function of a protein using primary structure. And we show efficient in protein domain characterization and classification by calculation weight value in determining domain association in each selected substring, and also reveal that more efficient results are acquired through claculated model score result in an inference about degree of association with each CDS(coding sequence) in domain.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2016.05a
• /
• pp.197-197
• /
• 2016

Forecasting future drought events in a region plays a major role in water management and risk assessment of drought occurrences. The creeping characteristics of drought make it possible to mitigate drought's effects with accurate forecasting models. Drought forecasts are inevitably plagued by uncertainties, making it necessary to derive forecasts in a probabilistic framework. In this study, a new probabilistic scheme is proposed to forecast droughts, in which a discrete-time finite state-space hidden Markov model (HMM) is used aggregated with the Representative Concentration Pathway 8.5 (RCP) precipitation projection (HMM-RCP). The 3-month standardized precipitation index (SPI) is employed to assess the drought severity over the selected five stations in South Kore. A reversible jump Markov chain Monte Carlo algorithm is used for inference on the model parameters which includes several hidden states and the state specific parameters. We perform an RCP precipitation projection transformed SPI (RCP-SPI) weight-corrected post-processing for the HMM-based drought forecasting to derive a probabilistic forecast that considers uncertainties. Results showed that the HMM-RCP forecast mean values, as measured by forecasting skill scores, are much more accurate than those from conventional models and a climatology reference model at various lead times over the study sites. In addition, the probabilistic forecast verification technique, which includes the ranked probability skill score and the relative operating characteristic, is performed on the proposed model to check the performance. It is found that the HMM-RCP provides a probabilistic forecast with satisfactory evaluation for different drought severity categories, even with a long lead time. The overall results indicate that the proposed HMM-RCP shows a powerful skill for probabilistic drought forecasting.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.24 no.3
• /
• pp.10-31
• /
• 2021

The mixed-use concept definition, this study reveals, is that the mixing three or more major types of urban uses implements for economical, social and environmental values in our urban space. With this definition the study explores Seoul's mixed-use phenomenon. The quantification method, the study uses, is the relative entropy which calculate the balance of each urban use in a certain area. The relative entropy method, also known as the LUM(land-use mix score), uses three urban-use categories which is derived from the mixed-use concept definition. Hundreds of building-use types in the building regulations are categorized and calculate the LUM of Seoul's legal-status neighborhoods. The result interpreted as the criteria of Seoul's mixed-use phenomenon and categorize mixed land-use status in a certain value: 'non mixed-use' category has a value 0.631 and below, 'unbalanced mixed-use' category has a value between 0.631 and 0.884, 'balanced mixed-use' category has a value between 0.884 and 0.991 and 'complete mixed-use' category has a value 0.991 and over.

• Journal of Korean Academy of Nursing
• /
• v.49 no.2
• /
• pp.113-125
• /
• 2019

Purpose: The purpose of this study was to examine the effects of a daily life-based physical activity enhancement program performed by middle-aged women at risk for cardiovascular disease. Methods: This study used a randomized control group pretest-posttest design. Middle-aged women aged 45 to 64 were recruited from two outpatient cardiology departments, and randomly assigned to an experimental group (n=28) and a control group (n=30). For the experimental group, after providing one-on-one counseling and education, we provided customized text messages to motivate them in daily life. To monitor the practice of physical activity, they also used an exercise diary and mobile pedometer for 12 weeks. Subjects' physical activities (MET-min/week) were measured using the International Physical Activity Questionnaire (IPAQ). Their physiological data were obtained by blood tests using a portable analyzer, and the data were analyzed using the SPSS 21.0/WIN program. Results: There were significant differences in exercise self-efficacy, health behavior, IPAQ score, body fat, body muscle, and fasting blood sugar between the two groups. However, there were no significant differences in total cholesterol, hemoglobin A1c, high-density lipoprotein cholesterol, and waist-to-hip ratio. Conclusion: Strengthening physical activity in daily life without being limited by cost burden and time and space constraints. Therefore, it is essential to motivate middle-aged women at risk for cardiovascular disease to practice activities that are easily performed in their daily lives.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.18 no.2
• /
• pp.29-37
• /
• 2019

In this study, emotional adjectives about the operating sound quality of the vehicle power seat are constructed, and the effectiveness of the emotional adjectives are verified by evaluating the operating sound quality. First, emotional adjectives were collected from the literature related to the automobile field and other sound qualities. A questionnaire was made using these adjectives. The questionnaire was designed to be able to select all adjectives that could express the operating noise of the power seat slide adjuster by applying the multiple- response method. Next, a subjective sound quality evaluation was conducted using the emotional adjectives. In the evaluation, we first recorded the operating noise for two power seats. Second, the subjective sound quality evaluation was performed on the recorded operating noise using a loudspeaker. Finally, through a statistical analysis on the sound quality evaluation results, the relationship between the semantic space and the preference score was verified, and the validity of the emotional adjectives was verified.

• Journal of the Korean Society of School Health
• /
• v.35 no.3
• /
• pp.143-151
• /
• 2022

Purpose: The purpose of this study was to examine the effects of being aware of the physical and psychosocial environment of the school on subjective feeling of happiness in Korean middle and high school students. Methods: The data of "Health and lifestyle Survey (2019)" conducted by the National Youth Policy Institute were analyzed after receiving approval though the website. A total of 5,311 middle and high school students were included in the analysis. Descriptive statistics, t-test, one-way ANOVA, pearson correlation, and multiple regression analysis were executed using SAS 9.4. Results: The mean score of subjective feeling of happiness was 6.92±0.56 out of 10. From the univariate analysis, the more positive the perception of the physical school environment was, such as classrooms, restrooms, exercise facilities, catering facilities, health facilities, other school facilities and school uniform, the higher the subjective feeling of happiness was (p for all <.001). In addition, the psychosocial environment of the school was significantly related to the happiness of adolescents (p<.001). After controlling for gender, school level, school grade, socio-economic status, and stress, positive perception of classrooms (B=0.04, p<.001), catering facilities (B=0.01, p=.021), health facilities (B=0.08, p<.001), and the psychosocial environment of the school (B=0.18, p<.001) was significantly associated with happiness of the students. Conclusion: Positive perception of the school environment was found to increase happiness in adolescents. Therefore, efforts should be made to make classrooms, catering facilities, and health facilities a pleasant space as well as to create a school atmosphere that values health.

• Korean Journal of Construction Engineering and Management
• /
• v.23 no.5
• /
• pp.34-42
• /
• 2022

Construction site layout is attracting attention as efficient use of construction site space greatly affects the duration and cost of the overall construction. Therefore, there are many studies that automate and optimize construction site layout planning. However, the usability of construction site, which consists of goal variables of the studies, has still been unknown. Therefore, the authors present the evaluation criteria for usability of construction site layout and evaluate the usability of domestic construction sites through user survey. Furthermore, the difference in usability between construction site managers and construction site workers was confirmed. As a result of the survey, domestic construction site layout had a low effectiveness and had the lowest score in the environment category. In addition, construction site workers scored lower overall than construction site managers. Through such usability evaluation results, it contributed to the construction site layout theory by assessing current construction site layout practice and suggesting an improvement direction for automating site layout planning.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.12
• /
• pp.4008-4023
• /
• 2022

Since machine learning was introduced into cross-site scripting (XSS) attack detection, many researchers have conducted related studies and achieved significant results, such as saving time and labor costs by not maintaining a rule database, which is required by traditional XSS attack detection methods. However, this topic came across some problems, such as poor generalization ability, significant false negative rate (FNR) and false positive rate (FPR). Moreover, the automatic clustering property of graph convolutional networks (GCN) has attracted the attention of researchers. In the field of natural language process (NLP), the results of graph embedding based on GCN are automatically clustered in space without any training, which means that text data can be classified just by the embedding process based on GCN. Previously, other methods required training with the help of labeled data after embedding to complete data classification. With the help of the GCN auto-clustering feature and labeled data, this research proposes an approach to detect XSS attacks (called GCNXSS) to mine the dependencies between the units that constitute an XSS payload. First, GCNXSS transforms a URL into a word homogeneous graph based on word co-occurrence relationships. Then, GCNXSS inputs the graph into the GCN model for graph embedding and gets the classification results. Experimental results show that GCNXSS achieved successful results with accuracy, precision, recall, F1-score, FNR, FPR, and predicted time scores of 99.97%, 99.75%, 99.97%, 99.86%, 0.03%, 0.03%, and 0.0461ms. Compared with existing methods, GCNXSS has a lower FNR and FPR with stronger generalization ability.