• Asian Journal of Atmospheric Environment
• /
• v.9 no.4
• /
• pp.247-258
• /
• 2015

Exposure of high concentration of ground-level ozone (GLO) can trigger a variety of health problems including chest pain, coughing, throat irritation, asthma, bronchitis and congestion. There are substantial human and animal toxicological data that support health effects associated with exposure to ozone and associations have been observed with a wide range of outcomes in epidemiological studies. The aim of the present study is to estimate the spatial distributions of GLO using geostatistical method (ordinary kriging) for assessing the exposure level of ozone in the eastern part of Texas, U.S.A. GLO data were obtained from 63 U.S. EPA's monitoring stations distributed in the region of study during the period January, 2012 to December, 2012. The descriptive statistics indicate that the spatial monthly mean of daily maximum 8 hour ozone concentrations ranged from 30.33 ppb (in January) to 48.05 (in June). The monthly mean of daily maximum 8 hour ozone concentrations was relatively low during the winter months (December, January, and February) and the higher values observed during the summer months (April, May, and June). The higher level of spatial variations observed in the months of July (Standard Deviation: 10.33) and August (Standard Deviation: 10.02). This indicates the existence of regional variations in climatic conditions in the study area. The range of the semivariogram models varied from 0.372 (in November) to 15.59 (in April). The value of the range represents the spatial patterns of ozone concentrations. Kriging maps revealed that the spatial patterns of ozone concentration were not uniform in each month. This may be due to uneven fluctuation in the local climatic conditions from one region to another. Thus, the formation and dispersion processes of ozone also change unevenly from one region to another. The ozone maps clearly indicate that the concentration values found maximum in the north-east region of the study area in most of the months. Part of the coastal area also showed maximum concentrations during the months of October, November, December, and January.

• Journal of the Economic Geographical Society of Korea
• /
• v.11 no.3
• /
• pp.459-475
• /
• 2008

This study analyzes the network structure of the Metropolitan Seoul subway system by applying complex network analysis methods. For the purpose, we construct the Metropolitan Seoul subway system as a network graph, and then calculate various indices introduced in complex network analysis. Structural characteristics of Metropolitan Seoul subway network are discussed by these indices. In particular, this study determines the shortest paths between nodes based on the weighted distance (physical and time distance) as well as topological network distance, since urban travel movements are more sensitive for them. We introduce an accessibility measurement based on the shortest distance both in terms of physical distance and network distance, and then compare the spatial structure between two. Accessibility levels of the system have been getting up overall, and thus the accessibility gaps have been getting lessen between center located subway stops and remote ones during the last 10 years. Passenger traffic volumes are explored from real passenger transaction databases by utilizing data mining techniques, and mapped by GIS. Clear differences reveal between the spatial patterns of real passenger flows and accessibility. That is, passenger flows of the Metropolitan Seoul subway system are related with population distribution and land use around subway stops as well as the accessibility supported by the subway network.

• Journal of Information Processing Systems
• /
• v.20 no.3
• /
• pp.375-390
• /
• 2024

Edge computing architecture has effectively alleviated the computing pressure on cloud platforms, reduced network bandwidth consumption, and improved the quality of service for user experience; however, it has also introduced new security issues. Existing anomaly detection methods in big data scenarios with cloud-edge computing collaboration face several challenges, such as sample imbalance, difficulty in dealing with complex network traffic attacks, and difficulty in effectively training large-scale data or overly complex deep-learning network models. A lightweight deep-learning model was proposed to address these challenges. First, normalization on the user side was used to preprocess the traffic data. On the edge side, a trained Wasserstein generative adversarial network (WGAN) was used to supplement the data samples, which effectively alleviates the imbalance issue of a few types of samples while occupying a small amount of edge-computing resources. Finally, a trained lightweight deep learning network model is deployed on the edge side, and the preprocessed and expanded local data are used to fine-tune the trained model. This ensures that the data of each edge node are more consistent with the local characteristics, effectively improving the system's detection ability. In the designed lightweight deep learning network model, two sets of convolutional pooling layers of convolutional neural networks (CNN) were used to extract spatial features. The bidirectional long short-term memory network (BiLSTM) was used to collect time sequence features, and the weight of traffic features was adjusted through the attention mechanism, improving the model's ability to identify abnormal traffic features. The proposed model was experimentally demonstrated using the NSL-KDD, UNSW-NB15, and CIC-ISD2018 datasets. The accuracies of the proposed model on the three datasets were as high as 0.974, 0.925, and 0.953, respectively, showing superior accuracy to other comparative models. The proposed lightweight deep learning network model has good application prospects for anomaly traffic detection in cloud-edge collaborative computing architectures.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.14 no.4
• /
• pp.875-885
• /
• 2010

CBR (Case-Based Reasoning) is a technique to infer the relationships between existing data and case data, and the method to calculate similarity and Euclidean distance is mostly frequently being used. However, since those methods compare all the existing and case data, it also has a demerit that it takes much time for data search and filtering. Therefore, to solve this problem, various researches have been conducted. This paper suggests the method of SE(Speed Euclidean-distance) calculation that utilizes the patterns discovered in the existing process of computing similarity and Euclidean distance. Because SE calculation applies the patterns and weight found during inputting new cases and enables fast data extraction and short operation time, it can enhance computing speed for temporal or spatial restrictions and eliminate unnecessary computing operation. Through this experiment, it has been found that the proposed method improves performance in various computer environments or processing rate more efficiently than the existing method that extracts data using similarity or Euclidean method does.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.11 no.6
• /
• pp.703-710
• /
• 2018

Although various efforts have been made every year to reduce electric fire accidents such as accident analysis and inspection for electric fire accidents, there is no effective countermeasure due to lack of effective decision support system and existing cumulative data utilization method. The purpose of this study is to develop an algorithm for predicting electric fire based on data such as electric safety inspection data, electric fire accident information, building information, and weather information. Through the pre-processing of collected data for each institution such as Korea Electrical Safety Corporation, Meteorological Administration, Ministry of Land, Infrastructure, and Transport, Fire Defense Headquarters, convergence, analysis, modeling, and verification process, we derive the factors influencing electric fire and develop prediction models. The results showed insulation resistance value, humidity, wind speed, building deterioration(aging), floor space ratio, building coverage ratio and building use. The accuracy of prediction model using random forest algorithm was 74.7%.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.51 no.2
• /
• pp.68-80
• /
• 2023

With the recent changes in society and the introduction of new technologies, the usage patterns of parks have become diverse, leading to increased complexity in park management. As a result, there is a growing demand for flexible and diverse park management that can adapt to these new requirements. However, there is inadequate discussion on these new demands and whether urban park management policies can respond. Therefore, empirical research on how park usage patterns are evolving is critical. To address this, blog data, in which individuals share their experiences, was used to examine the spatial consumption patterns through semantic network and topic analysis. This study also explored whether these spatial consumption patterns exhibit experiential consumption characteristics according to the experience economy theory. The results showed that consumption behaviors, such as renting picnic sets and having food and drinks delivered, were prominent and that emotional experiences were pursued. Furthermore, these findings were consistent with the experiential consumption characteristics of the experience economy theory. This suggests that park planning and maintenance methods need to become more flexible and diverse in response to the changing demands for park usage.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.7 no.12
• /
• pp.3274-3292
• /
• 2013

Unsupervised methods for image segmentation are recently drawing attention because most images do not have labels or tags. A topic model is such an unsupervised probabilistic method that captures latent aspects of data, where each latent aspect, or a topic, is associated with one homogeneous region. The results of topic models, however, usually have noises, which decreases the overall segmentation performance. In this paper, to improve the performance of image segmentation using topic models, we propose two topic masks applicable to topic assignments of homogeneous regions obtained from topic models. The topic masks capture the noises among the assigned topic assignments or topic labels, and remove the noises by replacements, just like image masks for pixels. However, as the nature of topic assignments is different from image pixels, the topic masks have properties that are different from the existing image masks for pixels. There are two contributions of this paper. First, the topic masks can be used to reduce the noises of topic assignments obtained from topic models for image segmentation tasks. Second, we test the effectiveness of the topic masks by applying them to segmented images obtained from the Latent Dirichlet Allocation model and the Spatial Latent Dirichlet Allocation model upon the MSRC image dataset. The empirical results show that one of the masks successfully reduces the topic noises.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.3
• /
• pp.891-910
• /
• 2021

Previous QoS-aware service composition methods mainly focus on how to generate composite service with the optimal QoS efficiently for a single request. However, in the real application scenarios, there are multiple service requests and multiple service providers. It is more important to compose services with suboptimal QoS and maintain the load balance between services. To solve this problem, in this paper, we propose a service composition method, named as dynamically change and balancing composition method (DCBC). It assumes that the QoS of service is not static, and the services can adjust the value of QoS to gain more opportunities to be selected for composition. The method mainly includes two steps, which are the preprocessing step and the service selection step. In the preprocessing step, a backward global best QoS calculation is performed which regarding the static and dynamic QoS respectively; then guided by the global QoS, the feasible services can be selected efficiently in the service selection step. The experiments show that the DCBC method can not only improve the overall quality of composite services but also guarantee the fulfill ratio of requests and the load balance of services.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2008.11a
• /
• pp.307-310
• /
• 2008

GIS 기술의 발달로 많은 양의 공간 데이터가 축적됨에 따라 공간 데이터 마이닝의 중요성이 커지고 있다. 본 논문에서는 새로운 공간 데이터 마이닝 시스템인 SD-Miner를 제안한다. SD-Miner는 크게 GUI 모듈과 데이터 마이닝 함수 모듈, 데이터 관리 모듈의 세부분으로 구성된다. GUI 모듈은 사용자의 입력과 출력을 담당한다. SD-Miner의 핵심 부분인 데이터 마이닝 함수 모듈은 공간 데이터 마이닝의 주요 기법인 공간 클러스터링, 공간 분류, 공간 특성화, 시공간 연관규칙 탐사 기능을 제공한다. 데이터 관리 모듈은 DBMS를 이용하여 데이터를 저장하고 관리한다. 실제 공간 데이터를 이용한 마이닝을 수행함으로써 개발된 SD-Miner의 실용성을 규명하고, 의미 있는 마이닝 결과들을 도출한다.

• Geophysics and Geophysical Exploration
• /
• v.17 no.4
• /
• pp.209-215
• /
• 2014

In order to develop a new mineral exploration technique, a study was carried out about the potential mapping of Moisan area using SIP (Spectral Induced Polarization) data. The SIP inversion results were classified according to the geological regions, and the distribution characteristics of resistivity and phase values of SIP data were analyzed at the ore region. Based on the characteristics of SIP of ore bodies, we performed 3D potential mapping of Moisan area. The analyzed potential map was verified using that the locations and patterns of high potential regions of the results are well matched with those of the known ore bodies. If we get the higher spatial resolution SIP data, the potential mapping technique using SIP data can be effectively applied to the estimation of mining deposit.