• Journal of Korea Water Resources Association
• /
• v.56 no.2
• /
• pp.139-150
• /
• 2023

Terretial LiDAR surveying is highly useful for maintenance of civil facilities as it can easily detect the temporal deformation of structures or topography. However, for river facilities such as levess, it is difficult to detect the deformation of the topography or structure under vegetations due to the influence of vegetation. Vegetation filters can be divided into color filters and morphological filters. In this study, combined filters with color and morphology are developed to improve the accuracy of vegetation filters. 8 color filters, 6 morphological filters, and 4 combined filters are applied to the vegetation removal on the embankment slope, and their accuracy and calculation time are compared. Color filters show a short calculation time, but the accuracy was low in the vegetation area. Morphological filters show high accuracy in the vegetation area, but low accuracy in places with severe local topographical changes such as heavy rocks. Combined filters also show a tendency similar to morphological filters, but in the case of ExGGM, the accuracy is excellent in both the vegetation and rock area. Considering the accuracy and calculation time, the combined filter ExGGM is suitable for general cases, and the shape filter GrMIn or the complex filter ExGISL is suitable for cases where the local topographical change is not severe.

• Journal of Korea Water Resources Association
• /
• v.56 no.10
• /
• pp.641-653
• /
• 2023

As climate change and urbanization are causing unprecedented natural disasters in urban areas, it is crucial to have urban flood predictions with high fidelity and accuracy. However, conventional physically- and deep learning-based urban flood modeling methods have limitations that require a lot of computer resources or data for high-resolution flooding analysis. In this study, we propose and implement a method for improving the spatial resolution of urban flood analysis using a deep learning based super-resolution technique. The proposed approach converts low-resolution flood maps by physically based modeling into the high-resolution using a super-resolution deep learning model trained by high-resolution modeling data. When applied to two cases of retrospective flood analysis at part of City of Portland, Oregon, U.S., the results of the 4-m resolution physical simulation were successfully converted into 1-m resolution flood maps through super-resolution. High structural similarity between the super-solution image and the high-resolution original was found. The results show promising image quality loss within an acceptable limit of 22.80 dB (PSNR) and 0.73 (SSIM). The proposed super-resolution method can provide efficient model training with a limited number of flood scenarios, significantly reducing data acquisition efforts and computational costs.

• Journal of the Korean Geosynthetics Society
• /
• v.23 no.2
• /
• pp.9-17
• /
• 2024

When constructing on soft ground, managing ground settlement and safety is crucial. However, there often exists a significant disparity between the actual behavior of the ground and the design plans. In this study, we aimed to compare and analyze the difference between the predicted settlement based on theoretical formulas and the measured settlement during construction, in order to predict settlement. For this purpose, we analyzed settlement data from 18 construction sites. The results indicated that the back analysis settlement values were similar to the measured settlement values, whereas the design settlement values were significantly higher compared to the measured settlement values. Specifically, the design settlement values were 1.2 to 1.4 times higher than those derived from back analysis using measured values. The RMSE analysis revealed a value of 0.6212m for the design settlement and 0.1697m for the back analysis settlement. The difference between the back analysis settlement and the measured settlement was more than 70% lower than the difference between the design settlement and the measured settlement. This indicates that the back analysis settlement values exhibit lower error rates compared to the design settlement values.

• Korean Chemical Engineering Research
• /
• v.62 no.1
• /
• pp.27-35
• /
• 2024

Fuel gases such as methane and propane are used in explosion hazardous area of domestic plants and can form non-uniform mixtures with the influence of process conditions due to leakage. The fire-explosion risk assessment using literature data measured under uniform mixtures, damage prediction can be obtained the different results from actual explosion accidents by gas leaks. An explosion characteristics such as explosion pressure and flame velocity of non-uniform gas mixtures with concentration change similar to that of facility leak were examined. The experiments were conducted in a closed 0.82 m long stainless steel duct with observation recorded by color high speed camera and piezo pressure sensor. Also we proposed the quantification method of non-uniform mixtures from a regression analysis model on the change of concentration difference with time in explosion duct. For the non-uniform condition of this study, the area of flame surface enlarged with increasing the concentration non-uniform in the flame propagation of methane and was similar to the wrinkled flame structure existing in a turbulent flame. The time to peak pressure of methane decreased as the non-uniform increased and the explosion pressure increased with increasing the non-uniform. The ranges of K_G (Deflagration index) of methane with the concentration non-uniform were 1.30 to 1.58 [MPa·m/s] and the increase rate of K_G was 17.7% in methane with changing from uniform to non-uniform.

• Journal of Intelligence and Information Systems
• /
• v.17 no.1
• /
• pp.111-125
• /
• 2011

Clustering is a process of grouping similar or relevant documents into a cluster and assigning a meaningful concept to the cluster. By this process, clustering facilitates fast and correct search for the relevant documents by narrowing down the range of searching only to the collection of documents belonging to related clusters. For effective clustering, techniques are required for identifying similar documents and grouping them into a cluster, and discovering a concept that is most relevant to the cluster. One of the problems often appearing in this context is the detection of a complex concept that overlaps with several simple concepts at the same hierarchical level. Previous clustering methods were unable to identify and represent a complex concept that belongs to several different clusters at the same level in the concept hierarchy, and also could not validate the semantic hierarchical relationship between a complex concept and each of simple concepts. In order to solve these problems, this paper proposes a new clustering method that identifies and represents complex concepts efficiently. We developed the Hierarchical Overlapping Clustering (HOC) algorithm that modified the traditional Agglomerative Hierarchical Clustering algorithm to allow overlapped clusters at the same level in the concept hierarchy. The HOC algorithm represents the clustering result not by a tree but by a lattice to detect complex concepts. We developed a system that employs the HOC algorithm to carry out the goal of complex concept detection. This system operates in three phases; 1) the preprocessing of documents, 2) the clustering using the HOC algorithm, and 3) the validation of semantic hierarchical relationships among the concepts in the lattice obtained as a result of clustering. The preprocessing phase represents the documents as x-y coordinate values in a 2-dimensional space by considering the weights of terms appearing in the documents. First, it goes through some refinement process by applying stopwords removal and stemming to extract index terms. Then, each index term is assigned a TF-IDF weight value and the x-y coordinate value for each document is determined by combining the TF-IDF values of the terms in it. The clustering phase uses the HOC algorithm in which the similarity between the documents is calculated by applying the Euclidean distance method. Initially, a cluster is generated for each document by grouping those documents that are closest to it. Then, the distance between any two clusters is measured, grouping the closest clusters as a new cluster. This process is repeated until the root cluster is generated. In the validation phase, the feature selection method is applied to validate the appropriateness of the cluster concepts built by the HOC algorithm to see if they have meaningful hierarchical relationships. Feature selection is a method of extracting key features from a document by identifying and assigning weight values to important and representative terms in the document. In order to correctly select key features, a method is needed to determine how each term contributes to the class of the document. Among several methods achieving this goal, this paper adopted the $x^2$�� statistics, which measures the dependency degree of a term t to a class c, and represents the relationship between t and c by a numerical value. To demonstrate the effectiveness of the HOC algorithm, a series of performance evaluation is carried out by using a well-known Reuter-21578 news collection. The result of performance evaluation showed that the HOC algorithm greatly contributes to detecting and producing complex concepts by generating the concept hierarchy in a lattice structure.

• Journal of Korea Water Resources Association
• /
• v.57 no.7
• /
• pp.437-449
• /
• 2024

Rainfall-runoff prediction studies using deep learning while considering catchment attributes have been gaining attention. In this study, we selected two models: the Transformer model, which is suitable for large-scale data training through the self-attention mechanism, and the LSTM-based multi-state-vector sequence-to-sequence (LSTM-MSV-S2S) model with an encoder-decoder structure. These models were constructed to incorporate catchment attributes and predict the inflow of 10 multi-purpose dam watersheds in South Korea. The experimental design consisted of three training methods: Single-basin Training (ST), Pretraining (PT), and Pretraining-Finetuning (PT-FT). The input data for the models included 10 selected watershed attributes along with meteorological data. The inflow prediction performance was compared based on the training methods. The results showed that the Transformer model outperformed the LSTM-MSV-S2S model when using the PT and PT-FT methods, with the PT-FT method yielding the highest performance. The LSTM-MSV-S2S model showed better performance than the Transformer when using the ST method; however, it showed lower performance when using the PT and PT-FT methods. Additionally, the embedding layer activation vectors and raw catchment attributes were used to cluster watersheds and analyze whether the models learned the similarities between them. The Transformer model demonstrated improved performance among watersheds with similar activation vectors, proving that utilizing information from other pre-trained watersheds enhances the prediction performance. This study compared the suitable models and training methods for each multi-purpose dam and highlighted the necessity of constructing deep learning models using PT and PT-FT methods for domestic watersheds. Furthermore, the results confirmed that the Transformer model outperforms the LSTM-MSV-S2S model when applying PT and PT-FT methods.

• Archives of design research
• /
• v.19 no.1 s.63
• /
• pp.253-262
• /
• 2006

Research of color has been developed and also has raised consumer desire through changing from a tool to pursue curiosity or beauty to a tool creating effects in the 20th century. People have been interested in colors as a dynamic expression of results since the color TV appeared. The meaning of colors has been recently diversified as the roles of colors became important to the emotional aspects of design. While auto colors have developed along with such changes of the times, black led the color trend during the first half of the 20th century from 1900 to 1950, a transitional period of economic growth and world war. Since then, automobile production has increased apace with the rapid economic growth throughout the world and automobiles became the most expensive item out of the goods that people use. Accordingly, increasing production induced facility investment in mass production and a technology leveling was achieved. Auto manufacturing processes are very complicated, auto makers gradually recognized that software changes such as to colors or materials was an easier way for the improvement of brand identity as opposed to hardware changes such as the mechanical or design components of the body. Color planning and development systems were segmented in various aspects. In the segmentation issue, pigment technology and painting methods are important elements that have an influence on body colors and have a higher technical correlation with colors than in other industries. In other words, the advanced mixture of pigments is creating new body colors that have not existed previously. This diversifies the painting structure and methods and so maximizes the transparency and depth of body colors. Thus, body colors that are closely related to technical factors will increase in the future and research on color preferences by region have been systemized to cope with global competition due to the expansion and change of auto export regions.

• Journal of KIISE:Computing Practices and Letters
• /
• v.13 no.5
• /
• pp.293-299
• /
• 2007

Intelligent pipeline inspection gauges (PIGs) are inspection vehicles that move along within a (gas or oil) pipeline and acquire signals (also called sensor data) from their surrounding rings of sensors. By analyzing the signals captured in intelligent PIGs, we can detect pipeline defects, such as holes and curvatures and other potential causes of gas explosions. There are two major data access patterns apparent when an analyzer accesses the pipeline signal data. The first is a sequential pattern where an analyst reads the sensor data one time only in a sequential fashion. The second is the repetitive pattern where an analyzer repeatedly reads the signal data within a fixed range; this is the dominant pattern in analyzing the signal data. The existing PIG software reads signal data directly from the server at every user#s request, requiring network transfer and disk access cost. It works well only for the sequential pattern, but not for the more dominant repetitive pattern. This problem becomes very serious in a client/server environment where several analysts analyze the signal data concurrently. To tackle this problem, we devise a fast in-memory cache manager, called T-Cache, by considering pipeline sensor data as multiple time-series data and by efficiently caching the time-series data at T-Cache. To the best of the authors# knowledge, this is the first research on caching pipeline signals on the client-side. We propose a new concept of the signal cache line as a caching unit, which is a set of time-series signal data for a fixed distance. We also provide the various data structures including smart cursors and algorithms used in T-Cache. Experimental results show that T-Cache performs much better for the repetitive pattern in terms of disk I/Os and the elapsed time. Even with the sequential pattern, T-Cache shows almost the same performance as a system that does not use any caching, indicating the caching overhead in T-Cache is negligible.

• Journal of Intelligence and Information Systems
• /
• v.29 no.3
• /
• pp.287-316
• /
• 2023

As global energy crisis and the COVID-19 pandemic have emerged as social issues, there is a growing demand for companies to move away from profit-centric business models and embrace sustainable management that balances environmental, social, and governance (ESG) factors. ESG activities of companies vary across industries, and industry-specific weights are applied in ESG evaluations. Therefore, it is important to develop strategic management approaches that reflect the characteristics of each industry and the importance of each ESG factor. Additionally, with the stance of strengthened focus on ESG disclosures, specific guidelines are needed to identify and report on sustainable management activities of domestic companies. To understand corporate sustainability strategies, analyzing ESG reports and news articles by industry can help identify strategic characteristics in specific industries. However, each company has its own unique strategies and report structures, making it difficult to grasp detailed trends or action items. In our study, we analyzed ESG reports (2019-2021) and news articles (2019-2022) of six companies in the 'Finance,' 'Manufacturing,' and 'IT' sectors to examine the sustainability strategies of leading domestic ESG companies. Text mining techniques such as keyword frequency analysis and topic modeling were applied to identify industry-specific, ESG element-specific management strategies and issues. The analysis revealed that in the 'Finance' sector, customer-centric management strategies and efforts to promote an inclusive culture within and outside the company were prominent. Strategies addressing climate change, such as carbon neutrality and expanding green finance, were also emphasized. In the 'Manufacturing' sector, the focus was on creating sustainable communities through occupational health and safety issues, sustainable supply chain management, low-carbon technology development, and eco-friendly investments to achieve carbon neutrality. In the 'IT' sector, there was a tendency to focus on technological innovation and digital responsibility to enhance social value through technology. Furthermore, the key issues identified in the ESG factors were as follows: under the 'Environmental' element, issues such as greenhouse gas and carbon emission management, industry-specific eco-friendly activities, and green partnerships were identified. Under the 'Social' element, key issues included social contribution activities through stakeholder engagement, supporting the growth and coexistence of members and partner companies, and enhancing customer value through stable service provision. Under the 'Governance' element, key issues were identified as strengthening board independence through the appointment of outside directors, risk management and communication for sustainable growth, and establishing transparent governance structures. The exploration of the relationship between ESG disclosures in reports and ESG issues in news articles revealed that the sustainability strategies disclosed in reports were aligned with the issues related to ESG disclosed in news articles. However, there was a tendency to strengthen ESG activities for prevention and improvement after negative media coverage that could have a negative impact on corporate image. Additionally, environmental issues were mentioned more frequently in news articles compared to ESG reports, with environmental-related keywords being emphasized in the 'Finance' sector in the reports. Thus, ESG reports and news articles shared some similarities in content due to the sharing of information sources. However, the impact of media coverage influenced the emphasis on specific sustainability strategies, and the extent of mentioning environmental issues varied across documents. Based on our study, the following contributions were derived. From a practical perspective, companies need to consider their characteristics and establish sustainability strategies that align with their capabilities and situations. From an academic perspective, unlike previous studies on ESG strategies, we present a subdivided methodology through analysis considering the industry-specific characteristics of companies.

• Journal of Environmental Impact Assessment
• /
• v.26 no.2
• /
• pp.160-170
• /
• 2017

The purpose of this study is to perform clustering of the habitat types and to identify the characteristics of species in the habitat types using mammal data (70,562) of the 3rd National Ecosystem Survey conducted from 2006 to 2012. The 15 habitat types recorded in the field-paper of the 3rd National ecosystem survey were reclassified, which was followed by the statistical analysis of mammal habitat types. In the habitat types cluster analysis, non-hierarchical cluster analysis (k-means cluster analysis), hierarchical cluster analysis, and non-metric multidimensional scaling method were applied to 14 habitat types recorded more than 30 times. A total of 7 Orders, 16 Families, and 39 Species of mammals were identified in the 3rd National Ecosystem Survey collected nationwide. When 11 clusters were classified by habitat types, the simple structure index was the highest (ssi = 0.07). As a result of the similarities and hierarchies between habitat types suggested by the hierarchical clustering analysis, the residential areas were the most different habitat types for mammals; the next following type was a cluster together with rivers and coasts. The results of the non-metric multidimensional scaling analysis demonstrated that both Mus musculus and Rattus norvegicus restrictively appeared in a residential area, which is the most discriminating habitat type. Lutra lutra restrictively appeared in coastal and river areas. In summary, according to our results, the mammalian habitat can be divided into the following four types: (1) the forest type (using forest as the main habitat and migration route); (2) the river type (using water as the main habitat); (3) the residence habitat (living near residential area); and (4) the lowland type (consuming grain or seeds as the main feeding resource).