• KIPS Transactions on Software and Data Engineering
• /
• v.13 no.1
• /
• pp.35-49
• /
• 2024

Video captioning technology, as a significant outcome of the integration between computer vision and natural language processing, has emerged as a key research direction in the field of artificial intelligence. This technology aims to achieve automatic understanding and language expression of video content, enabling computers to transform visual information in videos into textual form. This paper provides an initial analysis of the research trends in deep learning-based video captioning and categorizes them into four main groups: CNN-RNN-based Model, RNN-RNN-based Model, Multimodal-based Model, and Transformer-based Model, and explain the concept of each video captioning model. The features, pros and cons were discussed. This paper lists commonly used datasets and performance evaluation methods in the video captioning field. The dataset encompasses diverse domains and scenarios, offering extensive resources for the training and validation of video captioning models. The model performance evaluation method mentions major evaluation indicators and provides practical references for researchers to evaluate model performance from various angles. Finally, as future research tasks for video captioning, there are major challenges that need to be continuously improved, such as maintaining temporal consistency and accurate description of dynamic scenes, which increase the complexity in real-world applications, and new tasks that need to be studied are presented such as temporal relationship modeling and multimodal data integration.

• Proceedings of the KOR-KST Conference
• /
• 1995.12a
• /
• pp.45-73
• /
• 1995

The current paper presents a system dynamics model which can generate the land use anq transportation system performance simultaneously is proposed. The model system consists of 7 submodels (population, migration of population, household, job growth-employment-land availability, housing development, travel demand, and traffic congestion level), and each of them is designed based on the causality functions and feedback loop structure between a large number of physical, socio-economic, and policy variables. The important advantages of the system dynamics model are as follows. First, the model can address the complex interactions between land use and transportation system performance dynamically. Therefore, it can be an effective tool for evaluating the time-by-time effect of a policy over time horizons. Secondly, the system dynamics model is not relied on the assumption of equilibrium state of urban systems as in conventional models since it determines the state of model components directly through dynamic system simulation. Thirdly, the system dynamics model is very flexible in reflecting new features, such as a policy, a new phenomenon which has not existed in the past, a special event, or a useful concept from other methodology, since it consists of a lots of separated equations. In Chapter I, II, and III, overall approach and structure of the model system are discussed with causal-loop diagrams and major equations. In Chapter V _, the performance of the developed model is applied to the analysis of the impact of highway capacity expansion on land use for the area of Montgomery County, MD. The year-by-year impacts of highway capacity expansion on congestion level and land use are analyzed with some possible scenarios for the highway capacity expansion. This is a first comprehensive attempt to use dynamic system simulation modeling in simultaneous treatment of land use and transportation system interactions. The model structure is not very elaborate mainly due to the problem of the availability of behavioral data, but the model performance results indicate that the proposed approach can be a promising one in dealing comprehensively with complicated urban land use/transportation system.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.52 no.4
• /
• pp.18-31
• /
• 2024

This study examines the inscription trends and characteristics of 121 cultural landscapes inscribed on the UNESCO World Heritage List to gain a comprehensive understanding of their inherent values and attributes. By employing a dual methodology involving descriptive statistical analysis and in-depth case studies, this research investigates the geographical distribution, temporal inscription patterns, selection criteria, and typologies of these landscapes. The data for this study were collected from official documents and databases available on the UNESCO World Heritage Center website, ensuring the reliability and authenticity of the information. The analysis reveals that cultural landscapes are predominantly concentrated in Europe and Asia, with a steady increase in inscriptions since 1992. These landscapes are primarily recognized for their uniqueness in reflecting human-nature interactions, as well as the importance of traditional culture and land-use practices, resulting in their inscription mainly under criteria (iv), (iii), (v), and (ii). Furthermore, cultural landscapes can be broadly categorized into three types: designed landscapes, organically evolved landscapes, and associative landscapes. Among these, organically evolved landscapes, formed through long-term interactions between human activities such as agriculture and industry and the natural environment, constitute a significant proportion. These findings suggest that UNESCO World Heritage cultural landscapes possess a complex value system encompassing nature and culture, tangible and intangible elements, and material and non-material aspects. This necessitates a fundamental shift in the perception and preservation approaches to cultural heritage, requiring an integrated approach that emphasizes the overall context rather than individual elements and focuses on the dynamic process of landscape evolution itself. Moreover, cultural landscapes have the potential to contribute to sustainable development models by fostering regional identity, strengthening community resilience, and promoting sustainable economic growth. Therefore, the preservation and management of cultural landscapes require a perspective that holistically views the dynamic evolution process of the landscape and a governance system based on the active participation of local communities and stakeholders. This study contributes to enhancing the in-depth understanding of the characteristics and values of cultural landscapes and provides a foundation for the selection and management of future cultural landscape heritage sites.

• Journal of Intelligence and Information Systems
• /
• v.17 no.4
• /
• pp.109-130
• /
• 2011

One of the major problems in the area of data mining is the size of the data, as most data set has huge volume these days. Streams of data are normally accumulated into data storages or databases. Transactions in internet, mobile devices and ubiquitous environment produce streams of data continuously. Some data set are just buried un-used inside huge data storage due to its huge size. Some data set is quickly lost as soon as it is created as it is not saved due to many reasons. How to use this large size data and to use data on stream efficiently are challenging questions in the study of data mining. Stream data is a data set that is accumulated to the data storage from a data source continuously. The size of this data set, in many cases, becomes increasingly large over time. To mine information from this massive data, it takes too many resources such as storage, money and time. These unique characteristics of the stream data make it difficult and expensive to store all the stream data sets accumulated over time. Otherwise, if one uses only recent or partial of data to mine information or pattern, there can be losses of valuable information, which can be useful. To avoid these problems, this study suggests a method efficiently accumulates information or patterns in the form of rule set over time. A rule set is mined from a data set in stream and this rule set is accumulated into a master rule set storage, which is also a model for real-time decision making. One of the main advantages of this method is that it takes much smaller storage space compared to the traditional method, which saves the whole data set. Another advantage of using this method is that the accumulated rule set is used as a prediction model. Prompt response to the request from users is possible anytime as the rule set is ready anytime to be used to make decisions. This makes real-time decision making possible, which is the greatest advantage of this method. Based on theories of ensemble approaches, combination of many different models can produce better prediction model in performance. The consolidated rule set actually covers all the data set while the traditional sampling approach only covers part of the whole data set. This study uses a stock market data that has a heterogeneous data set as the characteristic of data varies over time. The indexes in stock market data can fluctuate in different situations whenever there is an event influencing the stock market index. Therefore the variance of the values in each variable is large compared to that of the homogeneous data set. Prediction with heterogeneous data set is naturally much more difficult, compared to that of homogeneous data set as it is more difficult to predict in unpredictable situation. This study tests two general mining approaches and compare prediction performances of these two suggested methods with the method we suggest in this study. The first approach is inducing a rule set from the recent data set to predict new data set. The seocnd one is inducing a rule set from all the data which have been accumulated from the beginning every time one has to predict new data set. We found neither of these two is as good as the method of accumulated rule set in its performance. Furthermore, the study shows experiments with different prediction models. The first approach is building a prediction model only with more important rule sets and the second approach is the method using all the rule sets by assigning weights on the rules based on their performance. The second approach shows better performance compared to the first one. The experiments also show that the suggested method in this study can be an efficient approach for mining information and pattern with stream data. This method has a limitation of bounding its application to stock market data. More dynamic real-time steam data set is desirable for the application of this method. There is also another problem in this study. When the number of rules is increasing over time, it has to manage special rules such as redundant rules or conflicting rules efficiently.

• The Korean Journal of Financial Management
• /
• v.6 no.1
• /
• pp.31-62
• /
• 1989

By using deterministic dynamic models, we observe the behavior of the foreign exchange rate of a small open economy with rational expectation formation and different restrictions on the international economic integrations. First, an economy connected to the world by purchasing power parity and uncovered interest parity is studied in the next section. In both sections, financial assets available in the economy are domestic money and bonds. Stocks are added as a financial instrument in the next section, and real capital accumulation is also taken into account. Furthermore, the economy concerned there is fairly autonomous, and not directly governed by either purchasing power parity or uncovered interest parity. The expectation formation used throughout the whole paper is complete perfect foresight, which is the certainty version of rational expectation and free from any forecast errors. It is found that upon monetary expansion the short run depreciation of the foreign exchange rate is a fairly robust result regardless of the degree of the international economic integration, while it is not true for fiscal expansion. The expectation on the long run state significantly affects the short run response of the exchange rate. All of our models postulate that the current account should be balanced eventually. As the result, the short run behavior of the exchange rate is affected by the expectation on the long run balance and may well be a blend of the traditional flow view and modem asset view. The initial overshooting of the exchange rate is easily observed even in the fairly autonomous economy Furthermore, the initial overshooting is not reduced over time, but augmented for some time before it is eventually eliminated. As long as we maintain rational expectaion, introducing time delay in the adjustment of the foreign goods price to the foreign exchange rate does not make much difference.

• Korean Journal of Ecology and Environment
• /
• v.42 no.1
• /
• pp.9-18
• /
• 2009

The objectives of this study were to evaluate seasonal and interannual variations of water quality and nutrient input (N, P) in Junam Reservoir, a nesting waterbody of migratory birds, over 10 years during 1998$\sim$2007 along with dynamic relations of trophic parameters using empirical models. Concentrations of COD averaged 7.8 mg $L^{-1}$ during the study, while TN and TP were $1.4\;mg\;L^{-1}$ and $83{\mu}g\;L^{-1}$, respectively, indicating an eutrophic-hypereutrophic state. Values of monthly COD had strong positive relations (r=0.669, p<0.001) with conductivity, indicating that summer rainfall resulted in an ionic dilution of the reservoir water by rainwater and contributed better water quality. One-way ANOVA tests showed significant differences (F=$5.2{\sim}12.9$, p<0.05) in TN and TP between the before and after the bird migration. In other words, nutrient levels were greater in the absence of migratory birds than in the presence of the migratory birds, suggesting a no-effect on nutrient inputs by the birds. Also, one-way ANOVA indicated no significant differences (F=$0.37{\sim}0.48$, p>0.05) in $NO_{3^-}N$ and $NH_{3^-}N$ between the before and after the birds migration. Linear empirical models using trophic parameters showed that algal biomass as CHL, had significant low correlations with TN ($R^2$=0.143, p<0.001, n=119) and TP ($R^2$=0.192, p<0.001, n=119). These results suggest that influences of nutrients on the CHL were evident, but the effect was weak. This fact was supported by analysis of Trophic State Index Deviation (TSID). Over 70% in the observed values of "TSI (CHL)-TSI (SD)" and "TSI (CHL)-TSI (TP)" were less than zero, suggesting a light limitation on the CHL by inorganic suspended solids.

• Korean Journal of Remote Sensing
• /
• v.37 no.6_1
• /
• pp.1739-1756
• /
• 2021

Atmospheric nitrogen dioxide (NO₂) is mainly caused by anthropogenic emissions. It contributes to the formation of secondary pollutants and ozone through chemical reactions, and adversely affects human health. Although ground stations to monitor NO₂ concentrations in real time are operated in Korea, they have a limitation that it is difficult to analyze the spatial distribution of NO₂ concentrations, especially over the areas with no stations. Therefore, this study conducted a comparative experiment of spatial interpolation of NO₂ concentrations based on two linear-regression methods(i.e., multi linear regression (MLR), and regression kriging (RK)), and two machine learning approaches (i.e., random forest (RF), and support vector regression (SVR)) for the year of 2020. Four approaches were compared using leave-one-out-cross validation (LOOCV). The daily LOOCV results showed that MLR, RK, and SVR produced the average daily index of agreement (IOA) of 0.57, which was higher than that of RF (0.50). The average daily normalized root mean square error of RK was 0.9483%, which was slightly lower than those of the other models. MLR, RK and SVR showed similar seasonal distribution patterns, and the dynamic range of the resultant NO₂ concentrations from these three models was similar while that from RF was relatively small. The multivariate linear regression approaches are expected to be a promising method for spatial interpolation of ground-level NO₂ concentrations and other parameters in urban areas.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.25 no.4
• /
• pp.398-403
• /
• 2023

Process-based K-cabbage model is based on physiological processes such as photosynthesis and phenology, making it possible to predict crop growth under different climate conditions that have never been experienced before. Current first-stage process-based models can be used to assess climate impact through yield prediction based on climate change scenarios, but no comparison has been performed between big data obtained from the main production area and model prediction so far. The aim of this study was to find out the direction of model improvement when using the current model for yield prediction. For this purpose, model performance evaluation was conducted based on data collected from farmers growing 'Chungwang' cabbage in Taebaek and Samcheok, the main producing areas of Chinese cabbage in highland region. The farms surveyed in this study had different cultivation methods in terms of planting date and soil water and nutrient management. The results showed that the potential biomass estimated using the K-cabbage model exceeded the observed values in all cases. Although predictions and observations at the time of harvest did not show a complete positive correlation due to limitations caused by the use of fresh weight in the model evaluation process (R²=0.74, RMSE=866.4), when fitting the model based on the values 2 weeks before harvest, the growth suitability index was different for each farm. These results are suggested to be due to differences in soil properties and management practices between farms. Therefore, to predict attainable yields taking into account differences in soil and management practices between farms, it is necessary to integrate dynamic soil nutrient and moisture modules into crop models, rather than using arbitrary growth suitability indices in current K-cabbage model.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.40 no.3
• /
• pp.206-213
• /
• 2004

As far as an opening device of fishing gears is concerned, applications of a kite are under development around the world. The typical examples are found in the opening device of the stow net on anchor and the buoyancy material of the trawl. While the stow net on anchor has proved its capability for the past 20 years, the trawl has not been wildly used since it has been first introduced for the commercial use only without sufficient studies and thus has revealed many drawbacks. Therefore, the fundamental hydrodynamics of the kite itself need to ne studied further. Models of plate and canvas kite were deployed in the circulating water tank for the mechanical test. For this situation lift and drag tests were performed considering a change in the shape of objects, which resulted in a different aspect ratio of rectangle and trapezoid. The results obtained from the above approaches are summarized as follows, where aspect ratio, attack angle, lift coefficient and maximum lift coefficient are denoted as A, B, $C_L$ and $C_{Lmax}$ respectively : 1. Given the triangular plate, $C_{Lmax}$ was produced as 1.26${\sim}$1.32 with A${\leq}$1 and 38$^{\circ}$B${\leq}$42$^{\circ}$. And when A${\geq}$1.5 and 20$^{\circ}$${\leq}$B${\leq}$50$^{\circ}$, $C_L$ was around 0.85. Given the inverted triangular plate, $C_{Lmax}$ was 1.46${\sim}$1.56 with A${\leq}$1 and 36$^{\circ}$B${\leq}$38$^{\circ}$. And When A${\geq}$1.5 and 22$^{\circ}$B${\leq}$26$^{\circ}$, $C_{Lmax}$ was 1.05${\sim}$1.21. Given the triangular kite, $C_{Lmax}$ was produced as 1.67${\sim}$1.77 with A${\leq}$1 and 46$^{\circ}$B${\leq}$48$^{\circ}$. And when A${\geq}$1.5 and 20$^{\circ}$B${\leq}$50$^{\circ}$, $C_L$ was around 1.10. Given the inverted triangular kite, $C_{Lmax}$ was 1.44${\sim}$1.68 with A${\leq}$1 and 28$^{\circ}$B${\leq}$32$^{\circ}$. And when A${\geq}$1.5 and 18$^{\circ}$B${\leq}$24$^{\circ}$, $C_{Lmax}$ was 1.03${\sim}$1.18. 2. For a model with A=1/2, an increase in B caused an increase in $C_L$ until $C_L$ has reached the maximum. Then there was a tendency of a very gradual decrease or no change in the value of $C_L$. For a model with A=2/3, the tendency of $C_L$ was similar to the case of a model with A=1/2. For a model with A=1, an increase in B caused an increase in $C_L$ until $C_L$ has reached the maximum. And the tendency of $C_L$ didn't change dramatically. For a model with A=1.5, the tendency of $C_L$ as a function of B was changed very small as 0.75${\sim}$1.22 with 20$^{\circ}$B${\leq}$50$^{\circ}$. For a model with A=2, the tendency of $C_L$ as a function of B was almost the same in the triangular model. There was no considerable change in the models with 20$^{\circ}$B${\leq}$50$^{\circ}$. 3. The inverted model's $C_L$ as a function of increase of B reached the maximum rapidly, then decreased gradually compared to the non-inverted models. Others were decreased dramatically. 4. The action point of dynamic pressure in accordance with the attack angle was close to the rear area of the model with small attack angle, and with large attack angle, the action point was close to the front part of the model. 5. There was camber vertex in the position in which the fluid pressure was generated, and the triangular canvas had large value of camber vertex when the aspect ratio was high, while the inverted triangular canvas was versa. 6. All canvas kite had larger camber ratio when the aspect ratio was high, and the triangular canvas had larger one when the attack angle was high, while the inverted triangluar canvas was versa.

• Journal of Intelligence and Information Systems
• /
• v.24 no.1
• /
• pp.101-124
• /
• 2018

Recently, most of the technologies have been developed in various forms through the advancement of single technology or interaction with other technologies. Particularly, these technologies have the characteristic of the convergence caused by the interaction between two or more techniques. In addition, efforts in responding to technological changes by advance are continuously increasing through forecasting promising convergence technologies that will emerge in the near future. According to this phenomenon, many researchers are attempting to perform various analyses about forecasting promising convergence technologies. A convergence technology has characteristics of various technologies according to the principle of generation. Therefore, forecasting promising convergence technologies is much more difficult than forecasting general technologies with high growth potential. Nevertheless, some achievements have been confirmed in an attempt to forecasting promising technologies using big data analysis and social network analysis. Studies of convergence technology through data analysis are actively conducted with the theme of discovering new convergence technologies and analyzing their trends. According that, information about new convergence technologies is being provided more abundantly than in the past. However, existing methods in analyzing convergence technology have some limitations. Firstly, most studies deal with convergence technology analyze data through predefined technology classifications. The technologies appearing recently tend to have characteristics of convergence and thus consist of technologies from various fields. In other words, the new convergence technologies may not belong to the defined classification. Therefore, the existing method does not properly reflect the dynamic change of the convergence phenomenon. Secondly, in order to forecast the promising convergence technologies, most of the existing analysis method use the general purpose indicators in process. This method does not fully utilize the specificity of convergence phenomenon. The new convergence technology is highly dependent on the existing technology, which is the origin of that technology. Based on that, it can grow into the independent field or disappear rapidly, according to the change of the dependent technology. In the existing analysis, the potential growth of convergence technology is judged through the traditional indicators designed from the general purpose. However, these indicators do not reflect the principle of convergence. In other words, these indicators do not reflect the characteristics of convergence technology, which brings the meaning of new technologies emerge through two or more mature technologies and grown technologies affect the creation of another technology. Thirdly, previous studies do not provide objective methods for evaluating the accuracy of models in forecasting promising convergence technologies. In the studies of convergence technology, the subject of forecasting promising technologies was relatively insufficient due to the complexity of the field. Therefore, it is difficult to find a method to evaluate the accuracy of the model that forecasting promising convergence technologies. In order to activate the field of forecasting promising convergence technology, it is important to establish a method for objectively verifying and evaluating the accuracy of the model proposed by each study. To overcome these limitations, we propose a new method for analysis of convergence technologies. First of all, through topic modeling, we derive a new technology classification in terms of text content. It reflects the dynamic change of the actual technology market, not the existing fixed classification standard. In addition, we identify the influence relationships between technologies through the topic correspondence weights of each document, and structuralize them into a network. In addition, we devise a centrality indicator (PGC, potential growth centrality) to forecast the future growth of technology by utilizing the centrality information of each technology. It reflects the convergence characteristics of each technology, according to technology maturity and interdependence between technologies. Along with this, we propose a method to evaluate the accuracy of forecasting model by measuring the growth rate of promising technology. It is based on the variation of potential growth centrality by period. In this paper, we conduct experiments with 13,477 patent documents dealing with technical contents to evaluate the performance and practical applicability of the proposed method. As a result, it is confirmed that the forecast model based on a centrality indicator of the proposed method has a maximum forecast accuracy of about 2.88 times higher than the accuracy of the forecast model based on the currently used network indicators.