• Information Systems Review
• /
• v.20 no.2
• /
• pp.63-85
• /
• 2018

Emerging hotspot and trendy areas are formed into alleys and blocks with the help of viral effects among social network services (SNS) users called "Golmogleo." These users search for every corner of the alleys to share and promote their own favorite places through SNS. An analysis of hot places is limited if it is only based on macroeconomic indicators such as commercial area data published by national organizations, large-scale visiting facilities, and commuter figures. Careful analyses based on consumers' actual activities are needed. This study develops a "social big data analysis methodology" using Instagram data, which is one of the most popular SNSs suitable to identify recent consumer trends. We build a spatial analysis model using Local Moran's I. Results show that our model identifies new trend zones on the basis of posting data in Instagram, which are not included in the commercial information prepared by national organizations. The proposed analysis methodology enables better identification of the latest trend areas formulated by SNS user activities. It also provides practical information for start-ups, small business owners, and alley merchants for marketing purposes. This analytical methodology can be applied to future studies on social big data analysis.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.26 no.6
• /
• pp.67-84
• /
• 2023

In some areas of the Republic of Korea, the designation and management of conservation areas do not adequately reflect regional characteristics and often impose behavioral regulations without considering the local context. One prominent example is the Busan EDC area. As a result, conflicts may arise, including large-scale civil complaints, regarding the conservation and utilization of these areas. Therefore, for the efficient designation and management of protected areas, it is necessary to consider various ecosystem factors, changes in land use, and regional characteristics. In this study, we specifically focused on the Busan EDC area and applied machine learning techniques to analyze the habitat of regional species. Additionally, we employed Explainable Artificial Intelligence techniques to interpret the results of our analysis. To analyze the regional characteristics of the waterfront area in the Busan EDC district and the habitat of migratory birds, we used bird observations as dependent variables, distinguishing between presence and absence. The independent variables were constructed using land cover, elevation, slope, bridges, and river depth data. We utilized the XGBoost (eXtreme Gradient Boosting) model, known for its excellent performance in various fields, to predict the habitat probabilities of 11 bird species. Furthermore, we employed the SHapley Additive exPlanations technique, one of the representative methodologies of XAI, to analyze the relative importance and impact of the variables used in the model. The analysis results showed that in the EDC business district, as one moves closer to the river from the waterfront, the likelihood of bird habitat increases based on the overlapping habitat probabilities of the analyzed bird species. By synthesizing the major variables influencing the habitat of each species, key variables such as rivers, rice fields, fields, pastures, inland wetlands, tidal flats, orchards, cultivated lands, cliffs & rocks, elevation, lakes, and deciduous forests were identified as areas that can serve as habitats, shelters, resting places, and feeding grounds for birds. On the other hand, artificial structures such as bridges, railways, and other public facilities were found to have a negative impact on bird habitat. The development of a management plan for conservation areas based on the objective analysis presented in this study is expected to be extensively utilized in the future. It will provide diverse evidential materials for establishing effective conservation area management strategies.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.11 no.6
• /
• pp.121-130
• /
• 2007

In this paper, large scale experimental model tests were performed to investigate the distribution of earth pressure acting on embedded rigid pipes having different bedding conditions. For these tests, very light weighted EPS blocks were installed at top and bottom of the rigid pipe and Jumunjin Standard Sand was used as a ground material. As results of model tests, for the case of no bedding on the pipe, the measured pressure at the bottom of the pipe was $4.96_{tf/m^2}$ whereas they were in the range of $1.87{\sim}4.96_{tf/m^2}$ in the case of EPS beddings being installed at the top and the bottom of the pipe. Therefore, for the case of EPS bedding being installed, the ratio of reduced pressures acting on the pipe, compared with the case of no EPS beddings, were in the rage of 16~62%. As a result of parametric test with changing the locations of EPS bedding, the trend of reducing the stress acting on the pipe was in the order of bottom bedding, top bedding, and top and bottom bedding. Effect of bedding positions on the reduced magnitude of acting pressure on the pipe was more significant in the case of top bedding than in the case of the bottom bedding.

• Journal of the Korea Computer Graphics Society
• /
• v.30 no.3
• /
• pp.149-158
• /
• 2024

Photo booths have traditionally provided a fun and easy way to capture and print photos to cherish memories. These booths allow individuals to capture their desired poses and props, sharing memories with friends and family. To enable diverse expressions, generative AI-powered photo booths have emerged. However, existing AI photo booths face challenges such as difficulty in taking group photos, inability to accurately reflect user's poses, and the challenge of applying different concepts to individual subjects. To tackle these issues, we present CINEMAPIC, a photo booth system that allows users to freely choose poses, positions, and concepts for their photos. The system workflow includes three main steps: pre-processing, generation, and post-processing to apply individualized concepts. To produce high-quality group photos, the system generates a transparent image for each character and enhances the backdrop-composited image through a small number of denoising steps. The workflow is accelerated by applying an optimized diffusion model and GPU parallelization. The system was implemented as a prototype, and its effectiveness was validated through a user study and a large-scale pilot operation involving approximately 400 users. The results showed a significant preference for the proposed system over existing methods, confirming its potential for real-world photo booth applications. The proposed CINEMAPIC photo booth is expected to lead the way in a more creative and differentiated market, with potential for widespread application in various fields.

• Nuclear Engineering and Technology
• /
• v.56 no.9
• /
• pp.3835-3850
• /
• 2024

The high-temperature gas-cooled reactor (HTGR) with spherical fuel elements contains complex pebble flow. The flow behavior of pebbles is influenced by various factors, such as pebble density, friction coefficient, wall structure, and discharge port size. Using a GPU-DEM numerical model, the effects of the friction coefficient on the cyclic loading and unloading of pebbles in the full-scale HTR-PM are studied. Numerical simulations with up to 420,000 spherical pebbles are conducted. Four sets of friction coefficient values are determined for comparative analysis based on experimental measurements. Discharging speed, residence time, stress, porosity, and velocity distribution are quantitatively analyzed. In addition, a comparison with the CT-PFD experiment is carried out to validate the numerical model. The results show that near-wall retention phenomena are observed in the reactor core only when using large friction coefficients. However, using friction coefficient values closer to the measured experimental values, the pebble bed in HTR-PM exhibited good flow characteristics. Furthermore, the friction coefficient also influences the porosity and velocity distribution of the pebble bed, with lower friction coefficients resulting in lower overall stress in the bed. The discharge outlet's influence varies with different friction coefficient values. In summary, this study demonstrates that the value of the friction coefficient has a complex influence on the pebble flow in HTR-PM, which provides important insights for future numerical and experimental studies in this field.

• Phonetics and Speech Sciences
• /
• v.16 no.3
• /
• pp.79-86
• /
• 2024

Transformer models have shown remarkable performance in extracting meaningful information from sequential input data such as text and images, and are gaining attention as end-to-end models for speech recognition. This study compared the performances of the Transformer speech recognition model and its enhanced versions, the Conformer and E-Branchformer, when applied to Korean speech recognition. Using Korean speech data from AIHub, we prepared a training set of approximately 7,500 hours and evaluated the models using the ESPnet toolkit. Additionally, we compared syllables and subwords as recognition units and analyzed the performance differences with changes in the number of tokens using Byte Pair Encoding. The results showed that the E-Branchformer achieved the best performance in Korean speech recognition and Conformer outperformed Transformer but degraded in performance for long utterances owing to cross-attention alignment errors. We aimed to determine the optimal settings by analyzing the performance changes with subword token adjustments. This study comprehensively evaluated model accuracy and processing speed to maximize the efficiency of Korean speech recognition. This is expected to contribute to the training of large-scale Korean speech recognition models and improve Conformer recognition errors. Future research should include additional experiments with diverse Korean speech datasets and enhance the recognition performance through structural improvements in the Conformer.

• Journal of Intelligence and Information Systems
• /
• v.20 no.2
• /
• pp.73-92
• /
• 2014

An Adaptive Clustering-based Collaborative Filtering Technique was proposed to solve the fundamental problems of collaborative filtering, such as cold-start problems, scalability problems and data sparsity problems. Previous collaborative filtering techniques were carried out according to the recommendations based on the predicted preference of the user to a particular item using a similar item subset and a similar user subset composed based on the preference of users to items. For this reason, if the density of the user preference matrix is low, the reliability of the recommendation system will decrease rapidly. Therefore, the difficulty of creating a similar item subset and similar user subset will be increased. In addition, as the scale of service increases, the time needed to create a similar item subset and similar user subset increases geometrically, and the response time of the recommendation system is then increased. To solve these problems, this paper suggests a collaborative filtering technique that adapts a condition actively to the model and adopts the concepts of a context-based filtering technique. This technique consists of four major methodologies. First, items are made, the users are clustered according their feature vectors, and an inter-cluster preference between each item cluster and user cluster is then assumed. According to this method, the run-time for creating a similar item subset or user subset can be economized, the reliability of a recommendation system can be made higher than that using only the user preference information for creating a similar item subset or similar user subset, and the cold start problem can be partially solved. Second, recommendations are made using the prior composed item and user clusters and inter-cluster preference between each item cluster and user cluster. In this phase, a list of items is made for users by examining the item clusters in the order of the size of the inter-cluster preference of the user cluster, in which the user belongs, and selecting and ranking the items according to the predicted or recorded user preference information. Using this method, the creation of a recommendation model phase bears the highest load of the recommendation system, and it minimizes the load of the recommendation system in run-time. Therefore, the scalability problem and large scale recommendation system can be performed with collaborative filtering, which is highly reliable. Third, the missing user preference information is predicted using the item and user clusters. Using this method, the problem caused by the low density of the user preference matrix can be mitigated. Existing studies on this used an item-based prediction or user-based prediction. In this paper, Hao Ji's idea, which uses both an item-based prediction and user-based prediction, was improved. The reliability of the recommendation service can be improved by combining the predictive values of both techniques by applying the condition of the recommendation model. By predicting the user preference based on the item or user clusters, the time required to predict the user preference can be reduced, and missing user preference in run-time can be predicted. Fourth, the item and user feature vector can be made to learn the following input of the user feedback. This phase applied normalized user feedback to the item and user feature vector. This method can mitigate the problems caused by the use of the concepts of context-based filtering, such as the item and user feature vector based on the user profile and item properties. The problems with using the item and user feature vector are due to the limitation of quantifying the qualitative features of the items and users. Therefore, the elements of the user and item feature vectors are made to match one to one, and if user feedback to a particular item is obtained, it will be applied to the feature vector using the opposite one. Verification of this method was accomplished by comparing the performance with existing hybrid filtering techniques. Two methods were used for verification: MAE(Mean Absolute Error) and response time. Using MAE, this technique was confirmed to improve the reliability of the recommendation system. Using the response time, this technique was found to be suitable for a large scaled recommendation system. This paper suggested an Adaptive Clustering-based Collaborative Filtering Technique with high reliability and low time complexity, but it had some limitations. This technique focused on reducing the time complexity. Hence, an improvement in reliability was not expected. The next topic will be to improve this technique by rule-based filtering.

• Korean Journal of Construction Engineering and Management
• /
• v.18 no.3
• /
• pp.12-21
• /
• 2017

From 1960, the government decided to build apartment houses on a large scale in order to resolve the rising housing problems. However, the maintenance issues that have arisen from the deterioration of housing has not received adequate attention. The policy focuses only on the supply of housing. By passing new laws, the durable period during which buildings allowed reconstruction was increased, and long term maintenance plans were treated as important issues. The government was then obligated to establish certain long term maintenance plans and costs by legislating a Housing Act and requiring it be adjusted every three years. However, when planning long-term repair costs, doing so without considering the time value of money would become a problem. In addition, if differences between the planned repair costs and actual costs occur, it becomes necessary to adjust the long-term repair costs but, as of yet, the criteria to adjust such things does not exist. For these reasons, if there is lack of money to execute large-scale repair work, a building is unlikely to respond to deterioration of housing; on the other hand, an unnecessary reserve or pool of money can lead to conflict among residents. Therefore, this paper will propose estimation and adjustment models considering the time value of money for long term maintenance costs of apartment houses.

• Journal of Intelligence and Information Systems
• /
• v.25 no.4
• /
• pp.53-65
• /
• 2019

Object tracking is one of important steps to achieve video-based surveillance systems. Object tracking is considered as an essential task similar to object detection and recognition. In order to perform object tracking, various machine learning methods (e.g., least-squares, perceptron and support vector machine) can be applied for different designs of tracking systems. In general, generative methods (e.g., principal component analysis) were utilized due to its simplicity and effectiveness. However, the generative methods were only focused on modeling the target object. Due to this limitation, discriminative methods (e.g., binary classification) were adopted to distinguish the target object and the background. Among the machine learning methods for binary classification, total error rate minimization can be used as one of successful machine learning methods for binary classification. The total error rate minimization can achieve a global minimum due to a quadratic approximation to a step function while other methods (e.g., support vector machine) seek local minima using nonlinear functions (e.g., hinge loss function). Due to this quadratic approximation, the total error rate minimization could obtain appropriate properties in solving optimization problems for binary classification. However, this total error rate minimization was based on a batch mode setting. The batch mode setting can be limited to several applications under offline learning. Due to limited computing resources, offline learning could not handle large scale data sets. Compared to offline learning, online learning can update its solution without storing all training samples in learning process. Due to increment of large scale data sets, online learning becomes one of essential properties for various applications. Since object tracking needs to handle data samples in real time, online learning based total error rate minimization methods are necessary to efficiently address object tracking problems. Due to the need of the online learning, an online learning based total error rate minimization method was developed. However, an approximately reweighted technique was developed. Although the approximation technique is utilized, this online version of the total error rate minimization could achieve good performances in biometric applications. However, this method is assumed that the total error rate minimization can be asymptotically achieved when only the number of training samples is infinite. Although there is the assumption to achieve the total error rate minimization, the approximation issue can continuously accumulate learning errors according to increment of training samples. Due to this reason, the approximated online learning solution can then lead a wrong solution. The wrong solution can make significant errors when it is applied to surveillance systems. In this paper, we propose an exactly reweighted technique to recursively update the solution of the total error rate minimization in online learning manner. Compared to the approximately reweighted online total error rate minimization, an exactly reweighted online total error rate minimization is achieved. The proposed exact online learning method based on the total error rate minimization is then applied to object tracking problems. In our object tracking system, particle filtering is adopted. In particle filtering, our observation model is consisted of both generative and discriminative methods to leverage the advantages between generative and discriminative properties. In our experiments, our proposed object tracking system achieves promising performances on 8 public video sequences over competing object tracking systems. The paired t-test is also reported to evaluate its quality of the results. Our proposed online learning method can be extended under the deep learning architecture which can cover the shallow and deep networks. Moreover, online learning methods, that need the exact reweighting process, can use our proposed reweighting technique. In addition to object tracking, the proposed online learning method can be easily applied to object detection and recognition. Therefore, our proposed methods can contribute to online learning community and object tracking, detection and recognition communities.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.47 no.2
• /
• pp.13-27
• /
• 2019

This study shows the changes in the space created by the planning and leisure activities of Hangang River Park, focusing on the Yeouido portion of the Hangang River Park, which has the most users and the greatest degree of planning. The relationship between planning, behavior, and space changes are explained based on Giddens's Structural Theory. As research material, Hangang River Park plans and satellite photos were interpreted and newspaper articles were used to identifying the space changes and their causes, and a model of the space changes was derived through the application of the theory. The flow of space change in the Yeouido portion of the Hangang River Park due to planning and leisure activities is as follows. In the 1970s, the first sports spaces are made due to need from residents near the riverside, but huge plans for the utilization of the entire space were not realized. In the 1980s, leisure spaces were planned and developed through a comprehensive plan. Various sports spaces were built, but the environment of the spaces became a slum. In the 1990s, various leisure activities were revitalized due to the revision of the legal system, regulations on the usage of space, and space maintenance, and from the late 1990s, ecological issues arose along the Hangang River. In the 2000s, there was an overall space improvement project directed by two comprehensive plans, and cultural and ecological issues appeared in the Hangang River Park plans. However, actual leisure spaces were developed along with the promotion of large-scale activities. Regarding the structuration theory, elements of interaction, modality, and structure are the aspects of space changes in the Yeouido portion Hangang River Park. As the flow of the space change, the proportions of the comprehensive plan and the individual plans were similar. The comprehensive plan was influenced by the change of public businesses and the proliferation of large-scale activities. Individual plans were influenced by the user's activities and opinions. However, both plans were influenced by the users and suppliers. The leisure space of the Hangang River Park can be viewed as a social space, in terms of the structuring as a theory due to the user repeatedly changing the use of the space. The purpos of this study is to investigate the changes in the Hangang River Park space through planning and leisure activities. Through this study, we can understand the characteristics of the Hangang River Park in planning the leisure activity space.