• Journal of Korea Multimedia Society
• /
• v.12 no.9
• /
• pp.1217-1232
• /
• 2009

In this paper, we propose a semi-automatic 3D building reconstruction method using uncalibrated images which includes the facade of target building. First, we extract feature points in all images and find corresponding points between each pair of images. Second, we extract lines on each image and estimate the vanishing points. Extracted lines are grouped with respect to their corresponding vanishing points. The adjacency graph is used to organize the image sequence based on the number of corresponding points between image pairs and camera calibration is performed. The initial solid model can be generated by some user interactions using grouped lines and camera pose information. From initial solid model, a detailed building model is reconstructed by a combination of predefined basic Euler operators on half-edge data structure. Automatically computed geometric information is visualized to help user's interaction during the detail modeling process. The proposed system allow the user to get a 3D building model with less user interaction by augmenting various automatically generated geometric information.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.4
• /
• pp.27-36
• /
• 2022

In this paper, to improve the conditions of the fish processing site, we propose a method to predict the cutting point of fish according to the target weight using AI machine vision. The proposed method performs image-based preprocessing by first photographing the top and front views of the input fish. Then, RANSAC(RANdom SAmple Consensus) is used to extract the fish contour line, and then 3D external information of the fish is obtained using 3D modeling. Next, machine learning is performed on the extracted three-dimensional feature information and measured weight information to generate a neural network model. Subsequently, the fish is cut at the cutting point predicted by the proposed technique, and then the weight of the cut piece is measured. We compared the measured weight with the target weight and evaluated the performance using evaluation methods such as MAE(Mean Absolute Error) and MRE(Mean Relative Error). The obtained results indicate that an average error rate of less than 3% was achieved in comparison to the target weight. The proposed technique is expected to contribute greatly to the development of the fishery industry in the future by being linked to the automation system.

• Steel and Composite Structures
• /
• v.44 no.2
• /
• pp.241-254
• /
• 2022

The cables in a cable-stayed bridge are critical load-carrying parts. The potential damage to cables should be identified early to prevent disasters. In this study, an efficient deep learning model is proposed for the damage identification of cables using both a multi-layer perceptron (MLP) and a graph neural network (GNN). Datasets are first generated using the practical advanced analysis program (PAAP), which is a robust program for modeling and analyzing bridge structures with low computational costs. The model based on the MLP and GNN can capture complex nonlinear correlations between the vibration characteristics in the input data and the cable system damage in the output data. Multiple hidden layers with an activation function are used in the MLP to expand the original input vector of the limited measurement data to obtain a complete output data vector that preserves sufficient information for constructing the graph in the GNN. Using the gated recurrent unit and set2set model, the GNN maps the formed graph feature to the output cable damage through several updating times and provides the damage results to both the classification and regression outputs. The model is fine-tuned with the original input data using Adam optimization for the final objective function. A case study of an actual cable-stayed bridge was considered to evaluate the model performance. The results demonstrate that the proposed model provides high accuracy (over 90%) in classification and satisfactory correlation coefficients (over 0.98) in regression and is a robust approach to obtain effective identification results with a limited quantity of input data.

• Journal of Intelligence and Information Systems
• /
• v.26 no.1
• /
• pp.23-45
• /
• 2020

Big data is creating in a wide variety of fields such as medical care, manufacturing, logistics, sales site, SNS, and the dataset characteristics are also diverse. In order to secure the competitiveness of companies, it is necessary to improve decision-making capacity using a classification algorithm. However, most of them do not have sufficient knowledge on what kind of classification algorithm is appropriate for a specific problem area. In other words, determining which classification algorithm is appropriate depending on the characteristics of the dataset was has been a task that required expertise and effort. This is because the relationship between the characteristics of datasets (called meta-features) and the performance of classification algorithms has not been fully understood. Moreover, there has been little research on meta-features reflecting the characteristics of multi-class. Therefore, the purpose of this study is to empirically analyze whether meta-features of multi-class datasets have a significant effect on the performance of classification algorithms. In this study, meta-features of multi-class datasets were identified into two factors, (the data structure and the data complexity,) and seven representative meta-features were selected. Among those, we included the Herfindahl-Hirschman Index (HHI), originally a market concentration measurement index, in the meta-features to replace IR(Imbalanced Ratio). Also, we developed a new index called Reverse ReLU Silhouette Score into the meta-feature set. Among the UCI Machine Learning Repository data, six representative datasets (Balance Scale, PageBlocks, Car Evaluation, User Knowledge-Modeling, Wine Quality(red), Contraceptive Method Choice) were selected. The class of each dataset was classified by using the classification algorithms (KNN, Logistic Regression, Nave Bayes, Random Forest, and SVM) selected in the study. For each dataset, we applied 10-fold cross validation method. 10% to 100% oversampling method is applied for each fold and meta-features of the dataset is measured. The meta-features selected are HHI, Number of Classes, Number of Features, Entropy, Reverse ReLU Silhouette Score, Nonlinearity of Linear Classifier, Hub Score. F1-score was selected as the dependent variable. As a result, the results of this study showed that the six meta-features including Reverse ReLU Silhouette Score and HHI proposed in this study have a significant effect on the classification performance. (1) The meta-features HHI proposed in this study was significant in the classification performance. (2) The number of variables has a significant effect on the classification performance, unlike the number of classes, but it has a positive effect. (3) The number of classes has a negative effect on the performance of classification. (4) Entropy has a significant effect on the performance of classification. (5) The Reverse ReLU Silhouette Score also significantly affects the classification performance at a significant level of 0.01. (6) The nonlinearity of linear classifiers has a significant negative effect on classification performance. In addition, the results of the analysis by the classification algorithms were also consistent. In the regression analysis by classification algorithm, Naïve Bayes algorithm does not have a significant effect on the number of variables unlike other classification algorithms. This study has two theoretical contributions: (1) two new meta-features (HHI, Reverse ReLU Silhouette score) was proved to be significant. (2) The effects of data characteristics on the performance of classification were investigated using meta-features. The practical contribution points (1) can be utilized in the development of classification algorithm recommendation system according to the characteristics of datasets. (2) Many data scientists are often testing by adjusting the parameters of the algorithm to find the optimal algorithm for the situation because the characteristics of the data are different. In this process, excessive waste of resources occurs due to hardware, cost, time, and manpower. This study is expected to be useful for machine learning, data mining researchers, practitioners, and machine learning-based system developers. The composition of this study consists of introduction, related research, research model, experiment, conclusion and discussion.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.30 no.2
• /
• pp.69-83
• /
• 2018

The South China Sea (SCS) is a typical marginal sea characterized with the deep basin, shelf break, shallow shelf, many straits, and complex bathymetry. This study investigated the tidal characteristics and propagation, and reproduced typhoon-induced storm surge in this region using the regional real-time tide-surge model, which was based on the unstructured grid, resolving in detail the region of interest and forced by tide at the open boundary and by wind and air pressure at the surface. Typhoon Haiyan, which occurred in 2013 and caused great damage in the Philippines, was chosen as a case study to simulate typhoon's impact. Amplitudes and phases of four major constituents were reproduced reasonably in general, and the tidal distributions of four constituents were similar to the previous studies. The modelled tide seemed to be within the acceptable levels, considering it was difficult to reproduce the tide in this region based on the previous studies. The free oscillation experiment results described well the feature of tide that the diurnal tide is prevailing in the SCS. The tidal residual current and total energy dissipation were discussed to understand the tidal and sedimentary environments. The storm-surge caused by typhoon Haiyan was reasonably simulated using this modeling system. This study established the regional real-time barotropic tide/water level prediction system for the South China Sea including the seas around the Philippines through the validation of the model and the understanding of tidal characteristics.

• Korean Journal of Remote Sensing
• /
• v.37 no.5_1
• /
• pp.1135-1147
• /
• 2021

In order to geometrically correct high-resolution satellite imagery, the sensor modeling process that restores the geometric relationship between the satellite sensor and the ground surface at the image acquisition time is required. In general, high-resolution satellites provide RPC (Rational Polynomial Coefficient) information, but the vendor-provided RPC includes geometric distortion caused by the position and orientation of the satellite sensor. GCP (Ground Control Point) is generally used to correct the RPC errors. The representative method of acquiring GCP is field survey to obtain accurate ground coordinates. However, it is difficult to find the GCP in the satellite image due to the quality of the image, land cover change, relief displacement, etc. By using image maps acquired from various sensors as reference data, it is possible to automate the collection of GCP through the image matching algorithm. In this study, the RPC of KOMPSAT-3A satellite image was corrected through the extracted matching point using the UAV (Unmanned Aerial Vehichle) imagery. We propose a pre-porocessing method for the extraction of matching points between the UAV imagery and KOMPSAT-3A satellite image. To this end, the characteristics of matching points extracted by independently applying the SURF (Speeded-Up Robust Features) and the phase correlation, which are representative feature-based matching method and area-based matching method, respectively, were compared. The RPC adjustment parameters were calculated using the matching points extracted through each algorithm. In order to verify the performance and usability of the proposed method, it was compared with the GCP-based RPC correction result. The GCP-based method showed an improvement of correction accuracy by 2.14 pixels for the sample and 5.43 pixelsfor the line compared to the vendor-provided RPC. In the proposed method using SURF and phase correlation methods, the accuracy of sample was improved by 0.83 pixels and 1.49 pixels, and that of line wasimproved by 4.81 pixels and 5.19 pixels, respectively, compared to the vendor-provided RPC. Through the experimental results, the proposed method using the UAV imagery presented the possibility as an alternative to the GCP-based method for the RPC correction.

• KIPS Transactions on Software and Data Engineering
• /
• v.5 no.2
• /
• pp.69-78
• /
• 2016

Ischemic stroke is a disease that the brain tissues cannot function by reducing blood flow due to thrombosis or embolisms. Due to the nature of the disease, it is most important to identify the status of cerebral vessel and the medical images are necessarily used for its diagnosis. Among many indicators, brain MRI is most widely utilized because experts can effectively obtain the semantic information such as cerebral anatomy aiding the diagnosis with it. However, in case of emergency diseases like ischemic stroke, even though a intelligent system is required for supporting the prompt diagnosis and treatment, the current systems have some difficulties to provide the information of medical images intuitively. In other words, as the current systems have managed the medical images based on the basic meta-data such as image name, ID and so on, they cannot consider semantic information inherent in medical images. Therefore, in this paper, to provide core information like cerebral anatomy contained in brain MRI, we suggest a template-driven medical images mapping method. The key idea of the method is defining the mapping characteristics between anatomic feature and representative images by using template images that can be representative of the whole brain MRI image set and revealing the semantic relations that only medical experts can check between images. With our method, it will be possible to manage the medical images based on semantic.

• Journal of Digital Convergence
• /
• v.10 no.10
• /
• pp.215-220
• /
• 2012

This paper proposes a ontology of tree structure approach for adaptive object recognition in a situation-variant environment. In this paper, we introduce a new concept, ontology of tree structure ontology, for context sensitivity, as we found that many developed systems work in a context-invariant environment. Due to the effects of illumination on a supreme obstinate designing context-sensitive recognition system, we have focused on designing such a context-variant system using ontology of tree structure. Ontology can be defined as an explicit specification of conceptualization of a domain typically captured in an abstract model of how people think about things in the domain. People produce ontologies to understand and explain underlying principles and environmental factors. In this research, we have proposed context ontology, context modeling, context adaptation, and context categorization to design ontology of tree structure based on illumination criteria. After selecting the proper light-ontology domain, we benefit from selecting a set of actions that produces better performance on that domain. We have carried out extensive experiments on these concepts in the area of object recognition in a dynamic changing environment, and we have achieved enormous success, which will enable us to proceed on our basic concepts.

• Tunnel and Underground Space
• /
• v.16 no.6 s.65
• /
• pp.526-535
• /
• 2006

An experimental study was carried out on a reduced scale tunnel model to grasp the behavioral feature of fire-induced smoke in the long tunnels. Based on Froude modeling, the 1/50 scaled tunnel model (20 m long) was constructed by acrylic tubes and paraffin gas was released inside the tunnel to simulate the 20 MW fire-induced smoke. me test results show, that after approximately 2 minutes of fire generation, was descended from the tunnel ceiling through the decrease of buoyancy, then it was symmetrically propagated about 90 meters for 4 minutes before jet fans were operated. The smoke was effectively controlled when the jet fans were operated and an air stream velocity was getting closed to reach a critical velocity (the minimum air velocity that requires to suppress the smoke spreading against the longitudinal ventilation flow during the tunnel fire situations). It was also found out that a range of smoke was spreaded about 3 meters from the origin of fire but the range was not propagated to the escape direction anymore. The early stage of the In operation, however, showed that the smoke was hardly controlled. It means that the operation of emergency ventilation system has many dangerous factors such as an intercepting breathing zone.

• Journal of Intelligence and Information Systems
• /
• v.19 no.3
• /
• pp.141-156
• /
• 2013

Social media is a representative form of the Web 2.0 that shapes the change of a user's information behavior by allowing users to produce their own contents without any expert skills. In particular, as a new communication medium, it has a profound impact on the social change by enabling users to communicate with the masses and acquaintances their opinions and thoughts. Social media data plays a significant role in an emerging Big Data arena. A variety of research areas such as social network analysis, opinion mining, and so on, therefore, have paid attention to discover meaningful information from vast amounts of data buried in social media. Social media has recently become main foci to the field of Information Retrieval and Text Mining because not only it produces massive unstructured textual data in real-time but also it serves as an influential channel for opinion leading. But most of the previous studies have adopted broad-brush and limited approaches. These approaches have made it difficult to find and analyze new information. To overcome these limitations, we developed a real-time Twitter trend mining system to capture the trend in real-time processing big stream datasets of Twitter. The system offers the functions of term co-occurrence retrieval, visualization of Twitter users by query, similarity calculation between two users, topic modeling to keep track of changes of topical trend, and mention-based user network analysis. In addition, we conducted a case study on the 2012 Korean presidential election. We collected 1,737,969 tweets which contain candidates' name and election on Twitter in Korea (http://www.twitter.com/) for one month in 2012 (October 1 to October 31). The case study shows that the system provides useful information and detects the trend of society effectively. The system also retrieves the list of terms co-occurred by given query terms. We compare the results of term co-occurrence retrieval by giving influential candidates' name, 'Geun Hae Park', 'Jae In Moon', and 'Chul Su Ahn' as query terms. General terms which are related to presidential election such as 'Presidential Election', 'Proclamation in Support', Public opinion poll' appear frequently. Also the results show specific terms that differentiate each candidate's feature such as 'Park Jung Hee' and 'Yuk Young Su' from the query 'Guen Hae Park', 'a single candidacy agreement' and 'Time of voting extension' from the query 'Jae In Moon' and 'a single candidacy agreement' and 'down contract' from the query 'Chul Su Ahn'. Our system not only extracts 10 topics along with related terms but also shows topics' dynamic changes over time by employing the multinomial Latent Dirichlet Allocation technique. Each topic can show one of two types of patterns-Rising tendency and Falling tendencydepending on the change of the probability distribution. To determine the relationship between topic trends in Twitter and social issues in the real world, we compare topic trends with related news articles. We are able to identify that Twitter can track the issue faster than the other media, newspapers. The user network in Twitter is different from those of other social media because of distinctive characteristics of making relationships in Twitter. Twitter users can make their relationships by exchanging mentions. We visualize and analyze mention based networks of 136,754 users. We put three candidates' name as query terms-Geun Hae Park', 'Jae In Moon', and 'Chul Su Ahn'. The results show that Twitter users mention all candidates' name regardless of their political tendencies. This case study discloses that Twitter could be an effective tool to detect and predict dynamic changes of social issues, and mention-based user networks could show different aspects of user behavior as a unique network that is uniquely found in Twitter.