• Information Systems Review
• /
• v.17 no.3
• /
• pp.95-111
• /
• 2015

The recommendation system automatically provides the predicted items which are expected to be purchased by analyzing the previous customer behaviors. This recommendation system has been applied to many e-commerce businesses, and it is generating positive effects on user convenience as well as the company's revenue. However, there are several limitations of the existing recommendation systems. They do not reflect specific criteria for evaluating products or the factors that affect customer buying decisions. Thus, our research proposes a collaborative recommendation model algorithm that utilizes each customer's online product reviews. This study deploys topic modeling method for customer opinion mining. Also, it adopts a kernel-based machine learning concept by selecting kernels explaining individual similarities in accordance with customers' purchase history and online reviews. Our study further applies a multiple kernel learning algorithm to integrate the kernelsinto a combined model for predicting the product ratings, and it verifies its validity with a data set (including purchased item, product rating, and online review) of BestBuy, an online consumer electronics store. This study theoretically implicates by suggesting a new method for the online recommendation system, i.e., a collaborative recommendation method using topic modeling and kernel-based learning.

• Geophysics and Geophysical Exploration
• /
• v.24 no.2
• /
• pp.53-66
• /
• 2021

Velocity model building is an essential procedure in seismic data processing. Conventional techniques, such as traveltime tomography or velocity analysis take longer computational time to predict a single velocity model and the quality of the inversion results is highly dependent on human expertise. Full-waveform inversions also depend on an accurate initial model. Recently, deep neural network techniques are gaining widespread acceptance due to an increase in their integration to solving complex and nonlinear problems. This study investigated cases of seismic velocity model building using deep neural network techniques by classifying items according to the neural networks used in each study. We also included cases of generating training synthetic velocity models. Deep neural networks automatically optimize model parameters by training neural networks from large amounts of data. Thus, less human interaction is involved in the quality of the inversion results compared to that of conventional techniques and the computational cost of predicting a single velocity model after training is negligible. Additionally, unlike full-waveform inversions, the initial velocity model is not required. Several studies have demonstrated that deep neural network techniques achieve outstanding performance not only in computational cost but also in inversion results. Based on the research results, we analyzed and discussed the characteristics of deep neural network techniques for building velocity models.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.38 no.6
• /
• pp.623-633
• /
• 2020

As the time spent in indoor space has increased, the demand for services targeting indoor spaces also continues to increase. To provide indoor spatial information services, the construction of indoor spatial information should be done first. In the study, a method of generation IndoorGML, which is the international standard data format for Indoor space, from existing BIM data. The characteristics of IFC objects were investigated, and objects that need to be converted to IndoorGML were selected and classified into objects that restrict the expression of Indoor space and internal passages. Using the proposed method, a part of data set provided by the BIMserver github and the IFC model of the 21st Century Building in University of Seoul were used to perform experiments to generate PrimalSpaceFeatures of IndoorGML. As a result of the experiments, the geometric information of IFC objects was represented completely as IndoorGML, and it was shown that NavigableBoundary, one of major features of PrimalSpaceFeatures in IndoorGML, was accurately generated. In the future, the proposed method will improve to generate various types of objects such as IfcStair, and additional method for automatically generating MultiLayeredGraph of IndoorGML using PrimalSpaceFeatures should be developed to be sure of completeness of IndoorGML.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.10
• /
• pp.85-92
• /
• 2023

In this paper, we propose a method for automatically generating story-based abbreviated summaries from long-form dramas and movies. From the shooting stage, the basic premise was to compose a frame with illusion of depth considering the golden division as well as focus on the object of interest to focus the viewer's attention in terms of content delivery. To consider how to extract the appropriate frames for this purpose, we utilized elemental techniques that have been utilized in previous work on scene and shot detection, as well as work on identifying focus-related blur. After converting the videos shared on YouTube to frame-by-frame, we divided them into a entire frame and three partial regions for feature extraction, and calculated the results of applying Laplacian operator and FFT to each region to choose the FFT with relative consistency and robustness. By comparing the calculated values for the entire frame with the calculated values for the three regions, the target frames were selected based on the condition that relatively sharp regions could be identified. Based on the selected results, the final frames were extracted by combining the results of an offline change point detection method to ensure the continuity of the frames within the shot, and an edit decision list was constructed to produce an abbreviated summary of 62.77% of the footage with F1-Score of 75.9%

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.43 no.6 s.312
• /
• pp.28-35
• /
• 2006

Statistical models of shape variability based on active shape models (ASMs) have been successfully utilized to perform segmentation and recognition tasks in two-dimensional (2D) images. Three-dimensional (3D) model-based approaches are more promising than 2D approaches since they can bring in more realistic shape constraints for recognizing and delineating the object boundary. For 3D model-based approaches, however, building the 3D shape model from a training set of segmented instances of an object is a major challenge and currently it remains an open problem in building the 3D shape model, one essential step is to generate a point distribution model (PDM). Corresponding landmarks must be selected in all1 training shapes for generating PDM, and manual determination of landmark correspondences is very time-consuming, tedious, and error-prone. In this paper, we propose a novel automatic method for generating 3D statistical shape models. Given a set of training 3D shapes, we generate a 3D model by 1) building the mean shape fro]n the distance transform of the training shapes, 2) utilizing a tetrahedron method for automatically selecting landmarks on the mean shape, and 3) subsequently propagating these landmarks to each training shape via a distance labeling method. In this paper, we investigate the accuracy and compactness of the 3D model for the human liver built from 50 segmented individual CT data sets. The proposed method is very general without such assumptions and can be applied to other data sets.

• Publications of The Korean Astronomical Society
• /
• v.36 no.3
• /
• pp.65-78
• /
• 2021

Jagyeokru, an automatic striking water clock described in the Sejong Sillok (Veritable Records of King Sejong) is essentially composed of a water quantity control device and a time-signal device, with the former controlling the amount or the flow rate of water and the latter automatically informing the time based on the former. What connects these two parts is a signal generating device or a power transmission device called the 'Jujeon' system, which includes a copper rod on the float and ball-racked scheduled plates. The copper products excavated under Gongpyeong-dong in Seoul include a lot of broken plate pieces and cylinder-like devices. If some plate pieces are put together, a large square plate with circular holes located in a zigzag can be completed, and at the upper right of it is carved 'the first scheduled plate (一箭).' Cylinder-like devices generally 3.8 cm in diameter are able to release a ball, and have a ginkgo leaf-like screen fixed on the inner axis and a bird-shaped hook of which the leg fixes another axis and the beak attaches to the leaf side. The lateral view of this cylinder-like device appears like a trapezoid and mounts an iron ball. The function of releasing a ball agrees with the description of Borugak Pavilion, where Jagyeokru was installed, written by Kim Don (1385 ~ 1440). The other accounts of Borugak Pavilion's and Heumgyeonggak Pavilion's water clocks describe these copper plates and ball releasing devices as the 'Jujeon' system. According to the description of Borugak Pavilion, a square wooden column has copper plates on the left and right sides the same height as the column, and the left copper plate has 12 drilled holes to keep the time of a 12 double-hours. Meanwhile, the right plate has 25 holes which represent seasonal night 5-hours (Kyeong) and their 5-subhours (Jeom), not 12 hours. There are 11 scheduled plates for seasonal night 5-hours made with copper, which are made to be attached or detached as the season. In accordance with Nujutongui (manual for the operation of the yardstick for the clepsydra), the first scheduled plate for the night is used from the winter solstice (冬至) to 2 days after Daehan (大寒), and from 4 days before Soseol (小雪) to a day before the winter solstice. Besides the first scheduled plate, we confirm discovering a third scheduled plate and a sixth scheduled plate among the excavated copper materials based on the spacing between holes. On the other hand, the width of the scheduled plate is different for these artifacts, measured as 144 mm compared to the description of the Borugak Pavilion, which is recorded as 51 mm. From this perspective, they may be the scheduled plates for the Heumgyeonggak Ongru made in 1438 (or 1554) or for the new Fortress Pavilion installed in Changdeokgung palace completed in 1536 (the 31^st year of the reign of King Jungjong) in the early Joseon dynasty. This study presents the concept of the scheduled plates described in the literature, including their new operating mechanism. In addition, a detailed model of 11 scheduled plates is designed from the records and on the excavated relics. It is expected that this study will aid in efforts to restore and reconstruct the automatic water clocks of the early Joseon dynasty.

• Korean Journal of Remote Sensing
• /
• v.37 no.5_2
• /
• pp.1329-1340
• /
• 2021

The intertidal zone, which is a transitional zone between the ocean and the land, requires continuous monitoring as various changes occur rapidly due to artificial activity and natural disturbance. Monitoring of coastal topography changes using remote sensing method is evaluated to be effective in overcoming the limitations of intertidal zone accessibility and observing long-term topographic changes in intertidal zone. Most of the existing coastal topographic monitoring studies using remote sensing were conducted through high spatial resolution images such as Landsat and Sentinel. This study extracted the waterline using the NDWI from the GOCI-II (Geostationary Ocean Color Satellite-II) data, identified the changes in the intertidal area in Gyeonggi Bay according to various tidal heights, and examined the utility of DEM generation and topography altitude change observation over a short period of time. GOCI-II (249 scenes), Sentinel-2A/B (39 scenes), Landsat 8 OLI (7 scenes) images were obtained around Gyeonggi Bay from October 8, 2020 to August 16, 2021. If generating intertidal area DEM, Sentinel and Landsat images required at least 3 months to 1 year of data collection, but the GOCI-II satellite was able to generate intertidal area DEM in Gyeonggi Bay using only one day of data according to tidal heights, and the topography altitude was also observed through exposure frequency. When observing coastal topography changes using the GOCI-II satellite, it would be a good idea to detect topography changes early through a short cycle and to accurately interpolate and utilize insufficient spatial resolutions using multi-remote sensing data of high resolution. Based on the above results, it is expected that it will be possible to quickly provide information necessary for the latest topographic map and coastal management of the Korean Peninsula by expanding the research area and developing technologies that can be automatically analyzed and detected.

• Economic and Environmental Geology
• /
• v.55 no.5
• /
• pp.551-561
• /
• 2022

Geophysical exploration methods are very useful for generating high-resolution images of underground structures, and such methods can be applied to investigation of buried cultural properties and for determining their exact locations. In this study, image feature extraction and image segmentation methods were applied to automatically distinguish the structures of buried relics from the high-resolution ground-penetrating radar (GPR) images obtained at the center of Silla Kingdom, Gyeongju, South Korea. The major purpose for image feature extraction analyses is identifying the circular features from building remains and the linear features from ancient roads and fences. Feature extraction is implemented by applying the Canny edge detection and Hough transform algorithms. We applied the Hough transforms to the edge image resulted from the Canny algorithm in order to determine the locations the target features. However, the Hough transform requires different parameter settings for each survey sector. As for image segmentation, we applied the connected element labeling algorithm and object-based image analysis using Orfeo Toolbox (OTB) in QGIS. The connected components labeled image shows the signals associated with the target buried relics are effectively connected and labeled. However, we often find multiple labels are assigned to a single structure on the given GPR data. Object-based image analysis was conducted by using a Large-Scale Mean-Shift (LSMS) image segmentation. In this analysis, a vector layer containing pixel values for each segmented polygon was estimated first and then used to build a train-validation dataset by assigning the polygons to one class associated with the buried relics and another class for the background field. With the Random Forest Classifier, we find that the polygons on the LSMS image segmentation layer can be successfully classified into the polygons of the buried relics and those of the background. Thus, we propose that these automatic classification methods applied to the GPR images of buried cultural heritage in this study can be useful to obtain consistent analyses results for planning excavation processes.

• Korean Journal of Remote Sensing
• /
• v.39 no.6_1
• /
• pp.1211-1224
• /
• 2023

Clouds cause many difficult problems in observing land surface phenomena using optical satellites, such as national land observation, disaster response, and change detection. In addition, the presence of clouds affects not only the image processing stage but also the final data quality, so it is necessary to identify and remove them. Therefore, in this study, we developed a new cloud detection technique that automatically performs a series of processes to search and extract the pixels closest to the spectral pattern of clouds in satellite images, select the optimal threshold, and produce a cloud mask based on the threshold. The cloud detection technique largely consists of three steps. In the first step, the process of converting the Digital Number (DN) unit image into top-of-atmosphere reflectance units was performed. In the second step, preprocessing such as Hue-Value-Saturation (HSV) transformation, triangle thresholding, and maximum likelihood classification was applied using the top of the atmosphere reflectance image, and the threshold for generating the initial cloud mask was determined for each image. In the third post-processing step, the noise included in the initial cloud mask created was removed and the cloud boundaries and interior were improved. As experimental data for cloud detection, CAS500-1 L2G images acquired in the Korean Peninsula from April to November, which show the diversity of spatial and seasonal distribution of clouds, were used. To verify the performance of the proposed method, the results generated by a simple thresholding method were compared. As a result of the experiment, compared to the existing method, the proposed method was able to detect clouds more accurately by considering the radiometric characteristics of each image through the preprocessing process. In addition, the results showed that the influence of bright objects (panel roofs, concrete roads, sand, etc.) other than cloud objects was minimized. The proposed method showed more than 30% improved results(F1-score) compared to the existing method but showed limitations in certain images containing snow.

• Journal of Internet Computing and Services
• /
• v.14 no.6
• /
• pp.71-84
• /
• 2013

Log data, which record the multitude of information created when operating computer systems, are utilized in many processes, from carrying out computer system inspection and process optimization to providing customized user optimization. In this paper, we propose a MongoDB-based unstructured log processing system in a cloud environment for processing the massive amount of log data of banks. Most of the log data generated during banking operations come from handling a client's business. Therefore, in order to gather, store, categorize, and analyze the log data generated while processing the client's business, a separate log data processing system needs to be established. However, the realization of flexible storage expansion functions for processing a massive amount of unstructured log data and executing a considerable number of functions to categorize and analyze the stored unstructured log data is difficult in existing computer environments. Thus, in this study, we use cloud computing technology to realize a cloud-based log data processing system for processing unstructured log data that are difficult to process using the existing computing infrastructure's analysis tools and management system. The proposed system uses the IaaS (Infrastructure as a Service) cloud environment to provide a flexible expansion of computing resources and includes the ability to flexibly expand resources such as storage space and memory under conditions such as extended storage or rapid increase in log data. Moreover, to overcome the processing limits of the existing analysis tool when a real-time analysis of the aggregated unstructured log data is required, the proposed system includes a Hadoop-based analysis module for quick and reliable parallel-distributed processing of the massive amount of log data. Furthermore, because the HDFS (Hadoop Distributed File System) stores data by generating copies of the block units of the aggregated log data, the proposed system offers automatic restore functions for the system to continually operate after it recovers from a malfunction. Finally, by establishing a distributed database using the NoSQL-based Mongo DB, the proposed system provides methods of effectively processing unstructured log data. Relational databases such as the MySQL databases have complex schemas that are inappropriate for processing unstructured log data. Further, strict schemas like those of relational databases cannot expand nodes in the case wherein the stored data are distributed to various nodes when the amount of data rapidly increases. NoSQL does not provide the complex computations that relational databases may provide but can easily expand the database through node dispersion when the amount of data increases rapidly; it is a non-relational database with an appropriate structure for processing unstructured data. The data models of the NoSQL are usually classified as Key-Value, column-oriented, and document-oriented types. Of these, the representative document-oriented data model, MongoDB, which has a free schema structure, is used in the proposed system. MongoDB is introduced to the proposed system because it makes it easy to process unstructured log data through a flexible schema structure, facilitates flexible node expansion when the amount of data is rapidly increasing, and provides an Auto-Sharding function that automatically expands storage. The proposed system is composed of a log collector module, a log graph generator module, a MongoDB module, a Hadoop-based analysis module, and a MySQL module. When the log data generated over the entire client business process of each bank are sent to the cloud server, the log collector module collects and classifies data according to the type of log data and distributes it to the MongoDB module and the MySQL module. The log graph generator module generates the results of the log analysis of the MongoDB module, Hadoop-based analysis module, and the MySQL module per analysis time and type of the aggregated log data, and provides them to the user through a web interface. Log data that require a real-time log data analysis are stored in the MySQL module and provided real-time by the log graph generator module. The aggregated log data per unit time are stored in the MongoDB module and plotted in a graph according to the user's various analysis conditions. The aggregated log data in the MongoDB module are parallel-distributed and processed by the Hadoop-based analysis module. A comparative evaluation is carried out against a log data processing system that uses only MySQL for inserting log data and estimating query performance; this evaluation proves the proposed system's superiority. Moreover, an optimal chunk size is confirmed through the log data insert performance evaluation of MongoDB for various chunk sizes.