• Korean Journal of Remote Sensing
• /
• 제35권2호
• /
• pp.279-288
• /
• 2019

We evaluated the land cover classification performance of SegNet, which features semantic segmentation of aerial imagery. We selected four semantic classes, i.e., urban, farmland, forest, and water areas, and created 2,000 datasets using aerial images and land cover maps. The datasets were divided at a 8:2 ratio into training (1,600) and validation datasets (400); we evaluated validation accuracy after tuning the hyperparameters. SegNet performance was optimal at a batch size of five with 100,000 iterations. When 200 test datasets were subjected to semantic segmentation using the trained SegNet model, the accuracies were farmland 87.89%, forest 87.18%, water 83.66%, and urban regions 82.67%; the overall accuracy was 85.48%. Thus, deep learning-based semantic segmentation can be used to classify land cover.

• Korean Journal of Remote Sensing
• /
• 제39권6_3호
• /
• pp.1771-1777
• /
• 2023

With the advancements of deep learning, many semantic segmentation-based methods for land cover classification have been proposed. However, existing deep learning-based models only use image information and cannot guarantee spatiotemporal consistency. In this study, we propose a land cover classification model using geographical coordinates. First, the coordinate features are extracted through the Coordinate Hash Encoder, which is an extension of the Multi-resolution Hash Encoder, an implicit neural representation technique, to the longitude-latitude coordinate system. Next, we propose an architecture that combines the extracted coordinate features with different levels of U-net decoder. Experimental results show that the proposed method improves the mean intersection over union by about 32% and improves the spatiotemporal consistency.

• Asia pacific journal of information systems
• /
• 제14권1호
• /
• pp.79-100
• /
• 2004

As a part of ebXML(Electronic Business using eXtensible Markup Language) framework, BPSS(Business Process Specification Schema) has been provided to support the direct specification of the set of elements required to configure a runtime system in order to execute a set of ebXML business transactions. The BPS,' is available in two stand-alone representations, a UML version and an XML version. Due to the limitations of UML notations and XML syntax, however, current ebXML BPSS specification fails to specify formal semantic constraints completely. In this study, we propose a constraint classification scheme for the BPSS specification and describe how to formally represent those semantic constraints using OCL(Object Constraint Language). As a way to validate p Business Process Specification(BPS) with the formal semantic constraints, we suggest a rule-based approach to represent the formal constraints and demonstrate its detailed mechanism for applying the rule-based constraints to the BPS with a prototype implementation.

• Smart Media Journal
• /
• 제9권2호
• /
• pp.69-77
• /
• 2020

Unlike the past, which was limited to terrestrial broadcasts, many dramas are currently being broadcast on cable channels and the Internet web. After watching the drama, viewers actively express their opinions through reviews and studies related to the analysis of these reviews are actively being conducted. Due to the nature of the drama, the genre is not clear, and due to the various age groups of viewers, reviews and ratings from other viewers help to decide which drama to watch. However, since it is difficult for viewers to check and analyze many reviews individually, a data analysis technique is required to automatically analyze them. Accordingly, this paper classifies the topics of reviews that have an important influence on drama selection and reclassifies them into semantic topics according to the similarity of words. In addition, we propose a model that classifies reviews into sentences according to semantic topics and sentiment analysis through sentiment words.

• International Journal of Computer Science & Network Security
• /
• 제21권12spc호
• /
• pp.712-718
• /
• 2021

Virtual communities are studied to analyze their characteristic features, types, and tole to modern society. The article is aimed at creating a classification of virtual communities according to specific characteristics, which can be used to model the interaction, and necessity of components that are important for the community. The classification of virtual communities will contribute to their better performance and satisfy the users' needs in information. The study reveals the value structure of virtual communities, educational and communicative influence, and the possible threats these communities may bring to society and security.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• 제19권6호
• /
• pp.227-233
• /
• 2019

Recently, along with the recent development of deep learning technique, neural networks are achieving success in computer vision filed. Convolutional neural network have shown outstanding performance in not only for a simple image classification task, but also for tasks with high difficulty such as object segmentation and detection. However many such deep learning models are based on supervised-learning, which requires more annotation labels than image-level label. Especially image semantic segmentation model requires pixel-level annotations for training, which is very. To solve these problems, this paper proposes a weakly-supervised semantic segmentation method which requires only image level label to train network. Existing weakly-supervised learning methods have limitations in detecting only specific area of object. In this paper, on the other hand, we use multi-classifier deep learning architecture so that our model recognizes more different parts of objects. The proposed method is evaluated using VOC 2012 validation dataset.

• The Journal of the Korea institute of electronic communication sciences
• /
• 제18권3호
• /
• pp.413-420
• /
• 2023

For a long time, researchers have presented excellent results in the field of image retrieval due to many studies on CBIR. However, there is still a semantic gap between these search results for images and human perception. It is still a difficult problem to classify images with a level of human perception using a small number of images. Therefore, this paper proposes an image classification model using deep learning-based transfer learning to minimize the semantic gap between images of people and search systems in image retrieval. As a result of the experiment, the loss rate of the learning model was 0.2451% and the accuracy was 0.8922%. The implementation of the proposed image classification method was able to achieve the desired goal. And in deep learning, it was confirmed that the CNN's transfer learning model method was effective in creating an image database by adding new data.

• International conference on construction engineering and project management
• /
• The 9th International Conference on Construction Engineering and Project Management
• /
• pp.752-759
• /
• 2022

The instantiation of spaces as a discrete entity allows users to utilize BIM models in a wide range of analyses. However, in practice, their utility has been limited as spaces are erroneously entered due to human error and often omitted entirely. Recent studies attempted to automate space allocation using artificial intelligence approaches. However, there has been limited success as most studies focused solely on the use of geometric features to distinguish spaces. In this study, in addition to geometric features, semantic relations between spaces and elements were modeled and used to improve space classification in BIM models. Graph Convolutional Networks (GCN), a deep learning algorithm specifically tailored for learning in graphs, was deployed to classify spaces via a similarity graph that represents the relationships between spaces and their surrounding elements. Results confirmed that accuracy (ACC) was +0.08 higher than the baseline model in which only geometric information was used. Most notably, GCN was able to correctly distinguish spaces with no apparent difference in geometry by discriminating the specific elements that were provided by the similarity graph.

• Proceedings of the CALSEC Conference
• /
• 한국전자거래학회 2004년도 e-Biz World Conference
• /
• pp.302-309
• /
• 2004

·Catalogs -information about products and services -Contents ＋ Classification Schema ＋ Operational Issues ·What do we do with them？ -[Schulten, et a;, 2001] ‥Narrow down search for complete set of applicable products ‥Comprehend individual description to the precision needed -Support other applications that use product information ‥SCM, ERP, e-Procurement, etc. ·Catalog Management System -Design, storage, navigation ＆ retrieval, transformation, communication, publication(omitted)

• Korean Journal of Remote Sensing
• /
• 제39권3호
• /
• pp.269-282
• /
• 2023

The purpose of this study was to construct land cover maps using a deep learning model and to select the optimal deep learning model for land cover classification by adjusting the dataset such as input image size and Stride application. Two types of deep learning models, the U-net model and the DeeplabV3+ model with an Encoder-Decoder network, were utilized. Also, the combination of the two deep learning models, which is an Ensemble model, was used in this study. The dataset utilized RapidEye satellite images as input images and the label images used Raster images based on the six categories of the land use of Intergovernmental Panel on Climate Change as true value. This study focused on the problem of the quality improvement of the dataset to enhance the accuracy of deep learning model and constructed twelve land cover maps using the combination of three deep learning models (U-net, DeeplabV3+, and Ensemble), two input image sizes (64 × 64 pixel and 256 × 256 pixel), and two Stride application rates (50% and 100%). The evaluation of the accuracy of the label images and the deep learning-based land cover maps showed that the U-net and DeeplabV3+ models had high accuracy, with overall accuracy values of approximately 87.9% and 89.8%, and kappa coefficients of over 72%. In addition, applying the Ensemble and Stride to the deep learning models resulted in a maximum increase of approximately 3% in accuracy and an improvement in the issue of boundary inconsistency, which is a problem associated with Semantic Segmentation based deep learning models.