• The KIPS Transactions:PartD
• /
• v.14D no.7
• /
• pp.819-828
• /
• 2007

In this paper, we propose a topic maps matching and merging approach based on the syntactic or semantic characteristics and constraints of the topic maps. Previous schema matching approaches have been developed to enhance effectiveness and generality of matching techniques. However they are inefficient because the approaches should transform input ontologies into graphs and take into account all the nodes and edges of the graphs, which ended up requiring a great amount of processing time. Now, standard languages for developing ontologies are RDF/OWL and Topic Maps. In this paper, we propose an enhanced version of matching and merging technique based on topic partitioning, several matching operations and merging conflict detection.

• Journal of Information Processing Systems
• /
• v.18 no.4
• /
• pp.535-548
• /
• 2022

Using a rich resource language to classify sentiments in a language with few resources is a popular subject of research in natural language processing. Burmese is a low-resource language. In light of the scarcity of labeled training data for sentiment classification in Burmese, in this study, we propose a method of transfer learning for sentiment analysis of a language that uses the feature transfer technique on sentiments in English. This method generates a cross-language word-embedding representation of Burmese vocabulary to map Burmese text to the semantic space of English text. A model to classify sentiments in English is then pre-trained using a convolutional neural network and an attention mechanism, where the network shares the model for sentiment analysis of English. The parameters of the network layer are used to learn the cross-language features of the sentiments, which are then transferred to the model to classify sentiments in Burmese. Finally, the model was tuned using the labeled Burmese data. The results of the experiments show that the proposed method can significantly improve the classification of sentiments in Burmese compared to a model trained using only a Burmese corpus.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.9
• /
• pp.407-418
• /
• 2023

The Multi-Object Goal Visual Navigation(MultiOn) is a visual navigation task in which an agent must visit to multiple object goals in an unknown indoor environment in a given order. Existing models for the MultiOn task suffer from the limitation that they cannot utilize an integrated view of multimodal context because use only a unimodal context map. To overcome this limitation, in this paper, we propose a novel deep neural network-based agent model for MultiOn task. The proposed model, MCFMO, uses a multimodal context map, containing visual appearance features, semantic features of environmental objects, and goal object features. Moreover, the proposed model effectively fuses these three heterogeneous features into a global multimodal context map by using a point-wise convolutional neural network module. Lastly, the proposed model adopts an auxiliary task learning module to predict the observation status, goal direction and the goal distance, which can guide to learn the navigational policy efficiently. Conducting various quantitative and qualitative experiments using the Habitat-Matterport3D simulation environment and scene dataset, we demonstrate the superiority of the proposed model.

• Journal of KIISE:Databases
• /
• v.33 no.4
• /
• pp.372-383
• /
• 2006

Among the approaches to image database management, content-based image retrieval (CBIR) is viewed as having the best support for effective searching and browsing of large digital image libraries. Typical CBIR systems allow a user to provide a query image, from which low-level features are extracted and used to find 'similar' images in a database. However, there exists the semantic gap between human visual perception and low-level representations. An effective methodology for overcoming this semantic gap involves relevance feedback to perform feature re-weighting. Current approaches to feature re-weighting require the number of components for a feature representation to be the same for every image in consideration. Following this assumption, they map each component to an axis in the n-dimensional space, which we call the metric space; likewise the feature representation is stored in a fixed-length vector. However, with the emergence of features that do not have a fixed number of components in their representation, existing feature re-weighting approaches are invalidated. In this paper we propose a feature re-weighting technique that supports features regardless of whether or not they can be mapped into a metric space. Our approach analyses the feature distances calculated between the query image and the images in the database. Two-sided confidence intervals are used with the distances to obtain the information for feature re-weighting. There is no restriction on how the distances are calculated for each feature. This provides freedom for how feature representations are structured, i.e. there is no requirement for features to be represented in fixed-length vectors or metric space. Our experimental results show the effectiveness of our approach and in a comparison with other work, we can see how it outperforms previous work.

• Industry Promotion Research
• /
• v.6 no.2
• /
• pp.55-62
• /
• 2021

The number of single-parent families in South Korea increased since 2000, related to a sharp rise in the divorce rate of 50s and an increase in male mortality rates among those aged 40s-50s. Middle-aged single mothers experience a critical period realizing self-actualization needs, while being in the middle adulthood from the lifespan developmental perspective. In this respect, it is significant to study self-actualization of middle-aged single mothers through guided imagery and music (GIM) in order to provide them with psychological support. This study was conducted from September 2018 to June 2020, and the GIM sessions were conducted at least 10 times. Four participants were selected among the middle-aged single mothers. The imagery experiences of participants in the GIM sessions were classified into four sub-elements: physicalness, emotion, memory, and sense. Within those sub-elements, eight semantic units were categorized into 46 elements. Finally, 152 semantic units were derived. Moreover, the self-actualization which participants experienced through GIM presented three archetypal images: shadow, persona, and the self. In the GIM sessions, experiences of putting their negative emotions associated with family into words and changing passive self-imagery into active one enabled participants to bring the shadow into their consciousness, there by recognizing their positive and bright internal self. Furthermore, participants could map that their current status as people marginalized by siblings and parents, enraged and holding double standards for others, was suppressed by their 'good daughter' and 'religious' personas. This realization lead them to realize and restore their persona. The use of GIM in the study allowed participants to elicit re-experiences of the negative events, while experiencing various imagery and music. This process helped participants achieve self-actualization.

• Spatial Information Research
• /
• v.22 no.1
• /
• pp.65-73
• /
• 2014

Recently indoor navigation with indoor map such as Indoor Google Maps is served. For the services, constructing indoor data are required. CityGML and IFC are widely used as standards for representing indoor data. The data models contains spatial information for the indoor visualization and analysis, but indoor navigation requires semantic and topological information like graph as well as geometry. For this reason, IndoorGML, which is a GML3 application schema and data model for representation, storage and exchange of indoor geoinformation, is under standardization of OGC. IndoorGML can directly describe geometric property and refer elements in external documents. Because a lot of data in CityGML or IFC have been constructed, a huge amount of construction time and cost for IndoorGML data will be reduced if CityGML can help generate data in IndoorGML. Thus, this paper suggest practical use of CityGML including deriving from and link to CityGML. We analyze relationships between IndoorGML and CityGML. In this paper, issues and solutions for linkage of IndoorGML and CityGML are addressed.

• The Journal of the Korea Contents Association
• /
• v.14 no.10
• /
• pp.438-453
• /
• 2014

This paper proposes a system to translate an RDB into an OWL ontology which enables the users to navigate the ontology in GUI. In order to accomplish the goals mentioned previously, the system overcame two difficulties. First, our system defines a new mapping algorithm to map between DB elements and ontology ones. Comparing with existing solutions, our algorithm is able to generate ontologies from more DB structures. Second, our system provides the same data generated by a reasoner to the users. Note that this operation does not load ABox ontology on a reasoner. In addition, Tableau-based reasoners have the tractability problem on a large ABox (e.g., large ABoxes translated from DBs practically cannot be served). To solve this, our system internally runs SQL queries to retrieve the same data as the one from a reasoner every time ABox elements are queried.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.23 no.1
• /
• pp.78-89
• /
• 1999

Clothes enhance visual images through the interaction between space and background of the wearer. The influence of background is important as that of the clothes when the observer understands the images. We look at fashion pictures used as important as that various backgrounds are presented depending on the image of the clothes. The clothing the model wears in the pictures takes on shape and space which supports the clothes. The background interact to from the whole image. The background has an important influence on the delivery of image for the clothes. However when the clothes are presented in the background there are some cases that all or parts of clothes can be shown. We must consider the composition ratio of the clothes and background which influences the whole image of the clothing. These interactions and influences on the whole image in regards to clothing background and the ratio will be the focus of this study. clothing was Modern Mannish Casual, Feminine, Ground was decided artificial setting 1 natural setting 1, indoor setting 1, artificial setting 2, natural setting 2, indoor setting 2, Percentage of Clothing was 80% , 140%, 200%,. Thus visual stimulus were 72 pictures that were combined Clothing Ground and Percentage of Clothing, the main survey of questionary consisted of their evaluation of the Picture image combined Clothing and Ground by 30 semantic differential bi-polar scales and the subjects were 50 students majoring in clothing and textile. The data analyzed by factor analysis MCA, MDS, The major finding were as follows : 1) As a result of factor analysis, 5 factors -Attractiveness Hardness and softness Cuteness Attention Cool and Warm factor were found out as constructing factors the Picture image combined Clothing and Ground 2) According to multidimensional positioning map were presented in a stimulus position the perceptive image differed in degree of similarity as a ground construction of stimulus in spite of same clothing image. It will aid in choosing the most beneficial background for any clothing brand. It will enhance the picture images to their full potential in any advertising medium.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.25 no.6_1
• /
• pp.507-516
• /
• 2007

Segmentation and organization of the LiDAR (Light Detection and Ranging) data of the Earth's surface are difficult tasks because the captured LiDAR data are composed of irregularly distributed point clouds with lack of semantic information. The reason for this difficulty in processing LiDAR data is that the data provide huge amount of the spatial coordinates without topological and/or relational information among the points. This study introduces LiDAR data segmentation technique by utilizing histograms of the LiDAR height image data and analyzing roof shape for 3D reconstruction and visualization of the buildings. One of the advantages in utilizing LiDAR height image data is no registration required because the LiDAR data are geo-referenced and ortho-projected data. In consequence, measurements on the image provide absolute reference coordinates. The LiDAR image allows measurement of the initial building boundaries to estimate locations of the side walls and to form the planar surfaces which represent approximate building footprints. LiDAR points close to each side wall were grouped together then the least-square planar surface fitting with the segmented point clouds was performed to determine precise location of each wall of an building. Finally, roof shape analysis was performed by accumulated slopes along the profiles of the roof top. However, simulated LiDAR data were used for analyzing roof shape because buildings with various shapes of the roof do not exist in the test area. The proposed approach has been tested on the heavily built-up urban residential area. 3D digital vector map produced by digitizing complied aerial photographs was used to evaluate accuracy of the results. Experimental results show efficiency of the proposed methodology for 3D building reconstruction and large scale digital mapping especially for the urban area.

• Proceedings of the Korea Society for Industrial Systems Conference
• /
• 2003.11a
• /
• pp.239-250
• /
• 2003

In this research, we propose a hybrid group decision support mechanism (H-GDSM) based on Fuzzy AHP (Analytic Hierarchy Process) and FCM (Fuzzy Cognitive Map). The AHP elicits a corresponding priority vector interpreting the preferred information among the decision makers. Corresponding vector was composed of the pairwise comparison values of a set of objects. Since pairwise comparison values are the judgments obtained from an appropriate semantic scale. However, AHP couldn't represent the causal relationship among information, which were used by decision makers. In contrast to AHP, FCM could represent the causal relationship among variables or information. Therefore, FCMs were successfully developed and used in several ill-structured domains, such as strategic decision-making, policy making, and simulations. Nonetheless, many researchers used subjective and voluntary inputs to simulate the FCM. As a result of subjective inputs, it couldn't avoid the rebukes of businessman. To overcome these limitations, we incorporated the Fuzzy membership functions, AHP and FCM into a H-GDSM. In contrast to current AHP methods and FCMs, the H-GDSM method developed herein could concurrently tackle the pairwise comparison involving causal relationships under a group decision-making environment. The strengths and contributions of our mechanism were 1) handling of qualitative knowledge and causal relationships, 2) extraction of objective input value to simulate the FCM, 3) multi-phase group decision support based on H-GDSM. To validate our proposed mechanism we developed a simple prototype system to support negotiation-based decisions in electronic commerce (EC).