• Journal of Digital Convergence
• /
• v.19 no.6
• /
• pp.251-258
• /
• 2021

In this paper, we proposed an encoder-decoder model utilizing residual learning to improve the accuracy of the U-Net-based semantic segmentation method. U-Net is a deep learning-based semantic segmentation method and is mainly used in applications such as autonomous vehicles and medical image analysis. The conventional U-Net occurs loss in feature compression process due to the shallow structure of the encoder. The loss of features causes a lack of context information necessary for classifying objects and has a problem of reducing segmentation accuracy. To improve this, The proposed method efficiently extracted context information through an encoder using residual learning, which is effective in preventing feature loss and gradient vanishing problems in the conventional U-Net. Furthermore, we reduced down-sampling operations in the encoder to reduce the loss of spatial information included in the feature maps. The proposed method showed an improved segmentation result of about 12% compared to the conventional U-Net in the Cityscapes dataset experiment.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.11
• /
• pp.1437-1444
• /
• 2020

With the development of computer vision systems, many advances have been made in the fields of surveillance, biometrics, medical imaging, and autonomous driving. In the field of autonomous driving, in particular, the object detection technique using deep learning are widely used, and the paved road detection is a particularly crucial problem. Unlike the ROI detection algorithm used in general object detection, the structure of paved road in the image is heterogeneous, so the ROI-based object recognition architecture is not available. In this paper, we propose a deep neural network architecture for atypical paved road detection using Semantic segmentation network. In addition, we introduce the multi-scale semantic segmentation network, which is a network architecture specialized to the paved road detection. We demonstrate that the performance is significantly improved by the proposed method.

• Proceedings of the IEEK Conference
• /
• 2001.06c
• /
• pp.109-112
• /
• 2001

This paper proposes an efficient algorithm of extracting anchor blocks for a semantic structure of a news video. We define the FRFD to calculate the frame difference of anchor face position rather than simply uses the general frame difference. Since, The FRFD value is sensitive to existing face in frame, anchor block can be efficiently extracted. In this paper, an algorithm to extract a face position using partial decoded MPEG data is also proposed. In this way a news video can be structured semantically using the extracted anchor blocks.

• Proceedings of the IEEK Conference
• /
• 2000.11d
• /
• pp.171-174
• /
• 2000

In this paper, We try to design combined source-channel coder that is compatible with video coding standards. This MAP decoder is proposed by adding semantic structure and semantic constraint of video coding standards to the method using redundnacy of the MAP decoders proposed previously. Then, We get the better performance than usual channel coder＇s.

• Korean Journal of English Language and Linguistics
• /
• v.4 no.1
• /
• pp.1-31
• /
• 2004

This paper has revisited the dative alternation in English, and defended the so-called polysemy view. The paper has argued for a particular format of lexical representation, one that allows reference to events. In addition to the semantic conditions, the paper has argued that the DO and PO constructions also allow for different information structures.

• Language and Information
• /
• v.5 no.1
• /
• pp.1-15
• /
• 2001

Floating quantifiers(FQs) in English exhibit both universal and language specific proper- ties This paper discusses how such syntactic and semantic characteristics can be explained in terms of a constraint-based, lexical approach to the floating quanti- fer construction within the framework of Head-Driven Phrase Structure Grammar(HPSG). Based on the assumption and FQs are base-generated VP modifiers, this paper proposes and account in which the semantic contribution of FQs consists of a "lexically retrieved" universal quantifier taking scope over the VP meaning.P meaning.

• Journal of KIISE:Software and Applications
• /
• v.32 no.3
• /
• pp.192-201
• /
• 2005

For the past ten years, the goal of ubiquitous computing research has been the establishment of a new technology system with the aim 'Anytime, Anywhere, and Any form'. The needs for agent technology innovations such as ontology-based structure, ontology-based agent communication language, and multi-agents frameworks have been identified. This paper proposes a noble multi-agents architecture for ubiquitous systems. We suggest four major steps in the interaction between human and agents which enable ubiquitous agents to process by themselves to provide adaptive service to meet human's needs. First, we propose a semantic web technology to represent the association between information resources more explicitly Second, we construct a semantic ontology so that agents can recognize web contents.'Third, we propose a method to communicate between agents using OWL ontologies. Finally, we suggest a multi-agents structure based on the JADE of FIPA to analyze messages and get information. The semantic multi-agents framework proposed in this paper infers semantic situations using semantic web technology based on ontologies. A service provided is inferred differently according to user state because the multi-agents communicate by using OWL ontology language. Therefore, our system better infers context information than other without ontologies.

• International Journal of Knowledge Content Development & Technology
• /
• v.5 no.1
• /
• pp.49-68
• /
• 2015

Given a query (a health question), retrieval of relevant frequently asked questions (FAQs) is essential as the FAQs provide both reliable and readable information to healthcare consumers. The retrieval requires the estimation of the semantic similarity between the query and each FAQ. The similarity estimation is challenging as semantic structures of Chinese healthcare FAQs are quite different from those of the FAQs in other domains. In this paper, we propose a conceptual model for Chinese healthcare FAQs, and based on the conceptual model, present a technique ECA that estimates conceptual similarities between FAQs. Empirical evaluation shows that ECA can help various kinds of retrievers to rank relevant FAQs significantly higher. We also make ECA online to provide services for FAQ retrievers.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2007.05a
• /
• pp.123-137
• /
• 2007

The information space of semantic web comprised of various resources, properties, and relationships is more complex than that of WWW comprised of just documents and hyperlinks. Therefore, ranking methods in the semantic web should be modified to reflect the complexity of the information space. In this paper we propose a method of ranking query results from RDF(Resource Description Framework) knowledge bases. The ranking criterion is the importance of a resource computed based on the link structure of the RDF graph. Our method is expected to solve a few problems in the prior research including the Tightly-Knit Community Effect. We illustrate our methods using examples and discuss directions for future research.

• The Journal of Society for e-Business Studies
• /
• v.7 no.1
• /
• pp.141-152
• /
• 2002

Data dictionary is a collection of meta-data, which describes data produced and consumed while performing business processes. Data dictionary is an essential element for business process standardization and automation, and has a fundamental role in ERP application management and customization. Also, data dictionary facilitates B2B processes by enabling painless integration of business processes between various enterprises. We implemented data dictionary support in SEA＋, a component- based scalable ERP system developed in ETRI, and found out that it's a plausible feature of business information system. We discovered that data dictionary promotes semantic, not syntactic, data management, which can make it possible to leverage viability of the tool in the coming age of more meta-data oriented computing world. We envision that business data dictionary is a firm foundation of adapting business knowledge, applications and processes into the semantic web based enterprise infra-structure.