• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.10
• /
• pp.1271-1279
• /
• 2020

Text region detection is a technology that detects text area in handwriting or printed documents. The detected text areas are digitized through a recognition step, which is used in various fields depending on the purpose of use. However, the detection result of the small text unit is not suitable for the industrial field. In addition, the border of tables in the document that it causes miss-detected results, which has an adverse effect on the recognition step. To solve the issues, we propose a method for detecting text region using the border information of the table. In order to utilize the border information of the table, the proposed method adjusts the flow of two decoders. Experimentally, we show improved performance using the table border pseudo label based on weak supervised learning.

• Nutritional Sciences
• /
• v.4 no.1
• /
• pp.55-62
• /
• 2001

Consumers'frequent use of micronutrient supplements has caused concerns o possible overdoses and prompted the view that the appropriate provision of nutrition information on such supplements is needed. In this study the nutrition information on vitamin-mineral supplements in Korea was evaluated based on the labels on the supplements. Consumers'use, reliance on and demand for nutrition information were examined by self-administered questionnaire. Subjects were 1,203 middle-aged housewives. Under examination were 141 multinutrient products (86.6%) and single nutrient products (13.4%). Various names and units were used for the same nutrient and the labels were not informative to consumers. The mode of nutrients contents in the supplements were several fold of RDA though not in the range of toxicity. %RDA value was seldom shown on the label. Currently these supplements are classified as general drugs in Korea so they are not subject to regulations on nutrition labeling. Half of the subjects read the nutrient content list but two-thirds of them did not understand the information. Numerous health claims related to diseases were listed on the label and more than half of the subjects read them and one-third believed those health claims. These results indicate the need for an appropriate format for nutrition information on vitamin-mineral supplements.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.15 no.4
• /
• pp.103-110
• /
• 2019

A patent contains detailed information of the developed technology and is published to the public. Thus, patents can be used to overcome the limitations of traditional technology trend research and prediction techniques. Recently, due to the advantages of patented analytical methodology, IP R&D is carried out worldwide. The patent is big data and has a huge amount, various domains, and structured and unstructured data characteristics. For this reason, there are many difficulties in collecting and researching patent information. Patent research generally writes the Search formula to collect patent documents from DB. The collected patent documents contain some noise patents that are irrelevant to the purpose of analysis, so they are removed. However, eliminating noise patents is a manual task of reading and classifying technology, which is time consuming and expensive. In this study, we propose a model that automatically classifies The Noise patent for efficient patent information research. The proposed method performs Patent Embedding using Word2Vec and generates Noise seed label. In addition, noise patent classification is performed using the Random forest. The experimental data is published and registered with the USPTO among the patents related to Ocean Surveillance & Tracking Network technology. As a result of experimenting with the proposed model, it showed 73% accuracy with the label actually given by experts.

• Proceedings of the Korean Information Science Society Conference
• /
• 2006.06d
• /
• pp.307-309
• /
• 2006

본 논문에서는 MPLS (Multiprotocol Label Switching)망의 네트워크 자원을 효율적으로 사용 하기위한 MPLS 망의 단계별 리라우트 기법을 제안한다. MPLS 망 내에서 특정 노드가 혼잡할 경우 노드의 단계별 등급을 증가 시켜서 리라우트하는 기법이다. 이는 LSP (Label Switched Path)를 통해 입구노드에서 출구노드까지의 최소 비용 경로가 정해진 상태에서 경로상의 어느 특정 노드가 트래픽의 증가로 인해 혼잡이 발생하면 자신이 가지고 있는 일정 등급 이상의 값을 가질 경우 경로 재설정 메시지를 통하여 새로운 대체 복구 경로를 찾아 리라우트한다. 또한 혼잡이 발생한 노드가 혼잡에서 벗어나 등급이 원래의 값으로 돌아올 경우 최초 정해진 경로상의 최소 비용을 갖는 최적 경로로 다시 리라우트 된다. 이는 제안하는 단계별 리라우트 기법이 입 출구 LER에 집중되는 스트레스를 모든 망 내의 자원이 분담함으로써 효율적으로 사용할 수 있는 방안을 보여줄 수 있다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.6 no.10
• /
• pp.2650-2662
• /
• 2012

Due to the semantic gap issue, the performance of automatic image annotation is still far from satisfactory. Active learning approaches provide a possible solution to cope with this problem by selecting most effective samples to ask users to label for training. One of the key research points in active learning is how to select the most effective samples. In this paper, we propose a novel active learning approach based on sparse graph. Comparing with the existing active learning approaches, the proposed method selects the samples based on two criteria: uncertainty and representativeness. The representativeness indicates the contribution of a sample's label propagating to the other samples, while the existing approaches did not take the representativeness into consideration. Extensive experiments show that bringing the representativeness criterion into the sample selection process can significantly improve the active learning effectiveness.

• Journal of Intelligence and Information Systems
• /
• v.7 no.1
• /
• pp.161-175
• /
• 2001

In this paper, a detection method of contradiction between input informations is proposed when the inference is processed in rule-based systems. The proposed method is accomplished by improving the label representation and the label management scheme in a conventional ATMS(Assumption-based Truth Maintenance System). The Proposed method also can represent and process input informations having uncertainty values.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.10c
• /
• pp.136-138
• /
• 2004

IP망을 활용한 VPN(Virtual Private Network)에서의 QoS 보장 및 광대역 서비스 제공에 대한 해결 방안으로 차세대 광 인터넷을 통한 OVPN(Optical VPN) 기술이 제시되고 있다. 차세대 광 인터넷의 구현이 IP/GMPLS(Generalized Multi-Protocol Label Switching) over DWDM(Dense Wavelength Division Multiplexing) 프로토콜 프레임워크로 표준화되고 있는 현실에 비추어 볼 때 IP/GMPLS over DWDM 백본망을 통한 OVPN은 차세대 가상사설망으로써 멀티미디어 서비스 제공을 위한 최적의 방안이다. 이러한 멀티미디어 서비스 제공을 위한 OVPN에서는 최적의 Optical-LSP(Label Switched Path)의 설립이 요구되고 있다. 따라서 본 논문에서는 차세대 OVPN의 모델 및 망의 blocking probability를 향상하기 위한 미래의 잠재적인 연결 요구에 대해 간섭을 최소화하면서 경로를 설정하는 MW-MIPR 라우팅 알고리즘을 제시하고 이를 라우팅 프로토콜인 OSPF-TE+(OSPF Extensions in Support of Generalized MPLS)에 맵핑하기 위한 방안을 제안한다.

• Proceedings of the KIEE Conference
• /
• 2003.10a
• /
• pp.300-302
• /
• 2003

This research aims to develop the multi-channel type label-free DNA chip that has the above characteristics and be able to solve the problems. At first, we fabricated a high integrated type DNA chip array by lithography technology. It is able to detect a various genes electrochemically after immobilization of a various probe DNA and hybridization of label-free target DNA on the electrode s simultaneously.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 1998.11a
• /
• pp.354-357
• /
• 1998

MPLS (Multiprotocol Label Switching)는 인터넷에서 속도, 확장성 그리고 서비스 제공 능력을 향상시키기 위한 백본 네트웍으로 이용하기 위하여 Internet Engineering Task Force (IETF) standard로 급속하게 성장하고 있다. MPLS는 기존의 인터넷 라우팅에서 사용하는 longest prefix match 방식을 이용하는 라우팅 방법 대신에 short label exact match 방식과 L3 forwarding 방법을 사용함으로써 고속 인터넷 서비스 기술을 제공한다. 한편, 기존 인터넷의 IP format을 보면 Host Id, (Address prefix, Host Id), Broadcasting, Multicasting의 네 가지 종류의 구조를 가지고 있다. 그러나 아직 MPLS에서의 멀티캐스트 서비스에 대한 방식이 아직 표준화되고 있지 않고 있는 상황에서, MPLS 서비스 도메인 내에서 멀티캐스트 패킷은 기존의 멀티캐스트 라우팅 프로토콜과 연계되어 MPLS상에서 멀티캐스트 서비스가 이루어져야 한다. 본 논문에서는 기존의 인터넷상에서 제공되어지는 멀티캐스트 IP 플로우들을 MPLS 상에서 수용하기 위한 방식을 제안한다.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.16 no.3
• /
• pp.25-36
• /
• 2020

Topics calculated using LDA topic modeling have to be labeled separately. When labeling a topic, we look at the words that represent the topic, and label the topic. Therefore, it is important to first make a good set of words that represent the topic. This paper proposes a method of calculating a set of words representing a topic using TextRank, which extracts the keywords of a document. The proposed method uses Relevance to select words related to the topic with discrimination. It extracts topic keywords using the TextRank algorithm and connects keywords with a high frequency of simultaneous occurrence to express the topic with a higher coverage.