• Journal of the Korean Institute of Intelligent Systems
• /
• v.13 no.6
• /
• pp.655-660
• /
• 2003

In general, Support Vector Machine has a good performance in binary classification, but it has the limitation on multi-pattern classification. So, we proposed an Import Vector Voting model for two or more labels classification. This model applied kernel bagging strategy to Import Vector Machine by Zhu. The proposed model used a voting strategy which averaged optimal kernel function from many kernel functions. In experiments, not only binary but multi-pattern classification problems, our proposed Import Vector Voting model showed good performance for given machine learning data.

• Annual Conference on Human and Language Technology
• /
• 2015.10a
• /
• pp.99-103
• /
• 2015

최근 딥러닝 기술의 발전에 힘입어 이미지로부터 자동으로 관련된 단어 혹은 문장을 생성하는 연구들이 진행되고 있는데, 많은 연구들은 이미지와 단어가 1:1로 대응된 잘 정련된 학습 집합을 필요로 한다. 한편 스마트폰 보급의 확산으로 인스타그램, 폴라 등의 이미지 기반 SNS가 급속하게 성장함에 따라 인터넷에는 한 이미지의 복수개의 단어(태그)가 부착되어있는 데이터들이 폭증하고 있는 것이 현실이다. 본 논문에서는 소규모의 잘 정련된 학습 집합뿐 아니라 이러한 대규모의 다중 레이블 데이터를 같이 활용하여 이미지로부터 태그를 생성하는 개선된 CNN구조 및 학습알고리즘을 제안한다. 기존의 분류 기반 모델에 은닉층을 추가하고 새로운 학습 방법을 도입한 결과, 어노테이션 성능이 기존 모델보다 11% 이상 향상되었다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.05a
• /
• pp.393-396
• /
• 2022

본 연구는 국방과학기술 분야의 특허 및 논문 실적을 이용하여 통계기반 기계학습 모델 4 종을 학습하고, 실제 분석 대상기관의 데이터 입력결과를 분석하여 실용성에 대한 한계점 분석을 목적으로 한다. 기존 연구에서는 특허분류코드를 기준으로 분류하여 특수 목적으로 활용하거나 세부 연구 범위 내 연구 주제탐색 및 특징연구 등 미시적인 관점에서의 상세연구 활용 목적인 반면, 본 연구는 거시적인 관점에서 연구의 전체적인 흐름과 경향성 파악을 목적으로 한다. 이에 ICT 기술 138 종의 특허 및 논문 30,965 건과 국방과학기술 192 종의 특허 및 논문 23,406 건을 학습데이터로 각 모델을 학습하였다. 비교한 통계기반 학습모델은 Support Vector Machines, Decision Tree, Naive Bayes, XGBoost 모델이다. 학습데이터에 대한 학습검증 단계에서는 최대 99.4%의 성능을 보였다. 다만, 실제 분석대상기관의 특허 및 논문 12,824 건으로 입력분석한 결과, 모델별 편향성 문제, 데이터 전처리 이슈, 다중클래스 및 다중레이블 문제를 확인, 도출한 문제에 대한 해결방안을 제시하고 추가 연구의 방향성을 제시한다.

• Journal of KIISE:Information Networking
• /
• v.29 no.1
• /
• pp.24-30
• /
• 2002

Label switching technology is currently emerging as a solution for the rapidly growing of Internet traffic demand. Multiprotocol label switching(MPLS) is one of the standards made by the Internet Engineering Task Force(IETE) intended to enhance speed, scalability, and inter-opearability between label switching technologies. In MPLS, utilization of label space is a very important factor of network performance because labels are basic unit in packet switching. We propose a algorithm to effectively use label space by a multiple disconnect timer at the label switching router. Our algorithm is based on multiple utilization of the connection release timer over the MPLS network with multiple domains. In our algorithm, a relatively linger timeout interval is assigned to the traffic with higher class by the aid of the packet classifier. This reduces delay for making a new connection and also reduces the amount of packets which will be routed to the layer 3. Simulation results shows that reduction of required label number in MPLS network and this indicate our algorithm offers better performance than the existing ones in term of utilization of label space.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.12
• /
• pp.1596-1603
• /
• 2018

Rapidly detecting and warning of fires is necessary for minimizing human injury and property damage. Generally, when fires occur, both the smoke and the flames are generated, so fire detection systems need to detect both the smoke and the flames. However, most fire detection systems only detect flames or smoke and have the disadvantage of slower processing speed due to additional preprocessing task. In this paper, we implemented a fire detection system which predicts the flames and the smoke at the same time by constructing a CNN model that supports multi-labeled classification. Also, the system can monitor the fire status in real time by using Grad-CAM which visualizes the position of classes based on the characteristics of CNN. Also, we tested our proposed system with 13 fire videos and got an average accuracy of 98.73% and 95.77% respectively for the flames and the smoke.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.12
• /
• pp.1-7
• /
• 2019

With the in-depth development of machine learning, the deep learning method has made great progress, especially with the Convolution Neural Network(CNN). Compared with traditional text sentiment classification methods, deep learning based CNNs have made great progress in text classification and processing of complex multi-label and multi-classification experiments. However, there are also problems with the neural network for text sentiment classification. In this paper, we propose a fusion model based on Long-Short Term Memory networks(LSTM) and CNN deep learning methods, and applied to multi-category news datasets, and achieved good results. Experiments show that the fusion model based on deep learning has greatly improved the precision and accuracy of text sentiment classification. This method will become an important way to optimize the model and improve the performance of the model.

• The Journal of Bigdata
• /
• v.7 no.2
• /
• pp.1-9
• /
• 2022

In the global era, the importance of imported food safety management is increasing. Address information of overseas food companies is key information for imported food safety management, and must be verified for prompt response and follow-up management in the event of a food risk. However, because each country's address system is different, one verification system cannot verify the addresses of all countries. Also, the purpose of address verification may be different depending on the field used. In this paper, we deal with the problem of classifying a given overseas food business address into the administrative district level of the country. This is because, in the event of harm to imported food, it is necessary to find the administrative district level from the address of the relevant company, and based on this trace the food distribution route or take measures to ban imports. However, in some countries the administrative district level name is omitted from the address, and the same place name is used repeatedly in several administrative district levels, so it is not easy to accurately classify the administrative district level from the address. In this study we propose a deep learning-based administrative district level classification model suitable for this case, and verify the actual address data of overseas food companies. Specifically, a method of training using a label powerset in a multi-label classification model is used. To verify the proposed method, the accuracy was verified for the addresses of overseas manufacturing companies in Ecuador and Vietnam registered with the Ministry of Food and Drug Safety, and the accuracy was improved by 28.1% and 13%, respectively, compared to the existing classification model.

• Information Systems Review
• /
• v.25 no.3
• /
• pp.27-41
• /
• 2023

Unlike the previous works focusing on the state-of-the-art methodologies to improve the performance of machine learning models, this study improves the 'quality' of training data used in machine learning. We propose a method to enhance the quality of training data through the processing of 'local grammar,' frequently used in corpus analysis. We collected a vast amount of unstructured corporate review text data posted by employees working in the top 100 companies in Korea. After improving the data quality using the local grammar process, we confirmed that the classification model with local grammar outperformed the model without it in terms of classification performance. We defined five factors of work engagement as classification categories, and analyzed how the pattern of reviews changed before and after the COVID-19 pandemic. Through this study, we provide evidence that shows the value of the local grammar-based automatic identification and classification of employee experiences, and offer some clues for significant organizational cultural phenomena.

• Annual Conference on Human and Language Technology
• /
• 2023.10a
• /
• pp.50-55
• /
• 2023

속성 기반 감정 분석은 텍스트 내에서 감정과 해당 감정이 특정 속성, 예를 들어 제품의 특성이나 서비스의 특징에 어떻게 연결되는지를 분석하는 태스크이다. 본 논문에서는 속성 기반 감정 분석 데이터를 사용한 다중 작업-토큰 레이블링 문제에 프롬프트 튜닝 기법을 적용하기 위한 포괄적인 방법론을 소개한다. 이러한 방법론에는 토큰 레이블링 문제를 시퀀스 레이블링 문제로 일반화하기 위한 감정 표현 영역 검출 파이프라인이 포함된다. 또한 분리된 시퀀스들을 속성과 감정에 대해 분류 하기 위한 템플릿을 선정하고, 데이터셋 특성에 맞는 레이블 워드를 확장하는 방법을 제안함으써 모델의 성능을 최적화한다. 최종적으로, 퓨샷 세팅에서의 속성 기반 감정 분석 태스크에 대한 몇 가지 실험 결과와 분석을 제공한다. 구축된 데이터와 베이스라인 모델은 AIHUB(www.aihub.or.kr)에 공개되어 있다.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.40 no.2
• /
• pp.91-108
• /
• 2022

In most cases, optical images have been used as training data of DL (Deep Learning) models for object detection, recognition, identification, classification, semantic segmentation, and instance segmentation. However, properties of 3D objects in the real-world could not be fully explored with 2D images. One of the major sources of the 3D geospatial information is DSM (Digital Surface Model). In this matter, characteristic information derived from DSM would be effective to analyze 3D terrain features. Especially, man-made objects such as buildings having geometrically unique shape could be described by geometric elements that are obtained from 3D geospatial data. The background and motivation of this paper were drawn from concept of the intrinsic image that is involved in high-level visual information processing. This paper aims to extract buildings after classifying terrain features by training DL model with DSM-derived information including slope, aspect, and SRI (Shaded Relief Image). The experiments were carried out using DSM and label dataset provided by ISPRS (International Society for Photogrammetry and Remote Sensing) for CNN-based SegNet model. In particular, experiments focus on combining multi-source information to improve training performance and synergistic effect of the DL model. The results demonstrate that buildings were effectively classified and extracted by the proposed approach.