• Journal of the Korea Society for Simulation
• /
• v.19 no.1
• /
• pp.103-111
• /
• 2010

Syntactic analysis is an important step in natural language processing. However, we cannot use the syntactic analyzer in Korean for low performance and without robustness. We propose new robust, high speed and high performance Korean syntactic analyzer using CRFs. We treat a parsing problem as a labeling problem. We use a cascaded chunking for Korean parsing. We label syntactic information to each Eojeol at each step using CRFs. CRFs use part-of-speech tag and Eojeol syntactic tag features. Our experimental results using 10-fold cross validation show significant improvement in the robustness, speed and performance of long Korea sentences.

• Journal of Korean Society of Rural Planning
• /
• v.28 no.4
• /
• pp.105-117
• /
• 2022

This study tested SVM(support vector machine), RF(random forest), and ANN(artificial neural network) machine-learning models that can predict net irrigation water requirements in paddy fields. For the Jeonju and Jeongeup meteorological stations, the net irrigation water requirement was calculated using K-HAS from 1981 to 2021 and set as the label. For each algorithm, twelve models were constructed based on cumulative precipitation, precipitation, crop evapotranspiration, and month. Compared to the CE model, the R² of the CEP model was higher, and MAE, RMSE, and MSE were lower. Comprehensively considering learning performance and learning time, it is judged that the RF algorithm has the best usability and predictive power of five-days is better than three-days. The results of this study are expected to provide the scientific information necessary for the decision-making of on-site water managers is expected to be possible through the connection with weather forecast data. In the future, if the actual amount of irrigation and supply are measured, it is necessary to develop a learning model that reflects this.

• Journal of Korea Society of Industrial Information Systems
• /
• v.19 no.2
• /
• pp.85-91
• /
• 2014

The objective of the research is to automatically recognize railway objects from MLS data in which 9 key objects including terrain, track, bed, vegetation, platform, barrier, posts, attachments, powerlines are targeted. The proposed method can be divided into two main sub-steps. First, multi-scale contextual features are extracted to take the advantage of characterizing objects of interest from different geometric levels such as point, line, volumetric and vertical profile. Second, by considering contextual interactions amongst object labels, a contextual classifier is utilized to make a prediction with local coherence. In here, the Conditional Random Field (CRF) is used to incorporate the object context. By maximizing the object label agreement in the local neighborhood, CRF model could compensate the local inconsistency prediction resulting from other local classifiers. The performance of proposed method was evaluated based on the analysis of commission and omission error and shows promising results for the practical use.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.27 no.3A
• /
• pp.240-248
• /
• 2002

This paper presents a new motion-based segmentation algorithm of moving objects in image sequences. The procedure toward complete segmentation consists of two steps: pixel labeling and motion segmentation. In the first step, we assign a label to each pixel according to magnitude of velocity vector. And velocity vector is generated by optical flow. And, in the second step, we have modeled motion field as a markov random field for noise canceling and make a segmentation of motion through energy minimization. We have demonstrated the efficiency of the presented method through experimental results.

• Journal of Intelligence and Information Systems
• /
• v.15 no.4
• /
• pp.23-36
• /
• 2009

Network intrusion detection have been continuously improved by using data mining techniques. There are two kinds of methods in intrusion detection using data mining-supervised learning with class label and unsupervised learning without class label. In this paper we have studied the way of improving network intrusion detection accuracy by using LBG clustering algorithm which is one of unsupervised learning methods. The K-means method, that starts with random initial centroids and performs clustering based on the Euclidean distance, is vulnerable to noisy data and outliers. The nonuniform binary split algorithm uses binary decomposition without assigning initial values, and it is relatively fast. In this paper we applied the EM(Expectation Maximization) based LBG algorithm that incorporates the strength of two algorithms to intrusion detection. The experimental results using the KDD cup dataset showed that the accuracy of detection can be improved by using the LBG algorithm.

• Annual Conference on Human and Language Technology
• /
• 2018.10a
• /
• pp.172-175
• /
• 2018

환자의 병력을 서술하는 임상문서에서 임상 개체명들은 그들 사이에 개체명이 아닌 단어들이 위치하기 때문에 거리상으로 서로 떨어져 있고, 임상 개체명인식에 많이 사용되는 조건부무작위장(conditional random fields; CRF) 모델은 Markov 속성을 따르기 때문에 서로 떨어져 있는 개체명 라벨 간의 전이 정보는 모델의 계산에서 무시된다. 본 논문에서는 라벨링 모델에 서로 떨어진 개체명 간 전이 관계를 표현하기 위하여 CRF 모델의 구조를 변경하는 방법론을 소개한다. 제안된 CRF 모델 디자인에서는 모델의 계산효율성을 빠르게 유지하기 위하여 Markov 속성을 유지하는 1차 모델 구조를 유지한다. 모델은 선행하는 개체명의 라벨 정보를 후행하는 개체명 엔터티에게 전달하기 위하여 선행 개체명의 라벨을 뒤 따르는 비개체명 라벨에 전이시키고 이를 통해 후행하는 개체명은 선행하는 개체명의 라벨 정보를 알 수 있게 된다. 라벨의 고차 전이 정보를 전달함에도 모델의 구조는 1차 전이 구조를 유지함으로 n차 구조의 모델보다 빠른 계산 속도를 유지할 수 있게 된다. 모델의 성능 평가를 위하여 서울대학교병원 류머티즘내과에서 퇴원한 환자들의 퇴원요약지에 병력과 관련된 엔터티가 태깅된 평가 데이터와 i2b2 2012/VA 임상자연어처리 shared task의 임상 개체명 추출 데이터를 사용하였고 기본 CRF 모델들(1차, 2차)과 비교하였다. 피처 조합에 따라 모델들을 평가한 결과 제안한 모델이 거의 모든 경우에서 기본 모델들에 비하여 F1-score의 성능을 향상시킴을 관찰할 수 있었다.

• Journal of the Korean Society of Food Science and Nutrition
• /
• v.27 no.3
• /
• pp.543-552
• /
• 1998

A sruvey was conducted to investigate the consumer perception of farm products and processed foods, and to figure out the future direction of food supply system to satisfy the consumer need. From the citizens in Taegu area, 532 housewives were selected as sample subjects by stratified random sam-pling procedure. The main criteria of consumers for purchasing farm products was quality and the main reason for purchasing imported products was cheap price(48.9%). Most of consumers(87%) thought that food safety of farm products was not belong to safe level. Consumers(79.7%) perceived that the labeling system for the place of origin and for the quality are necessary, but they did not have confidence in the current label. Nearly all the subjects(93.6%) were concerned about the hazardness of residual chemicals of imported products, desired the rigorous inspection system for imported products. Consumers in Taegu area had confidence in processed foods in the following order; farmerbrand-product(0.9%), government-authorized farm product(30.0%) and agricultural cooperative association product(26.4%). However, only 73.6% of the consumers had the experience to purchase farmers' processed foods. As a conclusion, it appeared that nutrition education for consumers on food-decision making is strongly required for the substantial segment of population who are still ignorant of safety of imported product and food distribution system.

• ETRI Journal
• /
• v.45 no.5
• /
• pp.822-835
• /
• 2023

Recent semantic segmentation frameworks usually combine low-level and high-level context information to achieve improved performance. In addition, postlevel context information is also considered. In this study, we present a Context ReFinement Network (CRFNet) and its training method to improve the semantic predictions of segmentation models of the encoder-decoder structure. Our study is based on postprocessing, which directly considers the relationship between spatially neighboring pixels of a label map, such as Markov and conditional random fields. CRFNet comprises two modules: a refiner and a combiner that, respectively, refine the context information from the output features of the conventional semantic segmentation network model and combine the refined features with the intermediate features from the decoding process of the segmentation model to produce the final output. To train CRFNet to refine the semantic predictions more accurately, we proposed a sequential training scheme. Using various backbone networks (ENet, ERFNet, and HyperSeg), we extensively evaluated our model on three large-scale, real-world datasets to demonstrate the effectiveness of our approach.

• The KIPS Transactions:PartC
• /
• v.9C no.1
• /
• pp.123-134
• /
• 2002

The requirement for QoS (Quality of Service) has become an important Issue as real-time or high bandwidth services are increasing, such as Internet Telephony, Internet broadcasting, and multimedia service etc. In order to guarantee the QoS of Internet application services, several approaches are being sought including IntServ (Integrated Service) DiffServ(Differentiated Srvices), and MPLS(Multi-Protocol Label Switching). In this paper, we describe the performance analysis of QoS guarantee mechanism using the DiffServ. To analyze how the DiffServ performance was affected by diverse input traffic models and the weight value in WFQ(Weighted Fair Queueing), we simulated and performed performance evaluation under a random, bursty, and self-similar input traffic models and for diverse input parameters. leased on the results of performance analysis, it was confirmed that significant difference exist in packet delay and loss depending on the input traffic models used. However, it was revealed that QoS guarantee is possible to the EF (expedited Forwarding) class and the service separation between RF and BE (Best Effort) classes may also be achieved. Next, we discussed the performance synthesis problem. (i. e. derived the conservation laws for a DiffServ networks, and analysed the performance variation and dynamic behavior based on the resource allocation (i.e., weight value) in WFQ.

• Korean journal of food and cookery science
• /
• v.30 no.3
• /
• pp.325-332
• /
• 2014

The purpose of this research is to investigate and analyze food allergy labelling for the arrangement of improvement plans. Survey was done as a quantitative research targeting food industry employees with 399 random workers in Seoul and Gyonggi area. The data was analyzed using SPSS windows (ver. 12.0) for frequency analysis, t-test and factor analysis. The importance and performance of the food allergen labelling were divided by 15 items. Only 43.1% of the workers understood the operation allergic food labels. The first improvement on allergic food labels was "using boldface for food allergen labes". The importance of all of these factors was significantly higher than performance. The selection attributes with relatively low the performance but high importance(2 quadrant) were "consumer education for allergic food labels" and "training of professional counselors on food allergy". Therefore, the factors to be improved through the IPA were consumer education and training of professional counselors. With this research and extended efforts for revision of laws, reliability of food industry and accuracy of food labelling would improve, thereby boosting the productive commercial activities in labelling code.