• The Journal of the Korea institute of electronic communication sciences
• /
• v.13 no.4
• /
• pp.845-850
• /
• 2018

In this paper, we propose a method to estimate the number of biofouling attached to the surface of marine structures. This method estimates the number of biofouling by calculating the region maxima using images taken in underwater. To do this, we analyze the correlation between the region maxima and the number of biofouling. The analysis showed that there is a significant correlation between the number of region maxima and the number of biofouling. By using the results of this analysis, the experiments were conducted on images taken in the underwater. Experimental results show that the higher the region maxima of the image, is greater than the number of biofouling in the image. The proposed method can be used as an important technology in computer vision for underwater images.

• Korean Journal of Environmental Biology
• /
• v.35 no.4
• /
• pp.468-475
• /
• 2017

This study is for the consideration of the existence tendency of Kudoa septempunctata in olive flounder. In general, muscle has shown a strong PCR positive reaction in spores containing tissues rather than non-containing tissues. However, blood PCR results showed opposed tendency. In various organs of the tested fish containing spores in muscle tissue, heart had shown positive reaction along with muscle at PCR analysis. Muscle fiber necrosis was observed at the histological observation, and this degeneration was common in both samples. The one sample was the PCR positive muscle containing spore and the other was the PCR positive muscle non-containing spore. Both of muscle tissues indicated a positive reaction at ISH (in-situ hybridization) against K. septempunctata.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.19 no.4
• /
• pp.701-708
• /
• 2024

The advent of transformer architectures in deep learning has been a major breakthrough in natural language processing research. Object name recognition is a branch of natural language processing and is an important research area for tasks such as information retrieval. It is also important in the biomedical field, but the lack of Korean biomedical corpora for training has limited the development of Korean clinical research using AI. In this study, we built a new biomedical corpus for Korean biomedical entity name recognition and selected language models pre-trained on a large Korean corpus for transfer learning. We compared the name recognition performance of the selected language models by F1-score and the recognition rate by tag, and analyzed the errors. In terms of recognition performance, KlueRoBERTa showed relatively good performance. The error analysis of the tagging process shows that the recognition performance of Disease is excellent, but Body and Treatment are relatively low. This is due to over-segmentation and under-segmentation that fails to properly categorize entity names based on context, and it will be necessary to build a more precise morphological analyzer and a rich lexicon to compensate for the incorrect tagging.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.36S no.10
• /
• pp.103-112
• /
• 1999

Genetic algorithm, which uses principles of natural selection and population genetics, is an efficient method to find out an optimal solution. In conventional genetic algorithms, however, the size of gene pool needs to be increased to insure a convergency. Therefore, many memory spaces and much computation time were needed. Also, since child chromosomes were generated by chromosome crossover and gene mutation, the algorithms have a complex structure. Thus, in this paper, a compact stereo matching algorithm using a population-based incremental learning based on probability vector is proposed to reduce these problems. The PBIL method is modified for matching environment. Since th proposed algorithm uses a probability vector and eliminates gene pool, chromosome crossover, and gene mutation, the matching algorithm is simple and the computation load is considerably reduced. Even though the characteristics of images are changed, stable outputs are obtained without the modification of the matching algorithm.

• Smart Media Journal
• /
• v.12 no.4
• /
• pp.27-40
• /
• 2023

Many researchers have investigated ways to enhance recommender systems by integrating heterogeneous data to address the data sparsity problem. However, only a few studies have successfully integrated heterogeneous data using knowledge graph. Additionally, most of the knowledge graphs built in these studies only incorporate explicit relationships between entities and lack additional information. Therefore, we propose a method for expanding knowledge graphs by using deep learning to model latent relationships between heterogeneous data from multiple knowledge bases. Our extended knowledge graph enhances the quality of entity features and ultimately increases the accuracy of predicted user preferences. Experiments using real music data demonstrate that the expanded knowledge graph leads to an increase in recommendation accuracy when compared to the original knowledge graph.

• Journal of Korean Society of Forest Science
• /
• v.100 no.4
• /
• pp.558-564
• /
• 2011

This study was conducted to evaluate the effects of early revegetation by analyzing the characteristics of germination and growth of Lespedeza cyrtobotrya using boring technique in rock slopes. After making up a growing basis of approximately 20 cm depth and 10 cm diameter by using a boring machine, the surface of rock slopes was planted with vegetation-plant. The number of germinating populations by soil media was 23 in H.s, 22 in T.s, 12 in M.s, and 1 in M.g.s. The germination rate (%) by soil media was 19.2% in H.s, 18.3% in T.s, 10.0% in M.s and 0.8% in M.g.s. In monthly changes of growth rate, the aspect was northwest direction, the soil media was M.s, and the treatment was microorganism plot. The main factors affecting survivorship and growth of population were soil media and treatment plot. The interaction between each factor had a good effects in bearing ${\times}$ soil media, bearing ${\times}$ treatment plot, soil media ${\times}$ treatment plot. but, it is recommended that the mulching of vegetation plant is highly needed to help the germination of seed and growth of vegetation because of loss of seed and soil media occurred due to rainfall. Therefore, The result suggests that the revegetation technique using boring in rock slope was very efficient in respect of the early revegetation and the landscape.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.422-424
• /
• 2022

We propose a novel data-driven mutation strategy for parent individuals selection, namely tensor-based DE with parapatric and cross-generation (TPCDE).

• Annual Conference on Human and Language Technology
• /
• 2017.10a
• /
• pp.301-304
• /
• 2017

시간정보추출 연구는 자연어 문장으로부터 대화의 문맥과 상황을 파악하고 사용자의 의도에 적합한 서비스를 제공하는데 중요한 역할을 하지만, 한국어의 고유한 언어적 특성으로 인해 한국어 텍스트에서는 개체간의 시간관계를 정확하게 인식하기 어려운 경향이 있다. 특히, 시간표현이나 사건에 대한 상대적인 시간관계는 시간 문맥을 체계적으로 파악하기 위해 중요한 개념이다. 본 논문에서는 한국어 자연어 문장에서 상대적인 시간표현과 사건 간의 관계를 추출하기 위한 LSTM(long short-term memory) 기반의 상대시간관계 추출 모델을 제안한다. 시간정보추출 연구에는 TIMEX3, EVENT, TLINK 추출의 세 가지 과정이 포함되지만, 본 논문에서는 특정 문장에 대해서 이미 추출된 TIMEX3 및 EVENT 개체를 제공하고 상대시간관계 TLINK를 추출하는 것만을 목표로 한다. 또한, 사람이 직접 태깅한 한국어 시간정보 주석 말뭉치를 대상으로 LSTM 기반 제안모델들의 상대적 시간관계 추출 성능을 비교한다.

• 한국어정보학회:학술대회논문집
• /
• 2017.10a
• /
• pp.301-304
• /
• 2017

시간정보추출 연구는 자연어 문장으로부터 대화의 문맥과 상황을 파악하고 사용자의 의도에 적합한 서비스를 제공하는데 중요한 역할을 하지만, 한국어의 고유한 언어적 특성으로 인해 한국어 텍스트에서는 개체간의 시간관계를 정확하게 인식하기 어려운 경향이 있다. 특히, 시간표현이나 사건에 대한 상대적인 시간관계는 시간 문맥을 체계적으로 파악하기 위해 중요한 개념이다. 본 논문에서는 한국어 자연어 문장에서 상대적인 시간표현과 사건 간의 관계를 추출하기 위한 LSTM(long short-term memory) 기반의 상대시간관계 추출 모델을 제안한다. 시간정보추출 연구에는 TIMEX3, EVENT, TLINK 추출의 세 가지 과정이 포함되지만, 본 논문에서는 특정 문장에 대해서 이미 추출된 TIMEX3 및 EVENT 개체를 제공하고 상대시간관계 TLINK를 추출하는 것만을 목표로 한다. 또한, 사람이 직접 태깅한 한국어 시간정보 주석 말뭉치를 대상으로 LSTM 기반 제안모델들의 상대적 시간관계 추출 성능을 비교한다.

• Journal of Convergence for Information Technology
• /
• v.10 no.10
• /
• pp.32-39
• /
• 2020

In the large-scale infrastructure of cloud environment, illegal access rights are frequently caused by sharing applications and devices, so in order to actively respond to such attacks, a strengthened access control system is required to prepare for each situation. We proposed an entity attribute-based access control(EABAC) model based on security level and relation concept. This model has enhanced access control characteristics that give integrity and confidentiality to subjects and objects, and can provide different services to the same role. It has flexibility in authority management by assigning roles and rights to contexts, which are relations and context related to services. In addition, we have shown application cases of this model in multi service environment such as university.