• Korean Journal of Ecology and Environment
• /
• v.40 no.1
• /
• pp.103-109
• /
• 2007

To investigate the effects of artificial vegetation island (AVI) on fish distribution, we compared fish fauna from artificial vegetation island (AVI) area, which installed in 2000, natural vegetation area (NVA) and vegetation-free area (VFA) at Kyungan Stream area of Lake Paldang from Jul. to Nov., 2005. Results showed that 11 families 23 genera 24 fish species were distributed in the AVI and NVA. Squalidus japonicus coreanus, a small-size fish which generally lives at the downstream, dominated absolutely in the individual numbers. However, only 6 families 11 genera 12 species of fishes caught at the VFA, and dominant fishes were Hemibarbus labeo and Erythroculter erythropterus, a medium to large-size migratory fishes which live in mid-depth of water column. The dominance index was high at the AVI (0.778) and NVA (0.868), whereas the diversity index and evenness index were high at the VFA. Fish distribution at AVI was similar to that of the NVA in numbers of species, indicating that the AVI could playa role as spawning and inhabitation zone to a variety of fishes. We believe that AVI may be used for a restoration of the damaged and disturbed littoral ecosystem.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.8
• /
• pp.371-380
• /
• 2023

Relation extraction is to extract relationships between named entities from text. Traditionally, relation extraction methods only extract relations between predetermined subject and object entities. However, in end-to-end relation extraction, all possible relations must be extracted by considering the positions of the subject and object for each pair of entities, and so this method uses time and resources inefficiently. To alleviate this problem, this paper proposes a method that sets directions based on the positions of the subject and object, and extracts relations according to the directions. The proposed method utilizes existing relation extraction data to generate direction labels indicating the direction in which the subject points to the object in the sentence, adds entity position tokens and entity type to sentences to predict the directions using a pre-trained language model (KLUE-RoBERTa-base, RoBERTa-base), and generates representations of subject and object entities through probabilistic crossover operation. Then, we make use of these representations to extract relations. Experimental results show that the proposed model performs about 3 ~ 4%p better than a method for predicting integrated labels. In addition, when learning Korean and English data using the proposed model, the performance was 1.7%p higher in English than in Korean due to the number of data and language disorder and the values of the parameters that produce the best performance were different. By excluding the number of directional cases, the proposed model can reduce the waste of resources in end-to-end relation extraction.

• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.8
• /
• pp.343-348
• /
• 2019

In recent years, extractive summarization systems based on end-to-end deep learning models have become popular. These systems do not require human-crafted features and adopt data-driven approaches. However, previous related studies have shown that linguistic analysis features such as part-of-speeches, named entities and word's frequencies are useful for extracting important sentences from a document to generate a summary. In this paper, we propose an extractive summarization system based on deep neural networks using conventional linguistic analysis features. In order to prove the usefulness of the linguistic analysis features, we compare the models with and without those features. The experimental results show that the model with the linguistic analysis features improves the Rouge-2 F1 score by 0.5 points compared to the model without those features.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.228-231
• /
• 2022

Most CCTVs operated by public institutions for crime prevention and parking enforcement are located on roads. The angle of these CCTV's view is often changed for various reasons, such as bolt loosening by vibration or shocking by vehicles and workers, etc. In order to effectively provide AI services based on the collected images, the service target area(ROI, Region Of Interest) must be provided without interruption within the image. This is also related to the viewpoint of effective operation of computing power for image analysis. This study explains how to maximize the application of artificial intelligence technology by setting the ROI based on the marker on the road, setting the image analysis to be possible only within the area, and studying the process of finding the ROI.

• Korean Journal of Ichthyology
• /
• v.22 no.4
• /
• pp.225-229
• /
• 2010

A intergeneric hybrid between Rhodeus uyekii and Acheilognathus signifer was collected in the Jojongcheon Bukhan River. The hybrid showed intermediate characteristics of two parental types in some key characters, such as color pattern of body, pigmentation of dorsal, anal, and caudal fins, and body spot and stripe. In addition, the hybrid had a fairly large number of lateral line scales, while it lacked a barbel, which is known as a key intergeneric character. The probable occurrence of a natural hybrid is supported by a viable $F_1$ hybrid produced with the parental species.

• Korean journal of applied entomology
• /
• v.42 no.1
• /
• pp.21-27
• /
• 2003

This study was carried out to investigate the changes of insects diversity and host plants from 1998 to 2001 after the construction of an insect park in Suwon in Korea. After the construction in 1997 the insect species and populations have been increased yearly to date. A total of 343 species out of 138 families of 11 orders was surveyed at the park from April to November in 2001. The number of species increased from April to July and showed a peak in June. Coleoptera was a dominant order, and Dolichus halensis (Schaller) of Coleoptera, Artogeia rapae (Linne) of Lepidoptera, and Liorhyssus hyaalinus (Fabricius) of Hemiptera were dominant species.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2020.06a
• /
• pp.208-208
• /
• 2020

지구온난화와 하천환경의 변화로 수질 오염이 심각해지고 녹조 현상 등의 피해가 증가하고 있다. 특히, 기후변화로 인해 온도와 강우량의 변동성이 동시에 증가하고 있어 하천의 수환경 관리측면에서 어려움이 증가하고 있다. 최근 하천 개발 사업으로 인한 인공 구조물 축조로 하천의 오염도 변화는 중요한 논점으로 대두되었으며, 그에 따라 정확한 수질 전망이 요구되고 있다. 녹조평가에 있어 주요 대리변수(proxy variable)로 chlorophyll-a(Chl-a)가 사용되고 있지만, Chl-a는 규조류와 남조류(cyanobacteria) 모두에서 발견되는 지표로서, 녹조의 유해성을 Chl-a 수질 지표만을 사용하여 판단하기에는 한계가 있다. Chl-a뿐만 아니라 수질에 대한 유량, 온도, 영양염류 등의 영향 또한 기존 연구에서 밝혀진 바 있다. 하지만 기존의 물리기반의 결정론적모형은 수질의 추계학적(stochastic) 특성을 반영하는데 제한적이며, 다양한 수문기상학적 조건을 고려한 시나리오 기반의 분석을 수행하는데 한계가 있다. 따라서 본 연구에서는 특정 지점의 보 건설 이후 수문기상 자료를 이용하여 유해 남조류 개체수와 관계있는 수문기상학적 요인을 평가하고 최종적으로 Bayesian Poisson Regression 기반의 중·장기 녹조 예측 모형을 개발하였으며, 해설결과에 대한 불확실성 정보도 제공할 수 있도록 하였다.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.4
• /
• pp.181-188
• /
• 2024

Traditional profanity detection methods have limitations in identifying intentionally altered profanities. This paper introduces a new method based on Named Entity Recognition, a subfield of Natural Language Processing. We developed a profanity detection technique using sequence labeling, for which we constructed a dataset by labeling some profanities in Korean malicious comments and conducted experiments. Additionally, to enhance the model's performance, we augmented the dataset by labeling parts of a Korean hate speech dataset using one of the large language models, ChatGPT, and conducted training. During this process, we confirmed that filtering the dataset created by the large language model by humans alone could improve performance. This suggests that human oversight is still necessary in the dataset augmentation process.

• Korean Journal of Environmental Agriculture
• /
• v.16 no.2
• /
• pp.175-180
• /
• 1997

This experiment was conducted to find out the effects of lime materials application on reducing injury of simulated acid rain(SAR) in soybean grown in pot contained with sandy loam. Six treatments including control, slaked lime(SL), 1% and 2% lime water(LW) and composite treatments with SL+LW were applied. Slaked lime was applied to soil in pot before planting, and lime water was applied to leaves a day prior to the spray of SAR(pH 2.7) and normal rain(pH 6.0), and these were sprayed at 2-day intervals. Growth, yield and yield components, foliar injury rate, chrolophyll content and photosynthetic activity in leaves, content of mineral nutrients in plant and soil chemical properties were analyzed and investigated. These results obtained are summarized as follows : Seed yield of all lime treatment was reduced by SAR compared with control. But seed yield of all lime treatment was increased with treatment of lime material in soil and on leaves. After 15 and 45 times spray of SAR, all lime treatments were effective in injury reducing visible injury of leaves compared with none treatment. Chlorophyll content in leaves was highest in plants treated with slaked lime+ 1% lime water and photosynthetic activity was highest with treatment of slaked lime. Concentration of total nitrogen, phosphate, and sulfur in soybean plant were increased by the spray of SAR. Concentration of total nitrogen, potassium and calcium in soybean plant were increased with treatment of slaked lime into soil. By treatments of SAR, soil pH was decreased, and total nitrogen and sulfur concentration in soil were increased. However, available phosphate and exchangeable cations in soil such as calcium, magnesium and potassium were reduced. Soil pH, calcium and silicate concentration were increased with treatment of slaked lime into soil.

• Korean journal of applied entomology
• /
• v.57 no.4
• /
• pp.287-295
• /
• 2018

A meridic artificial diet, including whole milk powder, wheat bran, maize leaf powder, and sucrose as the main nutrients, was tested for rearing Locusta migratoria (Orthoptera: Acrididae). When locusts were supplied with only the artificial diet over their entire life cycle, a second generation was not produced. The same result was observed when the diet was supplied daily and fresh maize leaves were supplied every other day. However, when the diet and fresh maize leaves were supplied alternately every other day, four generations of L. migratoria were produced. Fecundity in adults reared with the alternating diet was higher than that in adults supplied with both the diet and maize leaves daily. These results indicate that this artificial diet could be used as a supplementary food for rearing of L. migratoria.