• Journal of Mushroom
• /
• v.9 no.3
• /
• pp.132-134
• /
• 2011

Two Inonotus species newly found in Japan were described. I. formosanus T.T. Chang & W.N. Chou was identified with the following characters; thin basidocarps with hispid when young and later the erect hyphae agglutinate to scrupose tuft, pore surface light yellow to rusty brown later, absence of setal hyhpae, ventricose hymenial setae, and small ellipsoid, hyaline to yellowish basidiospores. I. nodulosus (Fr.) P. Karst. was identified with the following characters; basidocarps nodulose, wart-like shape, scrupose to warted by agglutinated hayphae, margin up to 5 mm, pore surface cinnamon to rusty brown when dry with a whitish or silvery shine, absence of setal hyphae, acute straight hymenical setae, ellipsoid to subglobose basidiospores, which are weakly dextrinoid in Melzer's reagent.

• Animal Systematics, Evolution and Diversity
• /
• v.35 no.3
• /
• pp.143-150
• /
• 2019

The bamboo katydid, Palaeoagraecia lutea (Matsumura et Shiraki, 1908) is newly reported in South Korea. Previously, the species was only known in Japan, but currently its occurrence is confirmed in the far southern locality of Hampyeong, Jeollanam-do province of Korean Peninsula. This katydid was collected using a light trap and sound tracing in the bamboo forest. It is regarded as a rare stenotopic species. The features of male Palaeoagraecia lutea are illustrated and discussed in terms of song characteristics, and a key is provided for the genus Palaeoagraecia. A new synonym is proposed: P. philippina (Karny, 1926)=P. globicerata (Vickery et Kevan, 1999) syn. nov.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.01a
• /
• pp.27-30
• /
• 2021

경제 성장과 함께 자동차의 수요가 늘어남에 따라 교통사고 발생 빈도는 꾸준히 증가하고 있다. 이에, 본 연구에서는 교통사고를 야기하는 도로 및 기상환경과 같은 조건을 활용하여 기계학습 모델을 통해 서울시 교통사고 사상자 수를 예측하는 모형을 찾고자 한다. 활용한 데이터는 도로교통 공단에서 제공하는 교통사고 사상자 수 정보를 포함하는 데이터로 2015년부터 2018년도까지 데이터를 학습에 사용하였고 2019년도 데이터를 테스트 평가에 사용하였다. 실증연구를 통해 트리 기반의 모델 별 성능을 비교하였으며 본 연구에 대한 결과는 사고 발생 시 우선순위에 의한 구조활동이 가능하게 함과 도로상황 및 기상을 고려한 안전운전 가이드 지식으로 활용될 수 있다.

• Computers and Concrete
• /
• v.33 no.4
• /
• pp.409-423
• /
• 2024

Using an extensive database, a sensitivity analysis across fifteen machine learning (ML) classifiers was conducted to evaluate the impact of various data manipulation techniques, evaluation metrics, and explainability tools. The results of this sensitivity analysis reveal that the examined models can achieve an accuracy ranging from 72-93% in predicting the fire-induced spalling of concrete and denote the light gradient boosting machine, extreme gradient boosting, and random forest algorithms as the best-performing models. Among such models, the six key factors influencing spalling were maximum exposure temperature, heating rate, compressive strength of concrete, moisture content, silica fume content, and the quantity of polypropylene fiber. Our analysis also documents some conflicting results observed with the deep learning model. As such, this study highlights the necessity of selecting suitable models and carefully evaluating the presence of possible outcome biases.

• Journal of Korean Society of Forest Science
• /
• v.111 no.3
• /
• pp.405-417
• /
• 2022

The purpose of this study was to describe the photosynthetic features of Prunus maximowiczii and Prunus serrulate Lindl. var. pubescens (Makino) Nakai in response to drought stress. Specifically, we studied the effects of drought on photosynthetic ability and photosystem II activity. Drought stress (DS) was induced by cutting the water supply for 30 days. DS decreased the moisture contents in the soil, and between the 10th and 12th days of DS, both species had 10% or less of x., After the 15th day of DS, it was less than 5%, which is a condition for disease to start. We observed a remarkable decrease of maximum photosynthesis rate starting from 10th day of DS; the light compensation point was also remarkable. Dark respiration and net apparent quantum yield decreased significantly on the 15th day of DS, and then increased on the 20th day. In addition, the stomatal transpiration rate of P. maximowiczii decreased significantly on the15th day of DS, and then increased on the 20th day. Water use efficiency increased on the 15th day of DS, and then decreased on the 20th day. The stomatal transpiration rate of P. serrulate decreased significantly on the 20th day of DS, and then increased afterward, while its water use efficiency increased on the 20th day of DS, and then decreased afterward. These results indicate that the closure of stoma prevented water loss, resulting in a temporary increase of water use efficiency. Chlorophyll fluorescence analysis detected remarkable decreases in the functional index (PI_ABS) and energy transfer efficiency in P. maximowiczii after the 15th day of DS. Meanwhile, photosystem II activity decreased in P. serrulate after 20 days of DS. In addition, Ts-Ta, PI_ABS, DI_O/RC, ET_O/RC followed similar trends as those of the soil moisture content and photosynthetic properties, indicating that they can be used as useful variables in predicting DS in trees.

• Korean Journal of Environmental Biology
• /
• v.27 no.2
• /
• pp.191-197
• /
• 2009

In order to characterize the ecological traits of Q. mongolica, we treated the seedlings of this species with three environmental factors, light, moisture and nutrient gradients from March to October 2007, and measured morphological and ecological 17 characters. Lastly calculated ecological niche breadth and niche overlap between Q. mongolica-Q. acutissima and Q. mongolica-Q. variabilis, and analysed them with a special reference to ecological distribution pattern and their competition relationship in Korea. The ecological niche breadth of Q. mongolica showed the lowest in nutrient treatment, but the highest in soil moisture treatment. The ecological niche value under light was intermediate. On comparison of the ecological niche breadth of three oak species, Q. mongolica showed the highest in light environment, which might be a reason for the dominant distribution in the forest plant community, Korea. The ecological niche overlap of Q. mongolica-Q. acutissima and Q. mongolica-Q. varabilis was the widest in moisture treatment, but the narrowest in nutrient treatment and the intermediate in light one. These results means that these three oak species be most competitive in moisture environment than light or nutrient one, and that there are least differentiated among oak species for soil moisture condition. Cluster and PCA ordination showed that Q. mongolica and Q. acutissima were more closely arranged than Q. mongolica and Q. variabilis. From these results, it can be explained that Q. mongolica have more similar ecological niche with Q. acutissima than with Q. variabilis, consequently competition between Q. mongolica and Q. acutissima is intensive than Q. mongolica and Q. variabilis for environment condition, especially in soil moisture.

• The Journal of Society for e-Business Studies
• /
• v.26 no.3
• /
• pp.97-117
• /
• 2021

Predicting term deposit subscriptions is one of representative financial marketing in banks, and banks can build a prediction model using various customer information. In order to improve the classification accuracy for term deposit subscriptions, many studies have been conducted based on machine learning techniques. However, even if these models can achieve satisfactory performance, utilizing them is not an easy task in the industry when their decision-making process is not adequately explained. To address this issue, this paper proposes an explainable scheme for term deposit subscription forecasting. For this, we first construct several classification models using decision tree-based ensemble learning methods, which yield excellent performance in tabular data, such as random forest, gradient boosting machine (GBM), extreme gradient boosting (XGB), and light gradient boosting machine (LightGBM). We then analyze their classification performance in depth through 10-fold cross-validation. After that, we provide the rationale for interpreting the influence of customer information and the decision-making process by applying Shapley additive explanation (SHAP), an explainable artificial intelligence technique, to the best classification model. To verify the practicality and validity of our scheme, experiments were conducted with the bank marketing dataset provided by Kaggle; we applied the SHAP to the GBM and LightGBM models, respectively, according to different dataset configurations and then performed their analysis and visualization for explainable term deposit subscriptions.

• Tuberculosis and Respiratory Diseases
• /
• v.86 no.3
• /
• pp.203-215
• /
• 2023

Background: Surgical resection is the standard treatment for early-stage lung cancer. Since postoperative lung function is related to mortality, predicted postoperative lung function is used to determine the treatment modality. The aim of this study was to evaluate the predictive performance of linear regression and machine learning models. Methods: We extracted data from the Clinical Data Warehouse and developed three sets: set I, the linear regression model; set II, machine learning models omitting the missing data: and set III, machine learning models imputing the missing data. Six machine learning models, the least absolute shrinkage and selection operator (LASSO), Ridge regression, ElasticNet, Random Forest, eXtreme gradient boosting (XGBoost), and the light gradient boosting machine (LightGBM) were implemented. The forced expiratory volume in 1 second measured 6 months after surgery was defined as the outcome. Five-fold cross-validation was performed for hyperparameter tuning of the machine learning models. The dataset was split into training and test datasets at a 70:30 ratio. Implementation was done after dataset splitting in set III. Predictive performance was evaluated by R² and mean squared error (MSE) in the three sets. Results: A total of 1,487 patients were included in sets I and III and 896 patients were included in set II. In set I, the R² value was 0.27 and in set II, LightGBM was the best model with the highest R² value of 0.5 and the lowest MSE of 154.95. In set III, LightGBM was the best model with the highest R² value of 0.56 and the lowest MSE of 174.07. Conclusion: The LightGBM model showed the best performance in predicting postoperative lung function.

• Korean Journal of Plant Resources
• /
• v.37 no.2
• /
• pp.203-213
• /
• 2024

In this study, we investigated the growth and physiological responses of Iris laevigata Fisch. to shading treatments in order to suggest optimal light conditions for ex-situ conservation of the northern lineage plants. For this purpose, a control plant receiving full sunlight and different shading treatments (50%, 75%, 95%) were installed, and leaf mass per area, chlorophyll content and fluorescence response, and photosynthetic characteristics were investigated. I. laevigata developed leaves with higher photosynthetic efficiency to adapt to lower light intensity as shading levels increased. Chlorophyll content increased with increasing shading levels, and leaf mass per area decreased with increasing leaf area. The chlorophyll fluorescence responses Fv/Fm and NPQ did not change with shading, and the activity of the carbon fixation system did not differ between treatments. I. laevigata exhibited a light-saturation point equivalent to that of sun plants and maintained photosynthetic capacity similar to that of controls up to 75% shading. The apparent quantum yield of I. laevigata decreased significantly at 95% shading, indicating adaptation to lower light conditions. It seems that the photosynthetic capacity of I. laevigata decreases when grown under 95% shading level compared to full sunlight, and it is judged that the longer the light is restricted by continuous shading, the more unfavorable the growth will be.

• Korean Journal of Ecology and Environment
• /
• v.47 no.1
• /
• pp.32-40
• /
• 2014

This study was conducted to evaluate the growth response of economical six leafy vegetables that are crown daisy, pak-choi and four kinds of lettuce (Red leaf lettuce, Green leaf lettuce, Head lettuce, Romaine lettuce) by light treatment of LED in plant factory. The light treatments were composed of red, blue, red+farred, red+blue, red+blue+white LEDs, irradiation time ratio of the red and blue LED per minute (1 : 1, 2 : 1, 5 : 1, 10 : 1), and duty ratio of mixed light (100%, 99%, 97%). The following results were obtained in different LED light sources treatments: Shoot biomass and S/R ratio of romaine lettuce were the highest under mixed red+blue LEDs. S/R ratio of head lettuce was higher under mixed red+blue+white LEDs than red+blue LEDs. The others showed no difference in LED light treatment. Shoot biomass, total biomass and S/R ratio of green lettuce, head lettuce and pak-choi were highest in the higher red ratio (5 : 1) on irradiation time of red : blue LED ratios. By the different duty ratio (red+blue and red+blue+white LEDs), Under the mixed light of red+blue, shoot and root biomass of crown daisy and romaine lettuce were high in duty ratio of 100% and 99%, and S/R ratio was highest in all the 6 kinds in duty ratio of 97%. All the 6 kinds showed a fine growth state in low duty ratio (97%). Green lettuce, romaine lettuce and pak-choi showed relatively high shoot biomass and total biomass in low duty ratio of 97% under the mixed light of red+blue+white. S/R ratio of romaine lettuce and head lettuce were highest in the duty ratio of 97% with red+blue+white LEDs. Thus, we can cultivate stably without reference to external factors, if we use appropriate light sources and light quality in closed-type plant factory.