Latent Dirichlet Allocation (LDA) 모델 기반으로 한 인공 지능 (A.I.) 기술의 연구 활동 및 동향에 대한 체계적인 분석

정명석,이주연 한국경영정보학회 2018 한국경영정보학회 학술대회논문집 Vol.2018 No.5

국내외 특허데이터 기반의 인공지능분야 기술동향 분석

정명석,정소희,이주연 한국디지털정책학회 2018 디지털융복합연구 Vol.16 No.6

Investigating Heavy Metal Contamination Extent of Soil and Plant from Urban Gardens in Jinju

정명석,김권래,이미나,츄수르윈 한국토양비료학회 2023 한국토양비료학회지 Vol.56 No.2

In Korea, 90% of the population lives in urban areas, so urban agriculture is commonly carried out. However,research on the safety of urban soils for growing food still needs to be done. Thus, this study was conducted toevaluate the suitability of urban soil for crop cultivation by investigating the heavy metal concentration of soiland plant from urban gardens in Jinju. Soils and crop leaves were collected from 23 urban gardens, and theconcentrations of As, Cd, Cr, Cu, Ni, Pb, and Zn were analyzed. The average concentrations of garden soils inJinju were As 5.31, Cd 0.59, Cr 30.09, Cu 33.05, Ni 21.14, Pb 23.28, and Zn 121.68 mg kg-1, which did notexceed the Korean guidelines except for Zn in one study site. Geoaccumulation Index, calculated using thebackground values of heavy metals in Korean soil, showed that contamination of Cd, Cu, Pb, and Zn was inprogress. The inflow of Cu and Zn into the garden soils would be from the atmosphere and direct entry into thesoil by adding livestock manure. Differently, the other elements were more predominantly introduced fromthe atmosphere. Particularly, a significant amount of Pb was introduced into the soils from the atmosphere ina couple of gardens. Overall, the results from this study indicated that continuous monitoring for heavy metalsin urban garden soils is required for food safety.

Distribution of Heavy Metals in Agricultural Soils Near Major Roads in Medium-Sized Cities

정명석,이미나,츄수르윈,김권래 한국토양비료학회 2022 한국토양비료학회지 Vol.55 No.3

Due to rapid urbanization, urban lands have been expanded into existing agricultural areas. With such spatialchanges, agricultural lands in the expanding cities or peri-urban areas are easily exposed to contaminantsgenerated by anthropogenic activities such as traffic. Therefore, this study aimed to investigate heavy metalconcentrations in major roadside agricultural soils by distance in medium-sized cities, Jinju and Changwon,and to identify the influence of roadside dust on metal contamination. The roadside arable soils of paddy andupland, roadside tree soil, and roadside dust were sampled. In paddy, the heavy metal concentration changes bythe distance from the road were not observed because of soil puddling and waterlogging. However, in upland,Cu and Zn concentrations gradually decreased with the increased distance from the road. In roadside dust, Cuand Zn concentrations were very high, exceeding Korean guidelines, which indicates roadside dust could be aprimary source of Cu and Zn contamination in agricultural soils. Moreover, the roadside tree soil, which is notdisturbed by agricultural activities, showed higher heavy metal concentrations in topsoil rather than subsoil,even though the soil was newly introduced for tree planting. This implies that road dust containing the metalcontaminants may accumulate in the nearby soils. Many scientists have thought that eco-friendly compost isthe main reason for increasing Cu and Zn in urban agricultural soils. However, roadside dust needs to be morefocused on as a principal source of contamination.

개비자나무의 homoharringtonine 함량에 영향을 미치는 생물 및 무생물적 환경인자

정명석,현정오,이욱,백을선 한국자원식물학회 2010 한국자원식물학회지 Vol.23 No.2

This study was carried out to investigate abiotic and biotic environmental factors affecting homoharringtonine (HHT) contents of Cephalotaxus koreana, whereby, to provide basic information of high value-added industry production of HHT as a promising anti-cancer agent. For correlation between abiotic environmental factors (soil moisture, soil pH, habitat density and temperature) and HHT contents, the contents were highly correlated with soil moisture (0.77) and soil pH (-0.68). For multiple regression analysis of relationship between abiotic environmental factors (soil moisture and soil pH) and HHT contents, soil moisture appeared to be strongly affecting the contents relatively due to being significant at only its regression coefficient (26.48***). For the effect of biotic environmental factors (damage index) affecting HHT contents, the contents was quadratic with equation of H=278.23+1242D-398.87D2, also, damage index had strong effect on the contents. Finally, for the result of the most influencing an environmental factor on HHT contents, both damage index and soil moisture were suitable in second polynomial regression, also, damage index (R2=0.73***) was turned out to be more influencing factor than soil moisture (R2=0.67**) on HHT contents relatively. Therefore, we predict that HHT contents in the trees of Cephalotaxus koreana is produced as a chemical defense mechanism triggered by a stress-related damage of fungi or insects. 천연집단에 서식하는 개비자나무 개체들을 이용해 무생물 및 생물적 환경인자가homoharringtonine(HHT) 함량에 미치는 영향을 조사하여 향후 항암제 가능성이 있는 HHT 의 고부가가치 산업적인 생산이 기대되는 연구에 기초자료를 제공하고자 본 연구를 수행하였다. 무생물적 환경인자(토양습도, 토양pH, 서식밀도, 기온)와 HHT 함량과의 상관관계에 있어 HHT 는 토양습도(0.77)와 토양pH(-0.68)에서 높은 상관을 보였다. 고도에 따른 무생물적 환경인자(토양습도, 토양pH )와 HHT 의 함량 관계에 관해 다중회귀 분석을 실시한 결과, 토양 습도의 회귀계수(26.48***)만 유의하여 토양 습도가 상대적으로 HHT 함량에 높은 영향을 미치는 것으로 나타났다. 생물적 환경인자(damage index)에 따른 HHT 함량에 미치는 영향을 살펴 본 결과, HHT는 2차곡선회귀적으로 증가하다 감소하는 (H=278.23+1242D-398.87D2) 경향을 보였고 damage index는 HHT 함량에 높은 영향을 미치는 것으로 분석되었다. 마지막으로 HHT 의 함량에 영향을 미치는 최적환경인자를 분석한 결과, damage index와 토양 습도 모두가 2차다항회귀식으로 가장 적합하였고 결정계수는 각각 0.73와 0.67로 damage index가 상대적으로 HHT 함량에 높은 영향을 미치는 것으로 나타났다. 이는 섭식자 또는 균류와 같은 스트레스로 인한 방어기작이 HHT 의 생성에 높은 영향을 미치는 것으로 판단된다.

자기공명영상을 이용한 비인강 기도와 아데노이드의 측정

정명석 대한영상의학회 1993 대한영상의학회지 Vol.29 No.5

Adenoid is a kind of tonsil located in the posterior wall of nasopharynx. Enlargement of the adenoid can produce obstruction of the nasopharynx and Eustachian tube. Disturbance in discharge of nasal and paranasal secretions can be a cause of chronic rhinitis, sinusitis, and otitis media. Diagnosis of enlarged adenoid simply by inspection is difficult due to its location. Measurement of nasopharyngeal airway and adenoid using lateral radiogrpahs of nasopharynx may be inaccurate for magnification and rotation. It was some limitations in demonstrating the actual state of nasopharyngeal airway and adenoid because it gives only two-dimensional informations. The authors measured the sizes and areas of nasopharyngeal airway and adenoid using MRI with sagittal and oblique coronal pilot views of T1 weighted spin echo. We categorized the patients into 4 groups according th the scoring system by symptoms such as apnea, mouth breathing, and snoring. The results of several measurements and their ratios were evaluated in these 4 categorized patients. The ratios of area of adenoid and nasopharyngeal airway (AA/Na) in each patient group were 6.52, 7.76, 10.53, 15.93, respectively. And the ratios of adenoid and nasopharyngeal airway (A/N) by Fujioka's method were 0.6, 0.69, 0.71, respectively. We found that AA/Na might be the most effective index as an objective indicator in the evaluation of nasopharyngeal ostruction by the enlarged adenoid.

논문데이터 분석을 통한 인공지능 분야 주요 연구 동향 분석

정명석,박성현,채병훈,이주연 한국디지털정책학회 2017 디지털융복합연구 Vol.15 No.5

개비자나무의 천연집단 조사 및 자원파악과 개체 내 부위별 기능성 물질(homoharringtonine)의 함량분석

정명석,현정오,이재호 한국임학회 2004 한국임학회 학술발표논문집 Vol.2004 No.-

Investigating Heavy Metal Levels of Greenhouse Soils Using Long-Term Livestock Manure

정명석,김권래,이미나,츄수르윈,위남희,백태희 한국토양비료학회 2023 한국토양비료학회지 Vol.56 No.3

The use of eco-friendly compost, such as livestock manure, has increased due to the environmental pollution of chemical fertilizers. However, many farmers use livestock manure and inorganic fertilizer together, leading to excessive soil nutrients. Also, livestock manure includes heavy metals, so the long-term use of livestock manure could increase heavy metal levels, particularly in greenhouse soils. Therefore, this study aims to investigate heavy metal concentrations in greenhouse soils using long-term livestock manure. The soils were collected from 24 greenhouses applying livestock manure for 5 - 32 years in Gyeongnam province, Korea. The chemical characteristics and heavy metal concentrations of the soils were analyzed. As a result, soil pH, organic matter, available phosphorus, and exchangeable-Ca, Mg, and K of most soils were higher than the average values of greenhouses in Gyeongnam. The As, Cd, Cr, Cu, Ni, Pb, and Zn levels of the studied soils also exceeded Gyeongnam greenhouses’ average values. Moreover, Zn concentrations of three greenhouse soils were 394.4 mg kg-1, 305.3 mg kg-1, and 323.2 mg kg-1, which exceeded the Korean Zn threshold of 300 mg kg-1. The levels of Cu in these three soils showed higher values than in other soils, so the accumulation of Cu and Zn was mainly concerned with applying livestock manure. Thus, the soils using long-term livestock manure would be recommended for regular monitoring for food safety.

PC 사용자를 위한 인공지능 기반 거북목 경고 시스템 개발

정명석(Myeong Seok Jung),신동원(Dong Won Shin),임동원(Dong-Won Lim) 제어로봇시스템학회 2020 제어·로봇·시스템학회 논문지 Vol.26 No.5

In recent years, excessive use of laptop computers, tablets, smartphones, and other small portable digital devices has caused many side effects, including the FHP (Forward Head Posture) or the poking chin. It has been reported that FHP results in shoulder pain, neck ache, craniofacial pain, headache, or other adverse conditions. To prevent FHP, it is advised to consciously keep one’s head in an upright posture. This paper proposes a new FHP warning system, which can help a user maintain a good posture by signaling an alarm, when FHP is detected. The system consists of an FHP warning device, a measurement set, and a decision algorithm for FHP. Unlike previous studies and patents, the proposed system delivers the design that is comfortable for daily use (because it is not worn by a user) and highly accurate through the adaptation of an AI (Artificial Intelligence) algorithm. The warning device was created as a turtle doll, which neck and back is elongated and lighted by LEDs, respectively. The measurement set consists of a servo motor and two sensors that read the distances from the computer to the upper face and the chest with the angular displacement of the two parameters. To decide FHP, three popular AI algorithms that are relevant to the classification problem were considered and analyzed, namely the ANN (Artificial Neural Network), SVM (Support Vector Machine), and DT (Decision Tree). Measurement data were collected by 7 different users and 2 chairs with different heights for good posture and FHP scenarios. The test results of the trained algorithms yielded accuracy performances of 73.78%, 83.00%, and 86.26% for ANN, SVM, and DT, respectively. In this study, ANN’s poor performance due to various reasons (e.g., the small training sample size) was discussed. DT, which was suitable for a problem set of 0 or 1 discrete outputs, was selected for the FHP warning system.