• 스마트미디어저널
• /
• 제11권4호
• /
• pp.30-37
• /
• 2022

Disease threatens plant growth and recognizing the type of disease is essential to making a remedy. In recent years, deep learning has witnessed a significant improvement for this task, however, a large volume of labeled images is one of the requirements to get decent performance. But annotated images are difficult and expensive to obtain in the agricultural field. Therefore, designing an efficient and effective strategy is one of the challenges in this area with few labeled data. Transfer learning, assuming taking knowledge from a source domain to a target domain, is borrowed to address this issue and observed comparable results. However, current transfer learning strategies can be regarded as a supervised method as it hypothesizes that there are many labeled images in a source domain. In contrast, unsupervised transfer learning, using only images in a source domain, gives more convenience as collecting images is much easier than annotating. In this paper, we leverage unsupervised transfer learning to perform plant disease recognition, by which we achieve a better performance than supervised transfer learning in many cases. Besides, a vision transformer with a bigger model capacity than convolution is utilized to have a better-pretrained feature space. With the vision transformer-based unsupervised transfer learning, we achieve better results than current works in two datasets. Especially, we obtain 97.3% accuracy with only 30 training images for each class in the Plant Village dataset. We hope that our work can encourage the community to pay attention to vision transformer-based unsupervised transfer learning in the agricultural field when with few labeled images.

• 인간식물환경학회지
• /
• 제24권6호
• /
• pp.707-718
• /
• 2021

Background and objective: Due to the recent crisis of extinction in local areas, the mountain village promotion policy is recognized as an important task. This study examined the priorities of major policy projects in the forest sector that affect mountain village promotion. Methods: For research methods, literature search, expert advisory meetings, and a survey were conducted. The survey was conducted on 42 policy stakeholders from June 1 to August 13, 2021. The literature search was based on policy projects in the forest sector by 8 upper-level local governments including mountain villages. For questionnaire items, 173 forest policy projects were classified into 27 types through expert review, and the importance and performance of each type were rated on a 5-point Likert scale. Paired t-test, IPA, Locus for Focus model, and Borich needs assessment were used as the analysis methods, and the statistical program SPSS 21.0 was used as the analytical tool. Results: The results showed that 'creating forest-related jobs' and 'supporting cultivation of professional forestry workers' both showed high importance and performance, implying that they would show an effect in mountain village promotion. 'Creating forests for environmental improvement', 'discovering forest cultural assets' 'establishing and boosting forest tourism', 'providing forest therapy services', 'creating forest-related jobs', 'supporting community revitalization', and 'urban-rural exchanges' were found to be the types that needed improvement and concentration for mountain village promotion. In particular, 'creating forests for environmental improvement' and 'discovering forest cultural assets' were derived as priority considerations for mountain village promotion policies. Conclusion: In summary, it was found that in order to promote mountain villages, various content projects must be improved and carried out to enhance the physical environment and revitalize mountain villages.

• 농촌의학ㆍ지역보건
• /
• 제47권2호
• /
• pp.61-66
• /
• 2022

Objectives: In the epidemiology of communicable diseases, the term epidemic period, also referred to as "wave" is often used in the general and academic milieu. A wave refers to a natural pattern of increase in the number of sick individuals, a defined peak, and then a decline in the number of cases. It implies a pattern of peaks and valleys after a particular peak is taken. The idea of epidemic waves is a useful tool for predicting the course as well as helping to accurately describe an epidemic. However, in many domestic and foreign news as well as in various research results in Korea, most of the reports either had no standard, were inaccurate, had a questionable classification of the period of the epidemic, or the basis for classification of a given wave was not presented. Methods: The author reviewed and organized related literature with epidemic wave. The author made several suggestions of an epidemic wave as follows. Results: To start with, it should be based on the number of incident cases in consideration of the size of the outbreak, then the period from the bottom to the peak and then reaching the next bottom; also, the period over a certain scale based on the number of incident cases; and the period according to the change in the major infection type (mutation-dominant species). In addition, according to the period of change in the vaccination rate (formation of herd immunity), as well as the content and duration of the intervention, that is, classification according to the applied quarantine stage. Furthermore, the classification of epidemic periods by the time-dependent reproduction number or time-varying reproduction number (Rt), and lastly the application of mathematical methodology. Conclusions: Therefore, classifying the epidemic period into generally known and accepted time frames is considered to be a very important task for future research analysis and development of intervention strategies.

• 한국환경농학회지
• /
• 제42권3호
• /
• pp.253-258
• /
• 2023

In the environment, chromium often exists in a highly mobile and toxic form of Cr(VI). Therefore, the reduction of Cr(VI) to less toxic Cr(III) is considered an effective remediation strategy for Cr(VI)-contamination. In this study, the biological reduction of hexavalent chromium was examined at the concentrations of 0.01 mM, 0.1 mM, and 1 mM Cr(VI) by the dissimilatory metal-reducing bacterium, Shewanella sp. HN-41 in the presence of ferric-citrate. With the relatively condensed cell densities, the aqueous phase Cr(VI) was reduced at the proportions of 42%, 23%, and 31%, respectively for the 0.01 mM, 0.1 mM, and 1 mM Cr(VI) incubations, while Fe(III)-citrate was reduced at 95%, 88%, and 73%, respectively. Although the strain HN-41 was not considered to reduce Cr(VI) as the sole electron acceptor for anaerobic metabolism in the preliminary experiment, it has been presumed that outer-membrane c-type cytochromes such as MtrC and OmcA reduced Cr(VI) in the presence of ferric-citrate as the electron acceptor. Since this study indicated the potential of relatively high cell density for Cr(VI) reduction, it might propose a bioremediation strategy for Cr(VI) removal from contaminated waters using engineered systems such as bioreactors employing high cell growths.

• Journal of Veterinary Science
• /
• 제23권2호
• /
• pp.18.1-18.10
• /
• 2022

Background: Canine herpesvirus type 1 (CaHV-1) infects dogs and is associated with neonatal deaths and reproductive, ocular, neurological, and respiratory problems. In Brazil, reports of CaHV-1 have been restricted to the southeast and south regions, particularly in municipalities in the state of Rio Grande do Sul. Objectives: To assess the presence and variability of CaHV-1 in canine populations in the state of Pará, North Brazil. Methods: Biological samples from 159 dogs from 4 municipalities in the State of Pará were evaluated using polymerase chain reaction and phylogenetic analyses, with the target being the viral enzyme, thymidine kinase. Results: CaHV-1 was detected in 13 dogs (8.2%), with 2 animals being from the municipality of Santa Bárbara do Pará, 8 from Algodoal Island, 2 from Salinópolis, and one from Capanema. The study sequences revealed 100% identity among themselves and 64% to 100% identity with the other nucleotide sequences from Australia, Brazil, United Kingdom, and United States, including 100% identity with the 2002 isolate from Australia. The 1996 isolate from France was grouped in a branch that was different from the sequence of this study. Conclusions: This study presents the first molecular detection of CaHV-1 in dogs from the Amazon region in northern Brazil. The nucleotide identity between the strains and cytosine insertion in the sequences isolated in this study suggests at least 2 strains of CaHV-1 circulating in Brazil (Pará and BTU-1).

• 치위생과학회지
• /
• 제23권3호
• /
• pp.225-235
• /
• 2023

Background: This study aimed to analyze the effects of periodontal treatment and individual- and tooth-related factors on tooth extraction in people with disabilities. Methods: The Korea National Health Insurance claims data of individuals with disabilities aged 40~64 years with chronic periodontitis in 2008 were obtained. Of these, data on the disabled who underwent scaling/root plaining, subgingival curettage/periodontal surgery, or non-periodontal treatments, and data on their teeth were selected. The extraction of 716,688 teeth from 39,097 patients was tracked until 2018, and the patient- and tooth-level factors related to tooth loss were identified using a mixed-effect logistic regression analysis. Results: Data from approximately 17% of the teeth were extracted during a follow-up period of approximately 11 years. Among the tooth-level variables, scaling/root planing treatment at baseline and periodontal treatment during the follow-up period were associated with a lower risk of tooth loss (odds ratio=0.692 and 0.769, respectively, p<0.001). Non-vital teeth increased the risk of tooth loss by 3.159 times (p<0.001). Among the patient-level variables, females were less likely to have lost their teeth than males, and those with orthopedic impairment or brain lesions/mental disabilities, a higher age group, lower income level, or residents in medium/small cities or rural areas were more likely to have lost their teeth (p<0.001). Conclusion: Through approximately 11 years of follow-up, scaling or root planing, experience with periodontal treatment at least once, female sex, older age, lower income, smaller residential areas, type of disability, and pulp vitality were found to be associated with tooth loss in individuals with disabilities aged 40~64 years with chronic periodontitis. To prevent tooth loss in individuals with disabilities, it is necessary to establish a dental treatment plan that considers the timing of periodontal treatment and the characteristics of the patient and teeth.

• 대한원격탐사학회지
• /
• 제39권5_1호
• /
• pp.507-519
• /
• 2023

Multi-temporal optical images have been utilized for time-series monitoring of croplands. However, the presence of clouds imposes limitations on image availability, often requiring a cloud removal procedure. This study assesses the applicability of various machine learning algorithms for effective cloud removal in optical imagery. We conducted comparative experiments by focusing on two key variables that significantly influence the predictive performance of machine learning algorithms: (1) land-cover types of training data and (2) temporal variability of land-cover types. Three machine learning algorithms, including Gaussian process regression (GPR), support vector machine (SVM), and random forest (RF), were employed for the experiments using simulated cloudy images in paddy fields of Gunsan. GPR and SVM exhibited superior prediction accuracy when the training data had the same land-cover types as the cloud region, and GPR showed the best stability with respect to sampling fluctuations. In addition, RF was the least affected by the land-cover types and temporal variations of training data. These results indicate that GPR is recommended when the land-cover type and spectral characteristics of the training data are the same as those of the cloud region. On the other hand, RF should be applied when it is difficult to obtain training data with the same land-cover types as the cloud region. Therefore, the land-cover types in cloud areas should be taken into account for extracting informative training data along with selecting the optimal machine learning algorithm.

• 문화기술의 융합
• /
• 제10권2호
• /
• pp.531-536
• /
• 2024

최근 농업분야의 스마트 농기계로 분류되고 있는 방제드론은 농촌지역의 고령화 시대를 맞이하여 작업 시간 단축과 방제효과를 높이기 위해 하드웨어 및 소프트웨어를 결합하여 스마트 방제 및 자동방제 시스템 구축을 위해 노력하고 있다. 본 논문에서는 관리관제 및 자동방제 시스템 구축을 위한 기초연구로 방제드론 전용노즐의 특성을 분석하였다. 다양한 드론 모델의 종류, 방제사, 바람, 비행속도, 비행고도, 날씨 조건, UAV 농약 종류 등 다양한 변수를 고려하기 위해서는 노즐의 특성파악과 범용성을 고려하여 약제살포 기준 제시가 가능한 관련 연구가 필요하다. 따라서 다양한 변수 고려가 가능하도록 자체 설계노즐을 기반으로 유동해석(CFD) 시뮬레이션을 실시하고 감수지 실험을 통하여 액적분포의 이론값과 실험값을 비교 분석하였다. 추후 드론운용에 따른 다양한 변수를 고려하여 정확한 비산을 산출하고 관리관제 및 자동방제 시스템에 활용하고자 한다.

• Parasites, Hosts and Diseases
• /
• 제29권3호
• /
• pp.235-244
• /
• 1991

강원도 원주 지역 학등에 대하여 환경을 달리하는 4군을 adhesive cellotape anal swab 법으로 충란 검출률을 조사하였고 감염 집단에 대하여 구충제의 반착 투여로 감염률의 감소 현황과 재감염 을 관찰하였다. 1. 충란 검출률(1회 검사)은 19.9%(1,262명중 251명 양성, 남 19.7%, 여 20.1%)였으며 지역과 환경이 다른 산간 지역 13.0%, 농촌 지역 11.9%, 중 도시 15. l%, 집단생활 아동 61.9%로 나타났다. 2. 국민학생은 저학년(유치만 및 1,2학년생)에서 검출률(26.2∼32.2%)이 높았고 그 외는 최저 (6학년 생) 13.6%이었다. 3. 반복 검사(4∼5일 간격 3회)에 의한 누적 검출률은 높았으나(최초 58.5%에서 70.8%로) 매회의 검출률은 비슷한 비율(50.0%∼59.2%)을 보였다. 4. 반복검사 3회의 누적 검출률(70.8%, 130명 검사) 중 계속 양성자는 평균 39.2%이었다. 그리고 충란 검출률이 높은 군(87.5%)일수록 그 비율(71.9%)은 높았다. 5. 충란 양성자 17명에서 구충제 투여로 2,609마리 (성비는 12.4 : 1)의 충체를 수집하였다. 이는 평균 153마리 (4∼824범위) 감염에 해당된다. 6. 집단에 대하여 매회 충란 양성자에만 구충제를 투여 (3주간격 6회)한 바 양성률은 최초 54.8% (180명중)에서 15주 후에 2.3%로 감소되었으나 완전한 구충 효과는 얻지 못하였다. 그러나 매회 전 집단(양성자, 음성자 같이)에 대한 구충제 투여 (3주간격)에서는 4회 (9주째) 검사때 전부 음성으로 나타났다. 7. 국민학교 학생 양성자의 형제자매 중 충란 검출률은 70.0%(40명 중 28명)이었다. 가족 단위로는 69.7%의 같은 비율로 높았다. 이상으로 요충 감염은 아직까지 높은 상태임을 알았고 예방을 위한 집단 구충에는 전 집단에 대한 3회 이상의 반복구충이 효과적이었다. gas layers is also made. Low resolution spectral intensities at the boundary are obtained for uniform, parabolic and boundary layer type temeprature profiles using the obtained for uniform, parabolic and boundary layer type temperature profiles using the obtained WSGGM's with 9 gray gases. The results are compared with the narrow band spectral intensities as obtained by a narrow band model-based code with the Curtis-Godson approximation. Good agreement is found between them. Local heat source strength and total wall heat flux are also compared for the cases of Kim et al, which again gives promising agreement.면적 306~453$\textrm{cm}^2$, 유색계의 경우 수당면적 340~453$\textrm{cm}^2$ 일 때 경제능력을 제대로 발휘할 수 있고 경제성이 있는 것으로 나타났다. 첨가구가 높은 경향이 있었다8.4%. 79.7% 그리고 80.2%였다. 5. 체중구성요소들의 중상비율간의 상관근도는 계통간를 차이를 보이지 않았다. 체중구성요소중 체중과 상관정도가 높은 부위들은 방혈양, 두부, 각부, 흉부, 퇴경부등이였다. 복부지방(%)은 어느 계종에서나 주로 불가식내장과 높은 유의상관을 보였으나, 가식부위와의 상관정도는 매우 낮게 나타났다.ctivity of these

• 한국지역지리학회지
• /
• 제2권1호
• /
• pp.133-150
• /
• 1996

농촌의 최하위 계층 중심지에 발달한 정기시의 이동상인과 소비자의 공간적 특성을 파악하기 위하여 오래 전부터 개시(開市)된 옥천군 청산 정기시를 대상으로 출시자를 조사하여 분석한 결과 다음과 같은 점이 밝혀졌다. 이동상인은 장년 내지 노년층으로 구성되어 있으며, 일용잡화와 농산물을 취급하고, 정기시 출시(出市)의 주된 유형은 청산$\rightarrow$원남$\rightarrow$보온의 유형과 청산$\rightarrow$영동$\rightarrow$용산의 유형이다. 상인의 거주지는 정기시가 입지한 지역이 가장 많고 이어서 인접해 있는 하위 중심지인 청성면, 상위계층 중심지인 보은 영동읍과 대전시, 그리고 보은군 원남면으로, 이들은 정기시를 매일 자기 집에서 5일에 3일 이상 출시하거나 특정한 하나의 정기시만을 5일에 하루 출시하는 형태를 취하고 있다. 정기시를 이용하는 소비자는 $30{\sim}50$대가 대부분이고, 한달에 $2{\sim}6$회 정기시에서 재화를 구입하며, 이용하는 교통수단은 주로 버스이다. 그리고 생활필수품을 구입하기 위하여 출시하는데, 구입하는 상품은 주로 식료품이고 전문계도 고차 중심지보다 이 지역의 상위 중심지인 청산에서 구입하는데 이는 타 지역과 교통이 불편하고 거리도 밀어 상품을 구입할 매 비용이 추가되며, 상품을 구입한 후에도 아프터서비스를 받는데에도 불리하기 때문이다. 그러나 청산 정기시에서 구입하지 못하는 선매재나 전문재는 거리가 가까운 보은읍보다는 상위 중심지인 영동읍이나 대전시에서 구입하고 있다. 최하위 중심지의 정기시는 농촌인구의 감소, 주민의 소득증대와 생활수준의 향상, 중심지의 상설 상업시설의 등장, 유통기구의 변화, 교통기관의 발달 등 정기시의 외적 환경들이 변화됨에 따라 이동상인의 출시형태가 변화되었으나 상대적으로 교통이 불편한 지역의 소비자는 편의(便宜) 선매재(選買財)뿐만 아니라 전문재(專門財)도 최저차 중심지에서 많이 구입하고 있다는 점이 밝혀졌다.