• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.16 no.2
• /
• pp.87-96
• /
• 2023

Recently, research on predicting the treatment results of diseases using deep learning technology is also active in the medical community. However, small patient data and specific deep learning algorithms were selected and utilized, and research was conducted to show meaningful results under specific conditions. In this study, in order to generalize the research results, patients were further expanded and subdivided to derive the results of a study predicting mortality after lung cancer diagnosis for men and women in their 80s, 90s, and 100s. Using AutoML, which provides large-scale medical information and various deep learning algorithms from the Health Insurance Review and Assessment Service, five algorithms such as Decision Tree, Random Forest, Gradient Boosting, XGBoost, and Logistic Registration were created to predict mortality rates for 84 months after lung cancer diagnosis. As a result of the study, men in their 80s and 90s had a higher mortality prediction rate than women, and women in their 100s had a higher mortality prediction rate than men. And the factor that has the greatest influence on the mortality rate was analyzed as the treatment period.

• International Journal of Advanced Culture Technology
• /
• v.5 no.3
• /
• pp.40-45
• /
• 2017

This data mining technique was used to extract useful information from percutaneous coronary intervention data obtained from the US public data homepage. The experiment was performed by extracting data on the area, frequency of operation, and the number of deaths. It led us to finding of meaningful correlations, patterns, and trends using various algorithms, pattern techniques, and statistical techniques. In this paper, information is obtained through efficient decision tree and cluster analysis in predicting the incidence of percutaneous coronary intervention and mortality. In the cluster analysis, EM algorithm was used to evaluate the suitability of the algorithm for each situation based on performance tests and verification of results. In the cluster analysis, the experimental data were classified using the EM algorithm, and we evaluated which models are more effective in comparing functions. Using data mining technique, it was identified which areas had effective treatment techniques and which areas were vulnerable, and we can predict the frequency and mortality of percutaneous coronary intervention for heart disease.

• 대한예방의학회:학술대회논문집
• /
• 2002.10a
• /
• pp.202-203
• /
• 2002

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.5
• /
• pp.21-28
• /
• 2022

All health problems that occur in the circulatory system are refer to cardiovascular illness, such as heart and vascular diseases. Deaths from cardiovascular disorders are recorded one third of in total deaths in 2019 worldwide, and the number of deaths continues to rise. Therefore, if it is possible to predict diseases that has high mortality rate with patient's data and AI system, they would enable them to be detected and be treated in advance. In this study, models are produced to predict heart disease, which is one of the cardiovascular diseases, and compare the performance of models with Accuracy, Precision, and Recall, with description of the way of improving the performance of the Decision Tree(Decision Tree, KNN (K-Nearest Neighbor), SVM (Support Vector Machine), and DNN (Deep Neural Network) are used in this study.). Experiments were conducted using scikit-learn, Keras, and TensorFlow libraries using Python as Jupyter Notebook in macOS Big Sur. As a result of comparing the performance of the models, the Decision Tree demonstrates the highest performance, thus, it is recommended to use the Decision Tree in this study.

• The Plant Pathology Journal
• /
• v.37 no.2
• /
• pp.124-136
• /
• 2021

Bark canker, wood discoloration, and wilting of the duku tree (Lansium domesticum) along the watershed of Komering River, South Sumatra Province, Indonesia first appeared in 2013. The incidence of tree mortality was 100% within 3 years in badly infected orchards. A Ceratocystis species was consistently isolated from the diseased tissue and identified by morphological and sequence analyses of the internal transcribed spacer (ITS) and β-tubulin regions. Pathogenicity tests were conducted and Koch's postulates were confirmed. The fungus was also pathogenic on Acacia mangium, but was less pathogenic on mango. Partial flooding was unfavourable for disease development. Two described isolates (WRC and WBC) had minor variation in morphology and DNA sequences, but the former exhibited a more pathogenic on both duku and acacia. The ITS phylogenies grouped the most pathogenic isolate (WRC) causing wilting of the duku tree within the aggressive and widely distributed ITS5 haplotype of C. fimbriata.

• Journal of Korean Society of Forest Science
• /
• v.111 no.1
• /
• pp.150-164
• /
• 2022

This study was conducted to provide basic information for the development of silvicultural guidelines and manuals. This was achieved through analysis of tree and stand characteristics according to the first and second thinning in Korean white pine plantations. Data were collected from permanent plots installed at Korean white pine plantations according to thinning intensity, and residual tree and stand variables, including diameter at breast height (DBH), volume, and mortality at age 19-43, were analyzed using data repeatedly collected in 4-5 measurements by experiments. According to one-way variance of analysis, tree DBH and volume were significantly different according to thinning intensity (p<0.05). DBH distribution was skewed to the left side over time as thinning intensity was heavier. Thus, tree DBH values were larger in heavy thinning plots with increased age. The periodic annual increment (PAI) of DBH was higher with heavier thinning intensity and fewer years after thinning. The PAI range by thinning intensity was 0.48-0.95 cm/year at age 19-24. In addition, the PAI increased in heavy thinning plots after the second thinning; The PAI range by thinning intensity was 0.29-0.67 cm/year after the second thinning at age 37-42. The PAI of tree volume differed according to thinning intensity, and the PAI value did not decrease obviously, in contrast to the pattern of the DBH PAI. Stand volume was generally higher in high-density stands, and the PAI of stand volume was high in unthinned and light thinning plots. Mortality was highest in unthinned plots, and the differences in mortality according to thinning intensity increased over time. Consequently, the growth of DBH and tree volume was lower as stand density increased, but this growth was facilitated with appropriate first and second thinning operations.

• Fire Science and Engineering
• /
• v.23 no.4
• /
• pp.32-39
• /
• 2009

In this study, 18 plots were selected for particular investigation on Gangneung area and Samcheok area and Uljin area, where forest fire was occurred after thinning in 2007. After selection, a relationship between a damage of forest fire and thinning were compared and analyzed. Many factor such as a damaged species, a thinning or non-thinning, a direction of forest fire head, DBH, a height of tree, a mortality of tree, a leeward scorching ratio, a crown damage ratio, a forest tree standing crop density, a crown base height, a leaving of thinning slash, a location of plot (GPS), elevation, an aspect of slope, an angle of slope, and a topography were measured. Therefore, we analyzed a relationship with forest fire. In the result of this analysis, it was founded that the leeward scorching ratio was 24.7% on thinning area whereas 60.2% on non-thinning area. Subsequently, leeward scorching ratio on thinning area was increased by about 35.5% more than on non-thinning area. In the result of analysis about tree species, a forest of pine tree was more damaged than forest of oak tree. The mortality of tree was increased by about 41.4% on non-thinning area. When stands were close to thinning slashes, these were more damaged by 10${\sim}$20% than other stands for increasing of amount of a combustion material. Especially, as potential of re-ignition increased for more cumulated thinning slash, it will be more important to require a method for a periodical removing or practical utilization of slash.

• Journal of Environmental Impact Assessment
• /
• v.30 no.6
• /
• pp.361-379
• /
• 2021

About 10% of trees damaged by the development projects are to be transplanted when conducting the Environmental Impact Assessment. However, various problems have been raised during transplantation. In this study, we confirm the stakeholder's perceptions of the problems that occur during transplantation. The survey was conducted from October 9 to 25, 2020. Among the stakeholder groups, 36 respondents participated in the consulting institute group, 44 from the review institute group, and 83 from the developer·agency group (total of 163). All three groups responded that it was necessary to transplant some of the damaged trees even if the development charge increased because the damage caused by the development project was serious. The most serious problem was 'high mortality'. The response rate was high that all three groups should plant the same species with the same quantity as an alternative method in case of withering. In order to reduce the mortality rate, small-sized trees were transplanted and transplanted trees were expanded to include planted species and landscape trees. In addition, the number of transplanted trees was high in response to calculating the transplantratio to the number of native tree damaged. The percentage of respondents who said that it was necessary to allocate a separate manager was also high. The results will be used as basic data to improve problems that occur during transplantation of damaged trees.

• Parasites, Hosts and Diseases
• /
• v.54 no.4
• /
• pp.527-532
• /
• 2016

Head lice, Pediculus humanus capitis, infestation is an important public health problem in Egypt. Inadequate application of topical pediculicides and the increasing resistance to the commonly used pediculicides made the urgent need for the development of new agents able to induce irreversible changes in the exposed lice leading to their mortality. The aim of the present work is to evaluate pediculicidal efficacy of some natural products such as olive oil, tea tree oil, lemon juice, and ivermectin separately in comparison with tetramethrin-piperonyl butoxide (licid), as a standard pediculicide commonly used in Egypt. The effects of these products were evaluated by direct observation using dissecting and scanning electron microscopes (SEM). Results showed that after 1 hr exposure time in vitro, absolute (100%) mortalities were recorded after exposure to 1% ivermectin and fresh concentrate lemon juice. The mortalities were decreased to 96.7% after exposure to tea tree oil. Very low percentage of mortality (23.3%) was recorded after 1 hr of exposure to extra virgin olive oil. On the other hand, the reference pediculicide (licid) revealed only mortality rate of 93.3%. On the contrary, no mortalities were recorded in the control group exposed to distilled water. By SEM examination, control lice preserved outer smooth architecture, eyes, antenna, respiratory spiracles, sensory hairs, and legs with hook-like claws. In contrast, dead lice which had been exposed to pediculicidal products showed damage of outer smooth architecture, sensory hairs, respiratory spiracles and/or clinching claws according to pediculicidal products used.

• The Korean Journal of Pesticide Science
• /
• v.13 no.4
• /
• pp.267-274
• /
• 2009

This study was carried out to select effective preventive pesticides against pine wilt disease caused by pinewood nematode (PWN), Bursaphelenchus xylophilus on trunk injection. 1,000 fold aquatic solution of abamectin 1.8% EC and emamectin benzoate 2.15% EC were lower mortality (7.3% and 8.3% respectively) against PWN on 1 day after treatment. However effects of abamectin 1.8% EC, emamectin benzoate 2.15% EC, fosthiazate 30% SL and fenitrothion 30% SL were inhibited the reproduction of PWN over 99.6% in Botrytis cineria media. Effect of trunk injection of abamectin 1.8% EC and emamectin benzoate 2.15% EC at the rate of $10\;m{\ell}$ per 10 cm in diameter of breast height (DBH) on mortality of Japanese black pine, Pinus thungergii by inoculated PWN was 0% and 3.3%, respectively at the applied year however when injection of fosthiazate 30% SL were treated with the rate of $5\;m{\ell}$ per 10 cm tree DBH, mortality of tree was 63.3%. Abamectin 1.8% EC and emamectin benzoate 2.15% EC was showed high preventive efficacy representing >90% against PWN at the following year. PWN preventing efficacy of trunk injection was lower in naturally occurred area (mortality of pine tree in control was 11.7% at the first year) of PWN than artificially infected site (mortality of pine tree in control was >76.7% at the first year), PWN preventing efficacy of trunk injection of abamectin 1.8% EC and emamectin benzoate 2.15% EC at the rate of $10\;m{\ell}$ per 10 cm in DBH was 91.5% and 82.9%, respectively, at the applied year and 89.5% and 82.6% respectively at the following year in PWN naturally occurred site. Control efficacy by trunk injection of abamectin 1.8% EC and emamectin benzoate 2.15% EC was more higher in 10 fold dilution with 10 fold high amount of aquatic solution than no dilution with 10 fold less amount of aquatic solution. The preventive effect of trunk injection of abamectin 1.8% EC and emamectin benzoate 2.15% EC at the rate of $5\;m{\ell}$ per 10 cm in DBH was showed 100% at the applied year in PWN inoculated tree.