• Korean Journal of Artificial Intelligence
• /
• v.8 no.1
• /
• pp.7-9
• /
• 2020

In this paper, a study was conducted to find a self-diagnosis method to prevent the spread of COVID-19 based on machine learning. COVID-19 is an infectious disease caused by a newly discovered coronavirus. According to WHO(World Health Organization)'s situation report published on May 18th, 2020, COVID-19 has already affected 4,600,000 cases and 310,000 deaths globally and still increasing. The most severe problem of COVID-19 virus is that it spreads primarily through droplets of saliva or discharge from the nose when an infected person coughs or sneezes, which occurs in everyday life. And also, at this time, there are no specific vaccines or treatments for COVID-19. Because of the secure diffusion method and the absence of a vaccine, it is essential to self-diagnose or do a self-diagnosis questionnaire whenever possible. But self-diagnosing has too many questions, and ambiguous standards also take time. Therefore, in this study, using SVM(Support Vector Machine), Decision Tree and correlation analysis found two vital factors to predict the infection of the COVID-19 virus with an accuracy of 80%. Applying the result proposed in this paper, people can self-diagnose quickly to prevent COVID-19 and further prevent the spread of COVID-19.

• Asian Journal of Turfgrass Science
• /
• v.13 no.3
• /
• pp.159-170
• /
• 1999

Preference of chestnut brown chafer (CBC), Adoretus tenuimaculatus was examined from chestnut leaves which were treated with different light condition, temperature and nitrogen fertilization. More CBC was attracted to leaves which grown at $30^{\circ}C$ than grown at $20^{\circ}C$,$ 25^{\circ}C$ and in the field. When attracted number of CBC was compared among full sunlight-grown, cloth shaded-grown and dark-grown plants, 4.0 in full sunlight grown and 5.0 in dark-grown plants. Amount of nitrogen fertilizer did not influence CBC feeding. The attractiveness of undamaged leaves with non-feeding beetles, leaves with feeding damaged, and leaves with artificial damaged was compared in replicated laboratory trials by placing the treatments in the petri-dish and counted the number of beetles that landed on the plants after 6 hr treatment. The highest number of beetles was attracted to chestnut leaf with feeding damaged ($7.7\pm$0.6) than undamaged leaf with non-feeding beetles ($5.3\pm$0.6) and artificial damaged ($4.3\pm$0.6). Managnese content in the leaves of chestnut grown in shade cloth-grown condition was higher than that in the leaves of chestnut that had been exposed to full sunlight condition and dark condition, and feeding damaged leaf.

• International journal of advanced smart convergence
• /
• v.9 no.4
• /
• pp.132-138
• /
• 2020

Worldwide, the number of corona virus disease 2019 (COVID-19) confirmed cases is rapidly increasing. Although vaccines and treatments for COVID-19 are being developed, the disease is unlikely to disappear completely. By attaching a smart sensor to the respirator worn by medical staff, Internet of Things (IoT) technology and artificial intelligence (AI) technology can be used to automatically detect the medical staff's infection symptoms. In the case of medical staff showing symptoms of the disease, appropriate medical treatment can be provided to protect the staff from the greater risk. In this study, we design and develop a system that detects cough, a typical symptom of respiratory infectious diseases, by applying IoT technology and artificial technology to respiratory protection. Because the cough sound is distorted within the respirator, it is difficult to guarantee accuracy in the AI model learned from the general cough sound. Therefore, coughing and non-coughing sounds were recorded using a sensor attached to a respirator, and AI models were trained and performance evaluated with this data. Mel-spectrogram conversion method was used to efficiently classify sound data, and the developed cough recognition system had a sensitivity of 95.12% and a specificity of 100%, and an overall accuracy of 97.94%.

• The korean journal of orthodontics
• /
• v.52 no.2
• /
• pp.102-111
• /
• 2022

Objective: To develop and explore the usefulness of an artificial intelligence system for the prediction of the need for dental extractions during orthodontic treatments based on gender, model variables, and cephalometric records. Methods: The gender, model variables, and radiographic records of 214 patients were obtained from an anonymized data bank containing 314 cases treated by two experienced orthodontists. The data were processed using an automated machine learning software (Auto-WEKA) and used to predict the need for extractions. Results: By generating and comparing several prediction models, an accuracy of 93.9% was achieved for determining whether extraction is required or not based on the model and radiographic data. When only model variables were used, an accuracy of 87.4% was attained, whereas a 72.7% accuracy was achieved if only cephalometric information was used. Conclusions: The use of an automated machine learning system allows the generation of orthodontic extraction prediction models. The accuracy of the optimal extraction prediction models increases with the combination of model and cephalometric data for the analytical process.

• Korean Journal of Radiology
• /
• v.25 no.1
• /
• pp.86-102
• /
• 2024

Early diagnosis, accurate assessment, and localization of peritoneal metastasis (PM) are essential for the selection of appropriate treatments and surgical guidance. However, available imaging modalities (computed tomography [CT], conventional magnetic resonance imaging [MRI], and 18fluorodeoxyglucose positron emission tomography [PET]/CT) have limitations. The advent of new imaging techniques and novel molecular imaging agents have revealed molecular processes in the tumor microenvironment as an application for the early diagnosis and assessment of PM as well as real-time guided surgical resection, which has changed clinical management. In contrast to clinical imaging, which is purely qualitative and subjective for interpreting macroscopic structures, radiomics and artificial intelligence (AI) capitalize on high-dimensional numerical data from images that may reflect tumor pathophysiology. A predictive model can be used to predict the occurrence, recurrence, and prognosis of PM, thereby avoiding unnecessary exploratory surgeries. This review summarizes the role and status of different imaging techniques, especially new imaging strategies such as spectral photon-counting CT, fibroblast activation protein inhibitor (FAPI) PET/CT, near-infrared fluorescence imaging, and PET/MRI, for early diagnosis, assessment of surgical indications, and recurrence monitoring in patients with PM. The clinical applications, limitations, and solutions for fluorescence imaging, radiomics, and AI are also discussed.

• Clinical Endoscopy
• /
• v.57 no.1
• /
• pp.1-10
• /
• 2024

Barrett's esophagus (BE) is the precursor to esophageal adenocarcinoma (EAC), and is caused by chronic gastroesophageal reflux. BE can progress over time from metaplasia to dysplasia, and eventually to EAC. EAC is associated with a poor prognosis, often due to advanced disease at the time of diagnosis. However, if BE is diagnosed early, pharmacologic and endoscopic treatments can prevent progression to EAC. The current standard of care for BE surveillance utilizes the Seattle protocol. Unfortunately, a sizable proportion of early EAC and BE-related high-grade dysplasia (HGD) are missed due to poor adherence to the Seattle protocol and sampling errors. New modalities using artificial intelligence (AI) have been proposed to improve the detection of early EAC and BE-related HGD. This review will focus on AI technology and its application to various endoscopic modalities such as high-definition white light endoscopy, narrow-band imaging, and volumetric laser endomicroscopy.

• Journal of agriculture & life science
• /
• v.50 no.5
• /
• pp.183-188
• /
• 2016

This experiment was conducted to investigate the effects of artificial insemination(AI) frequency on reproductive performance of sows. A total of 48 F1 sows(Yorkshire×Landrace) were allocated to 1 of 4 treatments using completely randomized design(CRD). Four experimental treatments were AI frequency from one to four times(AI1, AI2, AI3, AI4) respectively. Estrus detection was done at approximately 09:00 and 21:00 daily by applying back pressure to females with the presence of a mature boar and the weaning to estrus interval(WEI) of all sows were 5~6 day. Sows detected in estrus were mated at 12 hour after and mating interval was 12 hour by treatments. This experiment demonstrated that the lowest farrowing rate was observed AI3 treatment. Frequency of AI did not influence on reproductive performance when WEI was 5-6 day. No significant differences were observed on litter size, born alive and litter birth weight. Consequently, decreased AI frequency did not have any detrimental effect on reproductive performance when estrus detection was adequate. Decreased AI frequency could reduce cost of production of pigs when sows showed normal reproductive performance.

• Horticultural Science & Technology
• /
• v.31 no.3
• /
• pp.352-358
• /
• 2013

For the germination and differentiation of immature embryos obtained by artificial crossing between tetraploid grape 'Fujiminori' (Vitis vinifera ${\times}$ V. labruscana) and triploid 'Summer Black' (V. labruscana ${\times}$ V. vinifera), were incubated in vitro using MS medium supplemented with $GA_3$ or coconut water (CW) at various concentrations. The percentage of embryo formation of 'Fujiminori' ${\times}$ 'Summer Black' was 64.3%. Embryo germination percentage was higher than 95% in all the $GA_3$ treatments at the concentrations of 0.01, 0.05, 0.25, and $1.25mg{\cdot}L^{-1}$. However, only 15.8-31.6% of the germinated embryos successfully developed into normal plantlets. At higher concentration of $GA_3$, the plantlets developed infirm hypocotyls with over elongated and less enlarged structure. Among the treatments of CW at the concentrations of 5, 10, 15, and 20% (v/v), 10% and 15% were more effective and plantlet achievement percentage were 68.4 and 66.7%, respectively. The addition of 10% CW was most effective to obtain plantlets with optimal shoot length, node and root numbers. 15% CW was suitable to obtain plantlets with longer roots. Accordingly, the embryo culture using the MS medium supplemented with 10-15% CW was observed to be more efficient for germinating and growing the immature embryos produced from artificial crossing between tetraploid grape 'Fujiminori' and triploid 'Summer Black'.

• Korean Journal of Agricultural Science
• /
• v.34 no.1
• /
• pp.37-46
• /
• 2007

This study was conducted to investigate the antler induction rate and production by artificial induction of antlerogenesis using $CaCl_2$ injection on both periosteum around area of horn development for the frontal bone of a female elk deer which do not have an antler. The results obtained from eleven deers for verifying effect of the female's antler induction on reproduction are as follows: The antler development induction by $CaCl_2$injection is higher on the treatments of 30 and 50% of $CaCl_2$ injection than those on the treatments of 15 %. The antler production is higher on the 30 % $CaCl_2$ injection than those of 15 and 50 % $CaCl_2$ injection. For 30 % $CaCl_2$ injection, the antler production is higher in 1.5 and 2.0 ml of % $CaCl_2$ injection than the other injection level. After the induction of antler development, the birth rate is not changed as of 75~100 %, while the regeneration rate of the antler which was not constant in approximately 45 % for five among eleven female deer. With these results, we assume that the injection concentration and amount of $CaCl_2$ injection are around 30 % and 1.5 and 2.0 ml level which can be not only most effective conditions for the antler induction rate and production, but also these conditions do not influence the reproduction during the period of the female elk's antler development induction.

• Korean Journal of Poultry Science
• /
• v.29 no.2
• /
• pp.101-108
• /
• 2002

An experiment was conducted to compare the influences of artificial zeolite(AZ) produced from fly ash and natural zeolite(NZ), those were supplemented into broiler diets, on performances, intestinal microbes and some blood chemistry for 5 wks. The experimental diets contained 21.5 and 19% CP fur starting and finishing period, respectively. The ME was 3,100 kcal/kg of feed in both starter and finisher diets. Three hundred twenty chicks were assigned to 5 treatments with 4 replicates and fed one of five experimental diets containing different levels of AZ or NZ ; 0% zeolite, 1.5% AZ, 3.0% AZ, 1.5% NZ, and 3.0% NZ. Weight gain, feed intake and feed conversion were measured with weekly basis. Blood cholesterol and intestinal microflora were analyzed at the end of the experiment. Weight gain of chicks fed with NZ tended to increase, but was not statistically different from other diet groups. However, the birds of fed with 3.0% AZ showed significant decrement of weight gain compared to that of control(P<0.05). No significant difference in feed intake was found among five treatment. Feed conversion was significantly improved in 3.0% NZ treatment relative to that of 3.0% AZ(P<0.05). There were no consistent differences in intestinal microbes between the control and zeolite groups. Blood cholesterol was significantly lower in 3.0% NZ treatments than the others(P<0.05). These results suggest that AZ can be added to broiler feeds less than 1.5% without any detrimental effects on chick performances.