• Research in Plant Disease
• /
• v.26 no.4
• /
• pp.229-238
• /
• 2020

Field validation of PBcast, an infection risk model for Phytophthora blight of pepper, was conducted through a designed field experiment in 2012 and 2013. Conduciveness of weather conditions at 26 locations in Korea in 2014-2017 was also evaluated using PBcast. The PBcast estimated daily infection risk (IR) of Phytophthora capsici based on weather and soil texture data. In the designed filed experiment, four treatments including routine sprays at 7-day intervals (RTN7), forecast-based sprays when IR reached 200 (IR200) and 224 (IR224), and no spray (CTRL) were compared in terms of disease incidence and number of sprays recommended for disease control. In 2012, IR had reached over 200 twice, but never reached 224. In 2013, IR had reached over 200 three times and once higher than 224. The RTN7 plots were sprayed 17 and 18 times in 2012 and 2013, respectively. Weather conditions throughout the country were generally conducive for Phytophthora blight and 3-4 times of fungicide sprays would have been reduced if the PBcast forecast information was adopted in the decision-making for fungicide sprays. In conclusion, the PBcast forecast would be useful to reduce fungicide applications without losing the disease control efficacy to protect pepper crop from Phytophthora blight.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.6
• /
• pp.67-74
• /
• 2021

Ground Operations Command (GOC) has studied various methods using artificial intelligence (AI) in order to accomplish ground missions more effectively and to strongly respond to variable strategic situations with advancements in fourth industrial revolution technology. As the result of various literature reviews, PEST-7S-SWOT is considered the most appropriate methodology for promoting strategies and for task development. These procedures consist of three stages. Phase 1 is analysis of external environmental factors from applying PEST procedures. We analyzed external environmental factors to determine opportunities and risk factors. Phase 2 is the analysis of internal environmental factors from applying 7S strategies. We analyzed the current state of an organization to find strengths and weaknesses. Phase 3 is SWOT analysis. It is based on the opportunities and risk factors from Phase 1 and the strength and weakness factors from Phase 2. We derive promotional strategies and tasks through SWOT analysis. In this study, four strategies and 11 tasks were derived for GOC AI systems. Those are promotion of policies and systems, reinforcing organizations, building an AI base, increasing expertise and capabilities, and validating PEST-7S-SWOT methodologies.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.6
• /
• pp.332-340
• /
• 2021

The purpose of this study was to present a method for the application of drones through analysis after surveying Jeollanam-do firefighters regarding the recognition, operation, field of application, necessary field of work, and the need for education on fire drones. As a result of the survey, 80.29% of respondents were found to be willing to operate drones, and the fields of work for which drones were considered the most necessary were in the order of rescue, fire suppression, life safety, first aid, and others. Besides, 77.38% of respondents thought that drones could contribute to the prevention of safety accidents for firefighters, and 70.13% of respondents thought that it would be appropriate to recruit firefighting drone operators through changing positions, and respondents chose firefighters in their 40s as the most suitable age group for firefighting drone operation. Also, 82.84% of respondents said they would participate in drone training, and they recognized that the use of drones could contribute to solving the physical problems caused by the aging of firefighters, and that drone training would also help firefighters manage their retirement. The fields where firefighting drones are used were investigated in the order of searching for requestors, checking on-site information, and checking on-site prior risk. In this study, a difference analysis for each group was performed according to the drone operation experience. There was a statistically significant difference in the items of safety measures for requestors. The results of variance analysis by work experience confirmed that there were statistically significant differences in a total of eight items, including four items related to the field of use of drones, and the age group of the drone operating crew, and whether or not to help retirement management.

• Journal of Korean Society of Forest Science
• /
• v.100 no.1
• /
• pp.62-69
• /
• 2011

Six commonly used non-linear growth functions were fitted to individual tree height-dbh data of eight major tree species measured by the $5^{th}$ National Forest Inventory in Chungcheong province. A total of 2,681 trees were collected from permanent sample plots across Chungcheong province. The available data for each species were randomly splitted into two sets: the majority (90%) was used to estimate model parameters and the remaining data (10%) were reserved to validate the models. The performance of the models was compared and evaluated by $R^2$, RMSE, mean difference (MD), absolute mean difference (AMD) and mean difference(MD) for diameter classes. The combined data (100%) were used for final model fitting. The results showed that these six sigmoidal models were able to capture the height-diameter relationships and fit the data equally well, but produced different asymptote estimates. Sigmoidal growth models such as Chapman-Richards, Weibull functions provided the most satisfactory height predictions. The effect of model performance on stem volume estimation was also investigated. Tree volumes of different species were computed by the Forest Resources Evaluation and Prediction Program using observed range of diameter and the predicted tree total height from the six models. For trees with diameter less than 30 cm, the six height-dbh models produced very similar results for all species, while more differentiation among the models was observed for large-sized trees.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.15 no.6
• /
• pp.1089-1098
• /
• 2020

In this study, we propose a method to detect red tide Cochlodinium Polykrikoide using by machine learning and geostationary marine satellite images. To learn the machine learning model, GOCI Level 2 data were used, and the red tide location data of the National Fisheries Research and Development Institute was used. The machine learning model used logistic regression model, decision tree model, and random forest model. As a result of the performance evaluation, compared to the traditional GOCI image-based red tide detection algorithm without machine learning (Son et al., 2012) (75%), it was confirmed that the accuracy was improved by about 13~22%p (88~98%). In addition, as a result of comparing and analyzing the detection performance between machine learning models, the random forest model (98%) showed the highest detection accuracy.It is believed that this machine learning-based red tide detection algorithm can be used to detect red tide early in the future and track and monitor its movement and spread.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.15 no.6
• /
• pp.1201-1208
• /
• 2020

A mass of seawater with similar properties in the ocean is called a water mass, and the front is a sea area where two masses of different properties meet. The gradient algorithm is a method of extracting where the sea water temperature pixel changes rapidly assuming that the slope is large, and the place with the large slope is assumed to be a front. This method is able to process large amounts of satellite data at once. Therefore, in this study, we tried to find the front lines in the sea area around the Korean Peninsula by using a gradient algorithm. The study data used gridded sea surface temperature satellite data. The resolution was 1/4°, and the monthly average data from January 1993 to December 2018 were used. There were major five fronts representatively, China Coastal Front, South Sea Coastal Front, Kuroshio Front/ Kuroshio Extension Front, Subpolar Front and the Subarctic Front. As a result of comparing the distribution of front by season, more types of front were distributed in winter and spring than in summer and autumn, and the distribution range was wider.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.19 no.6
• /
• pp.49-60
• /
• 2020

The number of traffic control equipment installed to prevent traffic accidents increases every year due to continuous installation by the National Police Agency and local governments. However, it is installed based on qualitative judgment rather than engineering analysis results. The purpose of this study was to present additional installations in the future by presenting the installation criteria considering the severity of accidents for each road type and calculating the appropriate number of installations. ARI indicators that can indicate the severity of traffic accidents were developed, and road types were classified through analysis of variance and cluster analysis, and accident information by road type was analyzed to derive ARI of clusters with high traffic accident severity. The ARI values required to determine the installation of equipment for each road type were presented, and 5,244 additional installation points were analyzed.

• Journal of Convergence for Information Technology
• /
• v.11 no.6
• /
• pp.120-130
• /
• 2021

This study was conducted for the purpose of developing an education program using smart apps that supports free play of children based on STEAM education and verifying its effectiveness. In order to achieve the purpose of the study, contents for using smart apps based on STEAM education for children's free play were derived through literature and data collection and field surveys in related fields, and a program was developed based on this. This program is a teaching strategy in which teachers and children interact at the start, middle, and end of free play using the 'Free Play' app installed on a smartphone. An experimental study was conducted to verify the effectiveness of the program using smart apps that support children's free play. As a result of the study, it was confirmed that the application of this program improves the self-regulation of children. This study is a teaching strategy to support both teachers and children during free play time, the core of early childhood education, and developed and applied the program with the idea of convergence of engineering and education, and hopes that it will be a starting point for revitalizing education using smart apps in the future education field.

• Imaging Science in Dentistry
• /
• v.51 no.2
• /
• pp.117-127
• /
• 2021

Purpose: The aim of this study was to evaluate the volumetric characteristics of mucous retention cysts(MRCs) in the maxillary sinus and to analyze potential associations of MRCs with dentoalveolar pathologies. Materials and Methods: Cone-beam computed tomography (CBCT) scans exhibiting bilateral maxillary sinuses that were acquired from January 2016 to February 2019 were initially screened. A total of 227 scans(454 sinuses) that fulfilled the inclusion criteria were included. The presence, location, and volumetric characteristics of the diagnosed MRCs were evaluated on CBCT images using the 3D-Slicer software platform. The presence of MRCs was correlated with potential influencing factors including age, sex, and dentoalveolar pathology. For MRCs located on the sinus floor, factors with a potential impact on the volume, surface, and diameter were analyzed. Results: An MRC was present in 130 (28.6%) of the 454 sinuses. Most MRCs were located on the sinus walls and floor. The mean MRC volume, surface, and diameter were 551.21±1368.04 mm³, 228.09±437.56 mm², and 9.63±5.40 mm, respectively. Significantly more sinuses with associated endodontically treated teeth/periapical lesions were diagnosed with an MRC located on the sinus floor. For MRCs located on the sinus floor, endodontic status exhibited a significant association with increased volume, surface, and diameter. Conclusion: Periapical lesions might be a contributing factor associated with the presence and volume of MRCs located on the sinus floor. The 3D-Slicer software platform was found to be a useful tool for clinicians to analyze the size of MRCs before surgical interventions such as sinus floor elevation procedures.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.3
• /
• pp.99-108
• /
• 2021

There are unrestricted conditions on the driver's face inside the vehicle, such as changes in lighting, partial occlusion and various changes in the driver's condition. In this paper, we propose a face identification system in an unrestricted vehicle environment. The proposed method uses a near-infrared (NIR) camera to minimize the changes in facial images that occur according to the illumination changes inside and outside the vehicle. In order to process a face exposed to extreme light, the normal face image is changed to a simulated overexposed image using mean and variance for training. Thus, facial classifiers are simultaneously generated under both normal and extreme illumination conditions. Our method identifies a face by detecting facial landmarks and aggregating the confidence score of each landmark for the final decision. In particular, the performance improvement is the highest in the class where the driver wears glasses or sunglasses, owing to the robustness to partial occlusions by recognizing each landmark. We can recognize the driver by using the scores of remaining visible landmarks. We also propose a novel robust rejection and a new evaluation method, which considers the relations between registered and unregistered drivers. The experimental results on our dataset, PolyU and ORL datasets demonstrate the effectiveness of the proposed method.