• The Journal of the Convergence on Culture Technology
• /
• v.8 no.5
• /
• pp.535-539
• /
• 2022

This study analyzed the efficient hose loading method for indoor fire hydrants, and the experimental results are as follows. An effective fire hose loading method is to be derived through an experiment comparing the fire hose loading method of an indoor fire hydrant and the speed of fire suppression. When the fire hose was loaded by folding, it took an average of 33 seconds to load the fire hose, and for the hangyeopsal, it took an average of 69 seconds to load the fire hose, showing a significant difference. First, in the folding hose deployment experiment, subjects A, C, D, and E showed similar values from 34 seconds to 37 seconds, respectively. The reason seems to be the result of the fact that the fire hose was not twisted when unfolding, and that it was possible to deploy the hose smoothly. Subject B showed the lowest deployment time at 25 seconds, which seems to be the result of B's experience in deploying the fire hose. Second, in the hose unfolding experiment, subjects A, B, C, and E had a similar time period of 44 to 76 seconds, respectively. However, the test subject D was significantly higher at 110 seconds. The reason is that the attempt to prevent hose kinking when deploying the fire hose and the unstable psychological state through tension are judged to increase the fire hose deployment time.

• Journal of the Korean Society for information Management
• /
• v.39 no.3
• /
• pp.165-193
• /
• 2022

It can be said that digital technology is at the center of the change in the modern work environment. In particular, in general public institutions that prove their work with records produced by business management systems and document production systems, the record management system is also the work environment itself. Gimpo City applied for the 2021 public cloud leading project of the National Information Society Agency (NIA) to proactively respond to the 4th industrial revolution technology era and implemented a public cloud-based AI-OCR technology enhancement project with 330 million won in support of 330 million won. Through this, it was converted into data beyond the limitations of non-electronic records limited to search and image viewing that depend on standardized index values. In addition, a 98% recognition rate was realized by applying a new technology called AI-OCR. Since digital technology has been used to improve work efficiency, productivity, development cost, and record management service levels of internal and external users, we would like to share the direction of enhancing expertise in the record management and implementation of work environment innovation.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.10
• /
• pp.29-41
• /
• 2022

Recently, with the development of deep learning technology, a variety of huge models with excellent performance have been devised by pre-training massive amounts of text data. However, in order for such a model to be applied to real-life services, the inference speed must be fast and the amount of computation must be low, so the technology for model compression is attracting attention. Knowledge distillation, a representative model compression, is attracting attention as it can be used in a variety of ways as a method of transferring the knowledge already learned by the teacher model to a relatively small-sized student model. However, knowledge distillation has a limitation in that it is difficult to solve problems with low similarity to previously learned data because only knowledge necessary for solving a given problem is learned in a teacher model and knowledge distillation to a student model is performed from the same point of view. Therefore, we propose a heterogeneous knowledge distillation method in which the teacher model learns a higher-level concept rather than the knowledge required for the task that the student model needs to solve, and the teacher model distills this knowledge to the student model. In addition, through classification experiments on about 18,000 documents, we confirmed that the heterogeneous knowledge distillation method showed superior performance in all aspects of learning efficiency and accuracy compared to the traditional knowledge distillation.

• Korean Journal of Plant Resources
• /
• v.35 no.4
• /
• pp.502-507
• /
• 2022

In the present study, plant regeneration through adventitious shoot formation from hypocotyl segments of in vitro seedlings of groundcherry (Physalis angulata L.) was investigated to determine the optimum culture conditions for highly efficient regeneration of the species. Adventitious shoots in hypocotyl segments were efficiently induced on MS media with low concentrations of BAP, specifically, with 0.5-1.0 mg/L BAP singly or in combination with 0.1-0.5 mg/L NAA. The 1.0 mg/L BAP single treatment was most effective for forming multiple adventitious shoots. When the induced shoots were transferred to the root induction media, low concentrations of NAA, IBA, and IAA enhanced the development of adventitious roots from adventitious shoots, suggesting that low concentrations of auxins were optimal for producing regenerated plantlets. The number of roots per shoot was large (> 2.0), and the root length exceeded 8.0 cm. In particular, the development and the overall shape of the roots were ideal. Furthermore, the number and length of shoots exceeded 2 and 6.0 cm, respectively. When the regenerated plantlets were transferred to compost soil, the root and shoot systems had developed well to the point that all of the regenerated plantlets acclimated successfully, resulting in normal morphology and growth characteristics, similar to those of the mother plant. Therefore, plant regeneration via adventitious shoot formation is expected to be one of the main methods for producing groundcherry on a large scale for a stable supply of the raw materials.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.8
• /
• pp.339-346
• /
• 2022

Recently, the resource depletion and climate change problem caused by the massive usage of fossil fuels for electric power generation has become a critical issue worldwide. According to this issue, interest in renewable energy resources that can replace fossil fuels is increasing. Especially, photovoltaic power has gaining much attention because there is no risk of resource exhaustion compared to other energy resources and there are low restrictions on installation of photovoltaic system. In order to use the power generated by the photovoltaic system efficiently, a more accurate photovoltaic power forecasting model is required. So far, even though many machine learning and deep learning-based photovoltaic power forecasting models have been proposed, they showed limited success in terms of interpretability. Deep learning-based forecasting models have the disadvantage of being difficult to explain how the forecasting results are derived. To solve this problem, many studies are being conducted on explainable artificial intelligence technique. The reliability of the model can be secured if it is possible to interpret how the model derives the results. Also, the model can be improved to increase the forecasting accuracy based on the analysis results. Therefore, in this paper, we propose an explainable photovoltaic power forecasting scheme based on BiLSTM (Bidirectional Long Short-Term Memory) and SHAP (SHapley Additive exPlanations).

• Journal of Aerospace System Engineering
• /
• v.16 no.5
• /
• pp.62-69
• /
• 2022

EHA (Electro-Hydrostatic Actuator) is more energy efficiency than a centralized hydraulic system. In particular, the EHA used for aircraft has a redundant design in preparation for failure scenario. Also, due to the aircraft's internal space limitation, the actuator's length must be optimized. Therefore, a series configuration of double rod and single rod cylinder is advantageous. However, due to the asymmetry of the cross-sectional area of the piston, the force fighting phenomenon between the two cylinder areas occurs during redundant operation with a general control system. In this paper, the force fighting phenomenon of redundant EHA was simulated. A controller with load compensation and a force control-based position controller as a method to suppress its stimulation

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.42 no.6
• /
• pp.790-799
• /
• 1997

Aegilops genus is known to include the donor species of the Band D genome of the bread wheat(ABD). An effort to establish a better strategy for phylogenetic relationships about Aegilops polyploids by AFLPs(Amplified Fragment Length Polymorphisms) was conducted using the 19 Aegilops sPP. and T. aestivum. The 207 polymorphic bands from the amplified products on the 6% acrylamide denaturing sequencing gels were obtained with the 7 AFLP primer combinations, and used to account for the genetic similarities and cluster analysis using NTSYS program. According to the genome analysis, the $M^h$-genome of Ae. heldreichii was estimated as an intermediate genome between the M-genome of Ae. comosa and N-genome of Ae. uniaristata and supposed to be incorporated in the establishing process of UM-genome as a possible diploid donor. And Ae. ventricosa(DN) was more close to Ae. umbellulata(U) than Ae. squarrosa(D). The close relationship between Ae. squarrosa and T. aestivum was perceived as a diploid donor of D-genome. As for the polyploid species, hexaploid Ae. triaristata was more closely related to Ae. columnaris rather than tetraploid Ae. triaristata. The clustered groups were, basically same to the previous Gihara's sections based on phenotypes and pairing analysis of interspecific hybrids. AFLP was evaluated as an efficient and powerful method in the genome evaluation of closely related species.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.35 no.4
• /
• pp.320-327
• /
• 1990

Experiments were conducted to investigate the method to raise seedling establishment rate and the optimum seeding dates and rates in direct seeding culture using transplanter under submerged field condition in Chuncheon area during 1986 to 1988. Direct seeding on submerged field using transplanting machine after sowing on seedling growing box contained with paddy or upland soil was possible. Higher rate of seedling establishment was obtained in case of sowing sprouted seed and intermittent irrigation after sowing. Seedling establishment rate was higher both in April 30 or May 10 seeding plot. Minimum daily average air and soil temperature to ensure more than 70 percent seedling establishment was 14.8$^{\circ}C$ and 16.3$^{\circ}C$ respectively. Optimum sowing date in the direct sowing was early May and optimum sowing rate was 200g per box, 6kg per l0a. In this case rice grain yield was 481kg per l0a and this is almost same yield level compared hand and machine transplanting.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.39 no.1
• /
• pp.55-62
• /
• 1994

The germplasms of naked barley evaluated for starch content were 137 crossing blacks and progeny lines obtained from the breeding program of the Wheat and Barley Research Institute, 540 Tabdong Kwonsungu Suwon, in the 1988/1989 season. Starch content was distributed between 49.15 and 62.50% with a mean of 57.20%. It was high in the bred lines and the Uz type lines than the imported, uz type or lax type ones. The range observed for seed coat weight was 1.12-3.02mg and the mean seed coat weight was 1.88mg. The seed coat weight ratio to kernel weight was measured between 4.0 and 8.7% with a mean of 6.5%. The varieties differ greatly in the characteristics depending on the plant type and origin of germplasms. The variation observed with protein content ranged from 9.60 to. 15.90% while the average was 12.86%. Starch content was negative relationships with kernel weight, seed coat weight, seed coat weight ratio., kernel width, kernel thickness and protein content, and starch content was higher in smaller kernels within a variety. The weight and weight ratio. of seed coat were positively correlated with the width, thick-ness of kernels, whilst they were negatively correlated with starch content. The heritability of starch content was 30.0%.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.40 no.6
• /
• pp.716-722
• /
• 1995

Near Infrared Reflectance Spectroscopy (NIRS) has been used as a tool for the rapid, accurate and nondestructive assay of small grain and forage quality analysis. The objective of this study was to establish the rapid, easy and accurate analysis method for major components of covered barley using NIRS system. NIRS used in this study was filter type instrument, Neotec 102. To obtain a useful calibration equation, standard regression between the data was analyzed by chemical analysis and by NIRS method. Standard errors of prediction (SEP) and simple correlations for unknown samples were calculated using obtained equation. SEPs for starch, $\beta$-glucan, protein and ash contents were 2.75%, 0.64%, 0.26% and 0.19%, respectively. The simple correlations for starch, $\beta$-glucan, protein and ash contents were 0.932, 0.588, 0.984 and 0.867, respectively. It was concluded that the NIRS method would be applicabl for the rapid determination of starch, protein and ash contents in barley grains.