• Journal of KIISE
• /
• v.42 no.11
• /
• pp.1397-1403
• /
• 2015

A named entity(NE) dictionary is an important resource for the performance of NE recognition. However, it is not easy to construct a NE dictionary manually since human annotation is time consuming and labor-intensive. To save construction time and reduce human labor, we propose a semi-automatic system for the construction of a NE dictionary. The proposed system constructs a pseudo-document with Wiki-categories per NE class by using an active learning technique. Then, it calculates similarities between Wiki entries and pseudo-documents using the BM25 model, a well-known information retrieval model. Finally, it classifies each Wiki entry into NE classes based on similarities. In experiments with three different types of NE class sets, the proposed system showed high performance(macro-average F1-score of 0.9028 and micro-average F1-score 0.9554).

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.41 no.1
• /
• pp.115-122
• /
• 1996

One of the most laborious work in rice farming is transplanting of rice seedling which has been required preparation of nursery bed and care of seedling during one month period. In this research, direct seeding in dry paddy(DS) and direct seeding in wet paddy(WS) were practiced to compare with traditional transplanting(TP) in Suwon. Growth stages in direct seeding were delayed as its planting time was about 21 days later than those of TP. Heading stage of direct seeding at Suwon was delayed about 9 days as compared to transplanting culture. Rice yield was not different between the seeding practises. Working-hour saving was about 17％(DS) and 28％(WS). Production cost of direct seeding was decreased 20％(DS) and 32％(WS), respectively. Amount of rice production per a unit working-hour in direct seeding could increase 14％(DS) and 39％(WS) compared to that of TP, respectively. Therefore, direct seeding could save significantly working hour and production cost without reducing rice yield. WS was more effective than DS in saving labor and production cost. Direct seeding was not efficient method in input of farming energy and agricultural chemicals.

• Journal of Biosystems Engineering
• /
• v.30 no.2 s.109
• /
• pp.81-88
• /
• 2005

Manual transplanting Chinese cabbage needs 184 hours per ha in Korea. Mechanization of Chinese cabbage transplanting operation has been highly required because it needs highly intensive labor during peak season. This study was conducted to developed walking-type Chinese cabbage transplanter. In order to find out design factor of the transplanter, a kinematic analysis software, RecurDyn, was used. The prototype was tested in the circular soil bin and its operating motion was captured and analyzed using high speed camera system. Prototype was one row type which utilized original parts of engine, transmission and etc. from walking-type rice transplanter in order to save the manufacturing cost. Success ratio of pick-up device of hole-pin type and latch type were $96.0\%$ and $99.2\%$, respectively. which was highly affected by feeding accuracy of feeding device of seedling. Transplanting device of the prototype produced a elliptic loci which were coincident with those produced by the computer simulation. Prototype proved good performance in transplanting with mulching and without mulching operation, either. Working performance of prototype was 22 hours per ha and operation cost of the prototype was 961,757 won per ha. So, it would reduce $88\%$ of the labor and $29\%$ of operation cost.

• Journal of Biosystems Engineering
• /
• v.37 no.2
• /
• pp.122-129
• /
• 2012

Purpose: Recent mechatronics technology is the most appropriate high technology in agricultural applications to save repetitious labor. Method: Cow's body parameters were measured by several traditional measurers. Image processing technology was used to measure automatically their parameters to reduce labor and time. The parameters were measured form a small model cow which is easily measured, instead to a real cow. The image processing system designed and built for this project was composed of a PC, grabber card, and two cameras, which are located on the side and the top of the model cow. Tests of verification had measured 10 dairy cows. Result: Nine parameters of the model cow's body were measured, and the difference between the real data and the data by image processing was less than 16.7%. Based on the results of the research, the parameters of a real cow had measured of chest depth, withers height, Pelvic arch height, body length, slope body length, chest width, hip width, thurl width, and pin bone width were compared with image processing data. Conclusions: In the Demonstration test, Result had obtained similar data of cow model experiments, and the most of errors were shown less than 5% relatively good result.

• Korean Journal of Medicinal Crop Science
• /
• v.28 no.2
• /
• pp.128-135
• /
• 2020

Background: Sowing seeds of Adenophora triphylla is known to be difficult owing to their small size and irregular seed shape. Therefore, this study was conducted to develop a seed pelleting technique to save labor during sowing. Methods and Results: To identify the optimal germination temperature for A. triphylla seeds, the temperature range was set from 17℃ to 32℃. Germination surveys were conducted in plastic greenhouse conditions in March, April, and May to determine the appropriate sowing time. The optimal germination temperature for A. triphylla seeds was 29℃ and May was the optimal sowing time in plastic greenhouse conditions. Covering materials for seed pelleting used talc (T), kaolin (K), calcium carbonate (C), and vermiculite (V). The pellet binder used agar (A), pectin, xanthan gum, polyvinyl alcohol (PVA), and sodium alginate (S). The best suited treatment mixture were the best suited in kaolin / calcium carbonate / vermiculite (KCV), talc / calcium carbonate / vermiculite (TCV) mixture treatment for covering material, and sodium alginate (S), agar (A) as pellet binder, respectively. The germination rate was the best in TCV mixed with S. Conclusion: The mixture of TCV (2 : 1 : 3) + 1.5% S (TCVS), was found to be the best pelleting materials for A. triphylla seeds, and seed pelleting can be labor-saving during sowing.

• Korean Journal of Agricultural Science
• /
• v.49 no.3
• /
• pp.619-627
• /
• 2022

In Korea, apples and pears are among the most important agricultural products to farmers who seek to earn money as income. Generally, farmers make decisions at various stages to maximize their income but they do not always know exactly which option will be the best one. Many previous studies were conducted to solve this problem by predicting farmers' income structure, but researchers are still exploring better approaches. Currently, machine learning technology is gaining attention as one of the new approaches for farmers' income prediction. The machine learning technique is a methodology using an algorithm that can learn independently through data. As the level of computer science develops, the performance of machine learning techniques is also improving. The purpose of this study is to predict the income structure of apples and pears using the automatic machine learning solution H2O.AI and to present some implications for apple and pear farmers. The automatic machine learning solution H2O.AI can save time and effort compared to the conventional machine learning techniques such as scikit-learn, because it works automatically to find the best solution. As a result of this research, the following findings are obtained. First, apple farmers should increase their gross income to maximize their income, instead of reducing the cost of growing apples. In particular, apple farmers mainly have to increase production in order to obtain more gross income. As a second-best option, apple farmers should decrease labor and other costs. Second, pear farmers also should increase their gross income to maximize their income but they have to increase the price of pears rather than increasing the production of pears. As a second-best option, pear farmers can decrease labor and other costs.

• Journal of the Korean Society of Industry Convergence
• /
• v.25 no.3
• /
• pp.349-356
• /
• 2022

Currently, the agricultural population in Korea indicates a decreasing and aging orientation. As the population of farm labor continues to decline, so farmers are feeling the pressure to be stable crop production. To solve the problem caused by the decreasing of farm labor, it is necessary to change over to "Digital agriculture". Digital agriculture is tools that digitally collect, store, analyze, and share electronic data and/or information in agriculture, and aims to integrate the several digital technologies into crop and livestock management and other processes in agriculture fields. In addition, digital agriculture can offer the opportunity to increase crop production, save costs for farmer. Therefore, in this study, for data-based Digital Agriculture, a greenhouse environment monitoring system for crop growth monitoring based on Node-RED, which even beginners can use easily, was developed, and the implemented system was verified in a hydroponic greenhouse. Several sensors, such as temperature, humidity, atmospheric pressure, CO₂, solar radiation, were used to obtain the environmental data of the greenhouse. And the environmental data were processed and visualized using Node-RED and MariaDB installed in rule.box digital. The environment monitoring system proposed in this study was installed in a hydroponic greenhouse and obtained the environmental data for almost two weeks. As a result, it was confirmed that all environmental data were obtained without data loss from sensors. In addition, the dashboard provides the names of installed sensors, real time environmental data, and changes in the last three days for each environmental data. Therefore, it is considered that farmers will be able to easily monitor the greenhouse environment using the developed system in this study.

• Fibers and Polymers
• /
• v.2 no.3
• /
• pp.164-170
• /
• 2001

Authors studied on the applicability of image analysis technique using a scanner with a CCD (charged coupled deviced) to the evaluation of evenness of nonwovens because it has distinctive features to considerably save time and labor in the analysis compared with other classical methods. As specimens fur the experiment, two different types that are unpatterned and patterned ones were prepared. For the unpatterned specimen, webs were chemically bonded, while for the patterned specimen, webs being thermally calendered with engraved roller. Several webs having various areal densities were prepared and bonded. Coefficient of variation (CV%) was used as a parameter to evaluate the evenness. Scanning conditions could be suitably set up through comparing the total variance to the between-group variance and to the within-group variance, respectively, on the images scanned at the different conditions. The 2D convolution method with smoothing filter kernel was introduced to further filter the noises on the scanned images. After the filtering process, the increase of web areal densities gave an uniform decrease of the CV%. This showed that the scanned image analysis with proper filtering process could be successfully applicable to the evaluation of evenness in nonwovens.

• Journal of Institute of Control, Robotics and Systems
• /
• v.11 no.6
• /
• pp.558-563
• /
• 2005

In this paper, we implemented a web-based virtual laboratory system(VLab system) with creative and interactive multimedia contents, which can be used to enhance the quality of education in the area of digital logic circuits. Since the proposed VLab system is implemented to describe the on-campus laboratory, the learners can obtain similar experimental data through it. Also, the VLab system is designed to increase the learning and teaching efficiencies of both the learners and the educators, respectively. The learners will be able to achieve high teaming standard and the educators save their time and labor. The virtual experiments on our VLab system are performed according to the following procedure: (1) Circuit composition on the virtual bread board (2). Applying input voltage (3) Output measurements (4) Checkout of experiment results. Furthermore, the circuit composition on the virtual bread board and its corresponding online schematic diagram are displayed together on the VLab system for the learner's convenience. Finally, we have obtained several affirmative effects such as reducing the total experimental hours and the damage rate for experimental equipments and increasing learning efficiencies as well as faculty productivity.

• Korean Journal of Soil Science and Fertilizer
• /
• v.46 no.6
• /
• pp.426-433
• /
• 2013

This study was aimed to classify soil desalination area for cultivation using NDVI (Normalized difference vegetation index) of high-resolution satellite image because the soil salinity affects the change of plant community in reclaimed lands. We measured the soil salinity and NDVI at 28 sites in the Saemangeum reclaimed land in June 2013. In halophyte and non-vegetation sites, no relation was found between NDVI and soil salinity. In glycophyte sites, however, we found that the soil salinity was below 0.1% and NDVI ranged from 0.11 to 0.57 which was greater than the other sites. So, we could distinguish the glycophyte sites from the halophyte sites and non-vegetation, and classify the area that soil salinty was below 0.1%. This technique could save the time and labor to measure the soil salinity in large area for agricultural utilization.