• Journal of Intelligence and Information Systems
• /
• v.24 no.4
• /
• pp.111-136
• /
• 2018

In this paper, we propose a methodology to extract answer information about queries from various types of unstructured documents collected from multi-sources existing on web in order to expand knowledge base. The proposed methodology is divided into the following steps. 1) Collect relevant documents from Wikipedia, Naver encyclopedia, and Naver news sources for "subject-predicate" separated queries and classify the proper documents. 2) Determine whether the sentence is suitable for extracting information and derive the confidence. 3) Based on the predicate feature, extract the information in the proper sentence and derive the overall confidence of the information extraction result. In order to evaluate the performance of the information extraction system, we selected 400 queries from the artificial intelligence speaker of SK-Telecom. Compared with the baseline model, it is confirmed that it shows higher performance index than the existing model. The contribution of this study is that we develop a sequence tagging model based on bi-directional LSTM-CRF using the predicate feature of the query, with this we developed a robust model that can maintain high recall performance even in various types of unstructured documents collected from multiple sources. The problem of information extraction for knowledge base extension should take into account heterogeneous characteristics of source-specific document types. The proposed methodology proved to extract information effectively from various types of unstructured documents compared to the baseline model. There is a limitation in previous research that the performance is poor when extracting information about the document type that is different from the training data. In addition, this study can prevent unnecessary information extraction attempts from the documents that do not include the answer information through the process for predicting the suitability of information extraction of documents and sentences before the information extraction step. It is meaningful that we provided a method that precision performance can be maintained even in actual web environment. The information extraction problem for the knowledge base expansion has the characteristic that it can not guarantee whether the document includes the correct answer because it is aimed at the unstructured document existing in the real web. When the question answering is performed on a real web, previous machine reading comprehension studies has a limitation that it shows a low level of precision because it frequently attempts to extract an answer even in a document in which there is no correct answer. The policy that predicts the suitability of document and sentence information extraction is meaningful in that it contributes to maintaining the performance of information extraction even in real web environment. The limitations of this study and future research directions are as follows. First, it is a problem related to data preprocessing. In this study, the unit of knowledge extraction is classified through the morphological analysis based on the open source Konlpy python package, and the information extraction result can be improperly performed because morphological analysis is not performed properly. To enhance the performance of information extraction results, it is necessary to develop an advanced morpheme analyzer. Second, it is a problem of entity ambiguity. The information extraction system of this study can not distinguish the same name that has different intention. If several people with the same name appear in the news, the system may not extract information about the intended query. In future research, it is necessary to take measures to identify the person with the same name. Third, it is a problem of evaluation query data. In this study, we selected 400 of user queries collected from SK Telecom 's interactive artificial intelligent speaker to evaluate the performance of the information extraction system. n this study, we developed evaluation data set using 800 documents (400 questions * 7 articles per question (1 Wikipedia, 3 Naver encyclopedia, 3 Naver news) by judging whether a correct answer is included or not. To ensure the external validity of the study, it is desirable to use more queries to determine the performance of the system. This is a costly activity that must be done manually. Future research needs to evaluate the system for more queries. It is also necessary to develop a Korean benchmark data set of information extraction system for queries from multi-source web documents to build an environment that can evaluate the results more objectively.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.45 no.4
• /
• pp.9-21
• /
• 2008

In this paper, we propose a GNSS-based RF receiver, A high precision localization architecture, and a high sensitivity localization architecture in order to solve the satellite navigation system's problem mentioned above. The GNSS-based RF receiver model should have the structure to simultaneously receive both the conventional GPS and navigation information data of future-usable Galileo. As a result, it is constructed as the multi-band which can receive at the same time Ll band (1575.42MHz) of GPS and El band (1575.42MHz), E5A band (1207.1MHz), and E4B band (1176.45MHz) of Galileo This high precision localization architecture proposes a delay lock loop with the structure of Early_early code, Early_late code, Prompt code, Late_early code, and Late_late code other than Early code, Prompt code, and Late code which a previous delay lock loop structure has. As we suggest the delay lock loop structure of 1/4chips spacing, we successfully deal with the synchronization problem with the C/A code derived from inaccuracy of the signal received from the satellite navigation system. The synchronization problem with the C/A code causes an acquisition delay time problem of the vehicle navigation system and leads to performance reduction of the receiver. In addition, as this high sensitivity localization architecture is designed as an asymmetry structure using 20 correlators, maximizes reception amplification factor, and minimizes noise, it improves a reception rate. Satellite navigation system repeatedly transmits the same C/A code 20 times. Consequently, we propose a structure which can use all of the same C/A code. Since this has an adaptive structure and can limit(offer) the number of the correlator according to the nearby environment, it can reduce unnecessary delay time of the system. With the use of this structure, we can lower the acquisition delay time and guarantee the continuity of tracking.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.7
• /
• pp.271-278
• /
• 2021

As the current cyber attacks become more intelligent, the existing Intrusion Detection System is difficult for detecting intelligent attacks that deviate from the existing stored patterns. In an attempt to solve this, a model of a deep learning-based intrusion detection system that analyzes the pattern of intelligent attacks through data learning has emerged. Intrusion detection systems are divided into host-based and network-based depending on the installation location. Unlike network-based intrusion detection systems, host-based intrusion detection systems have the disadvantage of having to observe the inside and outside of the system as a whole. However, it has the advantage of being able to detect intrusions that cannot be detected by a network-based intrusion detection system. Therefore, in this study, we conducted a study on a host-based intrusion detection system. In order to evaluate and improve the performance of the host-based intrusion detection system model, we used the host-based Leipzig Intrusion Detection-Data Set (LID-DS) published in 2018. In the performance evaluation of the model using that data set, in order to confirm the similarity of each data and reconstructed to identify whether it is normal data or abnormal data, 1D vector data is converted to 3D image data. Also, the deep learning model has the drawback of having to re-learn every time a new cyber attack method is seen. In other words, it is not efficient because it takes a long time to learn a large amount of data. To solve this problem, this paper proposes the Siamese Convolutional Neural Network (Siamese-CNN) to use the Few-Shot Learning method that shows excellent performance by learning the little amount of data. Siamese-CNN determines whether the attacks are of the same type by the similarity score of each sample of cyber attacks converted into images. The accuracy was calculated using Few-Shot Learning technique, and the performance of Vanilla Convolutional Neural Network (Vanilla-CNN) and Siamese-CNN was compared to confirm the performance of Siamese-CNN. As a result of measuring Accuracy, Precision, Recall and F1-Score index, it was confirmed that the recall of the Siamese-CNN model proposed in this study was increased by about 6% from the Vanilla-CNN model.

• Journal of Bio-Environment Control
• /
• v.32 no.1
• /
• pp.8-14
• /
• 2023

This study was conducted to develop a precision automatic irrigation system in a nursery by considering the problems and improvements of manual and the conventional automatic irrigation system. The amount of irrigated water between the conventional automatic irrigation system and manual irrigation was 28.7 ± 4.4 g and 14.2 ± 4.3 g, respectively, and the coefficient of variation was less than 30%. However, the coefficient of variation of the conventional automatic irrigation system of 15%, was higher than that of manual irrigation of 30%. The irrigation test using the developed uniform irrigation system attached with the nozzle of a spray angle 80° and most highest uniformity was at height 600 mm. And coefficient of variation of the irrigation uniformity at the center part was within 20%, but irrigation amount of the edge part was lower 50% and over compared to the center part. As a result of a tomato grafting seedling cultivation test using the developed uniform irrigation system, the average plant height of seedling at the edge part was 28 mm but plant height at the center part was higher as 72 mm. Therefore, it was necessary to apply additional irrigation device at the edge part. The irrigation uniformity of the edge concentrated irrigation system was investigated that the irrigation amount of the edge part was irrigated by more than 50% compared with the center part, and coefficient of variation of the irrigation amount at the center part was less than 30%. As a result of a cucumber grafting seedling cultivation test using the edge concentrated irrigation system, the plant height of seedlings in the edge and central part of cultivation bed were 24% and 26%, respectively, so irrigation uniformity was higher then the uniform irrigation system. In order to improve the uniformity of seedlings, it is necessary to adjust the height of boom according to the growth of the seedling by installing a distance sensor in the overhead watering and boom irrigation system.

• Journal of Astronomy and Space Sciences
• /
• v.22 no.3
• /
• pp.329-352
• /
• 2005

Long term observations of full-disk Lyman-o irradiance have been made by the instruments on various satellites. In addition, several sounding rockets dating back to the 1950s and up through the present have measured the $Lyman-{\alpha}$ irradiance. Previous full disk $Lyman-{\alpha}$ images of the sun have been very interesting and useful scientifically, but have been only five-minute 'snapshots' obtained on sounding rocket flights. All of these observations to date have been snapshots, with no time resolution to observe changes in the chromospheric structure as a result of the evolving magnetic field, and its effect on the Lyman-o intensity. The $Lyman-{\alpha}$ Imaging Solar Telescope(LIST) can provide a unique opportunity for the study of the sun in the $Lyman-{\alpha}$ region with the high time and spatial resolution for the first time. Up to the 2nd year development, the preliminary design of the optics, mechanical structure and electronics system has been completed. Also the mechanical structure analysis, thermal analysis were performed and the material for the structure was chosen as a result of these analyses. And the test plan and the verification matrix were decided. The operation systems, technical and scientific operation, were studied and finally decided. Those are the technical operation, mechanical working modes for the observation and safety, the scientific operation and the process of the acquired data. The basic techniques acquired through the development of satellite based solar telescope are essential for the construction of space environment forecast system in the future. The techniques which we developed through this study, like mechanical, optical and data processing techniques, could be applied extensively not only to the process of the future production of flight models of this kind, but also to the related industries. Also, we can utilize the scientific achievements which are obtained throughout the project And these can be utilized to build a high resolution photometric detectors for military and commercial purposes. It is also believed that we will be able to apply several acquired techniques for the development of the Korean satellite projects in the future.

• Tunnel and Underground Space
• /
• v.31 no.5
• /
• pp.374-384
• /
• 2021

In this study, we propose a new approach for automatic fracture detection in CT scan images of rock specimens. This approach is built on top of two-stage object detection deep learning algorithm called Faster R-CNN with a major modification of using rotated bounding box. The use of rotated bounding box plays a key role in the future work to overcome several inherent difficulties of fracture segmentation relating to the heterogeneity of uninterested background (i.e., minerals) and the variation in size and shape of fracture. Comparing to the commonly used bounding box (i.e., axis-align bounding box), rotated bounding box shows a greater adaptability to fit with the elongated shape of fracture, such that minimizing the ratio of background within the bounding box. Besides, an additional benefit of rotated bounding box is that it can provide relative information on the orientation and length of fracture without the further segmentation and measurement step. To validate the applicability of the proposed approach, we train and test our approach with a number of CT image sets of fractured granite specimens with highly heterogeneous background and other rocks such as sandstone and shale. The result demonstrates that our approach can lead to the encouraging results on fracture detection with the mean average precision (mAP) up to 0.89 and also outperform the conventional approach in terms of background-to-object ratio within the bounding box.

• Journal of Bio-Environment Control
• /
• v.22 no.4
• /
• pp.341-348
• /
• 2013

Maintenance of adequate soil tension or content during the period of crop growth is necessary to support optimum plant growth and yields. A better understanding of soil tension and content for precision irrigation would allow optimal soil water condition to crops and minimize the adverse effects of water stress on crop growth and development. This research reports on a comparison of soil water tension and content variations in differently textured soils over time under drip irrigation using two different water management methods, i.e. pulse time and required water irrigation methods. The pulse time-based irrigation was performed by turning the solenoid valve on and off for preset times to allow the wetting front to disperse in root zone before additional water was applied. The required water estimation method was a new water control logic designed by Rural Development Administration that applies the amount of water required based on a conversion of the measured water tension into water content. The use of the pulse time irrigation method under drip irrigation at a high tension of -20 kPa and high temperatures over $30^{\circ}C$ was not successful at maintaining moisture tensions within an appropriate range of 5 kPa because the preset irrigation times used for water control could not compensate for the change in evapotranspiration during day and night. The response time and pattern of water contents for all of the tested soils measured with capacitance-based sensor probes were faster and more direct than those of water tensions measured with porous and ceramic cup-based tensiometers when water was applied, indicating water content would be a better control variable for automatic irrigation. The required water estimation-based irrigation method provided relatively stable control of moisture tension, even though somewhat lower tension values were obtained as compared to the target tension of -20 kPa, indicating that growers could expect to be effective in controlling low tensions ranging from -10 to -20 kPa with the required water estimation system.

• Korean Journal of Food Science and Technology
• /
• v.51 no.6
• /
• pp.517-523
• /
• 2019

In this study, we investigated antioxidant capacity of 20 strawberry extract using the DPPH and ABTS assay and HPLC-DAD validation method. The total polyphenolic and flavonoids contents of 20 strawberry extracts were 22.77-107.61 mg TAE/100 g FW and 17.58-44.12 mg QE/100 g FW. The Aiberry and Elie star showed the highest total polyphenol and flavonoid contents, respectively. The DPPH radical scavenging activity of what was 1540.6-1124.0 μmol TEAC/100 g FW and Derunoka showed the highest activity. The ABTS radical scavenging activity was 6352.3-4592.3 μmol TEAC/100 g FW and FA23 showed the highest activity. The HPLC-DAD method for the quantitation of ellagic acid results showed high linearity in various concentration ranges, and the limit of detection was 2.35 μg/mL. The limit of quantification was 7.12 μg/mL. Relative standard deviation values from intra-and inter-day precision were less than 5.31%. Recovery rate at 10, 50, and 100 μg/mL, respectively, were 100.0-101.0% with relative standard deviation (RSD) values less than 5.30%. These results provide viable information for the validation of antioxidant capacity in strawberry fruits.

• Journal of Bio-Environment Control
• /
• v.18 no.4
• /
• pp.309-315
• /
• 2009

Maintenance of adequate soil water content during the period of crop growth is necessary to support optimum plant growth and yields. A better understanding of soil water movement for precision irrigation would allow efficient supply of water to crops, thereby resulting in minimization of water drainage and contamination of ground water. This research reports on the characterization of spatial and temporal variations in water contents through three different textured soils, such as loam, sandy loam, and loamy sand, when water is applied on the soil surface using an one-line drip irrigation system and the soils are dried after the irrigation stops, respectively. Water contents through each soil profile were continuously monitored using three Sentek probes, each consisting of three capacitance sensors at 10, 20, and 30cm depths. Spatial variability in water content for each soil type was strongly influenced by soil textural class. There were big differences in wetting pattern and the rate of downward movement between loam and sandy loam soils, showing that the loam soil had a wider wetting pattern and a slower rate of downward movement than did the sandy loam soil. The wetting pattern in loamy sand soil was not apparent due to a low variability in water content (< 10%) by a lower-water holding capacity as compared to those measured in the loam and sandy loam soils, implying that the rate of water drainage below a depth of 30cm was high. When soils were dried, there were highly exponential relationships between water content and time elapsed after irrigation stops ($r^2$${\geq}$0.98). It was estimated that equilibrium moisture contents for loam, sandy loam, and loamy sand soils would be 17.6%, 6.2%, and 4.2%, respectively.

• Journal of Korea Water Resources Association
• /
• v.51 no.10
• /
• pp.863-874
• /
• 2018

The purpose of this study is to evaluate the future climate change impact on stream aquatic ecology health of Han River watershed ($34,148km^2$) using SWAT (Soil and Water Assessment Tool) and random forest. The 8 years (2008~2015) spring (April to June) Aquatic ecology Health Indices (AHI) such as Trophic Diatom Index (TDI), Benthic Macroinvertebrate Index (BMI) and Fish Assessment Index (FAI) scored (0~100) and graded (A~E) by NIER (National Institute of Environmental Research) were used. The 8 years NIER indices with the water quality (T-N, $NH_4$, $NO_3$, T-P, $PO_4$) showed that the deviation of AHI score is large when the concentration of water quality is low, and AHI score had negative correlation when the concentration is high. By using random forest, one of the Machine Learning techniques for classification analysis, the classification results for the 3 indices grade showed that all of precision, recall, and f1-score were above 0.81. The future SWAT hydrology and water quality results under HadGEM3-RA RCP 4.5 and 8.5 scenarios of Korea Meteorological Administration (KMA) showed that the future nitrogen-related water quality in watershed average increased up to 43.2% by the baseflow increase effect and the phosphorus-related water quality decreased up to 18.9% by the surface runoff decrease effect. The future FAI and BMI showed a little better Index grade while the future TDI showed a little worse index grade. We can infer that the future TDI is more sensitive to nitrogen-related water quality and the future FAI and BMI are responded to phosphorus-related water quality.