• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.38 no.6
• /
• pp.599-610
• /
• 2020

The AED (Automated External Defibrillator) is not evaluated for spatial accuracy and temporal availability even if it is located within a building or a specific area that needed necessary to partition by spatial analysis and location allocation analysis. As a result of the analysis, the spatial analysis was performed using the existing public data of AED with applied the GIS location analysis method. A public institution (119 safety center, police box) was selected as a candidate for a public AED base that can operate 24 hours a day, 365 days a year according to the characteristics of each residential area. In addition, Thiessen Polygons were created for each candidate site and divided by regions. In the analysis of the service was analyzed regional in terms of accessibility to emergency medical services in consideration of the characteristics of AED, that emergency vehicles could arrive within 4 minutes of the time required for emergency medical treatment in most areas of the study area, but it did not areas outside of the city center. As a result, It was found that the operation of the AED base service center centered on vehicles of public institutions is effective for responding to AED patients at night and weekend hours. 19 Safety Center under and police box the jurisdiction of Daegu City to establish an AED service center for public institutions, location-based distance, attribute analysis, and minimization of overlapping areas that the method of using a vehicle appeared more efficient than using the existing walking type AED.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.20 no.1
• /
• pp.174-192
• /
• 2021

The LIDAR sensor, which provides higher cognitive performance than cameras and radar, is difficult to apply to ADAS or autonomous driving because of its high price. On the other hand, as the price is decreasing rapidly, expectations are rising to improve existing autonomous driving functions by taking advantage of the LIDAR sensor. In level 3 autonomous vehicles, when a dangerous situation in the cognitive module occurs due to a sensor defect or sensor limit, the driver must take control of the vehicle for manual driving. If the driver does not respond to the request, the system must automatically kick in and implement a minimum risk maneuver to maintain the risk within a tolerable level. In this study, based on this background, a LIDAR-based LKS MRM algorithm was developed for the case when the normal operation of LKS was not possible due to troubles in the cognitive system. From point cloud data collected by LIDAR, the algorithm generates the trajectory of the vehicle in front through object clustering and converts it to the target waypoints of its own. Hence, if the camera-based LKS is not operating normally, LIDAR-based path tracking control is performed as MRM. The HAZOP method was used to identify the risk sources in the LKS cognitive systems. B, and based on this, test scenarios were derived and used in the validation process by simulation. The simulation results indicated that the LIDAR-based LKS MRM algorithm of this study prevents lane departure in dangerous situations caused by various problems or difficulties in the LKS cognitive systems and could prevent possible traffic accidents.

• Journal of The Korean Association For Science Education
• /
• v.41 no.2
• /
• pp.83-92
• /
• 2021

The purpose of this study is to investigate elementary school students' understandings about scientific inquiry. Data were collected from 119 elementary students who are in the 4^th grade using the Views About Scientific Inquiry questionnaire for elementary students (VASI-E). We also conducted semi-structured interviews of 21 students from 119 students who responded to VASI-E. Students' responses were analyzed as naive, mixed, or informed views on each aspect of scientific inquiry that VASI-E includes. We found that, first, 53.8% of students have mixed views, and 30.3% of students have informed views, and 16% of students have naive views on the knowledge 'investigation begin with a question'. Second, 54.6% of students have naive views, 37.8% of students have mixed views, and 7.6% of students have informed views on the knowledge 'scientists use many methods to answer their questions.' Third, 47.9% of students have informed views, 34.5% of students have naive views, and 17.6% of students have mixed views on 'procedures guided by question asked.' Fourth, 55.5% of students have mixed views, 42% of students have informed views, and only 2.5% of students have naive views on 'conclusions must be consistent with data and explanations come from data and prior knowledge.' Based on the results, implications for teaching and learning scientific inquiry at elementary level in Korea were discussed.

• Geophysics and Geophysical Exploration
• /
• v.24 no.2
• /
• pp.53-66
• /
• 2021

Velocity model building is an essential procedure in seismic data processing. Conventional techniques, such as traveltime tomography or velocity analysis take longer computational time to predict a single velocity model and the quality of the inversion results is highly dependent on human expertise. Full-waveform inversions also depend on an accurate initial model. Recently, deep neural network techniques are gaining widespread acceptance due to an increase in their integration to solving complex and nonlinear problems. This study investigated cases of seismic velocity model building using deep neural network techniques by classifying items according to the neural networks used in each study. We also included cases of generating training synthetic velocity models. Deep neural networks automatically optimize model parameters by training neural networks from large amounts of data. Thus, less human interaction is involved in the quality of the inversion results compared to that of conventional techniques and the computational cost of predicting a single velocity model after training is negligible. Additionally, unlike full-waveform inversions, the initial velocity model is not required. Several studies have demonstrated that deep neural network techniques achieve outstanding performance not only in computational cost but also in inversion results. Based on the research results, we analyzed and discussed the characteristics of deep neural network techniques for building velocity models.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.2
• /
• pp.685-693
• /
• 2021

This study examined the fire risk of the region in Goyang City using the spatial information data of buildings. The economic damage by industry was assessed according to the probability of fire risk. The study area was confined to Goyang-si, Gyeonggi-do, and the same fire risk reduction rate was applied to each region for the convenience of analysis. The possibility of fire was derived based on the buildings' density and usage in the area by National GIS building-integrated information standard data. The calculation of economic damage by industry in Goyang City due to the fire risk was calculated by combining the Goyang-si industry-related model produced by matching with 30 industrial categories in Input-Output Statistics of Korea Bank and 20 industrial categories in the Goyang-si business survey and the possibility of fire. The basic scenario of production impossibility during six months and business loss due to fire was established and analyzed based on the supply model. The analysis showed that Ilsan-dong-gu, Ilsan-seo-gu, and Deokyang-gu suffered the most economic damage. The "electricity, gas, steam, and water business" showed the greatest loss by industry.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.24 no.1
• /
• pp.80-91
• /
• 2021

The purpose of this study is to present the applicability to the effective survey into the actual condition of lands such as analysis of occupied location of government owned lands based on orthoimages created from aerial photographs taken by UAV. The boundary point coordinates and areas of the parcels were observed respectively by VRS-GNSS surveying and orthoimages for each land use of two categories of land, i.e. building site and farmland. As a result of comparing boundary point coordinates and areas extracted from UAV orthoimages with VRS-GNSS surveying data which were used as reference data, the RMS error of the coordinates for the boundary points was ±0.074m for both X and Y in the building site, and ±0.150m and ±0.127m for the X and Y respectively in the farmland. The positional error of the boundary point was 1.7~ 2 times higher in the farmland than in the building site where the boundary points were relatively clear. The RMS error of ±8.964㎡ of areas in the farmland was 4.7 times higher than that of ±1.898㎡ of areas in the building site. The area errors of all 22 parcels measured from the orthoimage were found to be within the allowed error range, indicating that it is feasible to apply the orthoimage generated by UAV to survey of government owned lands in terms of accuracy.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.3
• /
• pp.13-23
• /
• 2022

In this study we leveraged a probing method to evaluate how a pre-trained L2 LSTM language model represents sentences with relative and coordinate clauses. The probing experiment employed adapted models based on the pre-trained L2 language models to trace the syntactic properties of sentence embedding vector representations. The dataset for probing was automatically generated using several templates related to different sentence structures. To classify the syntactic properties of sentences for each probing task, we measured the adaptation effects of the language models using syntactic priming. We performed linear mixed-effects model analyses to analyze the relation between adaptation effects in a complex statistical manner and reveal how the L2 language models represent syntactic features for English sentences. When the L2 language models were compared with the baseline L1 Gulordava language models, the analogous results were found for each probing task. In addition, it was confirmed that the L2 language models contain syntactic features of relative and coordinate clauses hierarchically in the sentence embedding representations.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.4
• /
• pp.169-178
• /
• 2022

Morphemes are most primitive units in a language that lose their original meaning when segmented into smaller parts. In Korean, a sentence is a sequence of eojeols (words) separated by spaces. Each eojeol comprises one or more morphemes. Korean morphological analysis (KMA) is to divide eojeols in a given Korean sentence into morpheme units. It also includes assigning appropriate part-of-speech(POS) tags to the resulting morphemes. KMA is one of the most important tasks in Korean natural language processing (NLP). Improving the performance of KMA is closely related to increasing performance of Korean NLP tasks. Recent research on KMA has begun to adopt the approach of machine translation (MT) models. MT is to convert a sequence (sentence) of units of one domain into a sequence (sentence) of units of another domain. Neural machine translation (NMT) stands for the approaches of MT that exploit neural network models. From a perspective of MT, KMA is to transform an input sequence of units belonging to the eojeol domain into a sequence of units in the morpheme domain. In this paper, we propose a deep learning model for KMA. The backbone of our model is based on the BERT-fused model which was shown to achieve high performance on NMT. The BERT-fused model utilizes Transformer, a representative model employed by NMT, and BERT which is a language representation model that has enabled a significant advance in NLP. The experimental results show that our model achieves 98.24 F1-Score.

• Journal of Practical Agriculture & Fisheries Research
• /
• v.23 no.2
• /
• pp.99-111
• /
• 2021

The connected farm that agricultural land, agricultural machinery and farmer are connected with an IoT gateway is in the commercialization stage. That has increased productivity, efficiency and profitability by intimate information exchange among those. In order to develop the educational program of intelligent agricultural machinery and the agricultural machinery safety education performance indicator, this study analyzed patent trends of agricultural machine with unmanned technology used in agriculture and efficiency technology applied advanced technologies such as ICT, robots and artificial intelligence. We investigated and analyzed patent trends in agricultural machinery of Korea, the USA and Japan as well as the countries in Europe. The United States is an advanced country in the field of unmanned technology and efficiency technology used in agriculture. Agricultural automation technology in Korea is insufficient compared to developed countries, which means rapid technological development is needed. In the sub-fields of field automation technology, path generation and following technology and working machine control technology through environmental awareness have activated.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.7
• /
• pp.273-282
• /
• 2022

Testing approaches for configurable software product lines differs significantly from a single software testing, as it requires consideration of common parts used by all member products of a product line and variable parts shared by some or a single product. Test coverage is a measure of the adequacy of testing performed. Test coverage measurements are important to evaluate the adequacy of testing at the software product line level, as there can be hundreds of member products produced from configurable software product lines. This paper proposes a method for measuring code coverage at the product line level in configurable software product lines. The proposed method tests the member products of a product line after hierarchizing member products based on the inclusion relationship of the selected features, and quantifies SPL(Software Product Line) test coverage by synthesizing the test coverage of each product. As a result of applying the proposed method to 11 configurable software product line cases, we confirmed that the proposed method could quantitatively visualize how thoroughly the SPL testing was performed to help verify the adequacy of the SPL testing. In addition, we could check whether the newly performed testing for a member product covers the newly added code parts of a feature.