• Tribology and Lubricants
• /
• v.37 no.2
• /
• pp.41-47
• /
• 2021

An experimental device was developed for analysis of hydraulic oil characteristics with dielectric constant sensors. Online analysis is the most effective method of the three methods used for analyzing lubricant oils. This is because it can monitor the machine condition effectively using oil sensors in real time without requiring excellent analysis skill and eliminates human errors. Determining the oil quality usually requires complex laboratory equipment for measuring factors such as density, viscosity, base number, acid number, water content, additive, and wear debris. However, the electric constant is another indicator of oil quality that can be measured on-site. The electric constant is the ratio of the capacitance of a capacitor using that material as a dielectric, compared with a similar capacitor that has a vacuum as its dielectric. The electric constant affects the factors such as the base oil, additive, temperature, electric field frequency, water content, and contaminants. In this study, the tendency of the electric constant is investigated with a variation of temperature, water content, and dust weight. The experimental device can control working temperature and mix the contaminants with oil. A machine condition monitoring program developed to analyze hydraulic oil is described. This program provides graph and digital values with variation of time. Moreover, it includes an alarm system for when the oil condition is bad.

• International Journal of Internet, Broadcasting and Communication
• /
• v.14 no.2
• /
• pp.55-62
• /
• 2022

A smart tourism chatbot is needed as a user interface to efficiently provide smart tourism services such as recommended travel products, tourist information, my travel itinerary, and tour guide service to tourists. We have been developed a smart tourism app and a smart tourism information system that provide smart tourism services to tourists. We also developed a smart tourism chatbot service consisting of khaiii morpheme analyzer, rule-based intention classification, and tourism information knowledge base using Neo4j graph database. In this paper, we develop the Korean and English smart tourism Name Entity (NE) datasets required for the development of the NER model using the pre-trained language models (PLMs) for the smart tourism chatbot system. We create the tourism information NER datasets by collecting source data through smart tourism app, visitJeju web of Jeju Tourism Organization (JTO), and web search, and preprocessing it using Korean and English tourism information Name Entity dictionaries. We perform training on the KoBERT-CRF NER model using the developed Korean and English tourism information NER datasets. The weight-averaged precision, recall, and f1 scores are 0.94, 0.92 and 0.94 on Korean and English tourism information NER datasets.

• Journal of Multimedia Information System
• /
• v.9 no.3
• /
• pp.177-182
• /
• 2022

A deep neural network (DNN) includes variables whose values keep on changing with the training process until it reaches the final point of convergence. These variables are the co-efficient of a polynomial expression to relate to the feature extraction process. In general, DNNs work in multiple 'dimensions' depending upon the number of channels and batches accounted for training. However, after the execution of feature extraction and before entering the SoftMax or other classifier, there is a conversion of features from multiple N-dimensions to a single vector form, where 'N' represents the number of activation channels. This usually happens in a Fully connected layer (FCL) or a dense layer. This reduced 2D feature is the subject of study for our analysis. For this, we have used the FCL, so the trained weights of this FCL will be used for the weight-class correlation analysis. The popular DNN models selected for our study are ResNet-101, VGG-19, and GoogleNet. These models' weights are directly used for fine-tuning (with all trained weights initially transferred) and scratch trained (with no weights transferred). Then the comparison is done by plotting the graph of feature distribution and the final FCL weights.

• Computers and Concrete
• /
• v.34 no.3
• /
• pp.355-365
• /
• 2024

TECSolverApp is an application that calculates the total equivalent seismic load (base shear) and shows the design spectra in accordance with the Turkish Earthquake Code (TEC). TECSolverApp software can present the spectral acceleration-period graph and the base shear (in terms of unit building weight) in MATLAB and .NET Core frameworks according to TEC 2007 and TEC 2018. In the software, three different building period evaluation options were provided, as entering the period directly, empirical calculation, and using the period calculation formula. In different period calculation scenarios, particular design input parameters such as site-specific spectral acceleration coefficients, local soil class, building importance coefficient, and structural system behavior coefficient are expected. TECSolverApp was produced in two different programming languages and published in MATLAB App Designer and ASP.NET Core MVC environments. To be shared in MATLAB App Designer, it was aimed at availability through the program and distributability as a desktop application. By deploying in ASP.NET Core MVC, open-source cross-platform coding and web-based accessibility were targeted. One of the strongest aspects of TECSolverApp is its developability thanks to software architecture. In this respect, it can be foreseen that other international seismic codes can be added to the calculations in the future.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.14 no.2
• /
• pp.168-174
• /
• 2021

According to the World Agricultural Productivity Report, the current annual average growth rate of agriculture is 1.63%, which is lower than 1.73% to support the world's 10 billion people, which is growing by 2050. The demand for food, feed, and bioenergy is not growing enough to continue to meet the demand, and it is predicting a future food shortage. The purpose of this study was to create a regional irrigation control model for the purpose of reducing the production cost of crops, increasing production, and improving quality, and presenting a model that can give advice to farmers who start farming in the region. The irrigation control modeling presented in this study means to represent the change of medium weight·supply liquid·drainage amount due to changes in the root zone environment according to the passage of time and climate in a graph model. For water control modeling, we collected data on the change in the amount of the root zone environment and the weight of the badge·supply amount·drainage amount from March to June in Nonsan, Buyeo, and Yesan regions in Chungnam Province through the measuring device of the Ministry of Environment in the root region. We set up the parameters for derivation and derived an irrigation control model that can confirm the change in weight·supply liquid·drainage amount over time through the parameters.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.47 no.6
• /
• pp.117-126
• /
• 2010

In the case of failure images with controlling lighting like backlighting and excessive frontlinghting, the compensation scheme for a specific area in an image is required. The interested region is first selected by user in our method to compensate the first frame. Then we define the matching function of brightness and energy function is proposed with weight of matching function and the relationship among the neighbors. Finally, the energy is minimized by the graph-cut algorithm to compensate the brightness of the first frame. Other frames are straightforwardly compensated using the results of the first frame. The brightness variations of the previous frame is transmitted to the next frame via motion vectors. The reliability of the brightness variation is calculated based on the motion vector reliability. Video compensation result is achieved by the process of the image case. Simulation show that the proposed algorithm provides more natural results than the conventional algorithms.

• Journal of the Korean Regional Science Association
• /
• v.33 no.1
• /
• pp.29-41
• /
• 2017

This study proposes an integrated accessibility measurement algorithm, which is applied to the Seoul Metropolitan public transportation system consisting of bus and subway networks, and analyzes the result. We construct a public transportation network graph linking bus-subway networks and take the time distance as the link weight in the graph. We develop a time-distance algorithm to measure the time distance between each pair of transit stations based on the T-card transaction database. The average travel time between nodes has been computed via the shortest-path algorithm applied to the time-distance matrix, which is obtained from the average speed of each transit route in the T-card transaction database. Here the walking time between nodes is also taken into account if walking is involved. The integrated time-distance accessibility of each node in the Seoul Metropolitan public transportation system has been computed from the T-card data of 2013. We make a comparison between the results and those of the bus system and of the subway system, and analyze the spatial patterns. This study is the first attempt to measure the integrated time-distance accessibility for the Seoul Metropolitan public transportation system consisting of 16,277 nodes with 600 bus routes and 16 subway lines.

• Journal of the Korean GEO-environmental Society
• /
• v.19 no.11
• /
• pp.5-14
• /
• 2018

Worldwide, soil compaction work is one of the most important activities that are carried out on civil engineering works sites. Compaction work, particularly in the area of road construction, is considered to be important, as poor compaction work is closely related with poor construction even after a construction is complete. Currently, the plate bearing test or the sand cone method relative to the unit weight of soil test are commonly used to measure the degree of compaction, but as these require a great deal of time, equipment and manpower, it is difficult to secure economic efficiency. The method that is used to measure the degree of compaction according to the penetration depth achieved by free fall objects through gravity is the Free-Fall Penetration Test (FFPT), which uses a so-called "portable compaction measuring meter (PCMM)." In this study, the degree of compaction was measured and a penetration depth graph was developed after the field test using the portable compaction measuring meter. The coefficient of determination was 0.963 at a drop height of 10 cm, showing the highest level of accuracy. Both horizontal axis and longitudinal axis were developed in a decimal form of graph, and the range of allowable error was ${\pm}1.28mm$ based on the penetration depth. The portable compaction measuring meter makes it possible to measure the degree of compaction simply, quickly and accurately in the field, which will ensure economic efficiency and facilitate the process management.

• Journal of the Korea Institute of Building Construction
• /
• v.21 no.6
• /
• pp.701-712
• /
• 2021

As the domestic housing supply problem has been resolved, the apartment construction market has shifted to a consumer-oriented market that wants high quality, and in particular, expectations in the area of finishing quality have increased. Looking at the status of complaints regarding apartment housing defects supplied by Korea Land and Housing Corporation, tile-related complaints are the type occurring the most frequently. While the Ministry of Land, Infrastructure and Transport(MOLIT) is making an ongoing effort to reduce complaints related to defects, through approaches such as drafting amendments to 「Investigation of defects in apartment houses, calculation of repair costs, and standards for determining defects」, the provision of preventive measures has been insufficient. In addition, by reviewing studies, there has been insufficient research to construct a classification system after deriving the characteristics of each type using the qualitative knowledge of experts, various quantitative indicators, and suggesting measures for reduction according to the causes of each type. Therefore, this study will reflect qualitative indicators to use the AHP analysis that makes it easy to identify the relationship between defects by surveying construction experts. Then, by visualizing the weight of 'Possibility of recurrence after repair,' 'Degree of difficulty in repairing defects' and 'Fault frequency' using a radial graph, we will analyze the characteristics of each type of tile construction defect and establish measures for reduction according to the cause. This will improve the quality of the living environment and contribute to the establishment of a system for smooth defect management and reduction of defects in apartment tile construction.

• Journal of Intelligence and Information Systems
• /
• v.27 no.4
• /
• pp.73-95
• /
• 2021

This study uses Node2vec graph embedding method and Light GBM link prediction to explore undeveloped export candidate countries in Korea's food and beverage industry. Node2vec is the method that improves the limit of the structural equivalence representation of the network, which is known to be relatively weak compared to the existing link prediction method based on the number of common neighbors of the network. Therefore, the method is known to show excellent performance in both community detection and structural equivalence of the network. The vector value obtained by embedding the network in this way operates under the condition of a constant length from an arbitrarily designated starting point node. Therefore, it has the advantage that it is easy to apply the sequence of nodes as an input value to the model for downstream tasks such as Logistic Regression, Support Vector Machine, and Random Forest. Based on these features of the Node2vec graph embedding method, this study applied the above method to the international trade information of the Korean food and beverage industry. Through this, we intend to contribute to creating the effect of extensive margin diversification in Korea in the global value chain relationship of the industry. The optimal predictive model derived from the results of this study recorded a precision of 0.95 and a recall of 0.79, and an F1 score of 0.86, showing excellent performance. This performance was shown to be superior to that of the binary classifier based on Logistic Regression set as the baseline model. In the baseline model, a precision of 0.95 and a recall of 0.73 were recorded, and an F1 score of 0.83 was recorded. In addition, the light GBM-based optimal prediction model derived from this study showed superior performance than the link prediction model of previous studies, which is set as a benchmarking model in this study. The predictive model of the previous study recorded only a recall rate of 0.75, but the proposed model of this study showed better performance which recall rate is 0.79. The difference in the performance of the prediction results between benchmarking model and this study model is due to the model learning strategy. In this study, groups were classified by the trade value scale, and prediction models were trained differently for these groups. Specific methods are (1) a method of randomly masking and learning a model for all trades without setting specific conditions for trade value, (2) arbitrarily masking a part of the trades with an average trade value or higher and using the model method, and (3) a method of arbitrarily masking some of the trades with the top 25% or higher trade value and learning the model. As a result of the experiment, it was confirmed that the performance of the model trained by randomly masking some of the trades with the above-average trade value in this method was the best and appeared stably. It was found that most of the results of potential export candidates for Korea derived through the above model appeared appropriate through additional investigation. Combining the above, this study could suggest the practical utility of the link prediction method applying Node2vec and Light GBM. In addition, useful implications could be derived for weight update strategies that can perform better link prediction while training the model. On the other hand, this study also has policy utility because it is applied to trade transactions that have not been performed much in the research related to link prediction based on graph embedding. The results of this study support a rapid response to changes in the global value chain such as the recent US-China trade conflict or Japan's export regulations, and I think that it has sufficient usefulness as a tool for policy decision-making.