• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.11
• /
• pp.471-480
• /
• 2023

The Korean construction order volume in South Korea grew significantly from 91.3 trillion won in public orders in 2013 to a total of 212 trillion won in 2021, particularly in the private sector. As the size of the domestic and overseas markets grew, the scale and complexity of EPC (Engineering, Procurement, Construction) projects increased, and risk management of project management and ITB (Invitation to Bid) documents became a critical issue. The time granted to actual construction companies in the bidding process following the EPC project award is not only limited, but also extremely challenging to review all the risk terms in the ITB document due to manpower and cost issues. Previous research attempted to categorize the risk terms in EPC contract documents and detect them based on AI, but there were limitations to practical use due to problems related to data, such as the limit of labeled data utilization and class imbalance. Therefore, this study aims to develop an AI model that can categorize the contract terms based on the FIDIC Yellow 2017(Federation Internationale Des Ingenieurs-Conseils Contract terms) standard in detail, rather than defining and classifying risk terms like previous research. A multi-text classification function is necessary because the contract terms that need to be reviewed in detail may vary depending on the scale and type of the project. To enhance the performance of the multi-text classification model, we developed the ELECTRA PLM (Pre-trained Language Model) capable of efficiently learning the context of text data from the pre-training stage, and conducted a four-step experiment to validate the performance of the model. As a result, the ensemble version of the self-developed ITB-ELECTRA model and Legal-BERT achieved the best performance with a weighted average F1-Score of 76% in the classification of 57 contract terms.

• Maritime Security
• /
• v.7 no.1
• /
• pp.31-60
• /
• 2023

This study proposes a new convergence weapon system that combines the covert placement and detection abilities of a self-propelled mobile mine with the rapid tracking and attack abilities of supercavitating rocket torpedoes. This innovative system has been designed to counter North Korea's new underwater weapon, 'Haeil'. The concept behind this convergence weapon system is to maximize the strengths and minimize the weaknesses of each weapon type. Self-propelled mobile mines, typically placed discreetly on the seabed or in the water, are designed to explode when a vessel or submarine passes near them. They are generally used to defend or control specific areas, like traditional sea mines, and can effectively limit enemy movement and guide them in a desired direction. The advantage that self-propelled mines have over traditional sea mines is their ability to move independently, ensuring the survivability of the platform responsible for placing the sea mines. This allows the mines to be discreetly placed even deeper into enemy lines, significantly reducing the time and cost of mine placement while ensuring the safety of the deployed platforms. However, to cause substantial damage to a target, the mine needs to detonate when the target is very close - typically within a few yards. This makes the timing of the explosion crucial. On the other hand, supercavitating rocket torpedoes are capable of traveling at groundbreaking speeds, many times faster than conventional torpedoes. This rapid movement leaves little room for the target to evade, a significant advantage. However, this comes with notable drawbacks - short range, high noise levels, and guidance issues. The high noise levels and short range is a serious disadvantage that can expose the platform that launched the torpedo. This research proposes the use of a convergence weapon system that leverages the strengths of both weapons while compensating for their weaknesses. This strategy can overcome the limitations of traditional underwater kill-chains, offering swift and precise responses. By adapting the weapon acquisition criteria from the Defense force development Service Order, the effectiveness of the proposed system was independently analyzed and proven in terms of underwater defense sustainability, survivability, and cost-efficiency. Furthermore, the utility of this system was demonstrated through simulated scenarios, revealing its potential to play a critical role in future underwater kill-chain scenarios. However, realizing this system presents significant technical challenges and requires further research.

• Journal of Intelligence and Information Systems
• /
• v.26 no.2
• /
• pp.57-78
• /
• 2020

With the development of the Internet, consumers have had an opportunity to check product information easily through E-Commerce. Product reviews used in the process of purchasing goods are based on user experience, allowing consumers to engage as producers of information as well as refer to information. This can be a way to increase the efficiency of purchasing decisions from the perspective of consumers, and from the seller's point of view, it can help develop products and strengthen their competitiveness. However, it takes a lot of time and effort to understand the overall assessment and assessment dimensions of the products that I think are important in reading the vast amount of product reviews offered by E-Commerce for the products consumers want to compare. This is because product reviews are unstructured information and it is difficult to read sentiment of reviews and assessment dimension immediately. For example, consumers who want to purchase a laptop would like to check the assessment of comparative products at each dimension, such as performance, weight, delivery, speed, and design. Therefore, in this paper, we would like to propose a method to automatically generate multi-dimensional product assessment scores in product reviews that we would like to compare. The methods presented in this study consist largely of two phases. One is the pre-preparation phase and the second is the individual product scoring phase. In the pre-preparation phase, a dimensioned classification model and a sentiment analysis model are created based on a review of the large category product group review. By combining word embedding and association analysis, the dimensioned classification model complements the limitation that word embedding methods for finding relevance between dimensions and words in existing studies see only the distance of words in sentences. Sentiment analysis models generate CNN models by organizing learning data tagged with positives and negatives on a phrase unit for accurate polarity detection. Through this, the individual product scoring phase applies the models pre-prepared for the phrase unit review. Multi-dimensional assessment scores can be obtained by aggregating them by assessment dimension according to the proportion of reviews organized like this, which are grouped among those that are judged to describe a specific dimension for each phrase. In the experiment of this paper, approximately 260,000 reviews of the large category product group are collected to form a dimensioned classification model and a sentiment analysis model. In addition, reviews of the laptops of S and L companies selling at E-Commerce are collected and used as experimental data, respectively. The dimensioned classification model classified individual product reviews broken down into phrases into six assessment dimensions and combined the existing word embedding method with an association analysis indicating frequency between words and dimensions. As a result of combining word embedding and association analysis, the accuracy of the model increased by 13.7%. The sentiment analysis models could be seen to closely analyze the assessment when they were taught in a phrase unit rather than in sentences. As a result, it was confirmed that the accuracy was 29.4% higher than the sentence-based model. Through this study, both sellers and consumers can expect efficient decision making in purchasing and product development, given that they can make multi-dimensional comparisons of products. In addition, text reviews, which are unstructured data, were transformed into objective values such as frequency and morpheme, and they were analysed together using word embedding and association analysis to improve the objectivity aspects of more precise multi-dimensional analysis and research. This will be an attractive analysis model in terms of not only enabling more effective service deployment during the evolving E-Commerce market and fierce competition, but also satisfying both customers.

• 한국지구물리탐사학회:학술대회논문집
• /
• 2005.09a
• /
• pp.21-36
• /
• 2005

Although the main geology of Korea consists of granite and gneiss, it Is not uncommon to encounter anisotropy Phenomena in crosshole radar tomography even when the basement is crystalline rock. To solve the anisotropy Problem, we have developed and continuously upgraded an anisotropic inversion algorithm assuming a heterogeneous elliptic anisotropy to reconstruct three kinds of tomograms: tomograms of maximum and minimum velocities, and of the direction of the symmetry axis. In this paper, we discuss the developed algorithm and introduce some case histories on the application of anisotropic radar tomography in Korea. The first two case histories were conducted for the construction of infrastructure, and their main objective was to locate cavities in limestone. The last two were performed In a granite and gneiss area. The anisotropy in the granite area was caused by fine fissures aligned in the same direction, while that in the gneiss and limestone area by the alignment of the constituent minerals. Through these case histories we showed that the anisotropic characteristic itself gives us additional important information for understanding the internal status of basement rock. In particular, the anisotropy ratio defined by the normalized difference between maximum and minimum velocities as well as the direction of maximum velocity are helpful to interpret the borehole radar tomogram.

• 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.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.25 no.1
• /
• pp.48-57
• /
• 2015

In a sodium-cooled fast reactor, which is a Generation-IV reactor, refueling is conducted by rotating, but not opening, the reactor head to prevent a reaction between the sodium, water and air. Therefore, an inspection technique that checks for the presence of any obstacles between the reactor core and the upper internal structure, which could disturb the rotation of the reactor head, is essential prior to the refueling of a sodium-cooled fast reactor. To this end, an ultrasound-based inspection technique should be employed because the opacity of the sodium prevents conventional optical inspection techniques from being applied to the monitoring of obstacles. In this study, a ranging inspection technique using a plate-type ultrasonic waveguide sensor was developed to monitor the presence of any obstacles between the reactor core and the upper internal structure in the opaque sodium. Because the waveguide sensor installs an ultrasonic transducer in a relatively cold region and transmits the ultrasonic waves into the hot radioactive liquid sodium through a long waveguide, it offers better reliability and is less susceptible to thermal or radiation damage. A 10 m horizontal beam waveguide sensor capable of radiating an ultrasonic wave horizontally was developed, and beam profile measurements and basic experiments were carried out to investigate the characteristics of the developed sensor. The beam width and propagation distance of the ultrasonic wave radiated from the sensor were assessed based on the experimental results. Finally, a feasibility test using cylindrical targets (corresponding to the shape of possible obstacles) was also conducted to evaluate the applicability of the developed ranging inspection technique to actual applications.

• Atmosphere
• /
• v.12 no.4
• /
• pp.20-42
• /
• 2002

Based on the "Mid to Long Term Plan for Space Development", a project to launch COMeS (Communication, Oceanography, and Meteorological Satellite) into the geostationary orbit is undergoing. Accordingly, KMA (Korea Meteorological Administration) has defined the meteorological missions and prepared the user requirements to fulfill the missions. To make a realistic user requirements, we prepared a first draft based on the ideal meteorological products derivable from a geostationary platform and sent the RFI (request for information) to the sensor manufacturers. Based on the responses to the RFI and other considerations, we revised the user requirement to be a realistic plan for the 2008 launch of the satellite. This manuscript introduces the revised user requirements briefly. The major mission defined in the revised user requirement is the augmentation of the detection and prediction ability of the severe weather phenomena, especially around the Korean Peninsula. The required payload is an enhanced Imager, which includes the major observation channels of the current geostationary sounder. To derive the required meteorological products from the Imager, at least 12 channels are required with the optimum of 16 channels. The minimum 12 channels are 6 wavelength bands used for current geostationary satellite, and additional channels in two visible bands, a near infrared band, two water vapor bands and one ozone absorption band. From these enhanced channel observation, we are going to derive and utilize the information of water vapor, stability index, wind field, and analysis of special weather phenomena such as the yellow sand event in addition to the standard derived products from the current geostationary Imager data. For a better temporal coverage, the Imager is required to acquire the full disk data within 15 minutes and to have the rapid scan mode for the limited area coverage. The required thresholds of spatial resolutions are 1 km and 2 km for visible and infrared channels, respectively, while the target resolutions are 0.5 km and 1 km.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.39 no.4
• /
• pp.347-357
• /
• 2003

This paper describes on the suppression of sea clutter on marine radar display using a cell-averaging CFAR(constant false alarm rate) technique, and on the analysis of radar echo signal data in relation to the estimation of ARPA functions and the detection of the shadow effect in clutter returns. The echo signal was measured using a X -band radar, that is located on the Pukyong National University, with a horizontal beamwidth of $$3.9^{\circ}$$, a vertical beamwidth of $20^{\circ}$, pulsewidth of $0.8 {\mu}s$ and a transmitted peak power of 4 ㎾ The suppression performance of sea clutter was investigated for the probability of false alarm between $l0-^0.25;and; 10^-1.0$. Also the performance of cell averaging CFAR was compared with that of ideal fixed threshold. The motion vectors and trajectory of ships was extracted and the shadow effect in clutter returns was analyzed. The results obtained are summarized as follows；1. The ARPA plotting results and motion vectors for acquired targets extracted by analyzing the echo signal data were displayed on the PC based radar system and the continuous trajectory of ships was tracked in real time. 2. To suppress the sea clutter under noisy environment, a cell averaging CFAR processor having total CFAR window of 47 samples(20+20 reference cells, 3+3 guard cells and the cell under test) was designed. On a particular data set acquired at Suyong Man, Busan, Korea, when the probability of false alarm applied to the designed cell averaging CFAR processor was 10$^{-0}$.75/ the suppression performance of radar clutter was significantly improved. The results obtained suggest that the designed cell averaging CFAR processor was very effective in uniform clutter environments. 3. It is concluded that the cell averaging CF AR may be able to give a considerable improvement in suppression performance of uniform sea clutter compared to the ideal fixed threshold. 4. The effective height of target, that was estimated by analyzing the shadow effect in clutter returns for a number of range bins behind the target as seen from the radar antenna, was approximately 1.2 m and the information for this height can be used to extract the shape parameter of tracked target..

• Korean Journal of Remote Sensing
• /
• v.39 no.5_1
• /
• pp.655-667
• /
• 2023

Algal bloom outbreaks are frequently reported around the world, and serious water pollution problems arise every year in Korea. It is necessary to protect the aquatic ecosystem through continuous management and rapid response. Many studies using satellite images are being conducted to estimate the concentration of chlorophyll-a (Chl-a), an indicator of algal bloom occurrence. However, machine learning models have recently been used because it is difficult to accurately calculate Chl-a due to the spectral characteristics and atmospheric correction errors that change depending on the water system. It is necessary to consider the factors affecting algal bloom as well as the satellite spectral index. Therefore, this study constructed a dataset by considering water quality, hydrological and meteorological factors, and sentinel-2 images in combination. Representative ensemble models random forest and extreme gradient boosting (XGBoost) were used to predict the concentration of Chl-a in eight weirs located on the Nakdong river over the past five years. R-squared score (R²), root mean square errors (RMSE), and mean absolute errors (MAE) were used as model evaluation indicators, and it was confirmed that R² of XGBoost was 0.80, RMSE was 6.612, and MAE was 4.457. Shapley additive expansion analysis showed that water quality factors, suspended solids, biochemical oxygen demand, dissolved oxygen, and the band ratio using red edge bands were of high importance in both models. Various input data were confirmed to help improve model performance, and it seems that it can be applied to domestic and international algal bloom detection.

• Journal of Intelligence and Information Systems
• /
• v.26 no.4
• /
• pp.127-148
• /
• 2020

The data center is a physical environment facility for accommodating computer systems and related components, and is an essential foundation technology for next-generation core industries such as big data, smart factories, wearables, and smart homes. In particular, with the growth of cloud computing, the proportional expansion of the data center infrastructure is inevitable. Monitoring the health of these data center facilities is a way to maintain and manage the system and prevent failure. If a failure occurs in some elements of the facility, it may affect not only the relevant equipment but also other connected equipment, and may cause enormous damage. In particular, IT facilities are irregular due to interdependence and it is difficult to know the cause. In the previous study predicting failure in data center, failure was predicted by looking at a single server as a single state without assuming that the devices were mixed. Therefore, in this study, data center failures were classified into failures occurring inside the server (Outage A) and failures occurring outside the server (Outage B), and focused on analyzing complex failures occurring within the server. Server external failures include power, cooling, user errors, etc. Since such failures can be prevented in the early stages of data center facility construction, various solutions are being developed. On the other hand, the cause of the failure occurring in the server is difficult to determine, and adequate prevention has not yet been achieved. In particular, this is the reason why server failures do not occur singularly, cause other server failures, or receive something that causes failures from other servers. In other words, while the existing studies assumed that it was a single server that did not affect the servers and analyzed the failure, in this study, the failure occurred on the assumption that it had an effect between servers. In order to define the complex failure situation in the data center, failure history data for each equipment existing in the data center was used. There are four major failures considered in this study: Network Node Down, Server Down, Windows Activation Services Down, and Database Management System Service Down. The failures that occur for each device are sorted in chronological order, and when a failure occurs in a specific equipment, if a failure occurs in a specific equipment within 5 minutes from the time of occurrence, it is defined that the failure occurs simultaneously. After configuring the sequence for the devices that have failed at the same time, 5 devices that frequently occur simultaneously within the configured sequence were selected, and the case where the selected devices failed at the same time was confirmed through visualization. Since the server resource information collected for failure analysis is in units of time series and has flow, we used Long Short-term Memory (LSTM), a deep learning algorithm that can predict the next state through the previous state. In addition, unlike a single server, the Hierarchical Attention Network deep learning model structure was used in consideration of the fact that the level of multiple failures for each server is different. This algorithm is a method of increasing the prediction accuracy by giving weight to the server as the impact on the failure increases. The study began with defining the type of failure and selecting the analysis target. In the first experiment, the same collected data was assumed as a single server state and a multiple server state, and compared and analyzed. The second experiment improved the prediction accuracy in the case of a complex server by optimizing each server threshold. In the first experiment, which assumed each of a single server and multiple servers, in the case of a single server, it was predicted that three of the five servers did not have a failure even though the actual failure occurred. However, assuming multiple servers, all five servers were predicted to have failed. As a result of the experiment, the hypothesis that there is an effect between servers is proven. As a result of this study, it was confirmed that the prediction performance was superior when the multiple servers were assumed than when the single server was assumed. In particular, applying the Hierarchical Attention Network algorithm, assuming that the effects of each server will be different, played a role in improving the analysis effect. In addition, by applying a different threshold for each server, the prediction accuracy could be improved. This study showed that failures that are difficult to determine the cause can be predicted through historical data, and a model that can predict failures occurring in servers in data centers is presented. It is expected that the occurrence of disability can be prevented in advance using the results of this study.