• International conference on construction engineering and project management
• /
• 2020.12a
• /
• pp.463-481
• /
• 2020

Cutter suction dredgers (CSDs) are widely used in various dredging constructions such as channel excavation, wharf construction, and reef construction. During a CSD construction, the main operation is to control the swing speed of cutter to keep the slurry concentration in a proper range. However, the slurry concentration cannot be monitored in real-time, i.e., there is a "time-lag effect" in the log of slurry concentration, making it difficult for operators to make the optimal decision on controlling. Concerning this issue, a solution scheme that using real-time monitored indicators to predict current slurry concentration is proposed in this research. The characteristics of the CSD monitoring data are first studied, and a set of preprocessing methods are presented. Then we put forward the concept of "index class" to select the important indices. Finally, an ensemble learning algorithm is set up to fit the relationship between the slurry concentration and the indices of the index classes. In the experiment, log data over seven days of a practical dredging construction is collected. For comparison, the Deep Neural Network (DNN), Long Short Time Memory (LSTM), Support Vector Machine (SVM), Random Forest (RF), Gradient Boosting Decision Tree (GBDT), and the Bayesian Ridge algorithm are tried. The results show that our method has the best performance with an R² of 0.886 and a mean square error (MSE) of 5.538. This research provides an effective way for real-time predicting the slurry concentration of CSDs and can help to improve the stationarity and production efficiency of dredging construction.

• International Journal of Computer Science & Network Security
• /
• v.24 no.2
• /
• pp.79-88
• /
• 2024

The use of the social media has become part of our daily life activities. The social web channels provide the content generation facility to its users who can share their views, opinions and experiences towards certain topics. The researchers are using the social media content for various research areas. Sentiment analysis, one of the most active research areas in last decade, is the process to extract reviews, opinions and sentiments of people. Sentiment analysis is applied in diverse sub-areas such as subjectivity analysis, polarity detection, and emotion detection. Stance classification has emerged as a new and interesting research area as it aims to determine whether the content writer is in favor, against or neutral towards the target topic or issue. Stance classification is significant as it has many research applications like rumor stance classifications, stance classification towards public forums, claim stance classification, neural attention stance classification, online debate stance classification, dialogic properties stance classification etc. This research study explores different feature sets such as lexical, sentiment-specific, dialog-based which have been extracted using the standard datasets in the relevant area. Supervised learning approaches of generative algorithms such as Naïve Bayes and discriminative machine learning algorithms such as Support Vector Machine, Naïve Bayes, Decision Tree and k-Nearest Neighbor have been applied and then ensemble-based algorithms like Random Forest and AdaBoost have been applied. The empirical based results have been evaluated using the standard performance measures of Accuracy, Precision, Recall, and F-measures.

• International Journal of Computer Science & Network Security
• /
• v.23 no.12
• /
• pp.101-106
• /
• 2023

Chronic illnesses are among the most common serious problems affecting human health. Early diagnosis of chronic diseases can assist to avoid or mitigate their consequences, potentially decreasing mortality rates. Using machine learning algorithms to identify risk factors is an exciting strategy. The issue with existing feature selection approaches is that each method provides a distinct set of properties that affect model correctness, and present methods cannot perform well on huge multidimensional datasets. We would like to introduce a novel model that contains a feature selection approach that selects optimal characteristics from big multidimensional data sets to provide reliable predictions of chronic illnesses without sacrificing data uniqueness.[1] To ensure the success of our proposed model, we employed balanced classes by employing hybrid balanced class sampling methods on the original dataset, as well as methods for data pre-processing and data transformation, to provide credible data for the training model. We ran and assessed our model on datasets with binary and multivalued classifications. We have used multiple datasets (Parkinson, arrythmia, breast cancer, kidney, diabetes). Suitable features are selected by using the Hybrid feature model consists of Lassocv, decision tree, random forest, gradient boosting,Adaboost, stochastic gradient descent and done voting of attributes which are common output from these methods.Accuracy of original dataset before applying framework is recorded and evaluated against reduced data set of attributes accuracy. The results are shown separately to provide comparisons. Based on the result analysis, we can conclude that our proposed model produced the highest accuracy on multi valued class datasets than on binary class attributes.[1]

• Journal of the Korean Institute of Traditional Landscape Architecture
• /
• v.38 no.1
• /
• pp.45-52
• /
• 2020

This study analyzed the components contained in the pine needles of first and second-year-olds to analyze the factors that the in vivo content of inorganic elements affects the sex determination of pine trees. In response, the plan for pine tree plant and maintenance was intended to be presented in consideration of the reproductive environment and physiological characteristics. The results are as follows. First, last year, when there were many encyclopedias, the analyzed N(%) content was found to be high. The nitrogen content of the previous year's soil was found to affect the production of the spheres the following year. This is believed to be possible to reduce the rate of Pine pollen produced in the new plant in the following year through a dispute over quality consumption in the spring of the previous year. Second, the weapons elements involved in the Pine cones and the generation of the Pine pollen in the new plant appeared to be P(%), K(%), Ca(%), and Fe(%). However, the nutrients from the previous year's leaves of Ca(%) and Fe(%) were found to have a low influence on the sex determination of first-year pine trees. Because Ca(%) and Fe(%) are not able to move nutrients accumulated in aging organs due to the nature of the components, feeding nutrients in the fall when the growth of the previous year's branches is reduced is expected to affect oral generation. Third, pine trees are extremely positive and Pine pollen is related to the time of the northeast wind. Therefore, it is believed that it would be good to be located in the northern direction, where the sunlight is good, in an outdoor space. In addition, it is important to use vaginal consumer products in spring and carry out a quarrel involving Mg and Fe during fall to reduce the effect of the Pine pollen, which is an outdoor plant. This is an important part of maintaining and managing pine trees in outdoor spaces as well as the sex determination of pine trees. This study suggested that plant planning, which derives the correlation between pine inorganic element content on sexual determination and takes into account the physiological characteristics of pine trees, is an important issue in the creation of outdoor space. Follow-up research on other factors affecting pine tree sex determination is expected.

• Journal of Intelligence and Information Systems
• /
• v.21 no.1
• /
• pp.161-177
• /
• 2015

With the rapid evolution of technology, the size, number, and the type of databases has increased concomitantly, so data mining approaches face many challenging applications from databases. One such application is discovery of fraud patterns from agricultural product wholesale transaction instances. The agricultural product wholesale market in Korea is huge, and vast numbers of transactions have been made every day. The demand for agricultural products continues to grow, and the use of electronic auction systems raises the efficiency of operations of wholesale market. Certainly, the number of unusual transactions is also assumed to be increased in proportion to the trading amount, where an unusual transaction is often the first sign of fraud. However, it is very difficult to identify and detect these transactions and the corresponding fraud occurred in agricultural product wholesale market because the types of fraud are more intelligent than ever before. The fraud can be detected by verifying the overall transaction records manually, but it requires significant amount of human resources, and ultimately is not a practical approach. Frauds also can be revealed by victim's report or complaint. But there are usually no victims in the agricultural product wholesale frauds because they are committed by collusion of an auction company and an intermediary wholesaler. Nevertheless, it is required to monitor transaction records continuously and to make an effort to prevent any fraud, because the fraud not only disturbs the fair trade order of the market but also reduces the credibility of the market rapidly. Applying data mining to such an environment is very useful since it can discover unknown fraud patterns or features from a large volume of transaction data properly. The objective of this research is to empirically investigate the factors necessary to detect fraud transactions in an agricultural product wholesale market by developing a data mining based fraud detection model. One of major frauds is the phantom transaction, which is a colluding transaction by the seller(auction company or forwarder) and buyer(intermediary wholesaler) to commit the fraud transaction. They pretend to fulfill the transaction by recording false data in the online transaction processing system without actually selling products, and the seller receives money from the buyer. This leads to the overstatement of sales performance and illegal money transfers, which reduces the credibility of market. This paper reviews the environment of wholesale market such as types of transactions, roles of participants of the market, and various types and characteristics of frauds, and introduces the whole process of developing the phantom transaction detection model. The process consists of the following 4 modules: (1) Data cleaning and standardization (2) Statistical data analysis such as distribution and correlation analysis, (3) Construction of classification model using decision-tree induction approach, (4) Verification of the model in terms of hit ratio. We collected real data from 6 associations of agricultural producers in metropolitan markets. Final model with a decision-tree induction approach revealed that monthly average trading price of item offered by forwarders is a key variable in detecting the phantom transaction. The verification procedure also confirmed the suitability of the results. However, even though the performance of the results of this research is satisfactory, sensitive issues are still remained for improving classification accuracy and conciseness of rules. One such issue is the robustness of data mining model. Data mining is very much data-oriented, so data mining models tend to be very sensitive to changes of data or situations. Thus, it is evident that this non-robustness of data mining model requires continuous remodeling as data or situation changes. We hope that this paper suggest valuable guideline to organizations and companies that consider introducing or constructing a fraud detection model in the future.

• Korean Journal of Remote Sensing
• /
• v.37 no.2
• /
• pp.245-256
• /
• 2021

This study was conducted to identify the applicability of a LiDAR sensor to forest resources inventories by comparing data on a tree's position, height, and DBH obtained by the sensor with those by existing forest inventory methods, for the tree species of Criptomeria japonica in Jeolmul forest in Jeju, South Korea. To this end, a backpack personal LiDAR (Greenvalley International, Model D50) was employed. To facilitate the process of the data collection, patterns of collecting the data by the sensor were divided into seven ones, considering the density of sample plots and the work efficiency. Then, the accuracy of estimating the variables of each tree was assessed. The amount of time spent on acquiring and processing the data by each method was compared to evaluate the efficiency. The findings showed that the rate of detecting standing trees by the LiDAR was 100%. Also, the high statistical accuracy was observed in both Pattern 5 (DBH: RMSE 1.07 cm, Bias -0.79 cm, Height: RMSE 0.95 m, Bias -3.2 m), and Pattern 7 (DBH: RMSE 1.18 cm, Bias -0.82 cm, Height: RMSE 1.13 m, Bias -2.62 m), compared to the results drawn in the typical inventory manner. Concerning the time issue, 115 to 135 minutes per 1ha were taken to process the data by utilizing the LiDAR, while 375 to 1,115 spent in the existing way, proving the higher efficiency of the device. It can thus be concluded that using a backpack personal LiDAR helps increase efficiency in conducting a forest resources inventory in an planted coniferous forest with understory vegetation, implying a need for further research in a variety of forests.

• Journal of Arbitration Studies
• /
• v.17 no.1
• /
• pp.183-215
• /
• 2007

The purpose of this paper is to study of WTO regulations related FTA such as Understanding on the Interpretation of Article XXIV of the General Agreement on Tariffs and Trade(GATT) 1994 and General Agreement on Trade in Service(GATS). In this study, the First introduced FTA rules of WTO in the chapter 2. The WTO agreement includes the "General Agreement on Tariffs an Trade(GATT) 1994". This instrument, known as "GATT 1994", is based on upon the original General Agreement on Tariffs and Trade referred to as "GATT 1947". The Second analyzed the relations between FTA and Article XXIV of GATT 1994 in the chapter 3. The Article XXIV of GATT 1994 is an agreement between the distinctive members for liberalizing trade. The Article XXIV of GATT 1994 is consist of three parts such as customs unions, free-trade area, and interim agreements that WTO is referred to as "Regional Trade Agreement(RTA)". There is a difference between the customs unions and the free-trade area. In the customs unions rules, the members should have the same tarifficatio and the same trade provision against non-members, but in the free-trade are a rules, the member is not necessary to have the same tarifficatio and the same trade provision against non-members. But, the both rules have a liberalization of trade in a common as a revoking tariffs and the government regulations for interfering with trade. In this case, however, the both rules include an inconsistency ele ment under WTO rules such as Most-Favoured-Nation Treatment(MFN) and National Treatment on Internal Taxation and Regulation(NTITR). This study reviewed neither inconsistency nor consistency on the both rules with the RTA of WTO under Article XXIV of GATT 1994. The Third analyzed the relations between FTA and Article V of GATS under WTO in the chapter 4. The GATS is a rule of WTO for the growing importance of trade in services for the growth and development of the world conomy. The GATS is a new rule rather than GATT's rule for concerning goods trade. The Article V of GATS under WTO is a rule that makes based on upon the Article XXIV of GATT. Therefore, If it is to be examined the Article V of GATS, it should be referred to a and an interpretation of the text of the Article XXIV of GATT. However, the Article V of GATS is on the undeveloped stage compare to the Article XXIV of GATT. Because, the statistics of WTO showed that the RTAs under the Article XXIV of GATT have 150 cases completed between nations, but the RTAs under the Article IV of GATS have 10 cases completed between nations. The Forth examined the interpretation of FTA rules under WTO in the chapter 5. Concerning the consistency issue of customs unions and free-trade area under the Article XXIV of GATT, the working parties in customs unions and in free-trade area have been reviewed the consistency is sue which had been not if to GATT. However, the parties finished to get up with one accord the both that are a consistency of argument and an inconsistency of argument with the interpretation of the Article XXIV of GATT. The interpretation of the Article XXIV of GATT has been raised as the issues when EEC by Rome Treaty established in 1957. However, the consistency is sue only agreed 6 working parties out of 69 working parties finished the reviewing of the interpretation up to the end of 1994. Also the consistency issue concerned with the special privilege measure of the customs unions and tree-trade area under the Article XXIV of GATT discussed only 3 cases between working parties up to now and did not accepted as an issue for working parties' report. In conclusion in the chapter 6, this study raised the issues of WTO that are a conference of a new round under WTO and the issues of clarity between FTA rule and WTO regulation.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.36 no.1
• /
• pp.80-89
• /
• 2008

Generally, trees lining the streets are the most easily accessible green areas in the city and constitute the smallest basic unit in the formation of the urban linear green axis. This study attempts to interpret issues related to city trees from a comprehensive and relational viewpoint. The site of this study is Central Park Street in front of Incheon Metropolitan City Hall. This street is representative of those in Incheon City. This study is an inter-relational interpretation of issues by measuring the vitality of these trees. The following are results of this study: First, the vitality of city trees is higher in those trees growing in natural ground than those growing in plant gratings. This observation can lead to budget savings and increased natural areas in the city. Also, if planter and multi-layering planting methods are introduced where damage to trees is predicted, variation to urban landscape can be achieved while linking to reinforced rearing foundation of street-side trees. Second, there is need for a holistic approach to caring for street-side trees regarding the damage caused by drastic pruning and strong street lights. The typical functions of these trees, like supplying freshness in summer, absorbing solar radiation, and controlling the urban micro-climate are closely related to the vitality of the trees. Accordingly, the function and ecology should be understood holistically, not separately. In this aspect, the functional and ecological use of the multi-layering planting method is effective in protecting pedestrians from vehicles as well. Third, the fallen leaves of monotonous rows of trees have different ecological and functional effects. Not only is the index of greenness in the urban setting increased, but there are also aesthetic and symbolic effects. Fourth, in spite of being the street along which Incheon Metropolitan City Hall, major administrative buildings and Central Park are located, this street does not have its own special identity to discriminate it from other streets. It fulfills only functional criteria based on uniformity. If there is no paradigm shift from today's street system based on vehicles, the role of landscape architecture will be very passive in regards to street-side trees, the minimum unit of urban green. Fifth, on this particular street, many trees were planted in December, which reflects a deficiency of short and long-term strategy, like a street-tree master plan. In this aspect, we still lack a mature culture concerning these trees as a basic unit in urban greenery. Furthermore, there needs to be cultural introspection concerning present administrative practices.

• Nuclear Engineering and Technology
• /
• v.39 no.1
• /
• pp.31-42
• /
• 2007

Energy supply is increasingly showing up as a major issue for electricity supply, transportation, settlement, and process heat industrial supply including hydrogen production. Nuclear power is part of the solution. For electricity supply, as exemplified in Finland and France, the EPR brings an immediate answer; HTR could bring another solution in some specific cases. For other supply, mostly heat, the HTR brings a solution inaccessible to conventional nuclear power plants for very high or even high temperature. As fossil fuels costs increase and efforts to avoid generation of Greenhouse gases are implemented, a market for nuclear generated process heat will be developed. Following active developments in the 80's, HTR have been put on the back burner up to 5 years ago. Light water reactors are widely dominating the nuclear production field today. However, interest in the HTR technology was renewed in the past few years. Several commercial projects are actively promoted, most of them aiming at electricity production. ANTARES is today AREVA's response to the cogeneration market. It distinguishes itself from other concepts with its indirect cycle design powering a combined cycle power plant. Several reasons support this design choice, one of the most important of which is the design flexibility to adapt readily to combined heat and power applications. From the start, AREVA made the choice of such flexibility with the belief that the HTR market is not so much in competition with LWR in the sole electricity market but in the specific added value market of cogeneration and process heat. In view of the volatility of the costs of fossil fuels, AREVA's choice brings to the large industrial heat applications the fuel cost predictability of nuclear fuel with the efficiency of a high temperature heat source tree of Greenhouse gases emissions. The ANTARES module produces 600 MWth which can be split into the required process heat, the remaining power drives an adapted prorated electric plant. Depending on the process heat temperature and power needs, up to 80% of the nuclear heat is converted into useful power. An important feature of the design is the standardization of the heat source, as independent as possible of the process heat application. This should expedite licensing. The essential conditions for success include: ${\bullet}$ Timely adapted licensing process and regulations, codes and standards for such application and design ${\bullet}$ An industry oriented R&D program to meet the technological challenges making the best use of the international collaboration. Gen IV could be the vector ${\bullet}$ Identification of an end user(or a consortium of) willing to fund a FOAK

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.13 no.4
• /
• pp.63-72
• /
• 2014

With the rapid development in the economy and other fields as well, the standard of living in South Korea has been improved, and consequently, the demand of automobiles has quickly increased. It leads to various traffic issues such as traffic congestion, traffic accident, and parking problem. In particular, this illegal parking caused by the increase in the number of automobiles has been considered one of the main reasons to bring about traffic congestion as intensifying any dispute between neighbors in relation to a parking space, which has been also coming to the fore as a social issue. Therefore, this study looked into Daejeon Metropolitan City, the city that is understood to have the highest automobile sharing rate in South Korea but with relatively few cases of illegal parking crackdowns. In order to investigate the theoretical problems of the illegal parking, this study conducted a decision-making tree model-based Exhaustive CHAID analysis to figure out not only what makes drivers park illegally when they try to park vehicles but also those factors that would tempt the drivers into the illegal parking. The study, then, comes up with solutions to the problem. According to the analysis, in terms of the influential factors that encourage the drivers to park at some illegal areas, it was learned that these factors, the distance, a driver's experience of getting caught, the occupation and the use time in order, have an effect on the drivers' deciding to park illegally. After working on the prediction model, four nodes were finally extracted. Given the analysis result, as a solution to the illegal parking, it is necessary to establish public parking lots additionally and first secure the parking space for the vehicles used for living and working, and to activate the campaign for enhancing illegal parking crackdown and encouraging civic consciousness.