• Journal of Korean Tunnelling and Underground Space Association
• /
• v.26 no.5
• /
• pp.519-532
• /
• 2024

Anomaly detection for the penetration rate of tunnel boring machines (TBMs) is crucial for effective risk management in TBM tunnel projects. However, previous machine learning models for predicting the penetration rate have struggled with imbalanced data between normal and abnormal penetration rates. This study aims to enhance the performance of machine learning-based anomaly detection for the penetration rate by utilizing a data augmentation technique to address this data imbalance. Initially, six input features were selected through correlation analysis. The lowest and highest 10% of the penetration rates were designated as abnormal classes, while the remaining penetration rates were categorized as a normal class. Two prediction models were developed, each trained on an original training set and an oversampled training set constructed using SMOTE (synthetic minority oversampling technique): an XGB (extreme gradient boosting) model and an XGB-SMOTE model. The prediction results showed that the XGB model performed poorly for the abnormal classes, despite performing well for the normal class. In contrast, the XGB-SMOTE model consistently exhibited superior performance across all classes. These findings can be attributed to the data augmentation for the abnormal penetration rates using SMOTE, which enhances the model's ability to learn patterns between geological and operational factors that contribute to abnormal penetration rates. Consequently, this study demonstrates the effectiveness of employing data augmentation to manage imbalanced data in anomaly detection for TBM penetration rates.

• Clean Technology
• /
• v.30 no.3
• /
• pp.175-187
• /
• 2024

Seaweeds are widely distributed along national coastlines around the world, and the biomass derived from them is an important marine biological organism. Seaweed is a crucial component of a healthy marine ecosystem. However, changes in marine environments have led to the occurrence of urchin barrens, and the damage caused by this phenomenon is steadily increasing. As a result, investigations into the distribution and spread of urchin barrens in the coastal areas of South Korea are being conducted regularly so efficient detection technologies are essential. One of the technologies that can swiftly and accurately analyze extensive areas is detection technology based on hyperspectral image information systems. This study aims to present the latest hyperspectral imaging technology for investigating the current status of urchin barrens and the methods for classifying this technology, including principles, preprocessing techniques, and correction methods. This study also proposes a classification technique for urchin barrens along the coast of Jeju Island that uses hyperspectral images and categorizes the urchin barrens into initial, intermediate, and advanced stages. The results showed that approximately 17.5% of the experimental areas were in the advanced stage. Based on this, various management and restoration methods tailored to different categories of urchin barren can be proposed.

• Journal of KIISE:Computing Practices and Letters
• /
• v.13 no.7
• /
• pp.520-533
• /
• 2007

The CRM(Customer Relationship Management) is the business strategy model for higher profits and competitive power of the enterprise in a new business environment. The large-scale customer response service technique uses internet, e-mail, SMS (Short Message Service), Telephony service, DM(Direct Mail) by customer channel point. Recently, business model diversify for new contract and retaining existing customer to the effort for a profitable model of business. This paper is based on Avaya PDS(Predictive Dialing System) model for CRM bond center. If the number of "available" agents are less than the number of inbound channels, then there may be real-time response problems in PDS system implemented. The Organization cannot afford to have many agents in available mode because of the high cost of manpower. This paper provides two contributions to the study. First, we present Call Object Management Mechanism of Customer Channel integration for reduce outbound consulting and reduce CallBack data in the PDS. Second, we design and implement the proposed system. Our simulation results show analysis of old model and proposed model. The proposed model can be efficiently used in Large-scale CRM.

• Korean Journal of Ecology and Environment
• /
• v.34 no.1 s.93
• /
• pp.62-69
• /
• 2001

This study was investigated discharge and water quality for rainy days at the inflow streams (Gog-Kyo, Mu-Han, Sap-Kyo and Nam-Won) into Lake Sap-Kyo from June to November of 1999. The eventual aim of this study was to improve the water quality of Lake Sap-Kyo. Therefore, in order to reduce inflow pollutants loading into Lake Sap-Kyo, we investigated characteristics of stormwater runoff and estimated pollutant loading for the rainy season. The results of that Sap-Kyo stream is $5.75\;m^3/sec$ flow and influences water quantity of Lake Sap-Kyo greatly during the dry weather. Gog-Kyo stream influence to quantity of Lake Sap-Kyo greatly for the rainy days. Gog-Kyo stream and Sap-Kyo stream are $12.13\;m^3/sec$ and $8.49\;m^3/sec$, respectively. The reason is that the watershed area of Gog-Kyo stream is larger than other streams. When we prepare to plan management to improve the water quality of Lake Sap-Kyo, we have to consider that runoff characteristics by land use. Among the annual total pollutants loading inflow Lake Sap-Kyo, the ratio of non-point pollutants loading estimated that SS, BOD, T-N and T-P are 62%, 43%, 41% and 27%, respectively. Therefore, in order to improve water quality of Lake Sap-Kyo, we have to reduce non-point pollutants loading.

• International Journal of Highway Engineering
• /
• v.13 no.3
• /
• pp.157-165
• /
• 2011

With respect to the trend of highway traffic accident, highway accident is in decline, whileas, the fatality is on an increasing trend. Thus, many efforts to decrease highway traffic accidents and improve the safety, are required. In particular, in case of highway, the management standard by grade for accident black spot is designated. Thus, investing the effect factors by grade for highway traffic accident is required in detail. Thus, in this study, the factors affecting the traffic accidents among the environmental factors based on the graded data for the accident black spot in the applicable section targeting the Seoul-Pusan Express Highway, were reviewed; accident forecasting model which would analyze the characteristics of the accidents for determining the accident grade, was developed. As a result of establishing a model by using Quantification Theory of Type II, considering the characteristics of the dependent and independent variables based on the geometric structure, 'the fixed variable' among the variables relating to the accident, for the variables influencing over the accident grade, 'the type of vans, a chassis and people', 'the trailers, special vehicles and chassis people' and 'the negligence of watching and cloudy weather' were analyzed as common factors, in case of 'horizontal alignment', 'longitudinal slope' and, 'barricade' respectively.

• Proceedings of the Korean Geotechical Society Conference
• /
• 1991.10a
• /
• pp.332-347
• /
• 1991

Accurate prediction of future settlement is essential for the settlement control of soft soil by pre-loading method. To predict future settlement in clayey soft soils, several methods like Asaoka method, Hyperbolic Method and Hoshino method are currently being used. These methods predict the future sett1ement by mathmatical treatment of the measured settlement data on the basis of consolidtion theory and empiricism. But the correlation coefficient between the measured and the predicted settlement was relatively low (0.8~0.9). Also, the prediction of future settlemet for the design load is very difficult. In this article, the measured field settlement data was treated as the the field consolidation test. Hence, condolidation coefficient(Cv) and compression index(Cc) was evaluated from the field settlement data. Cv and Cc values from field data was used to calculate the degree of consolidation and settlement at desired time. By this method, the correlation coefficent between the measured and the predicted settlement was significantly increased(0.97~0.99). Also the settlement by the design load after the improvement of soft soil could be predicted reasonably. This method is quite rational and sound but it requires thousands of calculation steps. Today, by the aid of low priced personal computers above mentioned technique could be used much acre economically and effectively than conventional methods. This article presented the mechanisms and capacities of this method and demonstrated the enhanced correlation coefficient when applied to actual field settlement data.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.17 no.2
• /
• pp.1-14
• /
• 2014

In this study, the change characteristics of urban spatial structure in Daegu were analyzed connecting with urban planning for efficient urban management. Urban development process from 1970 to 2010 in Daegu was analyzed utilizing Getis-Ord $G_i^*$ methodology, a spatial statistical method, and it was identified that Daegu was in the stage of disurbanization. However, as Daegu orients multi-nuclei city, it was difficult to explain the stage of urban development after disurbanization in 2000. Accordingly, to analyze detailed changes in spatial structure in multi-centric areas after 2000, population, land price and employment factor changes were analyzed using Bachi Measurement. According to analytical results, multi-centralization process has been continued in Daegu. Urban core area and Chilgok area showed spatial structure change into distribution process, Ansim area into concentration process, and Seongseo and Talseo area into concentration and distribution process. Therefore, urban planning considering the regional characteristics are needed for efficient urban management.

• Journal of the Korea Convergence Society
• /
• v.5 no.4
• /
• pp.61-68
• /
• 2014

In the present study, we aimed to examine the effects of Schroth exercise(three-dimensional convergence exercise) on pulmonary function(vital capacity, and chest expansion), Cobb's angle, scoliometer angle, and erector spinae muscle activity. We examined 40 students with idiopathic scoliosis(Cobb's angle $10^{\circ}$). They were divided into the Schroth and conventional exercise groups, with 20 people in each group. Statistical analysis was performed by using SPSS 18.0 with a paired t-test(pre-post difference) and an independent t-test(between-group differnence). the result of were as follows; 1) After 8 weeks of Schroth exercise, significant improvements were observed in Cobb's angle, rib hump, vital capacity, chest expansion, and right thoracic longissimus muscle activity. 2) After 8 weeks of conventional exercise, a significant improvement was observed only in chest expansion. These findings indicate that the Schroth exercise program improved the Cobb's angle, rib hump, pulmonary function, and sEMG results. Therefore, this study demonstrates the usefulness of the Schroth exercise program for idiopathic scoliosis.

• Journal of the Korean GEO-environmental Society
• /
• v.15 no.8
• /
• pp.5-11
• /
• 2014

In this study, chemical analysis and ecotoxicity tests of leachate from disposal site for foot-and-mouth disease carcasses (FMD leachate) were conducted to collect fundamental data that will be used to develop environmental risk assessment tools for FMD leachate. For chemical analysis, concentration of $Cl^-$, $NH{_4}{^+}-N$, Korea standard method indicators for detection of leachate released from animal carcasses burial site into groundwater and NRN (Ninhydrin-Reactive Nitrogens), a newly suggested screening test indicator to detect groundwater contamination by FMD leachate, were assessed. For ecotoxicity tests, luminescent bacteria (V. fischeri), micro-algae (P. subcapitata) and water flea (D. magna) were selected as test species. Correlation analysis between the concentration of $Cl^-$, $NH{_4}{^+}-N$, NRN and the toxicity to V. fischeri was performed to identify the better indicators to monitor FMD leachate contamination. From regression analysis, the concentration of the indicators in FMD leachate contaminated sample that induced halfmaximal toxic effect to V. fischeri was evaluated. Results obtained from this study can be applied to assess the risk by FMD leachate and to establish the guideline to manage risk in relation to FMD leachate.

• Korean Journal of Construction Engineering and Management
• /
• v.16 no.4
• /
• pp.50-59
• /
• 2015

While the international construction industry for Korean companies have grown in market size exponentially in the recent years, the profit rate of small and medium sized construction companies (SMCCs) are incomparably lower than those of large construction companies. Furthermore, small and medium size companies, especially subcontractor, lacks the judgement of project involvement appropriateness, which leads to an unpredictable profit rate. Therefore, this research aims to create a profit rate prediction model for the international construction project focusing on SMCCs. First, the factors that influence the profit rate and the area of profit zone are defined by using a total of 8,637 projects since the year 1965. Seconds, an extensive literature review is conducted to derive 10 influencing factors. Multiple regression analysis and corresponding judgement technique are used to derive the weight of each factor. Third, cased based reasoning (CBR) methodology is applied to develop the model for profit rate analysis in the project participation review stage. Using 120 validation data set, the developed model showed 11% (14 data sets) of error rate for type 1 and type 2 error. In utilizing the result, project decision makers are able to make decision based on authentic results instead of intuitive based decisions. The model additionally give guidance to the Korean subcontractors when advancing into the international construction based on the model result that shows the profit distribution and checks in advance for the quality of the project to secure a sound profit in each project.