• Journal of Appropriate Technology
• /
• v.5 no.2
• /
• pp.70-81
• /
• 2019

The garment industry is one of the most labor-intensive manufacturing industries, with its sewing process relying almost entirely on manual labor. Its costs highly depend on the efficiency of this production line and thus is crucial to determine the production rate in real-time for line balancing. However, current production tracking methods are costly and make it difficult for many Small and Medium-sized Enterprises (SMEs) to implement them. As a result, their reliance on manual counting of finished products is both time consuming and prone to error, leading to high manufacturing costs and inefficiencies. In this paper, a production tracking system that uses the sewing machines' energy consumption data to track and count the total number of sewing tasks completed through Convolutional Neural Network (CNN) classifiers is proposed. This system was tested on two target sewing tasks, with a resulting maximum classification accuracy of 98.6%; all sewing tasks were detected. In the developing countries, the garment sewing industry is a very important industry, but the use of a lot of capital is very limited, such as applying expensive high technology to solve the above problem. Applied with the appropriate technology, this system is expected to be of great help to the garment industry in developing countries.

• Journal of agriculture & life science
• /
• v.50 no.1
• /
• pp.117-124
• /
• 2016

Researches on soil microbial community are increasing to assess ecosystem responses to anthropogenic disturbances and to provide an indicator of ecosystem recovery. Microbial communities are able to respond more rapidly to environmental changes than plants and therefore they may provide an early indication of the ecosystem recovery trajectory. This study was conducted using 16S rRNA gene pyrosequencing of soil samples to compare soil bacterial community composition between artificially covered soils of the Baedudaegan ridgeline and their adjacent forest soils in two restoration project sites, Ihwaryeong and Yuksimnyeong, which were completed in 2012 and 2013, respectively. Richness of the Phylum level was 29.3 in Ihwaryeong and 32.3 in Yuksimnyeong. Significant difference in the richness between artificial restored soils and adjacent forest soils(p<0.01) was observed, however no significant difference was observed for site location and soil depth. Acidobacteria(37.3%) and Proteobacteria(31.1%) were more abundant than any other phylum in collected soil samples. Also, we found the significant difference in the relative abundance of the two abundant phyla between artificially restored soils and their adjacent forest soils (Proteobacteria, 38.1% in restored soils vs 24.2% in adjacent forest soils, p<0.01; Acidobacteria, 55.4% in restored soils vs 19.2% in adjacent forest soils, p<0.001). The results support the previous researches indicating that soil bacterial community composition is affected by nutritional status of soils and that Acidobacteria is also strongly influenced by pH, thus favoring soils with lower pH. This study could be utilized to monitor and evaluate restoration success of forest soil environment quantitatively.

• Journal of the Korean Institute of Gas
• /
• v.27 no.2
• /
• pp.7-15
• /
• 2023

The electric submersible pump (ESP) has been operating in production wells around the world because of its high applicability and operational efficiency among artificial lift techniques. When operating an ESP in a reservoir, variables such as temperature, pressure, gas/oil ratio, and flow rate are factors that affect ESP performance. In particular, free gas in the production fluid is a major factor that reduces the life and operational efficiency of ESP. This study presents the flow loop system which can implement the performance and damage tests of ESP considering field operating conditions to quantitatively analyze the variables that affect ESP performance. The developed apparatus in an integrated system that can diagnose the failure and causes of ESP, and detect leak of tubing by linking ESP and tubing as one system. In this study, the flow conditions for stable operation of ESP were identified through single phase and two phase flow experiments related to evaluation for the performance of ESP. The results provide the basic data to develop the failure prediction and diagnosis program of ESP, and are expected to be used for real-time monitoring for optimal operating conditions and failure diagnosis for ESP operation.

• Journal of Intelligence and Information Systems
• /
• v.29 no.2
• /
• pp.241-265
• /
• 2023

A corporate insolvency prediction model serves as a vital tool for objectively monitoring the financial condition of companies. It enables timely warnings, facilitates responsive actions, and supports the formulation of effective management strategies to mitigate bankruptcy risks and enhance performance. Investors and financial institutions utilize default prediction models to minimize financial losses. As the interest in utilizing artificial intelligence (AI) technology for corporate insolvency prediction grows, extensive research has been conducted in this domain. However, there is an increasing demand for explainable AI models in corporate insolvency prediction, emphasizing interpretability and reliability. The SHAP (SHapley Additive exPlanations) technique has gained significant popularity and has demonstrated strong performance in various applications. Nonetheless, it has limitations such as computational cost, processing time, and scalability concerns based on the number of variables. This study introduces a novel approach to variable selection that reduces the number of variables by averaging SHAP values from bootstrapped data subsets instead of using the entire dataset. This technique aims to improve computational efficiency while maintaining excellent predictive performance. To obtain classification results, we aim to train random forest, XGBoost, and C5.0 models using carefully selected variables with high interpretability. The classification accuracy of the ensemble model, generated through soft voting as the goal of high-performance model design, is compared with the individual models. The study leverages data from 1,698 Korean light industrial companies and employs bootstrapping to create distinct data groups. Logistic Regression is employed to calculate SHAP values for each data group, and their averages are computed to derive the final SHAP values. The proposed model enhances interpretability and aims to achieve superior predictive performance.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.403-403
• /
• 2021

비점오염물질은 강우에 의해 유출되며 계절적, 자연적 편차가 크게 나타나고, 오염원이 광범위하게 산재하고 있어 오염물질의 발생량과 부하량의 관리가 쉽지 않다. 따라서 비점오염원 관리지역은 오염물질이 하천에 미치는 수질 특성을 파악하는 것이 중요하다. 그러나 수질항목만으로 하천의 수질 특성을 파악하기에는 어려움이 있으며, 수질 특성을 파악하기 위해 다양한 분석방법이 필요하다. 본 연구에서는 비점오염원 관리지역 중 골지천 유역의 수질 특성을 파악하기 위해 통계분석 기법을 활용하여 수질항목간의 상관관계를 분석하고자 하였다. 2017년부터 2019년까지 골지천 유역 내 5개 지점에 대하여 비강우시 23회, 강우시 지점별 173회~196회의 모니터링 결과를 이용하였으며, EC, 탁도, BOD₅, SS, T-N, T-P, TOC의 수질항목을 이용하여 Pearson 상관관계 분석을 실시하였다. 상관관계 분석 결과 비강우시 분석 결과 EC는 -0.06~-0.32, T-N은 0.19~0.37로 낮은 상관성을 갖는 것으로 나타났으며, EC와 T-N을 제외한 탁도와 BOD₅, SS, T-P, TOC의 경우 서로 0.6 이상의 상관성을 갖는 것으로 나타났다. 특히, 탁도와 SS, T-P, T-P와 TOC는 0.9 이상의 높은 상관성을 갖는 것으로 나타났다. 강우시 분석 결과 EC는 비강우시와 유사하게 -0.07~-0.24로 낮은 상관성을 갖는 것으로 나타났으며, TOC를 제외한 탁도, BOD₅, SS, T-N, T-P의 경우 서로 0.6 이상의 상관성을 갖는 것으로 나타났다. TOC의 경우 BOD₅, SS와 0.6 이상의 상관성을 갖는 반면 탁도, T-N, T-P와는 0.45, 0.44, 0.57로 다른 항목에 비해 다소 낮은 상관성을 갖는 것으로 나타났다. 비강우시 T-N은 기저 유출에 의한 영향으로 높은 농도를 나타내 다른 항목에 비해 상관성이 낮은 것으로 나타났으며, 강우시에는 비점오염물질의 유입으로 인하여 모든 항목에서 비슷한 상관성을 보이는 것으로 나타났다. 본 연구 결과 탁도와 SS, T-P의 상관성이 비강우시 0.93, 강우시 0.78로 상당히 높은 것으로 나타나, 탁도를 측정하여 SS와 T-P로 환산하여 측정하는 방법에 대한 기초자료로 활용될 수 있을 것으로 판단된다. 그러나 연구 유역의 지형적 특성이 배제되었기 때문에 추후에 이를 반영한 연구가 필요할 것으로 판단된다.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.30 no.4A
• /
• pp.337-342
• /
• 2010

Generally most sluice gates are closed and opened by a mechanical winch, a winch using an oil-pressure, or a winch mixing both. Because of their size and structure, they should be safely operated with more than two pulling devices helping each other. At the moment of their opening and closing, there usually occur some additional loads to the structure which cannot be exactly measurable at the stage of designing. Such additional loads can cause the sluice gate to be unbalanced and make it hard to open and close the gate, and by also overloading a winch, they can inflict a significant damage to the safety of the sluice gate. This paper explains a FDC(Force-Displacement Control) system which simultaneously considered the oil-pressure and displacement in order to evenly distribute the force and make a winch balanced at the opening and closing motion. This FDC system was implemented by means of the PID(Proportional Integral Derivative) function of XG 5000 program. It was experimented on a model of the sluice gate winch with the hydraulic oil pressure cylinder. The experiments showed that the developed FDC system made the winch of hydraulic oil pressure cylinder open and close cooperatively in spite of various external loads. Therefore the FDC system is proven effective when it is applied to a winch of sluice gate.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.36 no.6
• /
• pp.407-414
• /
• 2023

In this study, an automated jack-up system, applicable to various fields, was employed for 3D concrete printing and developed as a simultaneous liftable 3D concrete printing system. This developed printing system enables safe and precise jack-up by monitoring the measured jack-up distance using Pearson correlation coefficient analysis and a hydraulic system with interquartile range analysis in real-time during 3D concrete printing operations. It is possible to secure the quality of 3D concrete printing structures, which is essential for expanding the application of 3D concrete printing to construct larger structures. Specimens were printed using both conventional 3D concrete printing and simultaneous liftable 3D concrete printing to evaluate the system performance. The printed specimens were investigated using a 3D scanner. The layer-wise diameter and angle of intersection of the scanned specimens were measured, and an analysis was performed to verify the advantages of the simultaneous liftable 3D concrete printing.

• Journal of Korean Society of Forest Science
• /
• v.112 no.4
• /
• pp.451-458
• /
• 2023

As forest fires continue to increase in scale worldwide, the importance of forest roads in relation to forest fire prevention and suppression has become increasingly evident. To ensure effective functioning during a forest fire disaster, it is crucial to apply appropriate road planning and ensure roads' structural integrity. However, previous studies have predominantly focused on the impact of forest fires on firebreak efficacy and road placement, meaning that insufficient attention has been paid to ensuring the safety of these facilities. Therefore, this study sought to compare the strength of concrete facilities within areas damaged by forest fires over the past three years by using the rebound hammer test to identify signs of thermal degradation. The results revealed that concrete facilities damaged by forest fires exhibited significantly lower strength (15.6 MPa) when compared with undamaged facilities (18.0 MPa) (p<0.001), and this trend was consistent across all the target facilities. Consequently, it is recommended that safety assessment criteria for concrete forest road facilities be established to prevent secondary disasters following forest fire damage. Moreover, continuous monitoring and research involving indoor experiments are imperative in terms of enhancing the stability of forest road structures. It is expected that such research will lead to the development of more effective strategies for forest fire prevention and suppression.

• Korean Journal of Remote Sensing
• /
• v.39 no.6_1
• /
• pp.1467-1475
• /
• 2023

The public-interest direct payment program involves providing direct payments to agricultural producers and rural residents through public funds, premised on performing public functions such as environmental conservation, stable food supply, and maintaining rural communities via agricultural activities. Scientific estimation of crop cultivation areas and production levels is crucial for formulating agricultural policies linked to regulating food supply, which increasingly impacts the national economy. Conducting comprehensive on-site inspections for compliance monitoring of direct payment programs has shown very low efficiency in relation to budget and time. The expansion of areas subject to compliance monitoring and various challenges in on-site inspections necessitate streamlining current monitoring methods and devising effective strategies. As a solution, the application of Remote Sensing technology and spatial information utilization, allowing swift acquisition of necessary information for policies without overall on-site visits, is being discussed as an efficient compliance monitoring method. Therefore, this study evaluated the potential use of remote sensing for improving operational efficiency in monitoring compliance with public-interest direct payment programs. Using satellite images during farming seasons in Gimje and Hapcheon, vegetation indices and spatial variations were utilized to identify cultivated areas, presence of mixed crops, validated against on-site inspection data.

• Economic and Environmental Geology
• /
• v.49 no.5
• /
• pp.381-388
• /
• 2016

The purpose of this study is to integrate and visualize using mapping techniques based on precise seabed geomorphology, seafloor backscattering images and high-resolution underwater images of the nearshore area around the Dokdo, in the East Sea. We have been obtained the precise topography map using multibeam echosounder system around the nearshore area(~50 m) of the southern part of the Seodo. Side scan sonar survey for analysis seafloor backscattering images was carried out in the same area of topography data. High-resolution underwater images(zone(a), zone(b), zone(c)) were taken in significant habitat scope of the nearshore area of the southern part of the Seodo. Using the results of bathymetry, seafloor backscattering images, high-resolution underwater images, we performed an integrated visualization about the nearshore area of the Dokdo. The integrated visualizing techniques are possible to make the seabed characteristic mapping results of the nearshore area of the Dokdo. The integrated visualization results present more complex and reliable information than separate geological products for seabed environmental mapping study and it is useful to understand the relation between seafloor characteristics and topographic environments of the study area. The integrated visualizing techniques and mapping analysis need to study sustainably and periodically, for effective monitoring of the nearshore ecosystem of the Dokdo.