• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.7 no.4
• /
• pp.594-601
• /
• 2006

Coding of occupational and industrial codes is a major operation in census survey of Korean statistics bureau. The coding process has been done manually. Such manual work is very labor and cost intensive and it usually causes inconsistent results. This paper proposes an automatic coding system based on example-based learning. The system converts natural language input into corresponding numeric codes using code generation system trained by example-based teaming after applying manually built rules. As experimental results performed with training data consisted of 400,000 records and 260 manual rules, the proposed system showed about 76.69% and 99.68% accuracy for occupational code classification and industrial code classification, respectively.

• Industrial Engineering and Management Systems
• /
• v.8 no.1
• /
• pp.66-71
• /
• 2009

This study proposes a new framework for designing disassembly methods. In recent years, environmental problems have become global issues. Recycling of used products or resources is recognized as a matter of significance since it may help reduce the risk of exhausting natural resources. Considering possible exhaustion of limited natural resources in the near future, reuse of products would gain more environmental significance. As yet, it relies hugely on manual disassembly, which labor cost places burden on the total recycling cost. The purpose of this study is to propose a methodology designing for manual disassembly works, and a creation method of a jig. By focusing on parts' connection and attachment relationship, parts are categorized in 5 categories (parent part, joint key part, attaching key part, child part, and independent part) according to the features that parts possess, and 3 kinds of connection relationships (parent part-joint key part connection, parent part-independent part connection and child part-child part connection) are clarified. Connection relationship and attachment relationship charts have also been created, and utilizing them, disassembly orders are settled, and a disassembly jig is devised. The proposed methodology is also applied to a real product and its work time is improved 42% form 31 to 13 seconds.

• The Journal of Korea Robotics Society
• /
• v.16 no.3
• /
• pp.189-198
• /
• 2021

In this paper, we introduce the software/hardware system that can reliably calculate the distance from sensor to the model regardless of point cloud density. As the 3d point cloud map is widely adopted for SLAM and computer vision, the accuracy of point cloud map is of great importance. However, the 3D point cloud map obtained from Lidar may reveal different point cloud density depending on the choice of sensor, measurement distance and the object shape. Currently, when measuring map accuracy, high reflective bands are used to generate specific points in point cloud map where distances are measured manually. This manual process is time and labor consuming being highly affected by Lidar sparsity level. To overcome these problems, this paper presents a hardware design that leverage high intensity point from three planar surface. Furthermore, by calculating distance from sensor to the device, we verified that the automated method is much faster than the manual procedure and robust to sparsity by testing with RGB-D camera and Lidar. As will be shown, the system performance is not limited to indoor environment by progressing the experiment using Lidar sensor at outdoor environment.

• KDI Journal of Economic Policy
• /
• v.44 no.2
• /
• pp.1-28
• /
• 2022

This paper studies how COVID-19 has affected the labor market in Korea through a general equilibrium model with multiple industries and occupations. In the model, workers are allocated to one of many occupations in an industry, and industrial or occupational shocks alter the employment structure. I calibrate the model with Korean data and identify industrial and occupational shocks, referred to here as COVID-19 shocks, behind the employment dynamics in 2020 and 2021. I find that COVID-19 shocks are more severe for those with jobs with a higher risk of infection and in those that are more difficult to do from home. Interestingly, the relationship between COVID-19 shocks and infection risk weakened as the pandemic progressed, whereas the relationship between COVID-19 shocks and easiness of work-from-home strengthened. I interpret the results as meaning that the pandemic may direct future technological changes to replace tasks that require contact-intensive steps, and I simulate the impact of such technological changes through the lens of the model. The results show that such technological changes will lower the demand for manual workers compared to the demands for other occupations. This contrasts with the earlier trend of job polarization, where manual workers continued to increase their employment share, with the share of routine workers secularly declining at the same time.

• Journal of the Korea Institute of Building Construction
• /
• v.15 no.1
• /
• pp.107-113
• /
• 2015

Recently mechanization construction methods are developed rapidly in the field of construction processing. The construction industry is one of the sector that still requires a lot of manual labor of the entire industry. There are still various kinds of work done by human labors, especially in the disassembling and separation of materials for recycling. However, database of relevant statistics including estimating standards are difficult to analyze by actual human workload, and furthermore the disassembling processes are being analyzed by qualitative assessment. This study attempted to introduce the accelerometer for the quantitative evaluation of human workload in the construction field. Still, it is possible to calculate the amount of energy which is required for the assembling and disassembling of nail and screw through three-dimensional accelerometer.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.8
• /
• pp.2381-2398
• /
• 2024

The construction of virtual indoor spaces is crucial for the development of metaverses, virtual production, and other 3D content domains. Traditional methods for creating these spaces are often cost-prohibitive and labor-intensive. To address these challenges, we present a pipeline for generating digital twins of real indoor environments from RGB-D camera-scanned data. Our pipeline synergizes space structure estimation, 3D object detection, and the inpainting of missing areas, utilizing deep learning technologies to automate the creation process. Specifically, we apply deep learning models for object recognition and area inpainting, significantly enhancing the accuracy and efficiency of virtual space construction. Our approach minimizes manual labor and reduces costs, paving the way for the creation of metaverse spaces that closely mimic real-world environments. Experimental results demonstrate the effectiveness of our deep learning applications in overcoming traditional obstacles in digital twin creation, offering high-fidelity digital replicas of indoor spaces. This advancement opens for immersive and realistic virtual content creation, showcasing the potential of deep learning in the field of virtual space construction.

• Korean Journal of Medicinal Crop Science
• /
• v.6 no.1
• /
• pp.57-61
• /
• 1998

Angelica gigas, Astragalus membranaceus and Ligusticum chuanxiong have been grown for a long time in Korea as medicinal crops with underground parts. Its harvesting method has been depended entirely on manual labor. Therefore, harvesting involved much work. This study was to determine an effective mechanized harvesting method for underground parts of some medicinal crops by several machines. Labor time was decreased by 61 percent in Angelica gigas and by 70 percent in Astragalus membranaceus by the use of poclain harvester, however, in Ligusticum chuanxiong was decreased 68 percent by multi - root harvester compared with conventional system (manual harvest). The poclain harvester was suitable for harvesting in Angelica gigas and Astragalus membranaceus plots, but multi - root harvester was not satisfactory. Multi - root harvester appeared to be appropriate harvester for Ligusticum chuanxing.

• Journal of the Korean association of regional geographers
• /
• v.3 no.1
• /
• pp.135-154
• /
• 1997

The purpose of this study is to clarify the reason of the change of production-and-marketing system and of the regional division. The data for this study were collected by administering interviews with people engaging in hemp fabric industry: namely, craftsmen and managers in the production and marketing of "hemp fabric" handcraft. The summary of this study is as follows: First, the hemp fabric industry is a main subsidiary business of agriculture in Andong. The process of making hemp fabric heavily depends on manual labor. The process is divided into five stages: namely, cultivating hemp, pre-reeling, reeling, weaving, and colouring. Second, Andong "hemp fabric" handicrafts industry had been continuously growth until the late 1960s. During the period of Japan colonization, it was under boom condition: while the other traditional fabric industries were declined. In the 1970s, the decrease of the demand of hemp fabric was the result of mass production of substitute goods on factory system: while, in the 1980s, the growth of per capital income play an important role in bringing about the increased demand of hemp fabric. Third, in the 1980s. production-and-marketing system was changed as the result of the effort to improve the quality and the process, the advanced age of craftsmen, and the weak function of existing marketing systems. The social division of labor within the district is well developed between cultivating hemp, reeling and weaving. The social division of labor is also found in the partly process of handcratfs, and between the production and marketing. The social division of labor between production and marketing is not strongly developed to establish a reliable enterprise that develops a new product and opens a new market. Fourth, the spatial boundary of the production of hemp fabric handcrafts becomes limited into a special region based on the regional specialization of hemp cultivating and the differentiation of utilization of labor.

• Journal of KIISE:Software and Applications
• /
• v.36 no.10
• /
• pp.825-835
• /
• 2009

The advance in medical technology has decreased death rates from diseases such as tubercle, pneumonia, malnutrition, and hepatitis. However, death rates from cardiac diseases are still increasing. To prevent cardiac diseases and quantify cardiac function, magnetic resonance imaging not harmful to the body is used for calculating blood volumes and ejection fraction(EF) on routine clinics. In this paper, automatic left ventricle(LV) segmentation is presented to segment LV and calculate blood volume and EF, which can replace labor intensive and time consuming manual contouring. Radial threshold determination is designed to segment LV and blood volume and EF are calculated. Especially, basal slices which were difficult to segment in previous researches are segmented automatically almost without user intervention. On short axis cardiac MRI of 36 subjects, the presented algorithm is compared with manual contouring and General Electronic MASS software. The results show that the presented algorithm performs in similar to the manual contouring and outperforms the MASS software in accuracy.

• The Journal of Korean Association of Computer Education
• /
• v.7 no.4
• /
• pp.51-60
• /
• 2004

This paper proposes an automated coding system of Korean standard industry/occupation for census which reduces a lot of cost and labor for manual coding. The proposed system converts natural language responses on survey questionnaires into corresponding numeric codes using information retrieval techniques and document classification algorithm. The system was experimented with 46,762 industry records and occupation 36,286 records using 10-fold cross -validation evaluation method. As experimental results, the system show 87.08% and 66.08% production rates when classifying industry records into level 2 and level 5 codes respectively. The system shows slightly lower performances on occupation code classification. We expect that the system is enough to be used as a semi-automate coding system which can minimize manual coding task or as a verification tool for manual coding results though it has much room to be improved as an automated coding system.