• Journal of Intelligence and Information Systems
• /
• v.26 no.1
• /
• pp.47-73
• /
• 2020

KTX rolling stocks are a system consisting of several machines, electrical devices, and components. The maintenance of the rolling stocks requires considerable expertise and experience of maintenance workers. In the event of a rolling stock failure, the knowledge and experience of the maintainer will result in a difference in the quality of the time and work to solve the problem. So, the resulting availability of the vehicle will vary. Although problem solving is generally based on fault manuals, experienced and skilled professionals can quickly diagnose and take actions by applying personal know-how. Since this knowledge exists in a tacit form, it is difficult to pass it on completely to a successor, and there have been studies that have developed a case-based rolling stock expert system to turn it into a data-driven one. Nonetheless, research on the most commonly used KTX rolling stock on the main-line or the development of a system that extracts text meanings and searches for similar cases is still lacking. Therefore, this study proposes an intelligence supporting system that provides an action guide for emerging failures by using the know-how of these rolling stocks maintenance experts as an example of problem solving. For this purpose, the case base was constructed by collecting the rolling stocks failure data generated from 2015 to 2017, and the integrated dictionary was constructed separately through the case base to include the essential terminology and failure codes in consideration of the specialty of the railway rolling stock sector. Based on a deployed case base, a new failure was retrieved from past cases and the top three most similar failure cases were extracted to propose the actual actions of these cases as a diagnostic guide. In this study, various dimensionality reduction measures were applied to calculate similarity by taking into account the meaningful relationship of failure details in order to compensate for the limitations of the method of searching cases by keyword matching in rolling stock failure expert system studies using case-based reasoning in the precedent case-based expert system studies, and their usefulness was verified through experiments. Among the various dimensionality reduction techniques, similar cases were retrieved by applying three algorithms: Non-negative Matrix Factorization(NMF), Latent Semantic Analysis(LSA), and Doc2Vec to extract the characteristics of the failure and measure the cosine distance between the vectors. The precision, recall, and F-measure methods were used to assess the performance of the proposed actions. To compare the performance of dimensionality reduction techniques, the analysis of variance confirmed that the performance differences of the five algorithms were statistically significant, with a comparison between the algorithm that randomly extracts failure cases with identical failure codes and the algorithm that applies cosine similarity directly based on words. In addition, optimal techniques were derived for practical application by verifying differences in performance depending on the number of dimensions for dimensionality reduction. The analysis showed that the performance of the cosine similarity was higher than that of the dimension using Non-negative Matrix Factorization(NMF) and Latent Semantic Analysis(LSA) and the performance of algorithm using Doc2Vec was the highest. Furthermore, in terms of dimensionality reduction techniques, the larger the number of dimensions at the appropriate level, the better the performance was found. Through this study, we confirmed the usefulness of effective methods of extracting characteristics of data and converting unstructured data when applying case-based reasoning based on which most of the attributes are texted in the special field of KTX rolling stock. Text mining is a trend where studies are being conducted for use in many areas, but studies using such text data are still lacking in an environment where there are a number of specialized terms and limited access to data, such as the one we want to use in this study. In this regard, it is significant that the study first presented an intelligent diagnostic system that suggested action by searching for a case by applying text mining techniques to extract the characteristics of the failure to complement keyword-based case searches. It is expected that this will provide implications as basic study for developing diagnostic systems that can be used immediately on the site.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.39 no.6
• /
• pp.691-702
• /
• 2019

Flood inundation map has various important roles in terms of municipal planning, timely dam operation, economic levee design, and building flood forecasting systems. Considering that the riparian areas adjacent to national rivers with high potential flood vulnerability conventionally imposed special cares to justify applications of recently available two- or three-dimensional flood inundation numerical models on top of digital elevation models of dense spatial resolution such as LiDAR irrespective of their high costs. On the contrary, local streams usually could not have benefits from recent technological advances, instead they inevitably have relied upon time-consuming manual drawings or have accepted DEMs with poor resolutions or inaccurate 1D numerical models for producing inundation maps due mainly to limited budgets and suitable techniques. In order to efficiently and cost-effectively provide a series of flood inundation maps dedicatedly for the local streams, this study proposed an OpenGIS-based flood mapping tool named Open Flood Mapper (OFM). The spatial accuracy of flood inundation map derived from the OFM was validated throughout comparison with an inundation trace map acquired after typhoon Nari in Hancheon basin located in Jeju Island. Also, a series of inundation maps from the OFM were comprehensively investigated to track the burst of flood in the extreme flood events.

• Analytical Science and Technology
• /
• v.7 no.1
• /
• pp.33-39
• /
• 1994

The purpose on this study was to develop a new improved chromatographic method for determination of trace phenols from environmental waste water. The research was carried out with selected 8 phenols, and solid-phase extraction was employed as sample pretreatment method. The coupling of XAD-4 and Dowex $1{\times}8$ resin as preconcentration column increased the selectivities toward interferences coexisted in matrix. Automation was accomplished with on-line process of pretreatment and HPLC system. After elution of sample through XAD-4 column, phenols were adsorbed by dispersion force, then displaced from it by ACN basified, simultaneously and selectively readsorbed via anion exchange on Dowex $1{\times}8$. Dowex $1{\times}8$ column was washed by water. Phenols readsorbed were removed from Dowex $1{\times}8$ column by a minimum volumn of methanol containing HCl. Each pretreatment step was connected by switching valves and the eluate was directly on-line injected to obtain fast and reliable results into the HPLC. Recovery of phenols was greater than 90%. To examine utility of this method, analysis of phenols from laboratory waste water sample which was added some organic pollutants to find with phenols on environmental waste water were also accomplished without their interference effects.

• Journal of Navigation and Port Research
• /
• v.34 no.6
• /
• pp.479-485
• /
• 2010

To handle container effectively is one of the most important factors in a port because working time is linked soon into cost. Since the middle of 1990s, RMGC(Rail-Mounted Gantry Crane) and RTGC(Rubber-Tired Gantry Crane) have been developed and widely used to operate containers in the yard. The RTGC is more difficult than RMGC in the automatic control system design. Although, the RTGC is largely advantaged to free driving environment, it has some considerable disadvantages in the system operating. In general, the problems are due to tire slip and lack of tire pressure etc. Therefore, a desirable research result has not been shown in this time. So, in this paper, we propose a new approach to design tracking control system for the RTGC in which the mathematical modeling is included. From the simulation results, the control performance of the designed control systems is evaluated.

• Korean Journal of Clinical Laboratory Science
• /
• v.47 no.3
• /
• pp.105-111
• /
• 2015

In late December 2013, the Ebola virus emerged from West Africa. The outbreak started in Guinea and rapidly spread to Liberia and Sierra Leone. Initially, the virus is spread to the human population after contact with infected wildlife and then spread person-to-person through direct contact with body fluids such as blood, sweat, urine, semen, and breast milk. The Ebola virus infects endothelial cells, mononuclear phagocytes and hepatocytes. It causes massive damage to internal tissues and organs, such as blood vessels and the liver, and ultimately death. Most tests for the virus RNA rely on a technology called reverse-transcriptase polymerase chain reaction (RT-PCR). While this method is highly sensitive, it is also expensive, requiring skilled scientists, and delicate power supplies. The strip analytical technique (enzyme-linked immunosorbent assay or ELISA) detects antigens or antibodies to the Ebola virus. This test is cheap and does not require electricity or refrigeration. Despite ongoing efforts directed at experimental treatments and vaccine development, current medical work on the Ebola viral disease is largely limited to supportive therapy. Thus, rapid and reliable diagnoses of the Ebola virus are critically important for patient management, infections, prevention, and control measures.

• Journal of Life Science
• /
• v.17 no.2 s.82
• /
• pp.266-271
• /
• 2007

Bisphenol A (BPA) has been widely used as a monomer for production of epoxy resins and polycarbonate plastics. The annual production of BPA exceeds 640,000 metric tons in worldwide. BPA, a suspected phenolic endocrine disrupter, is moderately soluble and frequently detected in industrial wastewater. To date, HPLC and GC has been used for BPA analysis. However, HPLC and GC-analysis need high operation lost, experts, and an elaborate pre-treatment of samples, and is difficult to apply on-time and mass analysis. Therefore, simple, mass and rapid detection of BPA in environments is necessary. In the present study, spectrophotometric method of BPA quantification was developed. Based on blue-color product formation with BPA and ferric chloride/ferricyanide under the optimized conditions, the standard curve was acquired $({\lambda}_{750}=0.061\;BPA\;[{\mu}M]+0.07155,\;R^2=0.992)$. Using an established method, the BPA contents in the soil extract, and different water samples and living products, including disposable syringe, cup and plastic tube, were analyzed. The results suggested that the method is useful for BPA determination from different massive samples. Since the BPA metabolites, nontoxic 4-hydroxyacetophenone or 4-hydroxybenzaldehyde, did not form blue-color product, this method is also useful to screen a microorganism for BPA bioremediation.

• Journal of IKEEE
• /
• v.21 no.4
• /
• pp.368-374
• /
• 2017

In this Paper, we developed a low power type LED security light using LED lighting that substitutes a 220[V] commercial power source for a solar cell module instead of a halogen or a sodium lamp. in addition, a PWM type drive control circuit is designed to minimize the heat generation problem and the drive current of the LED drive controller. in developed system, The light efficiency measurement value is 93.6[lm/W], and a high precision temperature sensor is used inside the controller to control the heat generation of the LED lamp. In order to eliminate the high heat generated from the LED lamp, it is designed to disperse quickly into the atmosphere through the metal insertion type heat sink. The heat control range of LED lighting was $50-55[^{\circ}C]$. The luminous flux and the lighting speed of the LED security lamp were 0.5[s], and the beam diffusion angle of the LED lamp was about $110[^{\circ}C]$ by the light distribution curve based on the height of 6[m].

• Journal of the Korean Institute of Gas
• /
• v.12 no.2
• /
• pp.48-52
• /
• 2008

According to extremely industrial growth, gas facilities, equipments and chemical plants are gradually increased due to incremental demands of annual amount of gases. The safety management of gases, however, is still far from their requirements. Methane, the principal ingredient of natural gas, is inflammable and explosive and is much used in factories and houses. Therefore, these gas safety management is essential. So, we, with a program of the gas safety management, hope to develop the detection system of methane gas leak using mid-infrared ray LED and PD with $3.2\;{\mu}m$. The cryogenic cooling device is indispensible at laser but needless at LED driven on the room temperature if manufacturing optical sensor with $3.2\;{\mu}m$. It, consequently, is not only possible to implement for subminiature and portable type but also able to speedily detect methane of extremely small quantities because the $CH_4$ absorption intensity at $3.2\;{\mu}m$ is stronger than that at $1.67\;{\mu}m$. Our objective of research is to prevent gas leak accidents from occurring previously and to minimize the extent of damage from them.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.23 no.6
• /
• pp.639-645
• /
• 2017

Application Specific Messages (ASM) have been introduced by a number of international bodies, such as the International Maritime Organization (IMO), the International Telecommunication Union (ITU) and the International Association of Lighthouse Authorities (IALA), for the purpose of resolving AIS overloading issues caused by an increasing number of ships using AIS systems. ASM communication will transmit a large amount of safety-related information at sea, including meteorological information, accident reporting, and navigational warnings. Specifically, this message transaction system is expected to be actively used for communication among ships and for ship-to-shore (4S), where VHF communication through voice was standard. In order to design a user-oriented service through standardised AIS-ASM messaging in the future, the need for analysis of this seems to be quite critical. In order to reflect users' AIS-ASM communication needs, therefore, frequently-occurring marine communication messages were analysed through a questionnaire survey conducted on 57 marine officers and 50 VTS operators. Based on the survey results, a list of key standardised messages was suggested as a reference for future AIS message development.

• Korean Journal of Construction Engineering and Management
• /
• v.20 no.2
• /
• pp.3-12
• /
• 2019

Despite the importance and function of productivity information, in the Korean construction industry, the method of collecting and analyzing productivity data has not been organized. Also, in most cases, productivity management is reliant on the experience and intuitions of field managers, and productivity data are rarely being utilized in planning and management. Accordingly, this study intends to develop a prediction model for interior finishes of apartment using deep learning techniques, so as to provide a foundation for analyzing the productivity impacting factors and predicting productivity. The result of the study, productivity prediction model for interior finishes of apartment using deep learning techniques, can be a basic module of apartment project management system by applying deep learning to reliable productivity data and developing as data is accumulated in the future. It can also be used in project engineering processes such as estimating work, calculating work days for process planning, and calculating input labor based on productivity data from similar projects in the past. Further, when productivity diverging from predicted productivity is discovered during construction, it is expected that it will be possible to analyze the cause(s) thereof and implement prompt response and preventive measures.