• Journal of Convergence for Information Technology
• /
• v.12 no.4
• /
• pp.260-269
• /
• 2022

In this paper, We propose an anomaly detection model using deep neural network to automate the identification of outliers of the national air pollution measurement network data that is previously performed by experts. We generated training data by analyzing missing values and outliers of weather data provided by the Institute of Environmental Research and based on the BeatGAN model of the unsupervised learning method, we propose a new model by changing the kernel structure, adding the convolutional filter layer and the transposed convolutional filter layer to improve anomaly detection performance. In addition, by utilizing the generative features of the proposed model to implement and apply a retraining algorithm that generates new data and uses it for training, it was confirmed that the proposed model had the highest performance compared to the original BeatGAN models and other unsupervised learning model like Iforest and One Class SVM. Through this study, it was possible to suggest a method to improve the anomaly detection performance of proposed model while avoiding overfitting without additional cost in situations where training data are insufficient due to various factors such as sensor abnormalities and inspections in actual industrial sites.

• Journal of Environmental Health Sciences
• /
• v.46 no.5
• /
• pp.513-524
• /
• 2020

Objective: The main purpose of this study is to evaluate the environmental and biological exposure of local residents who consumed arsenic-contaminated drinking water for less than one year. Methods: As a part of water quality inspections for small-scale water supply facilities, surveys were conducted of residents of two villages that exceeded the arsenic threshold for drinking water. The environmental impact survey consisted of surveys on water quality, soil, and crops in the surveyed area. Biological monitoring was performed by measuring the separation of arsenic species in urine and total arsenic in hair. Results: In the results of biological monitoring, the concentrations of AsIII and AsV were 0.08 and 0.16 ㎍/L, respectively. MMA and DMA were 0.87 and 36.19 ㎍/L. There was no statistically significant difference between the group who drank arsenic-removed groundwater or water from the small-scale supply facility and the group who drank tap water, purified water, or commercial bottled water. Some of the water samples exceeded the arsenic threshold for drinking water. There were no samples in the soil or rice that exceeded the acceptable threshold. Conclusion: In the case of short-term exposure to arsenic-contaminated drinking water for less than one year, there were no significant problems of concern from the evaluation of biological monitoring after arsenic was removed.

• Journal of Korean Society on Water Environment
• /
• v.34 no.2
• /
• pp.226-233
• /
• 2018

Small-scale wastewater discharge facilities account for 98% of all workplaces, but in the generation and emission of major pollutants, they account for 27.5 % and 23.5 %, respectively. Since the proportion of the emission load of the small-scale workplace is not large, the national environmental policy has been established mainly around large-scale wastewater discharge facilities. However, in the case of specific hazardous substances in water, the amount of the discharge load of the small-scale wastewater discharge facility was 2.4 times higher than that of the generation load. Certain types of specific hazardous substances in water, which have a higher discharge load than large-scale wastewater discharge facilities, account for 24 ~ 32 %. There are also cases in which the discharge load from a small-scale discharge facility is more than four times higher, depending on the specific kind of water pollutant. As a result of inspections, the violation rate of the small-scale wastewater discharge facility among the total violations by facilities is 93.9 ~ 97.5 %. As a result, the ecotoxicity value of small-scale wastewater discharge facilities was high in most industries, and there was a fluctuation in the measured value. This indicates that the ecological integrity of the water system can be largely influenced by small-scale wastewater discharge facilities. Therefore, it is necessary to expand the environmental management of small-scale wastewater discharge facilities, and in some cases, the effect of the improvement in quality may be more significant than in the management of large-scale wastewater discharge facilities.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.1
• /
• pp.453-458
• /
• 2016

One of the most common applications of machine vision is quality inspections in automated production. In this study, a welding inspection system that is controlled by a PC and a PLC equipped with a multi-camera setup was developed. The system was designed to measure the primary dimensions, such as the length and width of the welding areas. The TCP/IP protocols and multi-threading techniques were used for parallel control of the optical components and physical distribution. A coaxial light was used to maintain uniform lighting conditions and enhance the image quality of the weld areas. The core image processing system was established through a combination of various algorithms from the OpenCV library. The proposed vision inspection system was fully validated for an actual weld production line and was shown to satisfy the functional and performance requirements.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.183-183
• /
• 2023

Smart water cities (SWC) are urban municipalities that utilizes modern innovations in managing and preserving the urban water cycle in the city; with the purpose of securing sustainability and improving the quality of life of the urban population. Understanding the different urban water characteristics and management strategies of cities situate a baseline in the development of evaluation scheme in determining whether the city is smart and sustainable. This research herein aims to develop measurements and evaluation for SWC Key Performance Indicators (KPIs), and set up a unified global standard and certification scheme. The assessment for SWC is performed in technical, as well as governance and prospective aspects. KPI measurements under Technical Pillar assess the cities' use of technologies in providing sufficient water supply, monitoring water quality, strengthening disaster resilience, minimizing hazard vulnerability, and maintaining and protecting the urban water ecosystem. Governance and Prospective Pillar on the other hand, evaluates the social, economic and administrative systems set in place to manage the water resources, delivering water services to different levels of society. The performance assessment is composed of a variety of procedures performed in a quantitative and qualitative manner, such as computations through established equations, interviews with authorities in charge, field survey inspections, etc. The developed SWC KPI measurements are used to evaluate the urban water management practices for Busan Eco Delta city, a Semulmeori waterfront area in Gangseo district, Busan. The evaluation and scoring process was presented and established, serving as the basis for the application of the smart water city certification all over the world. The established guideline will be used to analyze future cities, providing integrated and comprehensive information on the status of their urban water cycle, gathering new techniques and proposing solutions for smarter measures.

• Journal of IKEEE
• /
• v.28 no.3
• /
• pp.474-478
• /
• 2024

In this paper, we proposes a deep learning network for quality inspection in a multi-camera inline inspection system for pharmaceutical containers. The proposed deep learning network is specifically designed for pharmaceutical containers by using data produced in real manufacturing environments, leading to more accurate quality inspection. Additionally, the use of an inline-capable deep learning network allows for an increase in inspection speed. The development of the deep learning network for quality inspection in the multi-camera inline inspection system consists of three steps. First, a dataset of approximately 10,000 images is constructed from the production site using one line camera for foreign substance inspection and three area cameras for dimensional inspection. Second, the pharmaceutical container data is preprocessed by designating regions of interest (ROI) in areas where defects are likely to occur, tailored for foreign substance and dimensional inspections. Third, the preprocessed data is used to train the deep learning network. The network improves inference speed by reducing the number of channels and eliminating the use of linear layers, while accuracy is enhanced by applying PReLU and residual learning. This results in the creation of four deep learning modules tailored to the dataset built from the four cameras. The performance of the proposed deep learning network for quality inspection in the multi-camera inline inspection system for pharmaceutical containers was evaluated through experiments conducted by a certified testing agency. The results show that the deep learning modules achieved a classification accuracy of 99.4%, exceeding the world-class level of 95%, and an average classification speed of 0.947 seconds, which is superior to the world-class level of 1 second. Therefore, the effectiveness of the proposed deep learning network for quality inspection in a multi-camera inline inspection system for pharmaceutical containers has been demonstrated.

• Journal of Service Research and Studies
• /
• v.14 no.3
• /
• pp.46-59
• /
• 2024

The purpose of this study is to understand how the image of a tourist destination perceived by potential tourists, who indirectly experience negative incidents through social media, affects their behavioral intentions. Based on the Theory of Planned Behavior, the relationship between image and behavioral intention is explained through attitudes toward the destination, subjective norms, and perceived behavioral control. Furthermore, the study analyzes whether the quality of the relationship with the tourist destination perceived by potential tourists moderates the relationship between the image of the destination and attitudes toward it when exposed to negative incidents. A scenario-based survey was conducted with 256 potential Chinese tourists. The results showed that the overall image of the destination had a positive effect (+) on attitudes toward the destination, subjective norms, and perceived control. In turn, attitudes toward the destination, subjective norms, and perceived control all positively (+) influenced behavioral intentions. Lastly, the moderating effect of relationship quality between overall image and attitudes toward the destination was verified. The implications of this study suggest that when negative incidents occur at a tourist destination, negative images can be perceived. Therefore, local governments should ensure thorough inspections and enforcement regarding pricing, services, and illegal operations to prevent such occurrences. Additionally, destination marketers should strive to enhance marketing management and promotion efforts, particularly working to establish positive relationship quality with tourists who have previously visited the destination.

• Journal of the Society of Disaster Information
• /
• v.17 no.3
• /
• pp.608-616
• /
• 2021

Purpose: Safety inspections by existing personnel have been limited in evaluation and data securing due to concerns about the safety of technicians or difficulty in accessing them, and are becoming a bigger problem as the number of maintenance targets increases due to the aging of facilities. As drone technology develops, it is possible to ensure the safety of personnel, secure visual data, and diagnose quickly, and use it is increasing as safety inspection of facilities by drones was introduced recently. In order to further enhance utilization, it is considered necessary to base a consideration standard for facility appearance investigation by drones, and in this paper, research was conducted on dams. Method: To calculate the quality, existing domestic safety inspection and drone-related consideration standards were investigated, and procedures related to safety inspection using drones were compared and analyzed to review work procedures and construction types. In addition, empirical data were collected through drone photography and elevation image production for the actual dam. Result: Work types for safety inspection of facilities using drones were derived, and empirical survey results were collected for two dams according to work types. The existing guidelines were applied for the adjustment ratios for each structural type and standard of the facility, and if a meteorological reference point survey was necessary, the unmanned aerial vehicle survey of the construction work standard was applied. Conclusion: The finer the GSD in appearance investigation using drones, the greater the number of photographs taken, and the concept of adjustment cost was applied as a correction to calculate the consideration standard. In addition, it was found that the problem of maximum GSD indicating limitations should be considered in order to maintain the safe distance.

• The KIPS Transactions:PartD
• /
• v.10D no.4
• /
• pp.727-734
• /
• 2003

Recently various quality assurance activities have been applied in software industry for the purpose of software qualify improvement, and the ultimate target of those activities are focused on removing defects from its developed applications. We declared "ZERO DEFECT 21" movement on March 1999 whose purpose is to deliver defect-free applications to the customer. In this paper we would like to introduce the followings $\circled1$ Approaching Methods, $\circled2$ Achievements of "ZERO DEFECT 21". After accomplishing first you of "ZERO DEFECT 21" movement which consist of Audits and Software inspections, we could get the following improvement . $\circled1$ due to conducting the "Audits," we could prevent 22 cases of customer claims, enhance 11.7% of design quality and improve 23.3% of deliverable reusability : $\circled2$ also, due to conducting the "Periodic Sampling inspection and Final inspection," we could enhance 123% of defect rate compared with early stage of development and 247% of defect rate compared with previous yew. Based on the survey results, we could conclude that "ZERO DEFECT 21 " movement provides confidence to project team members and reliability to our customers.ce to project team members and reliability to our customers.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.28 no.4
• /
• pp.55-61
• /
• 2024

Recently, the number of aging concrete structures is steadily increasing. This is because many of these structures are reaching their expected lifespan. Such structures require accurate inspections and persistent maintenance. Otherwise, their original functions and performance may degrade, potentially leading to safety accidents. Therefore, research on objective inspection technologies using deep learning and computer vision is actively being conducted. High-resolution images can accurately observe not only micro cracks but also spalling and exposed rebar, and deep learning enables automated detection. High detection performance in deep learning is only guaranteed with diverse and numerous training datasets. However, surface damage to concrete is not commonly captured in images, resulting in a lack of training data. To overcome this limitation, this study proposed a method for generating concrete surface damage images, including cracks, spalling, and exposed rebar, using stable diffusion. This method synthesizes new damage images by paired text and image data. For this purpose, a training dataset of 678 images was secured, and fine-tuning was performed through low-rank adaptation. The quality of the generated images was compared according to three base models of stable diffusion. As a result, a method to synthesize the most diverse and high-quality concrete damage images was developed. This research is expected to address the issue of data scarcity and contribute to improving the accuracy of deep learning-based damage detection algorithms in the future.