• The Journal of Bigdata
• /
• v.5 no.2
• /
• pp.53-67
• /
• 2020

This study employees a supervised learning prediction model to detect nonconformity in advance of processed food manufacturing and processing businesses. The study was conducted according to the standard procedure of machine learning, such as definition of objective function, data preprocessing and feature engineering and model selection and evaluation. The dependent variable was set as the number of supervised inspection detections over the past five years from 2014 to 2018, and the objective function was to maximize the probability of detecting the nonconforming companies. The data was preprocessed by reflecting not only basic attributes such as revenues, operating duration, number of employees, but also the inspections track records and extraneous climate data. After applying the feature variable extraction method, the machine learning algorithm was applied to the data by deriving the company's risk, item risk, environmental risk, and past violation history as feature variables that affect the determination of nonconformity. The f1-score of the decision tree, one of ensemble models, was much higher than those of other models. Based on the results of this study, it is expected that the official food control for food safety management will be enhanced and geared into the data-evidence based management as well as scientific administrative system.

• Korean Journal of Ecology and Environment
• /
• v.54 no.2
• /
• pp.108-119
• /
• 2021

We aimed to develop a naturalness index for forest-dwelling birds in four national parks in Korea and to simulate the effect of species loss on this naturalness index. Five bird specialists were asked to give 112 bird species a disturbance susceptibility score (DSS), and the naturalness index was calculated based on this. The 112 bird species represented 8 orders (Cuculiformes, Piciformes, Accipitriformes, Falconiformes, Columbiformes, Caprimulgiformes, Strigiformes, and Passeriformes). DSS was the highest for Terpsiphone atrocaudata and Pitta nympha, and lowest for Pica pica, Hypsipetes amaurotis, and Streptopelia orientalis. There was a significant negative relationship between a species' population number and its DSS. Among the four national parks, Mt. Songni had the highest naturalness index, followed by Mt. Wolak, Mt. Juwang, and Mt. Wolchul. We investigated the change in biodiversity indices under four scenarios, which assumed the extinction of species with less than 5 (Scenario 1), 10 (Scenario 2), 50 (Scenario 3), and 100 individuals (Scenario 4). The results showed that although all biodiversity indices decreased as the species loss increased, they all behaved differently. Fisher's alpha diversity decreased as the number of species proportionally decreased. There was almost no change in Shannon-Wiener H' index in Scenarios 1 and 2. The naturalness index showed increased sensitivity in Scenarios 1 and 4. Our future aims are to obtain the DSS for all forest-dwelling bird species, and to adopt the naturalness index to evaluate temporal and spatial changes in biodiversity.

• Journal of Korean Society of Occupational and Environmental Hygiene
• /
• v.30 no.4
• /
• pp.331-341
• /
• 2020

Objectives: This study was conducted to evaluate perceptions of safety and risk among Korean industrial hygienists and the change between before and after the Sewol Ferry Disaster in 2014. Two surveys with questionnaires composed of 51 questions were completed by attendees of the Korea Industrial Hygiene Association(KIHA) conference. Methods: One was conducted at the 2013 KIHA Fall Conference(N=181) and the other was from the 2014 KIHA Summer Conference(N=123). Between these two surveys was the Sewol Ferry Disaster on April 14, 2014, which was believed to seriously affect safety and risk perceptions in Korea. Results: It was revealed that industrial hygienists' awareness of safety rules strengthened after the Sewol Ferry Disaster(p<0.05). It was apparent that people over the age of 30 were more sensitive to social safety. There was no significant difference in the evaluation and attitude regarding governmental safety policy between the years of 2013 and 2014. The credibility of public organizations responsible for the disaster management system decreased. The self-evaluation of respondents' safety level also decreased. This trend shows mainly in the younger generation. It was evaluated that the overall social safety level decreased and the anxiety level increased. The score on social safety on a ±5 Likert scale was 0.68 in the 2013 survey and -0.33 in the 2014 survey(p<0.05). It was reported that the most serious threat factors for accident or disaster were 'building collapse > illegalities and corruption > side effects of radiation therapy >accidents in normal activity > occupational disease,' in order. They picked 'safety ignorance > hurry-up habits and culture > focusing on short-term benefit > easy-going attitude > insufficient safety education' for the causes of low social safety levels in 2013. In 2014, they were 'safety ignorance > easy-going attitude > focusing on short-term benefit > insufficient safety education > hurry-up habits and culture'. Conclusions: This study has some limitations because it was originally not designed to survey attitudes prior to the Sewol Ferry disaster in 2013. In addition, the survey targets are industrial hygienists who are familiar with occupational disease and injury.

• Journal of Cadastre & Land InformatiX
• /
• v.51 no.2
• /
• pp.83-106
• /
• 2021

Interests in clean fuels have been soaring because of environmental problems such as air pollution and global warming. Unlike fossil fuels, hydrogen obtains public attention as a eco-friendly energy source because it releases only water when burned. Various policy efforts have been made to establish a hydrogen based transportation network. The station that supplies hydrogen to hydrogen-powered trucks is essential for building the hydrogen based logistics system. Thus, determining the optimal location of refueling stations is an important topic in the network. Although previous studies have mostly applied optimization based methodologies, this paper adopts machine learning to review spatial attributes of candidate locations in selecting the optimal position of the refueling stations. Machine learning shows outstanding performance in various fields. However, it has not yet applied to an optimal location selection problem of hydrogen refueling stations. Therefore, several machine learning models are applied and compared in performance by setting variables relevant to the location of highway rest areas and random points on a highway. The results show that Random Forest model is superior in terms of F1-score. We believe that this work can be a starting point to utilize machine learning based methods as the preliminary review for the optimal sites of the stations before the optimization applies.

• Journal of the Korean Society of Safety
• /
• v.37 no.4
• /
• pp.120-128
• /
• 2022

Printed circuit boards (PCBs) are a basic component in the electronics industry and are widely used in nearly all electronic products, such as mobile phones, tablet computers, and digital cameras, as well as in electric equipment. PCB manufacturing involves the use of many chemicals and chemical processes and therefore has more risks than other manufacturing sectors. This study aims to identify the causes of possible accidents during PCB manufacturing through risk assessment, develop and implement safety measures, and evaluate the effectiveness of these measures. Note that the safety measures developed to mitigate the risks of a certain process were also implemented for other similar processes. The risk assessments conducted over seven years, from 2015 to 2021, at a PCB manufacturing company identified 361 hazardous processes. Between 2016 and 2019, 41-56 hazardous processes were identified per year; such processes decreased to fewer than 20 per year after 2020. Application of the risk assessment results to the improvement of the hazardous processes with the similar characteristics seems to be effective in decreasing the risks. Equipment-related factors such as lack of appropriate maintenance, low work standards, and defective protection devices were responsible for 59.8% of all possible accidents. Because PCB manufacturing involves many chemicals, skin contact with hazardous substances, electric shock, fire, and explosion were the most common types of possible accidents (81.7%). In total, 505 safety measures were implemented, including 157 related to purchase and improvement of equipment and devices for safety (31.1%), 147 related to the installation/modification of fire prevention facilities (29.1%), and 69 related to the use of standard electrical appliances (13.7%). Risk assessment conducted after implementing the safety measures showed that these measures significantly decreased risk; 247 processes (68.4%) had a risk level of 3, corresponding to "very low," and 114 processes (31.6%) showed a risk level of 4, corresponding to "low." In particular, risk assessment of 104 processes with risk scores of 12 and 10 other processes with risk score of 16 showed that the risk decreased to 4 after implementing the safety measures. Thus, implementing these measures in similar manufacturing sectors that involve chemical processes can mitigate risk.

• KOREAN JOURNAL OF PACKAGING SCIENCE & TECHNOLOGY
• /
• v.29 no.2
• /
• pp.119-128
• /
• 2023

This study was examined for investigating the quality changes of spring kimchi cabbage under various treatments (pre-drying/pre-cooling, packaging types, and stacking and loading in container and pallete in the storage room) during cold storage. The results showed that control (upward stacking without pre-drying/pre-cooling and HDPE or PVC film cover) was increased significantly in weight loss and trimming loss, compared to other treatments such as DPDH (downard stacking + pre-drying + HDPE), DPDP (downard stacking + pre-drying + PVC), DPCH (downnard stacking + pre-cooling + HDPE), and UPCH (upward stacking + pre-cooling +HDPE) during storage for three months. In Sensory evaluation, judging from marketable properties, the desirable appearance of spring kimchi cabbage with the modified pallet-unit MA packed, PE, and PVC film wrapping could be maintained until 9 weeks after pre-drying/pre-cooling. Meanwhile, the control without any treatments after 6 weeks, the sensory score was declined, significantly. In general, the low temperature (10℃ and 2℃) of pre-treatment with combination of plastic film packaging in spring kimchi cabbage storage could inhibit the physiological activity and reduce the direct exposure of environmental cold air in the storage. Therefore, these two variables were the key points for extending the shelf-life of spring kimchi cabbage.

• Journal of Internet of Things and Convergence
• /
• v.9 no.2
• /
• pp.61-69
• /
• 2023

In recent years, due to heightened environmental awareness, Electric Power Steering (EPS) has been increasingly adopted as the steering control unit in manufactured vehicles. This has had numerous benefits, such as improved steering power, elimination of hydraulic hose leaks and reduced fuel consumption. However, for EPS systems to respond to actions, sensors must be employed; this means that the consistency of the sensor's linear variation is integral to the stability of the steering response. To ensure quality control, a reliable method for detecting defects and assessing linearity is required to assess the sensitivity of the EPS sensor to changes in the internal design characters. This paper proposes a data-driven defect and linearity assessment monitoring system, which can be used to analyze EPS component defects and linearity based on vehicle speed interval division. The approach is validated experimentally using data collected from an EPS test jig and is further enhanced by the inclusion of a Graphical User Interface (GUI). Based on the design, the developed system effectively performs defect detection with an accuracy of 0.99 percent and obtains a linearity assessment score at varying vehicle speeds.

• Journal of the Korean Society of Food Culture
• /
• v.23 no.5
• /
• pp.582-594
• /
• 2008

This study aimed at evaluating current sanitation management performances in Korean-Food restaurants by their operation types and to develop sanitary training posters based on the risk factors, in an attempt to improve the level of sanitation management in Korean food service facilities. Eighteen Korean-food restaurants that are managed by franchisor, franchisees as well as self-managed with large-scale and small-scale restaurants in Seoul and Gyeonggi-Do, were evaluated by on-the-spot inspectors with an auditing tool consisting of three dimensions, nine categories and thirty four items. Data were analyzed using SPSS. The total score of each group showed that restaurants managed by franchisees ranked the highest (59 out of 100 points), while self-managed, small-scale restaurants ranked the lowest (44 out of 100 points). In the categorization of sanitation management compliance, the dimensions of food hygiene during production recorded the lowest compliance rate of 47.7% (22.89/48.0 points) followed by the dimension of environmental hygiene 59.3% (20.17/34.0 points) and personal hygiene 60.5% (10.89/18.0 points). This indicated the need for urgent improvement. The items which showed the lowest compliance rates were 'proper thawing of frozen foods' (0%), 'notifying and observing heating/reheating temperature' (6%), 'using of hand-washing facility and proper hand-washing' (33%), 'monitoring temperature of frozen-foods and cold-foods' (35%), and 'prevention of cross-contamination' (36%) among thirty four items. Self-managed, small-scale restaurants, in particular, needed to improve sanitary practices such as 'sanitation education for employee', 'verifying the employee health inspection reports', 'storing food on the shelves 15 cm distance away from the wall', 'suitability of ventilation capacity of hoods' and 'cleanliness of drainage'. On the basis of the findings of this study, we developed sanitary training posters, especially for small-scale restaurant operators. This could be an effective tool to educate food service employees on sanitary knowledge and principles and could be used to improve the existing sanitary conditions in Korean food service facilities.

• Journal of Internet Computing and Services
• /
• v.24 no.5
• /
• pp.17-27
• /
• 2023

Today, as AI (Artificial Intelligence) technology develops and its practicality increases, it is widely used in various application fields in real life. At this time, the AI model is basically learned based on various statistical properties of the learning data and then distributed to the system, but unexpected changes in the data in a rapidly changing data situation cause a decrease in the model's performance. In particular, as it becomes important to find drift signals of deployed models in order to respond to new and unknown attacks that are constantly created in the security field, the need for lifecycle management of the entire model is gradually emerging. In general, it can be detected through performance changes in the model's accuracy and error rate (loss), but there are limitations in the usage environment in that an actual label for the model prediction result is required, and the detection of the point where the actual drift occurs is uncertain. there is. This is because the model's error rate is greatly influenced by various external environmental factors, model selection and parameter settings, and new input data, so it is necessary to precisely determine when actual drift in the data occurs based only on the corresponding value. There are limits to this. Therefore, this paper proposes a method to detect when actual drift occurs through an Anomaly analysis technique based on XAI (eXplainable Artificial Intelligence). As a result of testing a classification model that detects DGA (Domain Generation Algorithm), anomaly scores were extracted through the SHAP(Shapley Additive exPlanations) Value of the data after distribution, and as a result, it was confirmed that efficient drift point detection was possible.

• Journal of Bio-Environment Control
• /
• v.33 no.2
• /
• pp.120-128
• /
• 2024

Since ChatGPT was released in 2022, the generative artificial intelligence (AI) industry has seen massive growth and is expected to bring significant innovations to cognitive tasks. AI-based image generation, in particular, is leading major changes in the digital world. This study investigates the technical foundations of Midjourney, Stable Diffusion, and Firefly-three notable AI image generation tools-and compares their effectiveness by examining the images they produce. The results show that these AI tools can generate realistic images of tomatoes, strawberries, paprikas, and cucumbers, typical crops grown in greenhouse. Especially, Firefly stood out for its ability to produce very realistic images of greenhouse-grown crops. However, all tools struggled to fully capture the environmental context of greenhouses where these crops grow. The process of refining prompts and using reference images has proven effective in accurately generating images of strawberry fruits and their cultivation systems. In the case of generating cucumber images, the AI tools produced images very close to real ones, with no significant differences found in their evaluation scores. This study demonstrates how AI-based image generation technology can be applied in agriculture, suggesting a bright future for its use in this field.