• Journal of the Society of Naval Architects of Korea
• /
• v.34 no.1
• /
• pp.122-129
• /
• 1997

Thermo-elastic-plastic analyses used in solving plate forming process are often computationally expensive. To obtain an optimal process of line heating typically requires numerous iterations between the simulation and a finite element analysis. This process often becomes prohibitive due to the amount of computer time required for numerical simulation of line heating process. Therefore, a new techniques that could significantly reduce the computer time required to solve a complex analysis problem would be beneficial. In this paper, we considered factors that influence the bending effect by line heating and developed inference engine by using the concept of artificial neural network. To verify the validity of the neural network, we used results obtained from numerical analysis. We trained the neural network with the data made from numerical analysis and experiments varying the structure of neural network, in other words varying the number of hidden layers and the number of neurons in each hidden layers. From that we concluded that if the number of neurons in each hidden layers is large enough neural network having two hidden layers can be trained easily and errors between exact value and results obtained from trained network are not so large. Consequently, if there are enough number of training pairs, artificial neural network can infer similar results. Based on the numerical results, we applied the artificial neural network technique to deal with mechanical behavior of line heating at simulation stage effectively.

• Journal of the Society of Disaster Information
• /
• v.14 no.3
• /
• pp.360-366
• /
• 2018

Purpose: This study operation of Joint inter-agency Chemical Emergency Preparedness Center and contribute to the reduction of chemical accidents that occur continuously. Method: The Joint inter-agency Chemical Emergency Preparedness Center functions and Chemical accident statistics data of the ('13~'17) were utilized. Results: The number of chemical accidents is decreasing from 113 in '15, 78 in '16, 87 in '17(latest five years 469 chemical accidents). The Joint inter-agency Chemical Emergency Preparedness Center is located in the industrial complex that handling a large amount of chemical, and performs functions such as prompt response, probation & investigation, accident prevention training, safety patrol. It is believed that it contributes to the decreasing of chemical accident by local control accident prevention function. Conclusion: Decreasing the safety management according to the Chemicals control act('15.1.1). The Joint inter-agency Chemical Emergency Preparedness Center('14.1 set up manage organization), which is operated as a mission to prepare respond to chemical accidents, plays a role.

• KEPCO Journal on Electric Power and Energy
• /
• v.6 no.4
• /
• pp.413-418
• /
• 2020

It is necessary to manage the prediction accuracy of the machine learning model to prevent the decrease in the performance of the grid network condition prediction model due to overfitting of the initial training data and to continuously utilize the prediction model in the field by maintaining the prediction accuracy. In this paper, we propose an automation technique for maintaining the performance of the model, which increases the accuracy and reliability of the prediction model by considering the characteristics of the power grid state data that constantly changes due to various factors, and enables quality maintenance at a level applicable to the field. The proposed technique modeled a series of tasks for maintaining the performance of the power grid condition prediction model through the application of the workflow management technology in the form of a workflow, and then automated it to make the work more efficient. In addition, the reliability of the performance result is secured by evaluating the performance of the prediction model taking into account both the degree of change in the statistical characteristics of the data and the level of generalization of the prediction, which has not been attempted in the existing technology. Through this, the accuracy of the prediction model is maintained at a certain level, and further new development of predictive models with excellent performance is possible. As a result, the proposed technique not only solves the problem of performance degradation of the predictive model, but also improves the field utilization of the condition prediction model in a complex power grid system.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.25 no.6
• /
• pp.111-120
• /
• 2021

When a fire occurs in a commercial building, the evacuation route is complicated and the direction of smoke and flame is similar to that of the egress route of occupants, resulting in many casualties. Performance-based evacuation design for buildings is essential to minimize human casualties. In order to apply the performance-based evacuation design to buildings, it requires a complex fire simulation for each building, demanding a large amount of time and manpower. In order to supplement this, it would be very useful to develop an Available Safe Egress Time (ASET) prediction model that can rationally derive the ASET without performing a fire simulation. In this study, the correlations between fire temperature with visibility and toxic gas concentration were investigated through a fire simulation on a commercial building, from which databases for the training of artificial neural networks (ANN) were created. Based on this, an ANN model that can predict the available safe egress time was developed. In order to examine whether the proposed ANN model can be applied to other commercial buildings, it was applied to another commercial building, and the proposed model was found to estimate the available safe egress time of the commercial building very accurately.

• Journal of the Korean Regional Science Association
• /
• v.34 no.4
• /
• pp.3-18
• /
• 2018

These days, regional innovation draws more attention than ever as a growth engine for regional economies, and governments put a variety of efforts to establish Regional Innovation systems(RISs). In this circumstance, this study aims to analyze types of RISs and the combinations of the factors influencing innovation performance as measured by patent application. Most of previous works have depended on case-oriented or variable-oriented strategy to classify types of RISs or to analyze the effects on performance of innovation factors, having some limitations: Variable-oriented approaches fail to capture complex combinatory effects of factors, while case-oriented approaches tend to depend on subjective interpretation. This study made use of the recently proposed fs/QCA(Fuzzy-set Qualitative Comparative Analysis) to overcome the limitations of those strategies. Based on the theory of RIS, three factors for regional innovation-input, infrastructure, and network-are used to classify 16 Korean Provinces. The results show that eight types of regional innovation types are identified, and that most of the regions are classified into either IN-type, equipped with high levels of Input and Network, or F-type, with high levels of infrastructure. In addition, applying seven sub-variables of the three factors to the fussy-set combination factor analysis, we examine a combination of factors influencing patent application. The results show that regions with high levels of R&D expense, valid patent, industry-academia cooperation, IP budget, and TLO values, and low IP capital almost always have a high level of patent application. Therefore, for regional innovation, the public sector needs to provide institutional support for R & D personnel training. It is also important to for both the public and the private sectors to make efforts to stimulate IP financing.

• Journal of IKEEE
• /
• v.22 no.4
• /
• pp.1140-1146
• /
• 2018

Recently, a methodology for analyzing complex bio-signals using a deep learning model has emerged among studies that recognize human emotions. At this time, the accuracy of emotion classification may be changed depending on the evaluation method and reliability depending on the kind of data to be learned. In the case of biological signals, the reliability of data is determined according to the noise ratio, so that the noise detection method is as important as that. Also, according to the methodology for defining emotions, appropriate emotional evaluation methods will be needed. In this paper, we propose a wavelet -based noise threshold setting algorithm for verifying the reliability of data for multimodal bio-signal data labeled Valence and Arousal and a method for improving the emotion recognition rate by weighting the evaluation data. After extracting the wavelet component of the signal using the wavelet transform, the distortion and kurtosis of the component are obtained, the noise is detected at the threshold calculated by the hampel identifier, and the training data is selected considering the noise ratio of the original signal. In addition, weighting is applied to the overall evaluation of the emotion recognition rate using the euclidean distance from the median value of the Valence-Arousal plane when classifying emotional data. To verify the proposed algorithm, we use ASCERTAIN data set to observe the degree of emotion recognition rate improvement.

• Journal of Korean Society of Forest Science
• /
• v.110 no.2
• /
• pp.155-164
• /
• 2021

Many studies have been conducted on developing automatic plant identification algorithms using machine learning to various plant features, such as leaves and flowers. Unlike other plant characteristics, barks show only little change regardless of the season and are maintained for a long period. Nevertheless, barks show a complex shape with a large variation depending on the environment, and there are insufficient materials that can be utilized to train algorithms. Here, in addition to the previously published bark image dataset, BarkNet v.1.0, images of barks were collected, and a dataset consisting of 53 tree species that can be easily observed in Korea was presented. A convolutional neural network (CNN) was trained and tested on the dataset, and the factors that interfere with the model's performance were identified. For CNN architecture, VGG-16 and 19 were utilized. As a result, VGG-16 achieved 90.41% and VGG-19 achieved 92.62% accuracy. When tested on new tree images that do not exist in the original dataset but belong to the same genus or family, it was confirmed that more than 80% of cases were successfully identified as the same genus or family. Meanwhile, it was found that the model tended to misclassify when there were distracting features in the image, including leaves, mosses, and knots. In these cases, we propose that random cropping and classification by majority votes are valid for improving possible errors in training and inferences.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.26 no.7
• /
• pp.787-797
• /
• 2020

The marine officer plays a pivotal role in the shipping organization as a professional who performs a complex and diverse function. On the sea, unlike land duty, the possibility of turnover increases due to characteristics such as living in isolated spaces, continuous shift work during a set sailing period, high intensity work tension, stress, and social isolation. In this study, the impact of the organization's civic actions on the intention of turnover as a mediator of organizational immersion was divided into three groups of large companies, small and medium-sized enterprises, and public enterprises to check the differences between each category in a structural manner. Analysis showed that there were statistically significant differences between the groups in loyalty and turnover intention when the sub-factors of organizational commitment and organizational citizen behavior of the marine officer, and the size of turnover intention were included. Organization citizen behavior did not directly affect turnover intention, but when indirect effects were included, there was an effect through loyalty, and relationship-oriented organizational citizen behavior negatively affected turnover intention through loyalty. Excluding public enterprises, the non-standardization path coefficients were -0.229±0.117 and -0.319±0.068, respectively, showing a statistically significant effect in large companies and SMEs. These results indicate that in order to lower the employee turnover intention in large corporations and small and medium-sized shipping companies, it is necessary to consider not only organizational citizen behavior but also measures to increase organizational commitment.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.24 no.1
• /
• pp.92-111
• /
• 2021

As fine dust negatively affects disease, industry and economy, the people are sensitive to fine dust. Therefore, if the occurrence of fine dust can be predicted, countermeasures can be prepared in advance, which can be helpful for life and economy. Fine dust is affected by the weather and the degree of concentration of fine dust emission sources. The industrial sector has the largest amount of fine dust emissions, and in industrial complexes, factories emit a lot of fine dust as fine dust emission sources. This study targets regions with old industrial complexes in local cities. The purpose of this study is to explore the factors that cause fine dust and develop a predictive model that can predict the occurrence of fine dust. weather data and fine dust data were used, and variables that influence the generation of fine dust were extracted through multiple regression analysis. Based on the results of multiple regression analysis, a model with high predictive power was extracted by learning with a machine learning regression learner model. The performance of the model was confirmed using test data. As a result, the models with high predictive power were linear regression model, Gaussian process regression model, and support vector machine. The proportion of training data and predictive power were not proportional. In addition, the average value of the difference between the predicted value and the measured value was not large, but when the measured value was high, the predictive power was decreased. The results of this study can be developed as a more systematic and precise fine dust prediction service by combining meteorological data and urban big data through local government data hubs. Lastly, it will be an opportunity to promote the development of smart industrial complexes.

• Journal of Korea Water Resources Association
• /
• v.55 no.1
• /
• pp.71-84
• /
• 2022

The objective of this study is to develop a two-dimensional (2D) flood model that can perform accurate flood analysis with simple input data. The 2D flood inundation models currently used to create flood forecast maps require complex input data and grid generation tools. This sometimes requires a lot of time and effort for flood modeling, and there may be difficulties in constructing input data depending on the situation. In order to compensate for these shortcomings, in this study, a grid-based model that can derive accurate and rapid flood analysis by reflecting correct topography as simple input data was developed. The calculation efficiency was improved by extending the existing 2×2 sub-grid model to a 5×5. In order to examine the accuracy and applicability of the model, it was applied to the Gamcheon Basin where both urban and river flooding occurred due to Typhoon Rusa. For efficient flood analysis according to user's selection, flood wave propagation patterns, accuracy and execution time according to grid size and number of sub-grids were investigated. The developed model is expected to be highly useful for flood disaster mapping as it can present the results of flooding analysis for various situations, from the flood inundation map showing accurate flooding to the flood risk map showing only approximate flooding.