• Journal of the Computational Structural Engineering Institute of Korea
• /
• 제37권4호
• /
• pp.225-232
• /
• 2024

This study focuses on the determination of the fracture mode in composite laminates using deep learning. With the increase in the use of laminated composites in numerous engineering applications, the insurance of their integrity and performance is of paramount importance. However, owing to the complex nature of these materials, the identification of fracture modes is often a tedious and time-consuming task that requires critical domain knowledge. Therefore, to alleviate these issues, this study aims to utilize modern artificial intelligence technology to automate the fractographic analysis of laminated composites. To accomplish this goal, scanning electron microscopy (SEM) images of fractured tensile test specimens are obtained from laminated composites to showcase various fracture modes. These SEM images are then categorized based on numerous fracture modes, including fiber breakage, fiber pull-out, mix-mode fracture, matrix brittle fracture, and matrix ductile fracture. Next, the collective data for all classes are divided into train, test, and validation datasets. Two state-of-the-art, deep learning-based pre-trained models, namely, DenseNet and GoogleNet, are trained to learn the discriminative features for each fracture mode. The DenseNet models shows training and testing accuracies of 94.01% and 75.49%, respectively, whereas those of the GoogleNet model are 84.55% and 54.48%, respectively. The trained deep learning models are then validated on unseen validation datasets. This validation demonstrates that the DenseNet model, owing to its deeper architecture, can extract high-quality features, resulting in 84.44% validation accuracy. This value is 36.84% higher than that of the GoogleNet model. Hence, these results affirm that the DenseNet model is effective in performing fractographic analyses of laminated composites by predicting fracture modes with high precision.

• Journal of Intelligence and Information Systems
• /
• 제27권1호
• /
• pp.23-46
• /
• 2021

Collaborative filtering, which is often used in personalization recommendations, is recognized as a very useful technique to find similar customers and recommend products to them based on their purchase history. However, the traditional collaborative filtering technique has raised the question of having difficulty calculating the similarity for new customers or products due to the method of calculating similaritiesbased on direct connections and common features among customers. For this reason, a hybrid technique was designed to use content-based filtering techniques together. On the one hand, efforts have been made to solve these problems by applying the structural characteristics of social networks. This applies a method of indirectly calculating similarities through their similar customers placed between them. This means creating a customer's network based on purchasing data and calculating the similarity between the two based on the features of the network that indirectly connects the two customers within this network. Such similarity can be used as a measure to predict whether the target customer accepts recommendations. The centrality metrics of networks can be utilized for the calculation of these similarities. Different centrality metrics have important implications in that they may have different effects on recommended performance. In this study, furthermore, the effect of these centrality metrics on the performance of recommendation may vary depending on recommender algorithms. In addition, recommendation techniques using network analysis can be expected to contribute to increasing recommendation performance even if they apply not only to new customers or products but also to entire customers or products. By considering a customer's purchase of an item as a link generated between the customer and the item on the network, the prediction of user acceptance of recommendation is solved as a prediction of whether a new link will be created between them. As the classification models fit the purpose of solving the binary problem of whether the link is engaged or not, decision tree, k-nearest neighbors (KNN), logistic regression, artificial neural network, and support vector machine (SVM) are selected in the research. The data for performance evaluation used order data collected from an online shopping mall over four years and two months. Among them, the previous three years and eight months constitute social networks composed of and the experiment was conducted by organizing the data collected into the social network. The next four months' records were used to train and evaluate recommender models. Experiments with the centrality metrics applied to each model show that the recommendation acceptance rates of the centrality metrics are different for each algorithm at a meaningful level. In this work, we analyzed only four commonly used centrality metrics: degree centrality, betweenness centrality, closeness centrality, and eigenvector centrality. Eigenvector centrality records the lowest performance in all models except support vector machines. Closeness centrality and betweenness centrality show similar performance across all models. Degree centrality ranking moderate across overall models while betweenness centrality always ranking higher than degree centrality. Finally, closeness centrality is characterized by distinct differences in performance according to the model. It ranks first in logistic regression, artificial neural network, and decision tree withnumerically high performance. However, it only records very low rankings in support vector machine and K-neighborhood with low-performance levels. As the experiment results reveal, in a classification model, network centrality metrics over a subnetwork that connects the two nodes can effectively predict the connectivity between two nodes in a social network. Furthermore, each metric has a different performance depending on the classification model type. This result implies that choosing appropriate metrics for each algorithm can lead to achieving higher recommendation performance. In general, betweenness centrality can guarantee a high level of performance in any model. It would be possible to consider the introduction of proximity centrality to obtain higher performance for certain models.

• Journal of Korean Society for Atmospheric Environment
• /
• 제26권5호
• /
• pp.543-553
• /
• 2010

Almost five million citizens a day are using subways as a means of traffic communication in the Seoul metropolitan. As the subway system is typically a closed environment, indoor air pollution problems frequently occurs and passengers complain of mal-health impact. Especially $PM_{10}$ is well known as one of the major pollutants in subway indoor environments. The purpose of this study was to compare the indoor air quality in terms of $PM_{10}$ and to quantitatively compare its source contributions in a Seoul subway platform before and after installing platform screen doors (PSD). $PM_{10}$ samples were collected on the J station platform of Subway Line 7 in Seoul metropolitan area from Jun. 12, 2008 to Jan. 12, 2009. The samples collected on membrane filters using $PM_{10}$ mini-volume portable samplers were then analyzed for trace metals and soluble ions. A total of 18 chemical species (Ba, Mn, Cr, Cd, Si, Fe, Ni, Al, Cu, Pb, Ti, $Na^+$, $NH_4^+$, $K^+$, $Mg^{2+}$, $Ca^{2+}$, $Cl^-$, and ${SO_4}^{2-}$) were analyzed by using an ICP-AES and an IC after performing proper pre-treatments of each sample filter. Based on the chemical information, positive matrix factorization (PMF) model was applied to identify the source of particulate matters. $PM_{10}$ for the station was characterized by three sources such as ferrous related source, soil and road dust related source, and fine secondary aerosol source. After installing PSD, the average $PM_{10}$ concentration was decreased by 20.5% during the study periods. Especially the contribution of the ferrous related source emitted during train service in a tunnel route was decreased from 59.1% to 43.8% since both platform and tunnel areas were completely blocked by screen doors. However, the contribution of the fine secondary aerosol source emitted from various outside combustion activities was increased from 14.8% to 29.9% presumably due to ill-managed ventilation system and confined platform space.

• Journal of Korean Tunnelling and Underground Space Association
• /
• 제17권3호
• /
• pp.257-266
• /
• 2015

This study introduce that we studied optimization and possibility of smoke spread prevention with air-curtain system in undersea tunnel named from Ho-Nam to Jeju line in domestic if a fire break out in train. To verify performance, air-curtain system is installed between rescue station platform and each door of passenger car to provide safety route to evacuator and we studied simulation model of various cases about 15 MW fire severity considering domestic specifications. As a result we verified the fact that CASE1(air jet with 15degree toward passenger car) and CASE 5 (air jet with 15degree toward passenger car and pressure air blast from cross passage) is best Smoke Spread Prevention and less inflow carbon monoxide. Through above results, we expect that air-curtain system is one of the facilities for fire safety and provide us safety platform route in undersea tunnel.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• 제17권7호
• /
• pp.740-748
• /
• 2016

IT and communication technologies has contributed significantly to the convenience of passengers and the financial management of stations in accordance with the task automation in the field of the urban railway system. The foundation of the above development is based on the large amounts of data from various sensors installed in railways, trains, and stations. In particular, the sensor network that is installed in the station and train has played an important role in the railway information system. The performance of AP is affected by the number of APs and their locations installed in the station. In the installation of APs in stations, the intensity of the radio wave of the AP on its underlying position is considered to determine the number and position of APs. This paper proposes a method to estimate the number of APs and their position based on the structure of the underlying station and implemented a simulator to simulate the performance of the proposed method. The implemented simulator was applied to the decision of AP installation at Busan Seomyeon station to evaluate its performance.

• Journal of Intelligence and Information Systems
• /
• 제10권1호
• /
• pp.109-123
• /
• 2004

Corporate financial distress and bankruptcy prediction is one of the major application areas of artificial neural networks (ANNs) in finance and management. ANNs have showed high prediction performance in this area, but sometimes are confronted with inconsistent and unpredictable performance for noisy data. In addition, it may not be possible to train ANN or the training task cannot be effectively carried out without data reduction when the amount of data is so large because training the large data set needs much processing time and additional costs of collecting data. Instance selection is one of popular methods for dimensionality reduction and is directly related to data reduction. Although some researchers have addressed the need for instance selection in instance-based learning algorithms, there is little research on instance selection for ANN. This study proposes a genetic algorithm (GA) approach to instance selection in ANN for bankruptcy prediction. In this study, we use ANN supported by the GA to optimize the connection weights between layers and select relevant instances. It is expected that the globally evolved weights mitigate the well-known limitations of gradient descent algorithm of backpropagation algorithm. In addition, genetically selected instances will shorten the learning time and enhance prediction performance. This study will compare the proposed model with other major data mining techniques. Experimental results show that the GA approach is a promising method for instance selection in ANN.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• 제17권12호
• /
• pp.504-510
• /
• 2016

This study presents a model for blended problem-based learning (BPBL) for engineering colleges in Mongolia in order to efficiently train talented Mongolian specialists "With problem-solving skills for the current information technology era. BPBL is learner-centered teaching method that promotes learning. Moreover, current teaching methods in the engineering colleges of Mongolia should change to novel and flexible teaching environments and methods that meet learners' needs. Thus, using BPBL for engineering education development in Mongolia will provide more teaching possibilities, which will assist the professors. Over the past few years, universities in Mongolia have established the Center for Teacher Development, which provides training and gives advice to staff about teaching methods, although the majority of lectures are still fragmentary and anecdotal. Therefore, many professors teach the way they learned, and most teaching methods used up till now have been teacher-centered. However, modern college instructors and modem society demand different engineering teaching methods from teachers who are more familiar with old-fashioned methods. Furthermore, the methods should meet the needs of individuals and groups who prefer to apply technology in the engineering learning process. Using an effective engineering strategy in the development of a new engineering teaching method will lead to its success.

• The Journal of Korean Academic Society of Nursing Education
• /
• 제5권1호
• /
• pp.118-132
• /
• 1999

To improve the effectiveness and efficiency of public health personnel training, we evaluated not only how appropriate the students felt the objectives, contents, methods and multimedia used in the train ing courses, but also how much the students accomplished the objectives and applied skill and knowledge to their own works. We selected 5 courses for the study : Tuberculosis control, Radiological technique, Public health information, Immunization, Mental health management courses used by Kirkpatrick's evaluation model. Reaction evaluation was carried out in final day by questionnaire. The results showed that all of them were very satisfied with educational input and curricula, learn Ing environment. Secondly, we measured the degree of learning achievement on pre and post training by questionaire of specific behavioral objectives. The degree of learning achievement was statistically higher just after training than pre training (paired t-test, p<0.01). Thirdly, evaluation of behavioral change to job was conducted to find out how much students applied skill and knowledge to their own job in 3 months after training by questionnaire. The results of behavioral change evaluation showed that 43.5% of the students who were performing job related with the training courses in 3 months after training applied the learned skill and knowledge to their own job quite well and 37.8% of them applied relatively well, therefore total 81.4% of them applied to their own job. And effectiveness of training for the above mentioned students showed that 41.9 % of them had improved or enforced their jobs after training, 35.5% of them had had no remarkable changes, and 15.7% had newly applied the learned skill and knowledge to their jobs. For evaluating the degree of usefulness of material predistribution in two weeks before training, we compared experimental groups with control groups. The results showed that general reactions are helpful but the degree of learning achievement is no discrepancy.

• The Journal of Engineering Geology
• /
• 제15권1호
• /
• pp.67-76
• /
• 2005

This paper presents the application of a neural network for prediction of the unconfined compressive strength from physical properties and schmidt hardness number on rock samples. To investigate the suitability of this approach, the results of analysis using a neural network are compared to predictions obtained by statistical relations. The data sets containing 55 rock sample records which are composed of sandstone and shale were assembled in Daegu area. They were used to learn the neural network model with the back-propagation teaming algorithm. The rock characteristics as the teaming input of the neural network are: schmidt hardness number, specific gravity, absorption, porosity, p-wave velocity and S-wave velocity, while the corresponding unconfined compressive strength value functions as the teaming output of the neural network. A data set containing 45 test results was used to train the networks with the back-propagation teaming algorithm. Another data set of 10 test results was used to validate the generalization and prediction capabilities of the neural network.

• The Journal of the Korea Contents Association
• /
• 제17권1호
• /
• pp.299-336
• /
• 2017

The purpose of this study is to identify the differential effects of transformational leadership and organizational justice on psychological contract breach and work engagement, and to suggest practical implications. To this purpose, this study theoretically references equity theory which recognizes the relationship between organizational input and output, social exchange theory which explains the exchange relationship between members and organization, and job demand-resource (JD-R) model that combines job demands and job resources. A empirical study was conducted on 277 employees at 18 companies of diverse industries including manufacturing, distribution, and finance, and to eliminate the common method bias problem, the dependent variable was measured using peer evaluation. The results of this study showed that: 1) both transformational leadership and organizational justice had a significant positive effect on work engagement and significant negative effect on psychological contract breach; and 2) psychological contract breach played a partial mediating role in the relationship between transformational leadership and work engagement as well as between organizational justice and work engagement. Therefore, this study suggests that, as organizational justice has stronger influence on work engagement and psychological contract breach than transformational leadership, organizations should not only train its leaders but also guarantee fairness.