• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.35 no.5
• /
• pp.259-266
• /
• 2022

In this study, we developed a deep learning and vision sensor-based assembly performance evaluation method isfor prefabricated steel structures. The assembly parts were segmented using a modified version of the receptive field block convolution module inspired by the eccentric function of the human visual system. The quality of the assembly was evaluated by detecting the bolt holes in the segmented assembly part and calculating the bolt hole positions. To validate the performance of the evaluation, models of standard and defective assembly parts were produced using a 3D printer. The assembly part segmentation network was trained based on the 3D model images captured from a vision sensor. The sbolt hole positions in the segmented assembly image were calculated using image processing techniques, and the assembly performance evaluation using the k-nearest neighbor algorithm was verified. The experimental results show that the assembly parts were segmented with high precision, and the assembly performance based on the positions of the bolt holes in the detected assembly part was evaluated with a classification error of less than 5%.

• Smart Structures and Systems
• /
• v.29 no.6
• /
• pp.757-766
• /
• 2022

To train deep learning algorithms, a sufficient number of data are required. However, in most engineering systems, the acquisition of fault data is difficult or sometimes not feasible, while normal data are secured. The dearth of data is one of the major challenges to developing deep learning models, and fault diagnosis in particular cannot be made in the absence of fault data. With this context, this paper proposes an anomaly detection methodology for rotating machines using only normal data with self-labeling. Since only normal data are used for anomaly detection, a self-labeling method is used to generate a new labeled dataset. The overall procedure includes the following three steps: (1) transformation of normal data to self-labeled data based on a pretext task, (2) training the convolutional neural networks (CNN), and (3) anomaly detection using defined anomaly score based on the softmax output of the trained CNN. The softmax value of the abnormal sample shows different behavior from the normal softmax values. To verify the proposed method, four case studies were conducted, on the Case Western Reserve University (CWRU) bearing dataset, IEEE PHM 2012 data challenge dataset, PHMAP 2021 data challenge dataset, and laboratory bearing testbed; and the results were compared to those of existing machine learning and deep learning methods. The results showed that the proposed algorithm could detect faults in the bearing testbed and compressor with over 99.7% accuracy. In particular, it was possible to detect not only bearing faults but also structural faults such as unbalance and belt looseness with very high accuracy. Compared with the existing GAN, the autoencoder-based anomaly detection algorithm, the proposed method showed high anomaly detection performance.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.5
• /
• pp.1-8
• /
• 2021

Coronavirus disease 2019 (COVID-19) has affected the world seriously. Every person is required for wearing a mask properly in a public area to prevent spreading the virus. However, many people are not wearing a mask properly. In this paper, we propose an efficient mask detection system. In our proposed system, we first detect the faces of input images using YOLOv5 and classify them as the one of three scene complexity classes (Simple, Moderate, and Complex) based on the number of detected faces. After that, the image is fed into the Faster-RCNN with the one of three ResNet (ResNet-18, 50, and 101) as backbone network depending on the scene complexity for detecting the face area and identifying whether the person is wearing the mask properly or not. We evaluated our proposed system using public mask detection datasets. The results show that our proposed system outperforms other models.

• Journal of Korea Trade
• /
• v.24 no.3
• /
• pp.20-36
• /
• 2020

Purpose - As the global product network expands through both internationalization and diversification of the multimodal transportation system, corporate strategies have shifted to emphasize the importance of a high value-added international logistics system. To guide policies and strategies to attract relevant industries, this study aims to analyze the location competitiveness of regional logistics distribution center to serve Northeast Asia. Design/methodology - Multi-criteria techniques are considered to offer a promising framework for evaluating decision-making factors. This paper employed an analytic hierarchy process to analyze the hierarchal structure of determinants for selecting the location of a regional logistics distribution center. Adopting both qualitative and quantitative evaluations, this study suggest political implications for a regional logistics distribution center development, such as the direction of political support, service differentiation and infrastructure development. Findings - This study developed a location competitiveness evaluation model, based on the case study of the major port-cities in Northeast Asia. Evaluation model incorporates five factors underpinning 17 components extracted using factor analysis. The results revealed that the logistics factor is the most significant factor for evaluating the competitiveness of a regional logistics distribution center. The remaining factors were market, costs, and services environment. Comparing qualitative and quantitative evaluations, results provide useful insights for a regional logistics distribution center development in Northeast Asia. Originality/value - This study revealed differences between qualitative and quantitative evaluations. The finding implies that prior works on evaluation models of competitiveness has not successfully measured the gap between quantitative data and expert' evaluations. To overcome this limitation, this paper considered both actual data such as actual distance, cost, the number of companies located, and expert opinions.

• Journal of the Korea Computer Graphics Society
• /
• v.27 no.3
• /
• pp.13-23
• /
• 2021

In this paper, we proposed a framework that generates the trajectory of a single rigid body based on its COM configuration and contact pose. Because we use a smaller input dimension than when we use a full body state, we can improve the learning time for reinforcement learning. Even with a 68% reduction in learning time (approximately two hours), the character trained by our network is more robust to external perturbations tolerating an external force of 1500 N which is about 7.5 times larger than the maximum magnitude from a previous approach. For this framework, we use centroidal dynamics to calculate the next configuration of the COM, and use reinforcement learning for obtaining a policy that gives us parameters for controlling the contact positions and forces.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.11
• /
• pp.3991-4010
• /
• 2021

The Question Similarity Measurement of Chinese Crop Diseases and Insect Pests (QSM-CCD&IP) aims to judge the user's tendency to ask questions regarding input problems. The measurement is the basis of the Agricultural Knowledge Question and Answering (Q & A) system, information retrieval, and other tasks. However, the corpus and measurement methods available in this field have some deficiencies. In addition, error propagation may occur when the word boundary features and local context information are ignored when the general method embeds sentences. Hence, these factors make the task challenging. To solve the above problems and tackle the Question Similarity Measurement task in this work, a corpus on Chinese crop diseases and insect pests(CCDIP), which contains 13 categories, was established. Then, taking the CCDIP as the research object, this study proposes a Chinese agricultural text similarity matching model, namely, the AgrCQS. This model is based on mixed information extraction. Specifically, the hybrid embedding layer can enrich character information and improve the recognition ability of the model on the word boundary. The multi-scale local information can be extracted by multi-core convolutional neural network based on multi-weight (MM-CNN). The self-attention mechanism can enhance the fusion ability of the model on global information. In this research, the performance of the AgrCQS on the CCDIP is verified, and three benchmark datasets, namely, AFQMC, LCQMC, and BQ, are used. The accuracy rates are 93.92%, 74.42%, 86.35%, and 83.05%, respectively, which are higher than that of baseline systems without using any external knowledge. Additionally, the proposed method module can be extracted separately and applied to other models, thus providing reference for related research.

• Journal of the Korea Fashion and Costume Design Association
• /
• v.23 no.4
• /
• pp.39-56
• /
• 2021

The purpose of this study was to observe the expressive characteristics of Neo-Deconstruction design, examine the expressive characteristics of Neo-Deconstruction design in the collections of Jacquemus, and analyze their internal meanings. For research, observations were made based on the concepts and expressive characteristics of Deconstruction through prior research and literary review, and analysis was conducted focusing on the expressive characteristics of Neo-Deconstruction. The scope of analysis included a total of 605 photographs collected from a total of 17 season collections of Jacquemus from the 2013 S/S to the 2021 S/S season. The results are as follows. First, the Neo-Deconstruction of Jacquemus expresses the youth culture using bright images such as diverse colors and patterns with 'positive playfulness' and pass on positive messages with deconstructive and playful forms, such as exaggeration and reduction and recombination and reconstitution. Second, with tendencies of 'symbolic receptivity', Jacquemus gained inspiration from his own life, memories, and hometown, and attempted to express the street women of places such as southern France, Paris, and Monaco in a number of collections. Also, he proposed designs that can be worn easily by anyone, regardless of gender, and as plus size models began to become more common respect was given to the tastes and preferences of diverse individuals without distinctions based on body type or sexuality. Third, 'geometric simplicity' was generally expressed by pursuing simple and practical fashion with the addition of details, such as geometric forms including stripes or asymmetrical expressions centering around everyday material that is used in clothing. Fourth, with "open communication," Jacquemus constructed his identity by addressing the various needs of consumers based on social network services and continuously sharing his creative ideas with the public. He is gaining popularity in a unique way by responding quickly to the changing atmosphere of society.

• Journal of Veterinary Science
• /
• v.21 no.1
• /
• pp.9.1-9.15
• /
• 2020

Regenerative therapy holds great promise in the development of cures of some untreatable diseases such as cardiovascular diseases, and pluripotent stem cells (PSCs) including induced PSCs (iPSCs) are the most important regenerative seed cells. Recently, differentiation of human PSCs into functional tissues and cells in vitro has been widely reported. However, although porcine reports are rare they are quite essential, as the pig is an important animal model for the in vitro generation of human organs. In this study, we reprogramed porcine embryonic fibroblasts into porcine iPSCs (piPSCs), and differentiated them into cluster of differentiation 31 (CD31)-positive endothelial cells (ECs) (piPSC-derived ECs, piPS-ECs) using an optimized single-layer culture method. During differentiation, we observed that a combination of GSK3β inhibitor (CHIR99021) and bone morphogenetic protein 4 (BMP4) promoted mesodermal differentiation, resulting in higher proportions of CD31-positive cells than those from separate CHIR99021 or BMP4 treatment. Importantly, the piPS-ECs showed comparable morphological and functional properties to immortalized porcine aortic ECs, which are capable of taking up low-density lipoprotein and forming network structures on Matrigel. Our study, which is the first trial on a species other than human and mouse, has provided an optimized single-layer culture method for obtaining ECs from porcine PSCs. Our approach can be beneficial when evaluating autologous EC transplantation in pig models.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.46 no.1
• /
• pp.165-181
• /
• 2022

The fashion industry is creating innovative business models using artificial intelligence. To efficiently utilize artificial intelligence (AI), fashion data must be classified. Until now, such data have been classified focusing only on the objective properties of fashion products. Their subjective attributes, such as fashion brand sensibilities, are holistic and heuristic intuitions created by a combination of design elements. This study aims to improve the performance of collaborative filtering in the fashion industry by extracting fashion brand sensibility using computer vision technology. The image data set of fashion brand sensibility consists of high-end fashion brand photos that share sensibilities and communicate well in fashion. About 26,000 fashion photos of 11 high-end fashion brand sensibility labels have been collected from the 16FW to 21SS runway and 50 years of US Vogue magazines beginning from 1971. We use EfficientNet-B1 to establish the main architecture and fine-tune the network with ImageNet-ILSVRC. After training fashion brand sensibilities through deep learning, the proposed model achieved an F-1 score of 74% on accuracy tests. Furthermore, as a result of comparing AI machine and human experts, the proposed model is expected to be expanded to mass fashion brands.

• Journal of Korean Society for Quality Management
• /
• v.50 no.4
• /
• pp.701-716
• /
• 2022

Purpose: This study aims to predict the dry cargo transportation market economy. The subject of this study is the BDI (Baltic Dry Index) time-series, an index representing the dry cargo transport market. Methods: In order to increase the accuracy of the BDI time-series, we have pre-processed the original time-series via time-series decomposition and data augmentation techniques and have used them for ANN learning. The ANN algorithms used are Multi-Layer Perceptron (MLP), Recurrent Neural Network (RNN), and Long Short-Term Memory (LSTM) to compare and analyze the case of learning and predicting by applying time-series decomposition and data augmentation techniques. The forecast period aims to make short-term predictions at the time of t+1. The period to be studied is from '22. 01. 07 to '22. 08. 26. Results: Only for the case of the MAPE (Mean Absolute Percentage Error) indicator, all ANN models used in the research has resulted in higher accuracy (1.422% on average) in multivariate prediction. Although it is not a remarkable improvement in prediction accuracy compared to uni-variate prediction results, it can be said that the improvement in ANN prediction performance has been achieved by utilizing time-series decomposition and data augmentation techniques that were significant and targeted throughout this study. Conclusion: Nevertheless, due to the nature of ANN, additional performance improvements can be expected according to the adjustment of the hyper-parameter. Therefore, it is necessary to try various applications of multiple learning algorithms and ANN optimization techniques. Such an approach would help solve problems with a small number of available data, such as the rapidly changing business environment or the current shipping market.