• Journal of Korea Trade
• /
• v.26 no.5
• /
• pp.106-124
• /
• 2022

Purpose - The increasing share of Korean private label products (PLPs) in the domestic market helped generate lucrative revenue. In recent years, major South Korean retailers have begun to cast their sights on overseas markets and actively export their PLPs. In China, the proportion of private label fresh food (PLFF) is gradually expanding amid the development of the new retailing model. A profound understanding of the relationship between private label fresh produce and purchase intention may be the answer to helping Chinese retailer private labels expand supply chains in Korea. This study, taking Chinese retailers as an example, examines the impacts of selection factors of private label fresh food and perceived value on purchase intention. Apart from that, the relationship between the selection factors and purchase intention will be analyzed with perceived value as a mediator. Design/methodology - This work aims to empirically analyze the purchase intention of private label fresh food using statistical analysis. In this study, a hypothetical causal model consisting of 6 latent variables and 24 measured variables is developed based on the literature review. To validate the research hypotheses and the research model, SPSS23.0/AMOS23.0 is used to analyze factors such as validity and reliability, as well as structural equation modeling. Findings - The hypothetical model established in this study is of general applicability. In respect to PLFF, perceived value, while significantly influencing purchase intention in combination with four selection factors (perceived quality, perceived price, brand trust, and store image), mediates partially between the first three factors and purchase intention, which rules out the impact and mediating effect of store image on purchase intention. Originality/value - These research results, as helpful insights into the present circumstances of Chinese PLFF in the domestic market, provide useful information and guidance for Korean retailers and service providers to innovate production and service, as well as develop marketing and promotion strategies, so that they can shift private label goods with advantages from domestic demand to export, thus increasing overseas profitability. Further, this work will also contribute to relevant research.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.12
• /
• pp.1759-1768
• /
• 2022

This paper proposes a model to detect depression-related emotions in a user's speech using wellness dialogue scripts provided by AI Hub, topic-specific daily conversation datasets, and chatbot datasets published on Github. There are 18 emotions, including depression and lethargy, in depression-related emotions, and emotion classification tasks are performed using KoBERT and KOELECTRA models that show high performance in language models. For model-specific performance comparisons, we build diverse datasets and compare classification results while adjusting batch sizes and learning rates for models that perform well. Furthermore, a person performs a multi-classification task by selecting all labels whose output values are higher than a specific threshold as the correct answer, in order to reflect feeling multiple emotions at the same time. The model with the best performance derived through this process is called the Depression model, and the model is then used to classify depression-related emotions for user utterances.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.607-610
• /
• 2021

When learning a model in supervised learning, input data and the label of the data are required. However, labeling is high cost task and if automated, there is no guarantee that the label will always be correct. In the case of supervised learning in such a noisy labels environment, the accuracy of the model increases at the initial stage of learning, but decrease significantly after a certain period of time. There are various methods to solve the noisy label problem. But in most cases, the probability predicted by the model is used as the pseudo label. So, we proposed a method to predict the true label more quickly by refining the probabilities predicted by the model. Result of experiments on the same environment and dataset, it was confirmed that the performance improved and converged faster. Through this, it can be applied to methods that use the probability distribution predicted by the model among existing studies. And it is possible to reduce the time required for learning because it can converge faster in the same environment.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.7
• /
• pp.1807-1822
• /
• 2023

Innovation and rapid increased functionality in user friendly smartphones has encouraged shutterbugs to have picturesque image macros while in work environment or during travel. Formal signboards are placed with marketing objectives and are enriched with text for attracting people. Extracting and recognition of the text from natural images is an emerging research issue and needs consideration. When compared to conventional optical character recognition (OCR), the complex background, implicit noise, lighting, and orientation of these scenic text photos make this problem more difficult. Arabic language text scene extraction and recognition adds a number of complications and difficulties. The method described in this paper uses a two-phase methodology to extract Arabic text and word boundaries awareness from scenic images with varying text orientations. The first stage uses a convolution autoencoder, and the second uses Arabic Character Segmentation (ACS), which is followed by traditional two-layer neural networks for recognition. This study presents the way that how can an Arabic training and synthetic dataset be created for exemplify the superimposed text in different scene images. For this purpose a dataset of size 10K of cropped images has been created in the detection phase wherein Arabic text was found and 127k Arabic character dataset for the recognition phase. The phase-1 labels were generated from an Arabic corpus of quotes and sentences, which consists of 15kquotes and sentences. This study ensures that Arabic Word Awareness Region Detection (AWARD) approach with high flexibility in identifying complex Arabic text scene images, such as texts that are arbitrarily oriented, curved, or deformed, is used to detect these texts. Our research after experimentations shows that the system has a 91.8% word segmentation accuracy and a 94.2% character recognition accuracy. We believe in the future that the researchers will excel in the field of image processing while treating text images to improve or reduce noise by processing scene images in any language by enhancing the functionality of VGG-16 based model using Neural Networks.

• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.20 no.1
• /
• pp.59-72
• /
• 2009

This study investigates whether easy understanding of user interface could affect the use of electronic materials in a virtual academic library. The user interface of Duksung Women's University Library was analysed in terms of label description and array of menus. The frequencies of menu use were collected by analysis of use log files after modified user interface was applied. Clear label descriptions of link menus and sub-menus of electronic material searches significantly contributed to the increase of number of user clicks on the modified menus. This study reveals that the more clearly menu labels are described, the more frequently users click the menus on the academic library user interface.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.59 no.1
• /
• pp.19-27
• /
• 2023

The interest in greenhouse gases (GHG) emitted from all industries is emerging as a very important issue worldwide. This is affecting not only the global warming, but also the environmentally friendly competitiveness of the industry. The fisheries sector is increasingly interested in greenhouse gas emissions also due to the Paris Climate Agreement in 2015. Korean industry and government are also making a number of effort to reduce greenhouse gas emissions so far, but the effort to reduce GHG in the fishery sector is insufficient compared to other fields. Especially, the investigation on the GHG emissions from Korean fisheries did not carry out extensively. The studies on GHG emissions from Korean fishery are most likely dealt with the GHG emissions by fishery classification so far. However, the forthcoming research related to GHG emissions from fisheries is needed to evaluate the GHG emission level by species to prepare the adoption of Environmental labels and declarations (ISO 14020). The purpose of this research is to investigate which degree of GHG emitted to produce the species (swimming crab and snow crab) from various fisheries. Here, we calculated the GHG emission to produce the species from the fisheries using the life cycle assessment (LCA) method. The system boundary and input parameters for each process level are defined for LCA analysis. The fuel use coefficients of the fisheries for the species are also calculated according to the fuel type. The GHG emissions from sea activities by the fisheries will be dealt with. Furthermore, the GHG emissions for producing the unit weight species and annual production are calculated by fishery classification. The results will be helpful to establish the carbon footprint of seafood in Korea.

• Korean Journal of Clinical Pharmacy
• /
• v.33 no.2
• /
• pp.122-127
• /
• 2023

Background: This study was aimed to identify the safety signals of metoclopramide in Korea Adverse Event Reporting System (KAERS) database by proportionality analysis methods. Methods: The study was conducted using Korea Institute of Drug Safety and Risk Management-Korea Adverse Event Reporting System Database (KIDS-KD) reported from January 2013 to December 2017 through KAERS. Signals of metoclopramide that satisfied the data-mining indices of proportional reporting ratio (PRR), reporting odds ratio (ROR) and information component (IC) were defined. The detected signals were checked whether they included in drug labels in the Ministry of Food and Drug Safety (MFDS), U.S. Food and Drug Administration (FDA) and Micromedex^®. Results: A total number of drug AE reports associated with all drugs of data in this study was 2,665,429. Among them, the number of AE reports associated with metoclopramide was 22,583. Forty-two meaningful signals of metoclopramide were detected that satisfied with the criteria of data-mining indicies. Especially neurological signals including extrapyramidal reactions, represented in the safety letter of regulatory agencies were identified in this study. Conclusion: Neurological signals of metoclopramide including extrapyramidal reactions were detected. It is believed that this search for signals can contribute to ensuring safety in the use of metoclopramide.

• International conference on construction engineering and project management
• /
• 2022.06a
• /
• pp.792-799
• /
• 2022

Building Information Modeling (BIM) technology is a key component of modern construction engineering and project management workflows. As-is BIM models that represent the spatial reality of a project site can offer crucial information to stakeholders for construction progress monitoring, error checking, and building maintenance purposes. Geometric methods for automatically converting raw scan data into BIM models (Scan-to-BIM) often fail to make use of higher-level semantic information in the data. Whereas, semantic segmentation methods only output labels at the point level without creating object level models that is necessary for BIM. To address these issues, this research proposes a hybrid semantic-geometric approach for clutter-resistant floorplan generation from laser-scanned building point clouds. The input point clouds are first pre-processed by normalizing the coordinate system and removing outliers. Then, a semantic segmentation network based on PointNet++ is used to label each point as ceiling, floor, wall, door, stair, and clutter. The clutter points are removed whereas the wall, door, and stair points are used for 2D floorplan generation. A region-growing segmentation algorithm paired with geometric reasoning rules is applied to group the points together into individual building elements. Finally, a 2-fold Random Sample Consensus (RANSAC) algorithm is applied to parameterize the building elements into 2D lines which are used to create the output floorplan. The proposed method is evaluated using the metrics of precision, recall, Intersection-over-Union (IOU), Betti error, and warping error.

• International conference on construction engineering and project management
• /
• 2022.06a
• /
• pp.304-311
• /
• 2022

Construction inspection is a crucial stage that ensures that all contractual requirements of a construction project are verified. The construction inspection capabilities among state highway agencies have been greatly affected due to budget reduction. As a result, efficient inspection practices such as risk-based inspection are required to optimize the use of limited resources without compromising inspection quality. Automated prioritization of textual requirements according to their criticality would be extremely helpful since contractual requirements are typically presented in an unstructured natural language in voluminous text documents. The current study introduces a novel model for predicting the risk level of requirements using machine learning (ML) algorithms. The ML algorithms tested in this study included naïve Bayes, support vector machines, logistic regression, and random forest. The training data includes sequences of requirement texts which were labeled with risk levels (such as very low, low, medium, high, very high) using the fuzzy logic systems. The fuzzy model treats the three risk factors (severity, probability, detectability) as fuzzy input variables, and implements the fuzzy inference rules to determine the labels of requirements. The performance of the model was examined on labeled dataset created by fuzzy inference rules and three different membership functions. The developed requirement risk prediction model yielded a precision, recall, and f-score of 78.18%, 77.75%, and 75.82%, respectively. The proposed model is expected to provide construction inspectors with a means for the automated prioritization of voluminous requirements by their importance, thus help to maximize the effectiveness of inspection activities under resource constraints.

• Journal of the Microelectronics and Packaging Society
• /
• v.30 no.4
• /
• pp.69-78
• /
• 2023

With the rapid growth of artificial intelligence, the demand for semiconductors is enormously increasing everywhere. To ensure the manufacturing quality and quantity simultaneously, the importance of automatic defect detection during the packaging process has been re-visited by adapting various deep learning-based methodologies into automatic packaging defect inspection. Deep learning (DL) models require a large amount of data for training, but due to the nature of the semiconductor industry where security is important, sharing and labeling of relevant data is challenging, making it difficult for model training. In this study, we propose a new framework for securing sufficient data for DL models with fewer computing resources through a divide-and-conquer approach. The proposed method divides high-resolution images into pre-defined sub-regions and assigns conditional labels to each region, then trains individual sub-regions and boundaries with boundary loss inducing the globally coherent and seamless images. Afterwards, full-size image is reconstructed by combining divided sub-regions. The experimental results show that the images obtained through this research have high efficiency, consistency, quality, and generality.