• Journal of Intelligence and Information Systems
• /
• v.29 no.4
• /
• pp.325-345
• /
• 2023

In the rapidly evolving domain of e-commerce, our study presents a cohesive approach to enhance customer satisfaction prediction from online reviews, aligning methodological innovation with practical insights. We integrate the RFE-SHAP feature selection with LDA topic modeling to streamline predictive analytics in e-commerce. This integration facilitates the identification of key features-specifically, narrowing down from an initial set of 28 to an optimal subset of 14 features for the Random Forest algorithm. Our approach strategically mitigates the common issue of overfitting in models with an excess of features, leading to an improved accuracy rate of 84% in our Random Forest model. Central to our analysis is the understanding that certain aspects in review content, such as quality, fit, and durability, play a pivotal role in influencing customer satisfaction, especially in the clothing sector. We delve into explaining how each of these selected features impacts customer satisfaction, providing a comprehensive view of the elements most appreciated by customers. Our research makes significant contributions in two key areas. First, it enhances predictive modeling within the realm of e-commerce analytics by introducing a streamlined, feature-centric approach. This refinement in methodology not only bolsters the accuracy of customer satisfaction predictions but also sets a new standard for handling feature selection in predictive models. Second, the study provides actionable insights for e-commerce platforms, especially those in the clothing sector. By highlighting which aspects of customer reviews-like quality, fit, and durability-most influence satisfaction, we offer a strategic direction for businesses to tailor their products and services.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.18 no.2
• /
• pp.127-139
• /
• 2023

Compensation and pay dispersion has been rigorously scrutinized to investigate their impacts on productivity and organizational performance. However, it is difficult to find a systematic study on the systematic dynamics of compensation and pay dispersion effects specifically in the context of Korean venture companies. Venture companies should manage their organizational resources efficiently to maximize their organizational performance through pay structure by efficiently managing the inherent resources. However, we acknowledge that empirical studies on how compensation and pay dispersion affect organizational productivity and performance are rare to find in the Korean context. To overcome this supplement limitation, this study hypothesized that (1) pay and members' productivity are positively related, (2) pay dispersion and organizational productivity have U shaped relationship, and (3) organizational productivity mediates the positive relationship between compensation and organizational performance. Venture companies and professional sports teams share manifold common characteristics such as size, financial circumstances, and operational objectives. We collect 9 seasons (2013~2014 - 2021~2022) of 10 teams' data of Korean Basketball League teams to test our hypotheses. Methodologically, the assessment of our analysis is rendered with PROCESS macro model 58. The statistical results showed that all hypotheses are statistically supported. This study explains how compensation and pay dispersion affect organizational productivity and performance of venture companies in Korea.

• Journal of the Korean Geotechnical Society
• /
• v.40 no.3
• /
• pp.77-84
• /
• 2024

Aging and damaged underground utilities cause cavity and ground subsidence under roads, which can cause economic losses and risk user safety. This study used infrared cameras to assess the thermal characteristics of such cavities and evaluate their reliability using a CNN algorithm. PVC pipes were embedded at various depths in a test site measuring 400 cm × 50 cm × 40 cm. Concrete blocks were used to simulate road surfaces, and measurements were taken from 4 PM to noon the following day. The initial temperatures measured by the infrared camera were 43.7℃, 43.8℃, and 41.9℃, reflecting atmospheric temperature changes during the measurement period. The RP algorithm generates images in four resolutions, i.e., 10,000 × 10,000, 2,000 × 2,000, 1,000 × 1,000, and 100 × 100 pixels. The accuracy of the CNN model using RP images as input was 99%, 97%, 98%, and 96%, respectively. These results represent a considerable improvement over the 73% accuracy obtained using time-series images, with an improvement greater than 20% when using the RP algorithm-based inputs.

• Journal of Service Research and Studies
• /
• v.14 no.2
• /
• pp.101-116
• /
• 2024

As the spread of smartphones has become more common and the utilization rate has increased, the mobile shopping market is also growing and expectations for related industries are also increasing. Mobile shopping apps are converging with various industries such as fashion, beauty, and lifestyle, and competition among companies to increase the number of users is intensifying with the activation of non-face-to-face. Accordingly, in this study, a study on the perceived value and intention to use mobile shopping apps was conducted based on a VAM. In order to test the hypothesis of this study, a questionnaire was conducted on 266 people who had used a mobile shopping app and it was used for analysis. Looking at the results, it was confirmed that both usefulness and enjoyment among the perceived benefit of mobile shopping apps have a positive (+) effect on the perceived value. However, it was found that the technicality and perceived risk among the perceived sacrifices of mobile shopping apps did not significantly affect the perceived value. Finally, it was confirmed that the perceived value of the mobile shopping app had a positive (+) effect on the intention to use. Through this study, we would like to examine the factors that can affect perceived value and usage intention in the mobile shopping app industry, which is increasingly competitive among companies along with the rapid growth of mobile technology and market, and suggest practical implications for related companies and officials to establish efficient strategies to further increase mobile shopping app users.

• Journal of The Korean Society of Clinical Toxicology
• /
• v.21 no.2
• /
• pp.92-107
• /
• 2023

Purpose: This study investigated the characteristics and treatment outcomes of patients who visited the emergency department due to intoxication and analyzed the impact of the coronavirus disease 2019 (COVID-19) pandemic on their visits. Methods: A retrospective study was conducted using data from the National Emergency Department Information System (NEDIS) on patients who visited the emergency department due to intoxication between January 2014 and December 2020. In total, 277,791 patients were included in the study, and their demographic and clinical data were analyzed. A model was created from 2014 to 2019 and applied to 2020 (i.e., during the COVID-19 pandemic) to conduct a time series analysis distinguishing between unexpected accidents and suicide/self-harm among patients who visited the emergency department. Results: The most common reason for visiting the emergency department was unintentional accidents (48.5%), followed by self-harm/suicide attempts (43.8%). Unexpected accident patients and self-harm/suicide patients showed statistically significant differences in terms of sex, age group, hospitalization rate, and mortality rate. The time series analysis showed a decrease in patients with unexpected accidents during the COVID-19 pandemic, but no change in patients with suicide/self-harm. Conclusion: Depending on the intentionality of the intoxication, significant differences were found in the age group, the substance of intoxication, and the mortality rate. Therefore, future analyses of patients with intoxication should be stratified according to intentionality. In addition, the time series analysis of intentional self-harm/suicide did not show a decrease in 2010 in the number of patients, whereas a decrease was found for unintentional accidents.

• Journal of Applied Biological Chemistry
• /
• v.66
• /
• pp.213-220
• /
• 2023

The most common skin disease, acne, often occurs in adolescence, but it is also detected/observed in adults due to air pollution and drug abuse. One of the causative agents of acne, Cutibacterium acnes (C. acnes) plays a role in the development of skin acne by inducing inflammatory mediators. Torreya nucifera (TN) is an evergreen tree of the family Taxaceae, having well reported antioxidant, anti-proliferative, liver protection, and nerve protection properties. Improvement of these bioactive properties of natural products is one of the purposes of natural product chemistry and pharmaceuticals. We believe biorenovation could be one improvement strategy that utilizes microbial metabolism to produce unique derivatives having enhanced bioactivity. Therefore, in this study, the C. acnes-induced RAW264.7 inflammation model was used to evaluate the anti-inflammatory activity of the biorenovated Torreya nucifera product (TNB). The results showed improved viability of TNB-treated cells compared to TN-treated cells in the concentration range of 50, 100, and 200 ㎍/mL. At non-toxic concentrations, TNB inhibited the production of nitric oxide and prostaglandin E2 by suppression of inducible nitric oxide synthase and cyclooxygenase-2 protein expression. TNB also attenuated the expression of interleukin-1β, interleukin-6, interleukin-8, and tumor necrosis factor-α induced by C. acnes. Furthermore, TNB inhibited the nuclear factor-κB signaling pathway, a transcription factor known to regulate inflammatory mediators. Based on these results, this study suggests the potential of using TNB as natural material for the treatment of acnes and thus, supporting our postulation of biorenovation as an bioactivity improvement strategy.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.6
• /
• pp.649-654
• /
• 2024

The most common accidents at construction sites are caused by not wearing personal protective equipment. According to industrial accidents statistics, one of the main death causes is not wearing safety helmets, and although various efforts have been made to have workers wear safety helmets. One of the ways to manage the wearing of safety helmet is to use CCTV-based image deep learning algorithm, so various methods have been proposed to confirm workers' compliance with wearing safety helmets by the CNN. This can help with safety management by checking whether workers are complying with wearing safety helmets and identifying workers who violate safety rules. In this study, we proposed a model construction methodology that can effectively determine whether workers are not wearing safety helmets by utilizing YOLOv9. With CIS data set, we selected the optimal variables and data ratio for detecting workers not wearing safety helmets, and we aimed to increase field usability by analyzing the discrimination accuracy and error according to the distribution of data on wearing or not wearing safety helmets derived through various learning and verification.

• Journal of School Social Work
• /
• v.42
• /
• pp.209-236
• /
• 2018

The happiness of our children is at the lowest level among OECD countries. The purpose of this study is to describe a dream as a major factor in the happiness of children, what is relatively important among dream-related variables, and how those variables predict a happiness. For this purpose, this study analyzed the data from "2017 Korea future generation's dream survey" for 11 to 18 year-old youth in nation wide. As a result, the more concrete the dream is, the more self-determined the dream is, the greater the possibility of dream realization, the less change of dream, the more often they talk about the dream, the more they realized their dreams, the higher the happiness is. In addition, among the dream-related variables, except for self-determination and change degree of the dream, the difference between poverty and non-poverty youth showed the statistically significant difference. Finally, in the prediction model of happiness between poverty and non-poverty youth, the possibility of dream realization is suggested as common important factor of both models. However, realizing the dream is relatively important in the non-poverty group, while the existence of dream is important in poverty group. Based on these results, we emphasized that the intervention for dreams should be executed differently in order to achieve happiness for youth.

• Journal of the Korean Chemical Society
• /
• v.68 no.4
• /
• pp.205-220
• /
• 2024

This study aims to explore characteristics of pedagogical reasoning and action of beginning science teachers that naturally and spontaneously occurs in a professional learning community. Three novice middle school science teachers who majored chemistry education in A college of education, passed the examination for selecting secondary school chemistry teachers, and had a common goal of designing 8^th grade science lesson plan voluntarily created a professional learning community and had weekly meetings over a year. Main data sources included transcribed audio-recording of 11 meetings of three science teachers in a professional learning community. Data was analyzed using Shulman's pedagogical reasoning model that includes comprehension, transformation, instruction, evaluation, reflection, and new comprehension to identify characteristics and features of pedagogical reasoning in a professional learning community. Data analysis revealed that pedagogical reasoning in a professional learning community comprises not only preparation, representations, instructional selections, and adaptation but also evaluation, reflection, and new comprehension in transformation stage. Reflection in transformation stage leads teachers to be actively engaged in discussion and get new comprehension on each sub-component(preparation, representations, instructional selections, adaptation, and evaluation) of transformation stage.

• International Journal of Stem Cells
• /
• v.15 no.3
• /
• pp.311-323
• /
• 2022

Background and Objectives: Human mesenchymal stem cells (MSCs) are emerging as a treatment for atopic dermatitis (AD), a chronic inflammatory skin disorder that affects a large number of people across the world. Treatment of AD using human umbilical cord blood-derived MSCs (hUCB-MSCs) has recently been studied. However, the mechanism underlying their effect needs to be studied continuously. Thus, the objective of this study was to investigate the immunomodulatory effect of epidermal growth factor (EGF) secreted by hUCB-MSCs on AD. Methods and Results: To explore the mechanism involved in the therapeutic effect of MSCs for AD, a secretome array was performed using culture medium of hUCB-MSCs. Among the list of genes common for epithelium development and skin diseases, we focused on the function of EGF. To elucidate the effect of EGF secreted by hUCB-MSCs, EGF was downregulated in hUCB-MSCs using EGF-targeting small interfering RNA. These cells were then co-cultured with keratinocytes, Th2 cells, and mast cells. Depletion of EGF disrupted immunomodulatory effects of hUCB-MSCs on these AD-related inflammatory cells. In a Dermatophagoides farinae-induced AD mouse model, subcutaneous injection of hUCB-MSCs ameliorated gross scoring, histopathologic damage, and mast cell infiltration. It also significantly reduced levels of inflammatory cytokines including interleukin (IL)-4, tumor necrosis factor (TNF)-α, thymus and activation-regulated chemokine (TARC), and IL-22, as well as IgE levels. These therapeutic effects were significantly attenuated at all evaluation points in mice injected with EGF-depleted hUCB-MSCs. Conclusions: EGF secreted by hUCB-MSCs can improve AD by regulating inflammatory responses of keratinocytes, Th2 cells, and mast cells.