• Journal of Advanced Navigation Technology
• /
• v.26 no.2
• /
• pp.113-118
• /
• 2022

Motivated by people highlighting important phrases while reading or taking notes we propose a neural network training method by highlighting defective pixel areas to classify effectively defect types of images with complex background textures. To verify our proposed method we apply it to the problem of classifying the defect types of tire band fabric images that are too difficult to classify. In addition we propose a backlight highlighting technique which is tailored to the tire band fabric images. Backlight highlighting images can be generated by using both the GradCAM and simple image processing. In our experiment we demonstrated that the proposed highlighting method outperforms the traditional method in the view points of both classification accuracy and training speed. It achieved up to 13.4% accuracy improvement compared to the conventional method. We also showed that the backlight highlighting technique tailored for highlighting tire band fabric images is superior to a contour highlighting technique in terms of accuracy.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.1
• /
• pp.175-180
• /
• 2024

This paper investigates the effect of a deep learning-based system on data labeling task productivity by individuals with developmental disabilities. It was found that interventions, particularly those using AI, significantly improved productivity compared to self-serving task. AI interventions were notably more effective than job coach-led approaches. This research underscores the positive role of AI in enhancing task efficiency for those with developmental disabilities. This study is the first to apply AI technology to the data labeling tasks of individuals with developmental disabilities and highlighting deep learning's potential in vocational training and productivity enhancement for this group.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.47 no.1
• /
• pp.41-50
• /
• 2024

Korea is facing a significant problem with historically low fertility rates, which is becoming a major social issue affecting the economy, labor force, and national security. This study analyzes the factors contributing to the regional gap in fertility rates and derives policy implications. The government and local authorities are implementing a range of policies to address the issue of low fertility. To establish an effective strategy, it is essential to identify the primary factors that contribute to regional disparities. This study identifies these factors and explores policy implications through machine learning and explainable artificial intelligence. The study also examines the influence of media and public opinion on childbirth in Korea by incorporating news and online community sentiment, as well as sentiment fear indices, as independent variables. To establish the relationship between regional fertility rates and factors, the study employs four machine learning models: multiple linear regression, XGBoost, Random Forest, and Support Vector Regression. Support Vector Regression, XGBoost, and Random Forest significantly outperform linear regression, highlighting the importance of machine learning models in explaining non-linear relationships with numerous variables. A factor analysis using SHAP is then conducted. The unemployment rate, Regional Gross Domestic Product per Capita, Women's Participation in Economic Activities, Number of Crimes Committed, Average Age of First Marriage, and Private Education Expenses significantly impact regional fertility rates. However, the degree of impact of the factors affecting fertility may vary by region, suggesting the need for policies tailored to the characteristics of each region, not just an overall ranking of factors.

• Knowledge Management Research
• /
• v.24 no.4
• /
• pp.219-235
• /
• 2023

The advancement of digital technology and the impact of COVID-19 have brought about changes in corporate innovation and organizational culture, thereby highlighting the significance of Smart Learning in the field of HRD (Human Resource Development). This trend has led to an increased interest in personalized Smart Learning among employees due to the growth of hybrid work and the widespread adoption of smart work practices. This study aimed to illuminate the relative importance of the factors that constitute Smart Learning from the perspective of HRD practitioners. Through a review of prior literature, Smart Learning hierarchy and factors most fitting to the current context were identified, and their relative importance was determined using the AHP method. Consequently, in the first-tier factors, importance was confirmed in the order of 'Learning Activities', 'Teaching Activities', 'Learning Content', 'Assessment and Evaluations', and 'Learning Time and Space'. At the second-tier encompassing all factors, 'Pedagogical Strategy', 'Learning Results', 'Learning Tasks', 'Learning Goal', and 'Learning Support' emerged within the top five factors. These findings are significant in that they redefine the concept of smart learning and propose an academic framework for future research. Additionally, from a practical perspective, it is anticipated that this study will contribute valuable insights for HRD practitioners, aiding them in focusing on which factors to prioritize for enhancing and advancing Smart Learning initiatives.

• Journal of Technology Innovation
• /
• v.20 no.1
• /
• pp.17-43
• /
• 2012

Alliance formation has been recognized as an important strategy for firms who seek to survive through acquisition of sustainable competitive advantages. Specifically in high-tech industries, firms may consider formation of strategic alliances in order to access valuable external knowledge. These firms tend to be situated in a dilemma that they should choose between exploration and exploitation, which are two types of strategic choices suggested by March (1991). Working out the dilemma has been extensively discussed in the area of strategy or organization learning. Recently, however, an increasing number of studies have stressed on a balance between exploration and exploitation. Regarded as 'ambidextrous organizations' (Lavie and Rosenkopf, 2006), these firms that simultaneously pursue exploration and exploitation have emerged in high-tech industries, and many studies have provided evidence of positive association between organizational ambidexterity and firm performance. In the strategic alliance research, accordingly, scholars began to pay attention to the balanced choice between exploration-and exploitation-oriented alliances. Given these backgrounds, this study examines the relationship between alliance ambidexterity and firm performance. While previous research approached alliance ambidexterity mainly from the number of alliances, our study suggests ambidexterity in terms of alliance portfolio and alliance partner. Our dataset consists of biotechnology or pharmaceutical firms in the United States, which spans time period between 1990 and 2005. We conduct panel data analysis. The results show the strong link between alliance ambidexterity and firm performance, highlighting the balance between exploration and exploitation when firms make strategic decisions.