• Journal of the Korea Society of Computer and Information
• /
• v.27 no.5
• /
• pp.55-67
• /
• 2022

Sensor data can provide fault diagnosis for equipment. However, the cause analysis for fault results of equipment is not often provided. In this study, we propose an explainable convolutional neural network framework for the sensor-based time series classification model. We used sensor-based time series dataset, acquired from vehicles equipped with sensors, and the Wafer dataset, acquired from manufacturing process. Moreover, we used Cycle Signal dataset, acquired from real world mechanical equipment, and for Data augmentation methods, scaling and jittering were used to train our deep learning models. In addition, our proposed classification models are convolutional neural network based models, FCN, 1D-CNN, and ResNet, to compare evaluations for each model. Our experimental results show that the ResNet provides promising results in the context of time series classification with accuracy and F1 Score reaching 95%, improved by 3% compared to the previous study. Furthermore, we propose XAI methods, Class Activation Map and Layer Visualization, to interpret the experiment result. XAI methods can visualize the time series interval that shows important factors for sensor data classification.

• Journal of Science Education
• /
• v.47 no.1
• /
• pp.37-51
• /
• 2023

This study explored the factors influencing major satisfaction and academic satisfaction of science education major students at the College of Education using machine learning models, random forest, gradient boosting model, and SHAP. Analysis results showed that the performance of the gradient boosting model was better than that of the random forest, but the difference was not large. Factors influencing major satisfaction include 'satisfaction with science teachers in high school corresponding to the subject of one's major', 'motivation for teaching job', and 'age'. Through the SHAP value, the influence of variables was identified, and the results were derived for the group as a whole and for individual analysis. The comprehensive and individual results could be complementary with each other. Based on the research results, implications for ways to support pre-service science teachers' major and academic satisfaction were proposed.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.17 no.3
• /
• pp.176-182
• /
• 2024

In this study, we compared and analyzed various methods of missing data handling to build a machine learning model that can effectively analyze and predict time series data with a high percentage of missing values. For this purpose, Predictive State Model Filtering (PSMF), MissForest, and Imputation By Feature Importance (IBFI) methods were applied, and their prediction performance was evaluated using LightGBM, XGBoost, and Explainable Boosting Machines (EBM) machine learning models. The results of the study showed that MissForest and IBFI performed the best among the methods for handling missing values, reflecting the nonlinear data patterns, and that XGBoost and EBM models performed better than LightGBM. This study emphasizes the importance of combining nonlinear imputation methods and machine learning models in the analysis and prediction of time series data with a high percentage of missing values, and provides a practical methodology.

• The Mathematical Education
• /
• v.62 no.3
• /
• pp.435-455
• /
• 2023

This study primarily focused on the development of an Explainable Artificial Intelligence (XAI) model to discern and analyze papers with significant impact in the field of mathematics education. To achieve this, meta-information from 29 domestic and international mathematics education journals was utilized to construct a comprehensive academic research network in mathematics education. This academic network was built by integrating five sub-networks: 'paper and its citation network', 'paper and author network', 'paper and journal network', 'co-authorship network', and 'author and affiliation network'. The Random Forest machine learning model was employed to evaluate the impact of individual papers within the mathematics education research network. The SHAP, an XAI model, was used to analyze the reasons behind the AI's assessment of impactful papers. Key features identified for determining impactful papers in the field of mathematics education through the XAI included 'paper network PageRank', 'changes in citations per paper', 'total citations', 'changes in the author's h-index', and 'citations per paper of the journal'. It became evident that papers, authors, and journals play significant roles when evaluating individual papers. When analyzing and comparing domestic and international mathematics education research, variations in these discernment patterns were observed. Notably, the significance of 'co-authorship network PageRank' was emphasized in domestic mathematics education research. The XAI model proposed in this study serves as a tool for determining the impact of papers using AI, providing researchers with strategic direction when writing papers. For instance, expanding the paper network, presenting at academic conferences, and activating the author network through co-authorship were identified as major elements enhancing the impact of a paper. Based on these findings, researchers can have a clear understanding of how their work is perceived and evaluated in academia and identify the key factors influencing these evaluations. This study offers a novel approach to evaluating the impact of mathematics education papers using an explainable AI model, traditionally a process that consumed significant time and resources. This approach not only presents a new paradigm that can be applied to evaluations in various academic fields beyond mathematics education but also is expected to substantially enhance the efficiency and effectiveness of research activities.

• Knowledge Management Research
• /
• v.7 no.1
• /
• pp.49-63
• /
• 2006

The objective of the study is to verify the discriminatory power of technology innovation in predicting Early Stage Ventures' success or failure. To accomplish this objective, we test early stage ventures'(Firm's period is below 3 years)technology innovation and performance. The result of the study is expected to be useful in loan evaluation, investment decision, internal management decision making and business improvement. The results of study is as follows. First, Early Stage Ventures' technology innovation power is composed of 4 major indexes(technology, marketability, manufacturing infra and economic feasibility). Second, we find that thirty-seven minor indexes are significant ex-ante variable which are discriminating between firms' success and failure in Early Stage Ventures. Also thirty-seven minor indexes explain 57.2% of the total variance. This explainable power of these indexes is similar to that of the existing 58 index elements. Finally, we find that the most important technology innovation power of Early Stage Ventures' is economic feasibility.

• Journal of Pharmacopuncture
• /
• v.5 no.2
• /
• pp.116-119
• /
• 2002

Objective : This study was designed to show the possible functional groups from the herb medicine in boiling water. Results : The results are summarized as follows: 1. the new functional groups can be synthesized in water solution for herb medicine. 2. The boiling water solution may change the poison materials into harmless materials. 3. The multiplication, the offset, the contradiction, etc. in terms of mixed herb medicine can be explainable by these reactions. 4. After finding the new medicinal substances for the specific disease, we can synthesize, modify, and mass produce those for that disease.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1995.10a
• /
• pp.3-7
• /
• 1995

Force generated during grinding process causes elastic defomation. The effect of this deforms a workpiecs. So grinding system is explainable using the concept of macining elasticity phenomenon. Machining elasticity is defined as ratio between the true depth of c ut, and an importnat factor to affect material removal mchanism and productivity. Generally, to produce accurate surface and dimensionally precise components operators depend on their experiences. Because of these, productivity is reduced and time is wasted. The objective of this reserch is to study the effect of grinding conditions, such as table speed, depth of cut on the machining elasticity parameter.

• Annals of Clinical Neurophysiology
• /
• v.19 no.2
• /
• pp.79-92
• /
• 2017

Paraproteinemia is caused by a proliferation of monoclonal plasma cells or B lymphocytes. Approximately 10% of idiopathic neuropathies are associated with paraproteinemia, where a certain paraprotein acts like an antibody targeted at constituents of myelin or axolemma in peripheral nerves. The relationship between paraproteinemia and peripheral neuropathy remains unclear despite this being of interest for a long time. Neurologists frequently find paraproteinemia during laboratory examinations of patients presenting with peripheral neuropathy, especially in the elderly. The possibility of a relationship with paraproteinemia should be considered in cases without an explainable cause. We review the causal association between paraproteinemia and neuropathy as well as clinical, laboratory, and electrophysiologic features, and the treatment options for paraproteinemic neuropathy.

• Journal of Korea Technology Innovation Society
• /
• v.8 no.1
• /
• pp.277-295
• /
• 2005

The objective of the study is to verify the discriminatory power of valuation indexes in predicting IT small and medium sized manufacturing firms' going concern or firms' failure. The result of the study is expected to be useful in loan evaluation, investment decision, internal management decision making and business improvement. The results of study is as follows. First, we find that at least six valuation index elements are significant ex-ante variable which are discriminating between firms' going concern and firms' failure in IT small and medium sized manufacturing firms in various analysis' results. Second, these index elements are composed of 2 indexes-the ability of technology R&D, the efficient strategy of market penetration and six index elements explain 46% of the total variance. This explainable power of these indexed is similar to that of the existing 16 index elements. Finally, we find that the most important success factor of IT small and medium sized manufacturing firms are the ability of technology R&D and the efficient strategy of market penetration.

• Korean Management Science Review
• /
• v.19 no.2
• /
• pp.169-178
• /
• 2002

The growth of Internet usage even accelerated by the spread of high-speed Internet access network such as ADSI is affecting our socioeconomic activities and culture in a great way. Korea is recently reported to be the number one high-speed Internet network subscription per 100 people in the world. In a way to reflect this situation, we collect a moderate size of sample proportional to the population of each region across country and investigate what factors might explain the level of user's dissatisfaction with respect to Internet service they have been receiving. The results indicate that the set of gender, age, Internet usage, service kinds, incoming e-mails, and e-shopping is significantly influencing user's dissatisfaction, in that dissatisfaction is measured in 11 perspectives. In particular, user's age, gender, and e-shopping experiences are considered to be mostly explainable.