• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.07a
• /
• pp.315-316
• /
• 2022

본 논문은 스마트 인솔의 압력 데이터를 이용하는 컨볼루션 신경망 모델에 해석가능한 인공지능 방법인 Grad-CAM을 적용하는 방법을 제안한다. 학습된 각 모델에 Grad-CAM을 적용하여 모델에서 중요한 역할을 하는 압력센서와 중요하지 않은 압력센서를 알아내는 방법을 제안하고 데이터마다 학습을 진행하고 학습된 모델을 통해 실제로 중요한 압력센서와 그렇지 않은 압력센서에 대해서 알아본다.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.20 no.1
• /
• pp.31-45
• /
• 2024

The purpose of this study is to explain employment factors in the software field. For it, the Graduates Occupational Mobility Survey by the Korea employment information service is used. This paper proposes employment models in the software field using machine learning. Then, it explains employment factors of the models using explainable artificial intelligence. The models focus on both university graduates and vocational college graduates. Our works explain and interpret both black box model and glass box model. The SHAP and EBM explanation are used to interpret black box model and glass box model, respectively. The results describes that positive employment impact factors are major, vocational education and training, employment preparation setting semester, and intern experience in the employment models. This study provides a job preparation guide to universitiy and vocational college students that want to work in software field.

• Journal of Intelligence and Information Systems
• /
• v.29 no.2
• /
• pp.241-265
• /
• 2023

A corporate insolvency prediction model serves as a vital tool for objectively monitoring the financial condition of companies. It enables timely warnings, facilitates responsive actions, and supports the formulation of effective management strategies to mitigate bankruptcy risks and enhance performance. Investors and financial institutions utilize default prediction models to minimize financial losses. As the interest in utilizing artificial intelligence (AI) technology for corporate insolvency prediction grows, extensive research has been conducted in this domain. However, there is an increasing demand for explainable AI models in corporate insolvency prediction, emphasizing interpretability and reliability. The SHAP (SHapley Additive exPlanations) technique has gained significant popularity and has demonstrated strong performance in various applications. Nonetheless, it has limitations such as computational cost, processing time, and scalability concerns based on the number of variables. This study introduces a novel approach to variable selection that reduces the number of variables by averaging SHAP values from bootstrapped data subsets instead of using the entire dataset. This technique aims to improve computational efficiency while maintaining excellent predictive performance. To obtain classification results, we aim to train random forest, XGBoost, and C5.0 models using carefully selected variables with high interpretability. The classification accuracy of the ensemble model, generated through soft voting as the goal of high-performance model design, is compared with the individual models. The study leverages data from 1,698 Korean light industrial companies and employs bootstrapping to create distinct data groups. Logistic Regression is employed to calculate SHAP values for each data group, and their averages are computed to derive the final SHAP values. The proposed model enhances interpretability and aims to achieve superior predictive performance.

• Journal of the Korean Society of Radiology
• /
• v.81 no.6
• /
• pp.1305-1333
• /
• 2020

Deep learning has recently achieved remarkable results in the field of medical imaging. However, as a deep learning network becomes deeper to improve its performance, it becomes more difficult to interpret the processes within. This can especially be a critical problem in medical fields where diagnostic decisions are directly related to a patient's survival. In order to solve this, explainable artificial intelligence techniques are being widely studied, and an attention mechanism was developed as part of this approach. In this paper, attention techniques are divided into two types: post hoc attention, which aims to analyze a network that has already been trained, and trainable attention, which further improves network performance. Detailed comparisons of each method, examples of applications in medical imaging, and future perspectives will be covered.

• 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 The Korean Association of Information Education
• /
• v.24 no.5
• /
• pp.495-509
• /
• 2020

This study is a theoretical research to explore ways to effectively learn AI in the age of intelligent information driven by artificial intelligence (hereinafter referred to as AI). The emphasis is on presenting a teaching method to make AI education accessible not only to students majoring in mathematics, statistics, or computer science, but also to other majors such as humanities and social sciences and the general public. Given the need for 'Explainable AI(XAI: eXplainable AI)' and 'the importance of storytelling for a sensible and intelligent machine(AI)' by Patrick Winston at the MIT AI Institute [33], we can find the significance of research on AI storytelling learning model. To this end, we discuss the possibility through a pilot study targeting general students of an university in Daegu. First, we introduce the AI storytelling(AI+ST) learning method[30], and review the educational goals, the system of contents, the learning methodology and the use of new AI tools in the method. Then, the results of the learners are compared and analyzed, focusing on research questions: 1) Can the AI+ST learning method complement algorithm-driven or developer-centered learning methods? 2) Whether the AI+ST learning method is effective for students and thus help them to develop their AI comprehension, interest and application skills.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.16 no.6
• /
• pp.385-391
• /
• 2023

As the use of electric vehicles has increased to minimize carbon emissions, the analyzing the state and performance of lithium-ion batteries that is instrumental in electric vehicles have been important. Comprehensive analysis using not only the voltage, current and temperature of the battery pack, which can affect the condition and performance of the battery, but also the driving data and charging pattern data of the electric vehicle is required. Therefore, a thorough analysis is imperative, utilizing electric vehicle operation data, charging pattern data, as well as battery pack voltage, current, and temperature data, which collectively influence the condition and performance of the battery. Therefore, collection and preprocessing of battery data collected from electric vehicles, collection and preprocessing of data on driver driving habits in addition to simple battery data, detailed design and modification of artificial intelligence algorithm based on the analyzed influencing factors, and A battery analysis and evaluation model was designed. In this paper, we gathered operational data and battery data from real-time electric buses. These data sets were then utilized to train a Random Forest algorithm. Furthermore, a comprehensive assessment of battery status, operation, and charging patterns was conducted using the explainable Artificial Intelligence (XAI) algorithm. The study identified crucial influencing factors on battery status, including rapid acceleration, rapid deceleration, sudden stops in driving patterns, the number of drives per day in the charging and discharging pattern, daily accumulated Depth of Discharge (DOD), cell voltage differences during discharge, maximum cell temperature, and minimum cell temperature. These factors were confirmed to significantly impact the battery condition. Based on the identified influencing factors, a battery analysis and evaluation model was designed and assessed using the Random Forest algorithm. The results contribute to the understanding of battery health and lay the foundation for effective battery management in electric vehicles.

• Journal of Korea Multimedia Society
• /
• v.24 no.10
• /
• pp.1414-1424
• /
• 2021

In this paper, the importance of input factors of a DNN (Deep Neural Network) PM_2.5 forecasting model using LRP(Layer-wise Relevance Propagation) is analyzed, and forecasting performance is improved. Input factor importance analysis is performed by dividing the learning data into time and PM_2.5 concentration. As a result, in the low concentration patterns, the importance of weather factors such as temperature, atmospheric pressure, and solar radiation is high, and in the high concentration patterns, the importance of air quality factors such as PM_2.5, CO, and NO₂ is high. As a result of analysis by time, the importance of the measurement factors is high in the case of the forecast for the day, and the importance of the forecast factors increases in the forecast for tomorrow and the day after tomorrow. In addition, date, temperature, humidity, and atmospheric pressure all show high importance regardless of time and concentration. Based on the importance of these factors, the LRP_DNN prediction model is developed. As a result, the ACC(accuracy) and POD(probability of detection) are improved by up to 5%, and the FAR(false alarm rate) is improved by up to 9% compared to the previous DNN model.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.3
• /
• pp.974-992
• /
• 2021

Recently, the healthcare field has undergone rapid changes owing to the accumulation of health big data and the development of machine learning. Data mining research in the field of healthcare has different characteristics from those of other data analyses, such as the structural complexity of the medical data, requirement for medical expertise, and security of personal medical information. Various methods have been implemented to address these issues, including the machine learning model and cloud platform. However, the machine learning model presents the problem of opaque result interpretation, and the cloud platform requires more in-depth research on security and efficiency. To address these issues, this paper presents a recent technology for Internet-of-Things-based (IoT-based) health big data processing. We present a cloud-based IoT health platform and health big data processing technology that reduces the medical data management costs and enhances safety. We also present a data mining technology for health-risk prediction, which is the core of healthcare. Finally, we propose a study using explainable artificial intelligence that enhances the reliability and transparency of the decision-making system, which is called the black box model owing to its lack of transparency.

• Journal of Navigation and Port Research
• /
• v.47 no.4
• /
• pp.182-190
• /
• 2023

This study proposes a predictive model using XGBoost and SHapley Additive exPlanation (SHAP) to estimate fuel consumption in bulk carriers. Previous studies have also utilized ship engine data and weather data. However, they lacked reliability in predicted results and explanations of variables used in the fuel consumption prediction model implementation. To address these limitations, this study developed a predictive model using XGBoost and SHAP. It provides research background, scope, relevant regulations, previous studies, and research methodology. Additionally, it explains the data cleaning method for bulk carriers and verifies results of the predictive model.