• Review of KIISC
• /
• v.31 no.5
• /
• pp.21-31
• /
• 2021

컴퓨터 기술의 발전에 따라 ML(Machine Learning) 및 AI(Artificial Intelligence)의 도입이 활발히 진행되고 있으며, 정보보호 분야에서도 활용이 증가하고 있는 추세이다. 그러나 이러한 모델들은 black-box 특성을 가지고 있으므로 의사결정 과정을 이해하기 어렵다. 특히, 오탐지 리스크가 큰 정보보호 환경에서 이러한 문제점은 AI 기술을 널리 활용하는데 상당한 장애로 작용한다. 이를 해결하기 위해 XAI(eXplainable Artificial Intelligence) 방법론에 대한 연구가 주목받고 있다. XAI는 예측의 해석이 어려운 AI의 문제점을 보완하기 위해 등장한 방법으로 AI의 학습 과정을 투명하게 보여줄 수 있으며, 예측에 대한 신뢰성을 제공할 수 있다. 본 논문에서는 이러한 XAI 기술의 개념 및 필요성, XAI 방법론의 정보보호 분야 적용 사례에 설명한다. 또한, XAI 평가 방법을 제시하며, XAI 방법론을 보안 시스템에 적용한 경우의 결과도 논의한다. XAI 기술은 AI 판단에 대한 사람 중심의 해석정보를 제공하여, 한정된 인력에 많은 분석데이터를 처리해야 하는 보안담당자들의 분석 및 의사결정 시간을 줄이는데 기여할 수 있을 것으로 예상된다.

• Journal of Korean Society for Quality Management
• /
• v.51 no.1
• /
• pp.55-65
• /
• 2023

Purpose: The purpose of this study is to propose an optimization process to improve product yield in the process using process data. Recently, research for low-cost and high-efficiency production in the manufacturing process using machine learning or deep learning has continued. Therefore, this study derives major variables that affect product defects in the manufacturing process using eXplainable Artificial Intelligence(XAI) method. After that, the optimal range of the variables is presented to propose a methodology for improving product yield. Methods: This study is conducted using the injection molding machine AI dataset released on the Korea AI Manufacturing Platform(KAMP) organized by KAIST. Using the XAI-based SHAP method, major variables affecting product defects are extracted from each process data. XGBoost and LightGBM were used as learning algorithms, 5-6 variables are extracted as the main process variables for the injection process. Subsequently, the optimal control range of each process variable is presented using the ICE method. Finally, the product yield improvement methodology of this study is proposed through a validation process using Test Data. Results: The results of this study are as follows. In the injection process data, it was confirmed that XGBoost had an improvement defect rate of 0.21% and LightGBM had an improvement defect rate of 0.29%, which were improved by 0.79%p and 0.71%p, respectively, compared to the existing defect rate of 1.00%. Conclusion: This study is a case study. A research methodology was proposed in the injection process, and it was confirmed that the product yield was improved through verification.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.11a
• /
• pp.1122-1125
• /
• 2020

AI의 결과를 이해하기 위해서 XAI(eXplainable Artificial Intelligence)의 연구는 매우 중요하다. 세계적으로 XAI 개발 연구는 많이 진행되고 있지만 개발된 XAI를 평가하는 연구는 매우 적다. 본 논문은 사용성 측면에서 XAI를 평가하기 위해 AI 사용성 요소, 과학적 설명의 요소, 휴리스틱 평가 요소를 분류하고 의사결정 나무를 시각화여 심미도를 평가한다.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.31 no.4
• /
• pp.559-571
• /
• 2021

Along with the increase prevalence of computers, the number of malware distributions by attackers to ordinary users has also increased. Research to detect malware continues to this day, and in recent years, research on malware detection and analysis using AI is focused. However, the AI algorithm has a disadvantage that it cannot explain why it detects and classifies malware. XAI techniques have emerged to overcome these limitations of AI and make it practical. With XAI, it is possible to provide a basis for judgment on the final outcome of the AI. In this paper, we conducted malware group classification using XGBoost and Random Forest, and interpreted the results through SHAP. Both classification models showed a high classification accuracy of about 99%, and when comparing the top 20 API features derived through XAI with the main APIs of malware, it was possible to interpret and understand more than a certain level. In the future, based on this, a direct AI reliability improvement study will be conducted.

• Nuclear Engineering and Technology
• /
• v.54 no.4
• /
• pp.1271-1287
• /
• 2022

When abnormal operating conditions occur in nuclear power plants, operators must identify the occurrence cause and implement the necessary mitigation measures. Accordingly, the operator must rapidly and accurately analyze the symptom requirements of more than 200 abnormal scenarios from the trends of many variables to perform diagnostic tasks and implement mitigation actions rapidly. However, the probability of human error increases owing to the characteristics of the diagnostic tasks performed by the operator. Researches regarding diagnostic tasks based on Artificial Intelligence (AI) have been conducted recently to reduce the likelihood of human errors; however, reliability issues due to the black box characteristics of AI have been pointed out. Hence, the application of eXplainable Artificial Intelligence (XAI), which can provide AI diagnostic evidence for operators, is considered. In conclusion, the XAI to solve the reliability problem of AI is included in the AI-based diagnostic algorithm. A reliable intelligent diagnostic assistant based on a merged diagnostic algorithm, in the form of an operator support system, is developed, and includes an interface to efficiently inform operators.

• 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.

• Journal of Internet Computing and Services
• /
• v.24 no.5
• /
• pp.17-27
• /
• 2023

Today, as AI (Artificial Intelligence) technology develops and its practicality increases, it is widely used in various application fields in real life. At this time, the AI model is basically learned based on various statistical properties of the learning data and then distributed to the system, but unexpected changes in the data in a rapidly changing data situation cause a decrease in the model's performance. In particular, as it becomes important to find drift signals of deployed models in order to respond to new and unknown attacks that are constantly created in the security field, the need for lifecycle management of the entire model is gradually emerging. In general, it can be detected through performance changes in the model's accuracy and error rate (loss), but there are limitations in the usage environment in that an actual label for the model prediction result is required, and the detection of the point where the actual drift occurs is uncertain. there is. This is because the model's error rate is greatly influenced by various external environmental factors, model selection and parameter settings, and new input data, so it is necessary to precisely determine when actual drift in the data occurs based only on the corresponding value. There are limits to this. Therefore, this paper proposes a method to detect when actual drift occurs through an Anomaly analysis technique based on XAI (eXplainable Artificial Intelligence). As a result of testing a classification model that detects DGA (Domain Generation Algorithm), anomaly scores were extracted through the SHAP(Shapley Additive exPlanations) Value of the data after distribution, and as a result, it was confirmed that efficient drift point detection was possible.

• The Journal of Bigdata
• /
• v.7 no.2
• /
• pp.195-204
• /
• 2022

The tourism industry is facing a crisis due to the recent COVID-19 pandemic, and it is vital to improving profitability to overcome it. In situations such as COVID-19, it would be more efficient to sell additional products other than guest rooms to customers who have visited to increase the unit price rather than adopting an aggressive sales strategy to increase room occupancy to increase profits. Previous tourism studies have used machine learning techniques for demand forecasting, but there have been few studies on cross-selling forecasting. Also, in a broader sense, a resort is the same accommodation industry as a hotel. However, there is no study specialized in the resort industry, which is operated based on a membership system and has facilities suitable for lodging and cooking. Therefore, in this study, we propose a cross-selling prediction model using various machine learning techniques with an actual resort company's accommodation data. In addition, by applying the explainable artificial intelligence XAI(eXplainable AI) technique, we intend to interpret what factors affect cross-selling and confirm how they affect cross-selling through empirical analysis.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.05a
• /
• pp.273-276
• /
• 2021

최근의 기계 학습 (딥러닝)은 기존의 전통적인 통계 분석 방법들에 비해 효율성과 정확도가 높은 장점이 있지만, 처리과정이 블랙박스와 같아 결과 값의 중요한 원인 또는 근거 요인을 찾기 어렵다는 단점을 가지고 있다. 이를 해결하기 위한 최근의 XAI (eXplainable AI) 연구를 기반으로 하여, 본 논문에서는 의료기관에서 전정기관의 이상을 판별하기 위해 수작업으로 이루어지고 있는 HIT (head impulse test) 테스트 결과를 자동화하고, 설득력 있는 신뢰도 검정을 위해, XAI 기반 DoWhy 프레임 워크를 사용하였다. 전정기관 이상으로 의심되는 환자의 동공 움직임을 optical flow 로 추적하고, 정상인과의 Wasserstein metric 의 DoWhy 검증을 통해 전정기관 이상 여부의 신뢰도 구간을 검정한다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.07a
• /
• pp.387-390
• /
• 2021

최근 전자 상거래 시장이 급격한 성장을 이루면서 고객들의 급변하는 니즈를 파악하는 것이 기업들의 수익에 직결되는 요소로 인식되고 있다. 이에 기업들은 고객들의 니즈를 신속하고 정확하게 파악하기 위해, 기축적된 고객 관련 각종 데이터를 활용하려는 시도를 강화하고 있다. 기존 시도들은 주로 구매 행동 예측에 중점을 두었으나 고객 행동의 전후 과정을 해석하는데 있어 어려움이 존재했다. 본 연구에서는 고객이 구매한 상품을 확정 또는 환불하는 행동을 취할 때 해당 행동이 발생하는데 있어 어떤 요소들이 작용하였는지를 파악하고, 어떤 고객이 환불할 지를 예측하는 예측 모형을 새롭게 제시한다. 예측 모형 구현에는 트리 기반 앙상블 방법을 사용해 예측력을 높인 XGBoost 기법을 적용하였으며, 고객 의도에 영향을 미치는 요소들을 파악하기 위하여 대표적인 설명가능한 인공지능(XAI) 기법 중 하나인 SHAP 기법을 적용하였다. 이를 통해 특정 고객 행동에 대한 각 요인들의 전반적인 영향 뿐만 아니라, 각 개별 고객에 대해서도 어떤 요소가 환불결정에 영향을 미쳤는지 파악할 수 있었다. 이를 통해 기업은 고객 개개인의 의사 결정에 영향을 미치는 요소를 파악하여 개인화 마케팅에 사용할 수 있을 것으로 기대된다.