Earticle

Heart disease is a major cause of mortality in the world that is in dire need of accurate, interpretable predictive measures that could be utilized to manage it proactively. The writer of this paper proposes an Explainable AI (XAI) Ensemble Machine Learning model to predict heart disease using an 1,025 patient record dataset. To achieve methodological rigor and generalization, 5- Fold Stratified Cross-Validation (CV) was used to evaluate all models, such as LightGBM and Random Forest. LightGBM model was stable and better in performance as it had Mean CV Accuracy of ±0.9620 ±0.0178. Integration of XAI (SHAP/LIME) is the means of creating clinical trust; analysis has confirmed maximum heart rate (thalach) and type of chest pain (cp) as medically significant characteristics. This framework supports the sustainable smart city healthcare through a highly transparent decision-support system, which manages the resources in optimizing scalable public health programs.

The need to detect lung cancer accurately and early has been brought out through the fact that lung cancer has remained one of the top causes of cancer-related deaths in the world. A CT scan is usually interpreted manually which makes this time consuming and subjective. This paper hypothesizes that an explainable implementation of automated deep learning can be used to classify lung cancer based on the transfer learning models (VGG16, VGG19, ResNet50, and EfficientNetB3) on the IQ-OTH/NCCD dataset. The dataset was stratified by means of the SMOTE and was split into 80 and 20 percent training and validation subsets, respectively. All the pretrained CNNs were fine-tuned with the Adam optimizer and categorical cross-entropy loss. VGG16 performed the best and had a validation accuracy of 98.64, precision and recall of 98, and ROCAUC of 99. Visualization of tumor regions was done using explainable AI techniques (Grad-CAM, LIME), which are interpretable and have diagnostic transparency. The suggested framework proves that transfer learning combined with XAI is more effective in terms of accuracy and reliability in diagnosing medical images and is one of the steps to clinically reliable smart healthcare systems.

AI 기술의 비약적인 발전은 사회 전반에 걸쳐 다양한 기능을 수행할 수 있는 모델들이 등장했다. 이에 따라 AI 모델들은 점차 대규모화되고 복잡한 구조를 갖추게 되었으며, 그 결과 이들의 의사결정 과정은 인간이 직관적으로 이해하기 어려운 수준에 이르렀다. 이러한 복잡성을 해소하고자 설명 가능 한 인공지능(XAI, eXplainable Artificial Intelligence)에 대한 연구가 활발히 진행되고 있으며, 다양 한 설명 모델들이 제안되고 있다. 설명 가능한 인공지능 모델은 각기 다른 접근법을 통해 모델의 판단 근거를 설명하려고 시도하고 있지만, 제공되는 설명의 대상, 평가 방식, 그리고 설명이 충족해야 할 요 구사항 등에 대해서는 여전히 명확한 기준이 부재한 실정이다. 이로 인해 AI 시스템을 실제 사회 기 반 시스템에 적용하는 데에는 여러 제약이 존재한다. 또한, 기존 XAI 모델들은 직관적인 설명을 제공 하는 데 집중해왔으나, 그 설명에 대한 정량적‧정성적 평가 또는 명확한 요구사항 정립은 부족했다. 특 히, 공공 및 주요 사회 시스템에서 신뢰할 수 있는 XAI 개발이 요구되고 있음에도 불구하고, 어떤 기 능적 또는 비기능적 요구사항을 충족해야 하는지에 대한 논의는 미비하다. 본 연구는 텍스트 및 이미 지 도메인 전반을 아우르며, XAI 모델이 갖춰야 할 핵심 요구사항을 정의하고 이를 분류하는 것을 목 표로 한다. 이를 위해 다양한 XAI 모델들을 분석하고, 이들이 사용하는 핵심 요소와 한계를 식별하며, 소프트웨어공학적 관점에서 이를 체계적으로 해석한다. 특히 Goal-Question-Metric(GQM) 접근법 을 적용하여 각 모델의 신뢰성, 설득력, 효용성에 대해 평가하고 요구사항 도출을 위한 근거를 마련한다.

본 연구는 넷플릭스의 계정 공유 제한 강화 정책에 대한 이용자의 대응 행동을 예측하기 위해 기계학습 기반 다중 분류 모델을 구축하였다. 한국언론진흥재단의 설문 자료(n=681)를 활용하여 이용자 행동을 혼자 이용, 추가 요금 지불, 공유 중단, 편법 모색, 이탈의 5개 범주로 분류하고, 6가지 알고리즘을 비교한 결과 Random Forest가 정확도 0.664, Macro F1-score 0.602로 가장 우수한 성능을 보였으며, 이탈(89%)과 편법 모색(83%) 그룹을 높은 민감도로 탐지하였다. 순열 중요도(PI, Permutation Importance) 및 SHAP 분석 결과, 구독 구조(32.6%)와 공유 동기(25.1%)가 인구통계학적 변수(8.1%)보다 훨씬 큰 설명력을 보였다. 계정 소유자는 이탈 성향이, 공유 수혜자는 편법 모색 성향이 나타났다. 본 연구는 설명 가능한 AI 기법을 통해 이용자 행동을 다차원적으로 예측함으로써 OTT 서비스 의 정책 수립에 실질적 시사점을 제공한다.

This study developed a machine learning-based multi-class classification model to predict user responses to Netflix's account-sharing restriction policy. Using survey data from the Korea Press Foundation (n=681), user behaviors were categorized into five types: individual use, paying additional fees, stopping sharing, workaround-seeking, and service churn. Six algorithms were compared, with Random Forest achieving the highest performance (Accuracy 0.664, Macro F1-score 0.602) and high sensitivity in detecting churn (89%) and workaround-seeking (83%) groups. Permutation Importance and SHAP analyses revealed that subscription structure (32.6%) and sharing motivations (25.1%) had substantially greater explanatory power than demographic variables (8.1%). Account owners exhibited strong churn tendencies, while sharing beneficiaries sought workarounds. This study extends platform policy research by multidimensionally predicting user behaviors through explainable AI techniques, providing practical implications for OTT service policy formulation.

최근 발생한 기업의 대규모 보안 사고는 고도화된 공격 기법보다는 기본적인 보안 정책 미준수와 장기간의 탐지 실패가 초 래하는 치명적 결과임을 보여주었다. 이는 복잡해지는 IT 인프라 환경에서 단순 스크립트 점검의 한계로 인해, 수동 점검 방 식만으로는 보안 공백을 해소하기 어렵다는 점을 시사한다. 이러한 한계를 보완하기 위한 대안으로 대규모 언어모델을 활용한 AI 기반 보안감사 자동화 기술이 주목받고 있으나, 고도의 기밀성과 가용성이 요구되는 국방 분야에서는 생성형 AI의 환각 현상과 예측 불가능한 자율성이 도입에 주요 제약 요인으로 작용하고 있다. 본 논문에서는 이러한 문제를 해결하기 위해 국방 환경에 최적화된 LangGraph 기반의 설명 가능하고 제어 가능한 보안 감사 에이전트를 제안한다. 본 시스템은 한국인터넷진흥 원의 가이드라인에 기반한 화이트리스트 명령어 통제, 데이터 유출 방지를 위한 로컬 RAG, 그리고 관리자 승인 절차를 결합 하여 AI의 행동을 엄격히 통제함으로써 운영 안전성을 확보한다. 실험 결과, 폐쇄망 및 이기종 OS 환경에서 총 91가지 항목 을 환각으로 인한 오류 없이 진단하고 가이드 위반 사항을 식별하여 설명 가능한 리포트를 생성함으로써, 국방의 제약을 극복 한 실질적인 AI 도입 가능성을 입증하였다.

Recent large-scale security incidents have demonstrated that severe consequences often stem from basic policy violations and prolonged detection failures, revealing the limitations of manual inspections in complex IT environments. While AI-based automation offers a solution, its adoption in the defense sector is restricted by concerns over hallucinations and unpredictable autonomy. To address these challenges, this paper proposes a LangGraph-based explainable and controllable security audit agent optimized for defense environments. The system ensures operational safety by enforcing whitelist-based command control grounded in KISA technical vulnerability guidelines, utilizing Local RAG to prevent data leakage, and implementing administrator approval procedures. Experimental results confirm that the agent reliably diagnoses 91 inspection items across heterogeneous OS environments without hallucinations, generating explainable reports. This study demonstrates the practical feasibility of AI in defense by effectively balancing automation efficiency with strict security compliance.

[연구목적] 본 연구는 AI-Hub의 금융 합성 데이터를 활용하여 기업 부도 예측 모델을 개발하고, 복잡한 기계학습 모델의 ‘블랙박스’ 문제를 해결하기 위해 설명가능한 인공지능(XAI) 기법인 SHAP(SHapley Additive exPlanations)을 적용하였다. 이를 통해 높은 예측 성능을 확보함과 동시에, 주요 부도 위험 요인을 식별하여 예측의 투명성과 신뢰성을 제고하는 것을 목표로 하였다. [연구방법] 연구 방법으로는 LightGBM 기반 예측 모델을 구축하고, Optuna를 활용한 하이퍼파라미터 최 적화를 수행하였다. 불균형 데이터 특성을 반영한 모델링 후, SHAP 값을 이용해 주요 변수의 영향력을 정량적 으로 분석하고 위험 그룹 클러스터링을 실시하였다. [연구결과] 실험 결과, 부도기업 탐지 재현율은 74.53%, 정밀도는 38.96%를 기록하였으며, 재현율을 중시하 는 F₂-score는 0.6302로 나타났다. 5-Fold 교차검증 결과 평균 F₂-score는 0.6845(표준편차 0.0049)로 안정적 인 일반화 성능을 보였다. 변수 중요도 분석에서는 기업 신용평가등급과 종업원 수가 가장 큰 영향 요인으로 확인되었다. [연구의 시사점] 본 연구는 국내 공개 금융 합성 데이터를 활용하여 현실과 유사한 규모의 부도 예측 실증 을 수행함으로써 데이터 부족 문제를 겪는 연구자들에게 참고 사례를 제공한다. 또한 SHAP 기반의 모델 해석 을 통해 금융기관의 리스크 관리에 필요한 투명성과 설명가능성을 확보할 수 있음을 입증하였다. 향후 연구에 서는 실제 데이터를 활용한 검증과 비정형 데이터 통합, 다양한 XAI 기법 적용을 통한 해석 다양성 확보가 필요하다.

[Purpose] This study aims to develop a corporate bankruptcy prediction model using financial synthetic data from AI-Hub and to address the “black box” problem of complex machine learning models by applying the explainable artificial intelligence (XAI) technique SHAP (SHapley Additive exPlanations). The goal is to achieve high predictive performance while identifying major bankruptcy risk factors to enhance the transparency and reliability of predictions. [Methodology] A LightGBM-based prediction model was constructed, and hyperparameter optimization was conducted using Optuna. After modeling with consideration for the imbalanced data characteristics, SHAP values were utilized to quantitatively analyze the influence of key variables and to perform risk group clustering. [Findings] Experimental results showed that the recall for bankrupt firms was 74.53%, and the precision was 38.96%. The F₂-score, which emphasizes recall, was 0.6302. Five-fold cross-validation yielded an average F₂-score of 0.6845 with a standard deviation of 0.0049, demonstrating stable generalization performance. Variable importance analysis revealed that corporate credit rating and the number of employees were the most influential factors. [Implications] This study provides a practical case for researchers facing data scarcity by conducting empirical bankruptcy prediction on a realistic scale using publicly available domestic financial synthetic data. Furthermore, the SHAP-based model interpretation demonstrates that AI models can secure transparency and explainability in financial institutions’ risk management. Future research should validate the model using actual corporate data, integrate unstructured data such as news texts, and apply various XAI techniques to ensure diverse interpretability.

Artificial intelligence (AI) is a significant tool in modern military operations in that it helps to analyze a large volume of strategic, tactical, and operational data. On the other hand, current large language models (LLMs) like GPT-4 or Falcon have difficulty resolving problems in defense-specific contexts because of issues related to security, data confidentiality, and the lack of explainability. This document presents MilGPT, a secure and explainable LLM structure that aims at solving military problems only. To the model, fine-tuned open-source architectures with domain-specific defense datasets are integrated to elevate intelligence synthesis, decision-making, and threat prediction. On the benchmark, performance evaluation tasks show that MilGPT accounts for a 27% increase in contextual accuracy, an 18% reduction in hallucination rate, and an 33% improvement in explainability as measured by gradient-based feature attribution. In the proposed framework, military intelligence systems are not only secured but also made adaptive and humaninterpretable, thus, setting up a basis for the coming generation of AI models capable of defense-grade tasks.

Visual Question Answering (VQA) models suffer from a language bias problem, where they excessively rely on textual correlations. This study proposes a plausible counterfactual data generation method, named Plausible Counterfactual Data Generation (PCDG), which utilizes Grad- CAM-based visual importance to replace significant objects in a contextually appropriate manner. By synthesizing more contextually relevant samples than other existing augmentation methods, PCDS effectively strengthens visual-language alignment. In experiments on the VQA-CP v2 benchmark, our method achieved significant performance improvements, particularly a 10.56% increase in the 'Num' category and a 2.78% increase in the 'Other' category. This indicates that the proposed method enhances the VQA model's generalization ability and robustness through debiasing.

본 연구에서는 Normalizing Flow 기반 비지도 이상탐지 모델인 Multi-Scale Flow의 특징추출기에 다양한 모델을 적용하여 포트홀 이상탐지 성능에 미치는 영향을 정량·정성적으로 실험을 통해 분석한 다. 성능 평가는 이상 존재 여부를 판단하는 Detection AUROC와 이상 위치를 판단하는 Localization AUROC를 결합한 평균 성능을 기준으로 수행되었다. 실험 결과, 평균 AUROC 기준 85.84를 달성한 Swin Transformer가 포트홀 이상탐지에 있어 가장 높은 성능을 보임을 확인하였다. 또한 포트홀 이상 탐지에 가장 강인한 성능을 가지는 Swin Transformer 모델의 추가적인 성능 고도화를 위해 일반적으 로 사용하는 데이터 증강 기법과 Mix-Up, Cut-Mix 적용 여부에 따른 성능 분석을 진행하였다. 실험 결과, 데이터 증강 기법의 적용을 통해 포트홀 이상탐지 성능에 있어 소폭 상승하는 경향을 확인하였다.

본 연구는 문화유산 복원에서 인공지능(AI) 모델의 신뢰성 보장을 위한 설명가능한 인공지능(XAI) 알고리즘 을 분석하였다. 기존의 AI 복원 알고리즘은 내부 데이터 학습 과정의 불투명성으로 신뢰성 문제를 발생시킬 수 있다. 특히 전통 탑(Pagoda)의 복원에서 복원 근거는 신뢰성을 보장하는 중요한 요소이다. 연구에서는 Grad-CAM(Gradient-weighted Class Activation Mapping), LIME(Local Interpretable Model-agnostic Explanations), SHAP(SHapley Additive exPlanations) 세 가지 XAI 알고리즘을 비교하여 각 알고리즘의 적합 성을 분석하고, Base Case와 Worst Case를 구분하여 평가했다. 그 결과, Grad-CAM이 탑 복원에 가장 적합한 설명가능한 알고리즘으로 확인되었다. 각 알고리즘은 고유한 특성을 가지며, 향후 연구에서는 잘못 참조된 데이터 에 대한 역전파 기능을 활용하여 더욱 신뢰성 있는 복원 방법을 개발할 필요가 있다.

This study analyzes explainable artificial intelligence (XAI) algorithms for ensuring the reliability of AI-based cultural heritage restoration. Traditional AI restoration algorithms often suffer from opacity in their data learning processes, leading to issues with trustworthiness. In particular, the basis for restoration is crucial for ensuring reliability in the restoration of cultural heritage, such as traditional pagodas. The study compares three XAI algorithms Grad-CAM, LIME, and SHAP—by evaluating their suitability for pagoda restoration through Base Case and Worst Case analysis. The results demonstrate that Grad-CAM is the most suitable explainable AI algorithm for this task. While each algorithm has its unique characteristics, future research should focus on improving restoration reliability by incorporating backpropagation to correct misreferenced data.

In the default prediction problem, thecost from thefailure of forecasting defaults is much biggerthan that of forecastingnon-defaults. Thecost asymmetryis deeperin the corporatedefaultpredictionthan theretailas corporateloan portfolios arenot granular. However, thetwo typesof costs aretreatedequallyin generalas defaultpredictionmodels areusually estimatedto minimizepredictionerrorsor maximizestatistical performance. This practicemight not fulfill thegoal of risk managementto minimizeeconomiclosses. To mitigatethis issue, this study apply cost-sensitivelearningapproach to defaultprediction, which minimizeseconomiccosts insteadof statistical errors. Wedefineeconomic costs and testthemfor various levelsof thecost asymmetryby employingLogistic regression, XGBoost, and LightGBM. As a resultof empiricalexperimentswith Taiwaneseand Polish corporate default data, we first find that the proposed cost-sensitivemodels are superiorto thecost-insensitivecounterpartsin termsof economiccost, mostly regardless of thecost asymmetryscenarios. Secondly, neverthele,ssthedecreasesin thestatistical performanceare relativelysmall – economic costs decrease24.6% at theexpenseof the decrease in AUC of 4.6% on average. This suggests that financial firms can adopt the proposed default prediction models without violating the regulatory requirement on model quality. Lastly, we find that the features of high prediction power in the cost-sensitive and insensitive models are different, which has an important implication for credit monitoring.

본 연구는 산업 유사성과 지리적 근접성이 동물병원 지출을 예측하는데 어떤 역할을 하는지 검증하였다. 구체 적으로, 저자들은 머신러닝을 사용하여 산업 유사성이 지리적 근접성보다 더 중요한 역할을 한다는 것을 발견했 다. 특성 중요도를 비교하면 산업 유사성이 지리적 근접성보다 약 5배 정도 더 중요한 것으로 나타났다. 더불어, 본 연구는 지출자의 인구 특성 정보와 거주자의 인구 특성 정보의 중요성도 비교하였다. 그 결과, 일반적으로 지출 자의 인구 특성 정보가 거주자의 인구 특성 정보보다 더 중요하다는 것도 확인하였다. 한편, 거시적인 관점에서 거주자의 인구 특성 정보도 중요성을 지니는 것으로 나타났다.

The authors investigate the role of industrial similarity and geographic proximity in predicting spending on veterinary care. Using machine learning, they find that industrial similarity plays a more substantial role than geographic proximity. Specifically, comparing feature importance reveals that industrial similarity is roughly five times as important as geographic proximity. Further, this study also investigates the importance of spender demographic information and resident demographic information in prediction performance. The result shows that spender demographic information is more important than resident demographic information in general. However, from a macro perspective, resident demographic information also holds importance.

The escalating importance of online reviews in customers' purchasing behavior has led to growing concerns about the prevalence of manipulated reviews, causing confusion in their decision-making process. However, despite several efforts to develop models for manipulated review detection, a critical aspect that has not been addressed is examining the connection between manipulated review writer personality traits and manipulated review detection. In this study, we examine the role of reviewer personality traits among the factors related to review characteristics in manipulated review detection using deep learning and explainable AI. The purpose of this research is to answer the question are reviewer personality matter in manipulated review detection and what features have an impact on detection. To rich our purpose, we apply deep learning twice: 1) to infer reviewers' personality traits from review text (CNN), 2) to create manipulated review detection models (RNN and CNN). Furthermore, we equip manipulated reviews detection model with one of the XAI techniques - SHAP, that generates visual explanations of the model's decision-making process, thereby enhancing the model's interpretability and transparency. We conduct our experiment by utilizing real-world review data from Yelp.com.

AI 기술이 가진 가장 대표적인 취약점은 AI가 도출한 결과에 대한 설명가능함(Explainable)의 부족이다. 이런 전통적인 AI의 취약점을 보완하기 위해 등장한 기술이 ‘설명가능한 AI(eXplainable AI, XAI)로 XAI는 의료, 국방, 법과 질서 등과 같 은 추론결과의 신뢰성이 중요한 응용 분야에서 큰 관심을 끌고 있으며, 특히 최근 군사 응용 AI에 있어서는 필수 불가결한 요소로 판단되고 있다. 미 국방연구원(DARPA)의 경우 UC Berkeley, Carnegie Mellon University 등 11개의 대학 및 연 구소가 참여하는 XAI Program을 운용하며 군사 분야의 XAI 적용을 적극적으로 추진하고 있지만, 우리 군의 경우 AI 기능 개발에 집중하는 상황으로 XAI 개발에 관한 연구는 미진한 상황이다. 특히, 민간에서 개발된 다양한 XAI 기술을 군사적 어 떻게 접목하고 응용할 것인가에 대한 개념과 시나리오가 부족한 실정이다. 이에 본 논문에서는 군사적 XAI(Military-XAI, MXAI)의 개념과 방법론을 살펴보고 감시정찰, 지휘통제, 기동, 화력 등 전장기능별 AI 기술에 적용할 수 있는 XAI 기술적용 시나리오를 제시하여 산학연에서 향후 MXAI를 연구할 때 통찰과 이정표를 제시하고자 하였다.

The most significant weakness of AI technology is the lack of explainability of the results obtained by AI. The technology that has emerged to compensate for this weakness of traditional AI is eXplainable AI (XAI). XAI is attracting great attention in applications where the reliability of inference results is important, such as healthcare, defense, law, and has recently been judged to be indispensable for military applications. The U.S. Defense Advanced Research Projects Agency (DARPA) is actively promoting the application of XAI in the military field by operating the XAI Program, in which 11 universities and research institutes such as UC Berkeley and Carnegie Mellon University participate, but in the case of the Korean military, research on XAI development is underdeveloped due to the focus on developing AI capabilities. In this paper, we also examine the concept and methodology of XAI and propose a method for applying XAI technology that can be applied to AI technology for each battlefield functions. The concept and recent technology of XAI are summarized, and the concept of XAI operation and application scenario of AI that is expected to be applied to the weapon system for each battlefield function is presented.

Artificial intelligence has become familiar with modern society, not the distant future. As artificial intelligence and machine learning developed more highly and became more complicated, it became difficult for people to grasp its structure and the basis for decision-making. It is because machine learning only shows results, not the whole processes. As artificial intelligence developed and became more common, people wanted the explanation which could provide them the trust on artificial intelligence. This study recognized the necessity and importance of explainable artificial intelligence, XAI, and examined the trends of XAI research by analyzing social networks and analyzing topics with IEEE published from 2004, when the concept of artificial intelligence was defined, to 2022. Through social network analysis, the overall pattern of nodes can be found in a large number of documents and the connection between keywords shows the meaning of the relationship structure, and topic modeling can identify more objective topics by extracting keywords from unstructured data and setting topics. Both analysis methods are suitable for trend analysis. As a result of the analysis, it was found that XAI's application is gradually expanding in various fields as well as machine learning and deep learning.

교통 혼잡을 해결하기 위한 AI 기반 속도 예측 연구는 활발하게 진행되고 있다. 하지만, 인공지능의 추론 과정을 설명하는 설명 가능한 AI의 중요성이 대두되고 있는 가운데 AI 기반 속도 예측의 결과를 해석하고 원인을 추리하는 연구는 미흡하였다. 따라서 본 논문에서는 `설명 가능 그래프 심층 인공신경망 (GNN)`을 고안하여 속도 예측뿐만 아니라, GNN 모델 입력값의 마스킹 기법에 기반하여 인근 도로 영향력을 정량적으로 분석함으로써 혼잡 등의 상황에 대한 추론 근거를 도출하였다. TOPIS 통행 속도 데이터를 활용하여 서울 시내 혼잡 도로를 기준으로 예측 및 분석 방법론을 적용한 후 영향력 높은 인근 도로의 속도를 가상으로 조절하는 시뮬레이션 통하여 혼잡 도로의 통행 속도가 개선됨을 확인하여 제안한 방법론의 타당성을 입증하였다. 이는 교통 네트워크에 제안한 방법론을 적용하고, 그 추론 결과에 기반한 특정 인근 도로를 제어하여 교통 흐름을 개선할 수 있다는 점에 의미가 있다.

AI-based speed prediction studies have been conducted quite actively. However, while the importance of explainable AI is emerging, the study of interpreting and reasoning the AI-based speed predictions has not been carried out much. Therefore, in this paper, 'Explainable Deep Graph Neural Network (GNN)' is devised to analyze the speed prediction and assess the nearby road influence for reasoning the critical contributions to a given road situation. The model's output was explained by comparing the differences in output before and after masking the input values of the GNN model. Using TOPIS traffic speed data, we applied our GNN models for the major congested roads in Seoul. We verified our approach through a traffic flow simulation by adjusting the most influential nearby roads' speed and observing the congestion's relief on the road of interest accordingly. This is meaningful in that our approach can be applied to the transportation network and traffic flow can be improved by controlling specific nearby roads based on the inference results.

Explainable Artificial Intelligence (XAI) is crucial for the transition from the fourth to fifth industrial revolution, providing transparency and fostering user confidence in Artificial Intelligence (AI) powered systems. Since 2020, XAI applications demonstrate potential to transform manufacturing. This paper provides an extensive overview of XAI-based applications in Industries 4.0 and 5.0 by highlighting the trends regarding methods used, connecting XAI methods with important parameters and presenting XAI visualization approaches. The survey provides valuable insights for researchers, practitioners and industry leaders as it underscores the potential of XAI in shaping the future of manufacturing by enhancing transparency and user acceptance of AI-powered applications.

Identifying informative features in bioinformatics is challenging due to their small proportion within large datasets. We propose a scalable and interpretable feature selection framework for cancer RNA-seq by transforming non-image bio-data into 2D formats and applying convolutional neural networks (CNNs) with transfer learning for efficient classification. Explainable artificial intelligence (XAI) techniques identify and prioritize important features, while principal component analysis (PCA) determines the optimal number of selected features, ensuring transparency and reliability. Comparative analysis of CNN and XAI highlights the effectiveness of our approach, providing a robust framework for high-dimensional genomic data analysis with applications in cancer diagnosis and prognosis.

Explainable AI (XAI) has found numerous applications in computer vision. While image classification-based explainability techniques have garnered significant attention, their counterparts in semantic segmentation have been relatively neglected. Given the prevalent use of image segmentation, ranging from medical to industrial deployments, these techniques warrant a systematic look. In this paper, we present the first comprehensive survey on XAI in semantic image segmentation. We analyze and categorize the literature based on application categories and domains, as well as the evaluation metrics and datasets used. We also propose a taxonomy for interpretable semantic segmentation, and discuss potential challenges and future research directions.

Digital twins (DTs) are an emerging digitalization technology with a huge impact on today’s innovations in both industry and research. DTs can significantly enhance our society and quality of life through the virtualization of a real-world physical system, providing greater insights about their operations and assets, as well as enhancing their resilience through real-time monitoring and proactive maintenance. DTs also pose significant security risks, as intellectual property is encoded and more accessible, as well as their continued synchronization to their physical counterparts. The rapid proliferation and dynamism of cyber threats in today’s digital environments motivate the development of automated and intelligent cyber solutions. Today’s industrial transformation relies heavily on artificial intelligence (AI), including machine learning (ML) and data-driven technologies that allow machines to perform tasks such as self-monitoring, investigation, diagnosis, future prediction, and decision-making intelligently. However, to effectively employ AI-based models in the context of cybersecurity, human-understandable explanations, and their trustworthiness, are significant factors when making decisions in real-world scenarios. This article provides an extensive study of explainable AI (XAI) based cybersecurity modeling through a taxonomy of AI and XAI methods that can assist security analysts and professionals in comprehending system functions, identifying potential threats and anomalies, and ultimately addressing them in DT environments in an intelligent manner. We discuss how these methods can play a key role in solving contemporary cybersecurity issues in various real-world applications. We conclude this paper by identifying crucial challenges and avenues for further research, as well as directions on how professionals and researchers might approach and model future-generation cybersecurity in this emerging field.