Search Results (22)

Artificial intelligence (AI) plays a pivotal role in Industry 4.0, with predictive maintenance (PdM) emerging as a core application for improving operational efficiency by reducing unplanned downtime and extending asset life. Despite these advancements, the black-box nature of AI models remains a significant barrier to adoption, as industry stakeholders require systems that are both transparent and trustworthy. This study presents a systematic literature review examining how human-in-the-loop explainable AI (HITL-XAI) approaches can enhance the effectiveness and adoption of AI systems in PdM contexts. This review followed the PRISMA methodology, employing predefined search strings across Scopus, ProQuest, and EBSCO databases. Sixty-three peer-reviewed journal articles, published between 2019 and early 2025, were included in the final analysis. The selected studies span various domains, including industrial manufacturing, energy, and transportation, with findings synthesized through both descriptive and thematic analyses. A key gap identified is the limited empirical exploration of generative AI (GenAI) in improving the usability, interpretability, and trustworthiness of HITL-XAI systems in PdM applications. This review outlines actionable insights for integrating explainability and GenAI into existing rule-based PdM systems to support more adaptive and reliable maintenance strategies. Ultimately, the findings underscore the importance of designing HITL-XAI systems that not only demonstrate high model performance but are also effectively aligned with operational workflows and the cognitive needs of maintenance personnel. Full article

Post-Traumatic Stress Disorder (PTSD) poses complex clinical challenges due to its emotional volatility, contextual sensitivity, and need for personalized care. Conventional AI systems often fall short in therapeutic contexts due to lack of explainability, ethical safeguards, and narrative understanding. We propose a hybrid neuro-symbolic architecture that combines Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), symbolic controllers, and ensemble classifiers to support clinicians in PTSD follow-up. The proposal integrates real-time anonymization, session memory through patient-specific RAG, and a Human-in-the-Loop (HITL) interface. It ensures clinical safety via symbolic logic rules derived from trauma-informed protocols. The proposed architecture enables safe, personalized AI-driven responses by combining statistical language modeling with explicit therapeutic constraints. Through modular integration, it supports affective signal adaptation, longitudinal memory, and ethical traceability. A comparative evaluation against state-of-the-art approaches highlights improvements in contextual alignment, privacy protection, and clinician supervision. Full article

Educational assessment relies on well-constructed test items to measure student learning accurately, yet traditional item development is time-consuming and demands specialized psychometric expertise. Automatic item generation (AIG) offers template-based scalability, and recent large language model (LLM) advances promise to democratize item creation. However, fully automated approaches risk introducing factual errors, bias, and uneven difficulty. To address these challenges, we propose and evaluate a hybrid human-in-the-loop (HITL) framework for AIG that combines psychometric rigor with the linguistic flexibility of LLMs. In a Spring 2025 case study at Franklin University Switzerland, the instructor collaborated with ChatGPT (o4-mini-high) to generate parallel exam variants for two undergraduate business courses: Quantitative Reasoning and Data Mining. The instructor began by defining “radical” and “incidental” parameters to guide the model. Through iterative cycles of prompt, review, and refinement, the instructor validated content accuracy, calibrated difficulty, and mitigated bias. All interactions (including prompt templates, AI outputs, and human edits) were systematically documented, creating a transparent audit trail. Our findings demonstrate that a HITL approach to AIG can produce diverse, psychometrically equivalent exam forms with reduced development time, while preserving item validity and fairness, and potentially reducing cheating. This offers a replicable pathway for harnessing LLMs in educational measurement without sacrificing quality, equity, or accountability. Full article

Modern fly-by-wire (FBW) aircraft demand high-fidelity simulation systems for research and training, yet existing force-sensing solutions are often prohibitively expensive. This study presents the design, development, and validation of a low-cost, reconfigurable force-sensing sidestick. The system utilizes four strain-gauge load cells to capture pure pilot force inputs, integrated with a 6-DoF non-linear flight model. To evaluate its performance, a pitch-angle tracking task was conducted with 16 participants (pilots and non-pilots). Objective metrics revealed that the control strategy was a primary determinant of performance. Participants employing a proactive feedforward control strategy exhibited roughly an order of magnitude lower tracking-error variance than those relying on reactive corrections. Subjective assessments using the Cooper-Harper scale and NASA-TLX corroborated the objective data, confirming the sidestick’s ability to differentiate control techniques. This work demonstrates an open-source platform that makes high-fidelity FBW simulation accessible for academic research, pilot training, and human factors analysis at a fraction of the cost of commercial systems. Full article

The rising complexity of financial fraud in highly digitalized regions such as the Gulf Cooperation Council (GCC) poses challenging issues owing to class imbalance, adversarial attacks, concept drift, and explainability requirements. This paper suggests a hybrid machine-learning framework (HMLF) that incorporates SMOTEBoost and cost-sensitive learning to address imbalances, adversarial training and FraudGAN to ensure robustness, DDM and ADWIN to achieve adaptive learning, and SHAP, LIME, and human-in-the-loop (HITL) analysis to ensure explainability. Employing real transaction data from the GCC banks, the framework is tested through a design science research approach. Experiments illustrate significant gains in fraud recall (from 35% to 85%), adversarial robustness (attack success rate decreased from 35% to 5%), and drift recovery (within 24 h), while retaining operational latency below 150 milliseconds. This paper substantiates that incorporating technical resilience with institutional constraints offers an auditable, scalable, and regulation-compliant solution for detecting fraud in high-risk financial contexts. Full article

In this article, we introduce a novel framework for learning spatial concepts within a human-in-the-loop (HITL) context, highlighting the critical role of explainability in AI systems. By incorporating human feedback, the approach enhances the learning process, making it particularly suitable for applications where user trust and interpretability are essential, such as AiTR. Namely, we introduce a new parametric similarity measure for spatial relations expressed as histograms of forces (HoFs). Next, a spatial concept is represented as a spatially attributed graph and HoF bundles. Last, a process is outlined for utilizing this structure to make decisions and learn from human feedback. The framework’s robustness is demonstrated through examples with diverse user types, showcasing how varying feedback strategies influence learning efficiency, accuracy, and ability to tailor the system to a particular user. Overall, this framework represents a promising step toward human-centered AI systems capable of understanding complex spatial relationships while offering transparent insights into their reasoning processes. Full article

This paper presents a first-of-its-kind evaluation of integrating Large Language Models (LLMs) within a Human-In-The-Loop (HITL) framework for risk analysis in machinery functional safety, adhering to ISO 12100. The methodology systematically addresses LLM limitations, such as hallucinations and lack of domain-specific expertise, by embedding expert oversight to ensure reliable and compliant outputs. Applied to four diverse industrial case studies—motorized gates, autonomous transport vehicles, weaving machines, and rotary printing presses—this study assesses the applicability of ChatGPT in routine risk analysis tasks central to machinery functional safety workflows, such as hazard identification and risk assessment. The results demonstrated substantial improvements: during HITL involvement and the subsequent iterations of risk assessment with expert feedback, a complete agreement with ground truth was achieved across all four use cases. ChatGPT also identified additional scenarios and edge cases, enriching the risk analysis. Efficiency gains were notable, with time efficiency rated at 4.95 out of 5, on average, across case studies. Overall accuracy (4.7 out of 5) and usability (4.8 out of 5) ratings demonstrated the robustness of the HITL framework in ensuring reliable and practical outputs. Likert scale evaluations reflected high confidence in the refined outputs, emphasizing the critical role of HITL in enhancing both trust and usability. The study also highlights the importance of prompt design, revealing that longer initial prompts improve accuracy, while shorter iterative prompts maintain usability without compromising efficiency. The iterative HITL process further ensures that refined outputs align with safety standards and practical requirements. This evaluation underscores the transformative potential of generative AI in functional safety workflows, enhancing routine activities while ensuring rigorous human oversight in safety-critical, regulated industries. Full article

The introduction of Self-X capabilities into industrial control offers a tremendous potential in the development of resilient, adaptive production systems that enable circular economy. The Self-X capabilities, powered by Artificial Intelligence (AI), can monitor the production performance and enable timely reactions to problems or suboptimal operation. This paper presents a concept and prototype for Self-X AI in the process industry, particularly electric steelmaking with the EAF (Electric Arc Furnace). Due to complexity, EAF operation should be optimized with computational models, but these suffer from the fluctuating composition of the input materials, i.e., steel scrap. The fluctuation can be encountered with the Self-X method that monitors the performance, detecting anomalies and suggesting the re-training and re-initialization of models. These suggestions support the Human-in-the-Loop (HITL) in managing the AI models and in operating the production processes. The included Self-X capabilities are self-detection, self-evaluation, and self-repair. The prototype proves the concept, showing how the optimizing AI pipeline receives alarms from the external AI services if the performance degrades. The results of this work are encouraging and can be generalized, especially to processes that encounter drift related to the conditions, such as input materials for circular economy. Full article

This study introduces a multi-agent reinforcement learning approach to address the challenges of real-time scheduling in dynamic environments, with a specific focus on healthcare operations. The proposed system integrates the Human-in-the-Loop (HITL) paradigm, providing continuous feedback from human evaluators, and it employs a sophisticated reward function to attenuate the effects of human-driven events. Novel mapping between reinforcement learning (RL) concepts and the Belief–Desire–Intention (BDI) framework is developed to enhance the explainability of the agent’s decision-making. A system is designed to adapt to changes in patient conditions and preferences while minimizing disruptions to existing schedules. Experimental results show a notable decrease in patient waiting times compared to conventional methods while adhering to operator-induced constraints. This approach offers a robust, explainable, and adaptable solution for the challenging tasks of scheduling in the environments that require human-centered decision-making. Full article

Machine learning (ML) revolutionized traditional machine fault detection and identification (FDI), as complex-structured models with well-designed unsupervised learning strategies can detect abnormal patterns from abundant data, which significantly reduces the total cost of ownership. However, their opaqueness raised human concern and intrigued the eXplainable artificial intelligence (XAI) concept. Furthermore, the development of ML-based FDI models can be improved fundamentally with machine learning operations (MLOps) guidelines, enhancing reproducibility and operational quality. This study proposes a framework for the continuous development of ML-based FDI solutions, which contains a general structure to simultaneously visualize and check the performance of the ML model while directing the resource-efficient development process. A use case is conducted on sensor data of a hydraulic system with a simple long short-term memory (LSTM) network. Proposed XAI principles and tools supported the model engineering and monitoring, while additional system optimization can be made regarding input data preparation, feature selection, and model usage. Suggested MLOps principles help developers create a minimum viable solution and involve it in a continuous improvement loop. The promising result motivates further adoption of XAI and MLOps while endorsing the generalization of modern ML-based FDI applications with the HITL concept. Full article

Background/Objectives: The accurate quantification of ground-glass opacities (GGOs) and consolidation volumes has prognostic value in COVID-19 patients. Nevertheless, the accurate manual quantification of the corresponding volumes remains a time-consuming task. Deep learning (DL) has demonstrated good performance in the segmentation of normal lung parenchyma and COVID-19 pneumonia. We introduce a Human-in-the-Loop (HITL) strategy for the segmentation of normal lung parenchyma and COVID-19 pneumonia that is both time efficient and quality effective. Furthermore, we propose a Gaussian Mixture Model (GMM) to classify GGO and consolidation based on a probabilistic characterization and case-sensitive thresholds. Methods: A total of 65 Computed Tomography (CT) scans from 64 patients, acquired between March 2020 and June 2021, were randomly selected. We pretrained a 3D-UNet with an international dataset and implemented a HITL strategy to refine the local dataset with delineations by teams of medical interns, radiology residents, and radiologists. Following each HITL cycle, 3D-UNet was re-trained until the Dice Similarity Coefficients (DSCs) reached the quality criteria set by radiologists (DSC = 0.95/0.8 for the normal lung parenchyma/COVID-19 pneumonia). For the probabilistic characterization, a Gaussian Mixture Model (GMM) was fitted to the Hounsfield Units (HUs) of voxels from the CT scans of patients with COVID-19 pneumonia on the assumption that two distinct populations were superimposed: one for GGO and one for consolidation. Results: Manual delineation of the normal lung parenchyma and COVID-19 pneumonia was performed by seven teams on 65 CT scans from 64 patients (56 ± 16 years old (μ ± σ), 46 males, 62 with reported symptoms). Automated lung/COVID-19 pneumonia segmentation with a DSC > 0.96/0.81 was achieved after three HITL cycles. The HITL strategy improved the DSC by 0.2 and 0.5 for the normal lung parenchyma and COVID-19 pneumonia segmentation, respectively. The distribution of the patient-specific thresholds derived from the GMM yielded a mean of −528.4 ± 99.5 HU (μ ± σ), which is below most of the reported fixed HU thresholds. Conclusions: The HITL strategy allowed for fast and effective annotations, thereby enhancing the quality of segmentation for a local CT dataset. Probabilistic characterization of COVID-19 pneumonia by the GMM enabled patient-specific segmentation of GGO and consolidation. The combination of both approaches is essential to gain confidence in DL approaches in our local environment. The patient-specific probabilistic approach, when combined with the automatic quantification of COVID-19 imaging findings, enhances the understanding of GGO and consolidation during the course of the disease, with the potential to improve the accuracy of clinical predictions. Full article

Lower-limb exoskeletons (LLEs) can provide rehabilitation training and walking assistance for individuals with lower-limb dysfunction or those in need of functionality enhancement. Adapting and personalizing the LLEs is crucial for them to form an intelligent human–machine system (HMS). However, numerous LLEs lack thorough consideration of individual differences in motion planning, leading to subpar human performance. Prioritizing human physiological response is a critical objective of trajectory optimization for the HMS. This paper proposes a human-in-the-loop (HITL) motion planning method that utilizes surface electromyography signals as biofeedback for the HITL optimization. The proposed method combines offline trajectory optimization with HITL trajectory selection. Based on the derived hybrid dynamical model of the HMS, the offline trajectory is optimized using a direct collocation method, while HITL trajectory selection is based on Thompson sampling. The direct collocation method optimizes various gait trajectories and constructs a gait library according to the energy optimality law, taking into consideration dynamics and walking constraints. Subsequently, an optimal gait trajectory is selected for the wearer using Thompson sampling. The selected gait trajectory is then implemented on the LLE under a hybrid zero dynamics control strategy. Through the HITL optimization and control experiments, the effectiveness and superiority of the proposed method are verified. Full article

Lower limb exoskeletons have the potential to mitigate work-related musculoskeletal disorders; however, they often lack user-oriented control strategies. Human-in-the-loop (HITL) controls adapt an exoskeleton’s assistance in real time, to optimize the user–exoskeleton interaction. This study presents a HITL control for a knee exoskeleton using a CMA-ES algorithm to minimize the users’ physical effort, a parameter innovatively evaluated using the interaction torque with the exoskeleton (a muscular effort indicator) and metabolic cost. This work innovates by estimating the user’s metabolic cost within the HITL control through a machine-learning model. The regression model estimated the metabolic cost, in real time, with a root mean squared error of 0.66 W/kg and mean absolute percentage error of 26% (n = 5), making faster (10 s) and less noisy estimations than a respirometer (K5, Cosmed). The HITL reduced the user’s metabolic cost by 7.3% and 5.9% compared to the zero-torque and no-device conditions, respectively, and reduced the interaction torque by 32.3% compared to a zero-torque control (n = 1). The developed HITL control surpassed a non-exoskeleton and zero-torque condition regarding the user’s physical effort, even for a task such as slow walking. Furthermore, the user-specific control had a lower metabolic cost than the non-user-specific assistance. This proof-of-concept demonstrated the potential of HITL controls in assisted walking. Full article

The non-transparency of artificial intelligence (AI) systems, particularly in deep learning (DL), poses significant challenges to their comprehensibility and trustworthiness. This study aims to enhance the explainability of DL models through visual analytics (VA) and human-in-the-loop (HITL) principles, making these systems more transparent and understandable to end users. In this work, we propose a novel approach that utilizes a transition matrix to interpret results from DL models through more comprehensible machine learning (ML) models. The methodology involves constructing a transition matrix between the feature spaces of DL and ML models as formal and mental models, respectively, improving the explainability for classification tasks. We validated our approach with computational experiments on the MNIST, FNC-1, and Iris datasets using a qualitative and quantitative comparison criterion, that is, how different the results obtained by our approach are from the ground truth of the training and testing samples. The proposed approach significantly enhanced model clarity and understanding in the MNIST dataset, with SSIM and PSNR values of 0.697 and 17.94, respectively, showcasing high-fidelity reconstructions. Moreover, achieving an F₁m score of 77.76% and a weighted accuracy of 89.38%, our approach proved its effectiveness in stance detection with the FNC-1 dataset, complemented by its ability to explain key textual nuances. For the Iris dataset, the separating hyperplane constructed based on the proposed approach allowed for enhancing classification accuracy. Overall, using VA, HITL principles, and a transition matrix, our approach significantly improves the explainability of DL models without compromising their performance, marking a step forward in developing more transparent and trustworthy AI systems. Full article

The Human-in-the-Loop (HITL) system was first proposed by Robert Monarch, a machine learning expert. It adopted a “hybrid” strategy combining human intelligence and machine intelligence, aiming to improve the accuracy of machine learning models and assist human learning. At present, there have been a number ethical design attempts based on the HITL system, and some progress has been made in the ethical choices of disaster rescue robots and nursing robots. However, there is no analysis of why the HITL system can serve as an effective path in constructing ethical AI and how it can implement the efficiency of AI in ethical scenarios. This paper draws on the feasibility of the HITL system and analyzes how ethical AIs are possible when using the HITL system. We advocate for its application to the entire process of ethical AI design. Full article