Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Moacyr Machado Cardoso Junior has a total of 95 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Enhancing agricultural aviation safety analysis: a knowledge graph and ontology-based approach to systemic accident pattern detection

    by Francisco de Assis da Silva Junior, Guido Carim Junior, Moacyr Machado Cardoso Junior

    Brazilian agricultural aviation combines one of the world’s largest fleets with a rising accident rate, yet existing safety analyses remain predominantly descriptive and single-event in scope. This paper proposes and demonstrates a knowledge graph and ontology-based framework for the systemic investigation of agricultural aviation accidents, using final investigation reports published by the Brazilian Centre for Investigation and Prevention of Aeronautical Accidents (CENIPA) between 2017 and 2024. A domain ontology formalised in OWL 2 (Web Ontology Language) and aligned with the ICAO ADREP taxonomy and the Human–Aircraft–Environment–Management (HAEM) framework was instantiated as a Neo4j property graph over 16 final reports, yielding 67 weighted event–factor relationships across 20 causal factors. Weighted degree, betweenness and closeness centrality, Louvain community detection, and semantic inference rules were applied to identify systemic patterns invisible to retrospective single-event analysis. Community detection converged at modularity Q = 0.207, producing three risk clusters—Powerplant Failure Syndrome, Organisational Deficiency Cascade, and Low-Altitude Control Loss—confirmed by independent qualitative content analysis. Betweenness centrality confirmed that latent conditions—maintenance deficiency and supervisory failure—function as causal bridges, outranking all active failures and validating Reason’s accident causation model at the network level. The network-derived priority order redirects regulatory focus from pilot-centred interventions towards upstream maintenance oversight and operational supervision adequacy. The study delivers the first machine-readable ontology for Brazilian agricultural aviation accident causation and a replicable graph-based analytical pipeline extensible to other specialised aviation segments.

  • Open Access

    Organizational Pressure and Pilot Decision-Making in Adverse Weather: A Naturalistic Decision-Making Analysis of Helicopter Accidents

    by Douglas Estevam Casale, Rafaela Campos da Silva, Dante Ricardo Ambrosio, Mirian Kelly Miranda Drago, Moacyr Machado Cardoso Júnior, Luís Eduardo Vergueiro Loures da Costa

    This paper aims to analyze helicopter accidents occurring in meteorological scenarios where flights should have been avoided, identifying patterns that influence pilots’ misjudgments. This work uses two analytical frameworks: the Human Factors Analysis and Classification System (HFACS) and bow tie diagrams, applied to four selected helicopter accident cases. The HFACS model systematically categorizes failures at four hierarchical levels (organizational influences, unsafe supervision, preconditions for unsafe acts, and unsafe acts), whereas bow tie diagrams visually map threats, preventive barriers, the critical top event, and mitigation barriers related to the accidents. The results consistently revealed organizational and self-imposed pressures influencing the decision-making of pilots to proceed under unsafe weather conditions, but these decisions were also shaped by additional factors, such as inadequate training, insufficient operational oversight, fatigue, poor risk perception, spatial disorientation, and misuse of onboard instruments, such as the meteorological radar. The bow tie diagrams highlighted latent conditions, the inadequacy or absence of safety barriers, and the critical short timeframe available for mitigating actions once control was lost. The study concludes that enhancing organizational oversight, structured training, and proper understanding of avionic systems, particularly weather radar capabilities and limitations, are important to preventing similar accidents in the future.

  • Open Access

    A Method for Eliciting Safety Requirements for Military Unmanned Aircraft Systems Related to Critical Scenarios

    by Douglas Estevam Casale, Rafaela Campos da Silva, José Tupinambá Lopes Viana Júnior, Moacyr Machado Cardoso Junior, Luís Eduardo Vergueiro Loures da Costa

    The expansion of unmanned aircraft systems (UAS) usage has highlighted the need for robust safety mechanisms to mitigate operational risks in critical scenarios. In this context, it is envisioned that the potential of the critical decision method (CDM), a semi-structured interview technique that utilizes non-routine incidents to capture the decision-making processes employed in these situations and explore how different actions might have influenced the outcome, can be used to elicit knowledge that will contribute to safe UAS operation. However, there is a gap in the literature concerning the proposals and guidance for utilizing CDM in the systems development requirements elicitation process. This study aims to address this gap by applying CDM combined with model-based systems engineering to systematically elicit the safety requirements for UAS in critical operational scenarios. The methodology involves stakeholder interviews, scenario analysis, and requirements elicitation that reflect both operational insights and situational hazards. Sixty-eight safety requirements were identified for the UA and 51 for their ground control stations, providing a comprehensive framework for enhancing safety. The study concludes that CDM is an effective tool for eliciting requirements, offering significant contributions to the early design phases of UAS projects and supporting the development of safer and more resilient systems.


  • Open Access

    Uma proposta de abordagem curricular da prospecção tecnológica nas escolas de formação militar

    by Breno Ricardo de Araújo Leite, Francisco Cristovão Lourenço de Melo, Moacyr Machado Cardoso Júnior

    This study aimed to analyze the relevance of and propose approaches for integrating technological foresight into the curricula of the Brazilian Air Force Command's training schools. The goal was to empower future officers to confront and lead the challenges posed by the rapid evolution of technology in air power. The methodology employed involved a bibliographic review using databases such as Scielo and Web of Science, complemented by a document analysis of materials from the Ministry of Defense and the Air Force Command. The findings indicated that air power is a vital strategic component for the country's geopolitics and defense, intrinsically linked to technological advancement. It also revealed that the increasing complexity and speed of technological evolution in modern conflicts present a significant challenge for the defense sector, leading to uncertain future scenarios. In this context, technological foresight emerged as a crucial and strategic tool to be incorporated into the curricula of the Air Force Command's schools. The proposed curriculum modification aims to foster a proactive and strategic perspective in future officers, enabling them to identify technological trends and innovations that will define the future of air power. This initiative will prepare them to anticipate and lead, ensuring that they not only master current technologies but also actively participate in building Brazil's aerospace future. Such preparation is fundamental to ensuring national sovereignty and the deterrence capability of the Air Force Command in a constantly changing global landscape

  • Open Access

    Cognition and Computation in Decision-Making

    by Giovane De Morais, Ingrid Kawani Leandro Strohm, Moacyr Machado Cardoso Júnior, Guilherme Vieira Da Rocha, Nickolas Batista Mendonça Machado, Guilherme Micheli Bedini Moreira, Emilia Villani

    This paper examining how local Large Language Models (LLMs) can partially automate the Critical Decision Method (CDM) in aviation safety investigations. The CDM, while widely respected for its ability to elucidate human factors and decision-making processes in rare or complex scenarios, often requires labor-intensive qualitative coding. To address this challenge, we developed a pipeline employing two specialised models: \emph{Phi-3-Mini-Instruct} for generating structured responses and \emph{Zephyr-7B-Beta} as a “judge” to evaluate confidence, completeness, and groundedness. A single anonymised incident served as our pilot case. Seventy-two participants (36 aviation professionals (pilots) and 36 novices) responded to a 53-item CDM-inspired questionnaire, creating a human reference dataset. The pipeline’s performance was benchmarked against both this human data and a classical NLP baseline (TF-IDF + SVM). Results revealed that the LLM matched 78\% of the majority-human multiple-choice answers and achieved a mean absolute error (MAE) of 0.38 on Likert-scale questions. Its open-ended responses, although moderately accurate, occasionally exhibited factual hallucinations (e.g.\ referencing non-existent systems) and role misattributions. Further stratification showed that the LLM outperformed novices but did not match pilots’ domain expertise, underscoring the importance of operational familiarity for nuanced decision analyses. Despite the single-incident scope limiting statistical generalisation, these findings suggest that LLM-based tools can substantially expedite repetitive data processing and facilitate consistent categorisation tasks that often consume investigators’ bandwidth. Future work will expand to multiple incidents, integrate flight data recorder (FDR) and cockpit voice recorder (CVR) information to reduce speculation, and refine both self-evaluation mechanisms and ethical safeguards.

  • Open Access

    Improving Decision-Making of Civilian and Military Pilots Under Pressure

    by Giovane De Morais, Carolina Leão Giollo, Moacyr Machado Cardoso Júnior, Emilia Villani

    The expansion of Artificial Intelligence (AI), especially Large Language Models (LLMs), into safety-critical fields such as aviation raises fundamental questions about alignment with human expertise under risk. This study presents a controlled comparison of decision-making behaviour across professional pilots, lay participants and a LLM, each exposed to six hypothetical scenarios of Prospect Theory dilemmas and operational emergencies. A structured questionnaire measured risk preference, ethical reasoning, and context sensitivity; group differences were analysed using standard statistical methods. Results show that, in loss- and gain-framed dilemmas, both humans and the LLM display cognitive biases consistent with Prospect Theory. However, this mimicry fails to generalise: in operational risk scenarios, pilots consistently select the safest response, reflecting internalised safety culture and rapid pattern recognition. Lay participants show intermediate, more variable behaviour. By contrast, the LLM persistently selects risk-seeking, utilitarian strategies in operational domains, irrespective of prompt or training. The ethical dilemma scenario exposes further divergence: while nearly all humans act according to a deontological duty of care, prioritising those under their protection, the LLM favours maximising outcomes even when this increases risk for all. These findings show that current LLMs, despite surface-level alignment in abstract tasks, lack the tacit, context-dependent, and ethical knowledge needed for trustworthy deployment in safety-critical domains. Effective AI integration requires multi-layered alignment, expert feedback, explicit ethical constraints, and ongoing validation against expert practice. These results underscore the need for domain-specific alignment before adopting AI in aviation and related fields.

  • Open Access

    Improving Decision-Making of Civilian and Military Pilots Under Pressure

    by Giovane De Morais, Carolina Leão Giollo, Moacyr Machado Cardoso Júnior, Emilia Villani

    The expansion of Artificial Intelligence (AI), especially Large Language Models (LLMs), into safety-critical fields such as aviation raises fundamental questions about alignment with human expertise under risk. This study presents a controlled comparison of decision-making behaviour across professional pilots, lay participants and a LLM, each exposed to six hypothetical scenarios of Prospect Theory dilemmas and operational emergencies. A structured questionnaire measured risk preference, ethical reasoning, and context sensitivity; group differences were analysed using standard statistical methods. Results show that, in loss- and gain-framed dilemmas, both humans and the LLM display cognitive biases consistent with Prospect Theory. However, this mimicry fails to generalise: in operational risk scenarios, pilots consistently select the safest response, reflecting internalised safety culture and rapid pattern recognition. Lay participants show intermediate, more variable behaviour. By contrast, the LLM persistently selects risk-seeking, utilitarian strategies in operational domains, irrespective of prompt or training. The ethical dilemma scenario exposes further divergence: while nearly all humans act according to a deontological duty of care, prioritising those under their protection, the LLM favours maximising outcomes even when this increases risk for all. These findings show that current LLMs, despite surface-level alignment in abstract tasks, lack the tacit, context-dependent, and ethical knowledge needed for trustworthy deployment in safety-critical domains. Effective AI integration requires multi-layered alignment, expert feedback, explicit ethical constraints, and ongoing validation against expert practice. These results underscore the need for domain-specific alignment before adopting AI in aviation and related fields.

  • Open Access

    Cognition and Computation in Decision-Making

    by Giovane De Morais, Ingrid Kawani Leandro Strohm, Moacyr Machado Cardoso Júnior, Guilherme Vieira Da Rocha, Nickolas Batista Mendonça Machado, Guilherme Micheli Bedini Moreira, Emilia Villani

    This paper examining how local Large Language Models (LLMs) can partially automate the Critical Decision Method (CDM) in aviation safety investigations. The CDM, while widely respected for its ability to elucidate human factors and decision-making processes in rare or complex scenarios, often requires labor-intensive qualitative coding. To address this challenge, we developed a pipeline employing two specialised models: \emph{Phi-3-Mini-Instruct} for generating structured responses and \emph{Zephyr-7B-Beta} as a “judge” to evaluate confidence, completeness, and groundedness. A single anonymised incident served as our pilot case. Seventy-two participants (36 aviation professionals (pilots) and 36 novices) responded to a 53-item CDM-inspired questionnaire, creating a human reference dataset. The pipeline’s performance was benchmarked against both this human data and a classical NLP baseline (TF-IDF + SVM). Results revealed that the LLM matched 78\% of the majority-human multiple-choice answers and achieved a mean absolute error (MAE) of 0.38 on Likert-scale questions. Its open-ended responses, although moderately accurate, occasionally exhibited factual hallucinations (e.g.\ referencing non-existent systems) and role misattributions. Further stratification showed that the LLM outperformed novices but did not match pilots’ domain expertise, underscoring the importance of operational familiarity for nuanced decision analyses. Despite the single-incident scope limiting statistical generalisation, these findings suggest that LLM-based tools can substantially expedite repetitive data processing and facilitate consistent categorisation tasks that often consume investigators’ bandwidth. Future work will expand to multiple incidents, integrate flight data recorder (FDR) and cockpit voice recorder (CVR) information to reduce speculation, and refine both self-evaluation mechanisms and ethical safeguards.

  • Virtual Reality for the Human-Centred Design of Assistive Devices

    by Ivan de Souza Rehder, Moacyr Cardoso Machado Junior, Edmar Thomaz da Silva, Emilia Villani

  • A Framework Proposal for Augmented Reality Considering Human Errors in Sequential Tasks

    by Cardoso Júnior, Moacyr Machado, Henrique Costa Marques, de Lima, Marcos Vaz