Search Results (115)

The increasing integration of artificial intelligence agents (AIAs) based on large language models (LLMs) is transforming many spheres of society. These agents act as human assistants, forming Distributed Intelligent Systems (DISs) and engaging in opinion formation, consensus-building, and collective decision-making. However, complex DIS network topologies introduce significant uncertainty into these processes. We propose a quantum-inspired graph signal processing framework to model collective behavior in a DIS interacting with an external environment represented by an influence matrix (IM). System topology is captured using scale-free and Watts–Strogatz graphs. Two contrasting interaction regimes are considered. In the first case, the internal structure fully aligns with the external influence, as expressed by the commutativity between the adjacency matrix and the IM. Here, a renormalization-group-based scaling approach reveals minimal reservoir influence, characterized by full phase synchronization and coherent dynamics. In the second case, the IM includes heterogeneous negative (antagonistic) couplings that do not commute with the network, producing partial or complete spectral disorder. This disrupts phase coherence and may fragment opinions, except for the dominant collective (Perron) mode, which remains robust. Spectral entropy quantifies disorder and external influence. The proposed framework offers insights into designing LLM-participated DISs that can maintain coherence under environmental perturbations. Full article

Critical Infrastructures (CIs) are the backbone of modern societies, providing essential services whose disruption can have severe consequences. The interdependencies among the CIs, across sectors and national borders, add significant complexity to risk and resilience management. While various EU Directives and EU-funded projects have addressed CI risk management, most efforts have focused on individual infrastructures rather than systemic cross-sector and cross-border approaches. In the EU-funded project ATLANTIS, we address this gap by advancing CI risk and resilience assessment towards a fully integrated European protection framework. We emphasise a holistic, multi-level approach that transcends individual assets, enabling coordination across operators, sectors, and national borders. To this end, we introduce a comprehensive risk assessment methodology that explicitly accounts for interdependencies among CIs and evaluates potential impacts and probabilities of disruptive events. This methodology is underpinned by the tailored data management framework, structured across three integrated layers. To validate the approach, novel tools and methods were implemented and tested in three large-scale pilot exercises, conducted through a series of stakeholder workshops. Results indicated measurable improvements in CI preparedness and awareness, ranging from approximately 5% to 55%, depending on the threat scenario and stakeholder group. The findings demonstrate that our approach delivers added value by supporting enhanced decision-making and fostering consistent, cross-CI communication through a shared platform. This paper presents the key components, cross-CI and multi-threat risk assessment methodology, and testing outcomes of the ATLANTIS project, highlighting its contribution to advancing European CI resilience. Full article

Achieving consensus in group decision-making often involves overcoming significant challenges, particularly reconciling diverse perspectives and mitigating biases hindering agreement. Traditional methods relying on human facilitators are usually constrained by scalability and efficiency, especially in large-scale, fast-paced discussions. To address these challenges, this study proposes a novel real-time facilitation framework, employing large language models (LLMs) as automated facilitators within a custom-built multi-user chat system. This framework is distinguished by its real-time adaptive system architecture, which enables dynamic adjustments to facilitation strategies based on ongoing discussion dynamics. Leveraging cosine similarity as a core metric, this approach evaluates the ability of three state-of-the-art LLMs—ChatGPT 4.0, Mistral Large 2, and AI21 Jamba-Instruct—to synthesize consensus proposals that align with participants’ viewpoints. Unlike conventional techniques, the system integrates adaptive facilitation strategies, including clarifying misunderstandings, summarizing discussions, and proposing compromises, enabling the LLMs to refine consensus proposals based on user feedback iteratively. Experimental results indicate that ChatGPT 4.0 achieved the highest alignment with participant opinions and required fewer iterations to reach consensus. A one-way ANOVA confirmed that differences in performance between models were statistically significant. Moreover, descriptive analyses revealed nuanced differences in model behavior across various sustainability-focused discussion topics, including climate action, quality education, good health and well-being, and access to clean water and sanitation. These findings highlight the promise of LLM-driven facilitation for improving collective decision-making processes and underscore the need for further research into robust evaluation metrics, ethical considerations, and cross-cultural adaptability. Full article

New energy vehicles (NEVs) have gained increasing favor among NEV consumers due to their dual advantages of “low cost” and “environmental friendliness.” In recent years, the share of NEVs in the global automotive market has been steadily rising. For instance, in the Chinese market, the sales of new energy vehicles in 2024 increased by 35.5% year-on-year, accounting for 70.5% of global NEV sales. However, as the diversity of NEV brands and models expands, selecting the most suitable model from a vast amount of information has become the primary challenge for NEV consumers. Although online service platforms offer extensive user reviews and rating data, the uncertainty, inconsistent quality, and sheer volume of this information pose significant challenges to decision-making for NEV consumers. Against this backdrop, leveraging the strengths of the quasi OWA (QOWA) operator in information aggregation and interval basic uncertain linguistic information (IBULI) information aggregation and two-dimensional information representation of “information + quality”, this study proposes a large-scale group data aggregation method for decision support based on the IBULIQOWA operator. This approach aims to assist consumers of new energy vehicles in making informed decisions from the perspective of information quality. Firstly, the quasi ordered weighted averaging (QOWA) operator on the unit interval is extended to the closed interval $\left[0,\tau \right]$, and the extended basic uncertain information quasi ordered weighted averaging (EBUIQOWA) operator is defined. Secondly, in order to aggregate groups of IBULI, based on the EBUIQOWA operator, the basic uncertain linguistic information QOWA (BULIQOWA) operator and the IBULIQOWA operator are proposed, and the monotonicity and degeneracy of the proposed operators are discussed. Finally, for the problem of product decision making in online service platforms, considering the credibility of information, a product decision-making method based on the IBULIQOWA operator is proposed, and its effectiveness and applicability are verified through a case study of NEV product decision making in a car online service platform, providing a reference for decision support in product ranking of online service platforms. Full article

This study aims to systematically reveal, from the perspective of organizational scale, the differences between large and small architectural design organizations in China in terms of characteristics of production activities, technological capabilities and innovation levels, resource integration capabilities, and client groups, and to quantify the priority order of clients’ attention to architectural design products, thereby providing a reference for industry structure optimization and strategic decision making. This research combines case analysis and comparative study to construct a four-dimensional comparative framework. The results show that large design organizations, leveraging their advantages in technological research and development as well as resource integration, focus on large-scale complex projects, technology-driven projects, cultural landmark projects, and multi-stakeholder collaborative projects, primarily serving government agencies and large enterprises. In contrast, small design organizations excel in flexibility, concentrating on small-scale simple projects, specialized niche projects, localized projects, and short-cycle, low-budget projects, serving individual owners and small businesses. Furthermore, this study adopts the Analytic Hierarchy Process (AHP) to establish an evaluation model. Twenty experts from architectural design organizations, construction organizations, and research institutions were invited to score the survey questionnaires, and quantitative weight analysis was performed. The research findings provide support for the optimization of the industry. Full article

The growing ubiquity of digital platforms has enabled unprecedented participation in large-scale group decision-making processes. Nevertheless, integrating subjective linguistically expressed opinions into structured decision protocols remains a significant challenge. This paper presents a novel framework that leverages the semantic and affective capabilities of large language models to support large-scale group decision-making tasks by extracting and quantifying experts’ communicative traits—specifically clarity and trust—from natural language input. Based on these traits, participants are clustered into behavioural groups, each of which is assigned a representative preference structure and a weight reflecting its internal cohesion and communicative quality. A sentiment-informed consensus mechanism then aggregates these group-level matrices to form a collective decision outcome. The method enhances scalability and interpretability while preserving the richness of human expression. The results suggest that incorporating behavioural dimensions into large-scale group decision-making via large language models fosters fairer, more balanced, and semantically grounded decisions, offering a promising avenue for next-generation decision-support systems. Full article

The HEPscore benchmark, widely used for evaluating computational performance in high-energy physics, has been identified as requiring energy consumption metrics to address the increasing importance of energy efficiency in large-scale computing infrastructures. This study introduces an energy measurement extension for HEPscore, designed to operate across diverse hardware platforms without requiring administrative privileges or physical modifications. The extension utilizes the Running Average Power Limit (RAPL) interface available in modern processors and dynamically selects the most suitable measurement method based on system capabilities. When RAPL access is unavailable, the system automatically switches to alternative measurement approaches. To validate the accuracy of the software-based measurements, external hardware monitoring devices were used to collect reference data directly from the power supply circuit. Obtained results demonstrate a significant correlation across multiple test platforms running standard HEP workloads. The developed extension integrates energy consumption data into standard HEPscore reports, enabling the calculation of energy efficiency metrics such as HEPscore/Watt. This implementation meets the requirements of the HEPiX Benchmarking Working Group, providing a reliable and portable solution for quantifying energy efficiency alongside computational performance. The proposed method supports informed decision making in resource planning and hardware acquisition for HEP computing environments. Full article

Attachment styles, rooted in Bowlby’s Attachment Theory, significantly influence our romantic relationships, workplace behavior, and decision-making processes. Traditional methods like self-report questionnaires often have biases, so we aimed to develop a predictive model using objective physiological data. In our study, participants engaged in the Secretary problem, a sequential decision-making task, while their brain activity was recorded with a 16-electrode EEG device. We transformed this data into coherence graphs and used Node2Vec and PCA to convert these graphs into feature vectors. These vectors were then used to train a machine learning model, XGBoost, to predict attachment styles. Using participant-level nested 5-fold cross-validation, our first model achieved 80% accuracy for Secure and 88% for Fearful-avoidant styles but had difficulty distinguishing between Avoidant and Anxious styles. Analysis of the first three principal components showed these two groups overlapped in coherence space, explaining the confusion. To address this, we created a second model that categorized participants as Secure, Insecure, or Extremely Insecure, improving the overall accuracy to about 92%. Together, the results highlight (i) large-scale EEG connectivity as a viable biomarker of attachment, and (ii) the empirical similarity between Anxious and Avoidant profiles when measured electrophysiologically. This method shows promise in using EEG data and machine learning to understand attachment styles. Our findings suggest that future research should include larger and more diverse samples to refine these models. If validated in multi-site cohorts, such graph-based EEG markers could guide personalised interventions by objectively assessing attachment-related vulnerabilities. This study demonstrates the potential for using EEG data to classify attachment styles, which could have important implications for both research and therapeutic practices. Full article

Accurate short-term weather forecasting plays a vital role in disaster response, agriculture, and energy management, where timely and reliable predictions are essential for decision-making. Graph neural networks (GNNs), known for their ability to model complex spatial structures and relational data, have achieved remarkable success in meteorological forecasting by effectively capturing spatial dependencies among distributed weather stations. However, most existing GNN-based approaches rely on pairwise station connections, limiting their capacity to represent higher-order spatial interactions. Moreover, their dependence on supervised learning makes them vulnerable to spatial heterogeneity and temporal non-stationarity. This paper introduces a novel spatial–temporal pretraining framework, Hypergraph-enhanced Meteorological Pretraining (HyMePre), which combines hypergraph neural networks with self-supervised learning to model high-order spatial dependencies and improve generalization across diverse climate regimes. HyMePre employs a two-stage masking strategy, applying spatial and temporal masking separately, to learn disentangled representations from unlabeled meteorological time series. During forecasting, dynamic hypergraphs group stations based on meteorological similarity, explicitly capturing high-order dependencies. Extensive experiments on large-scale reanalysis datasets show that HyMePre outperforms conventional GNN models in predicting temperature, humidity, and wind speed. The integration of pretraining and hypergraph modeling enhances robustness to noisy data and improves generalization to unseen climate patterns, offering a scalable and effective solution for operational weather forecasting. Full article

The rapid advancement of artificial intelligence is transforming agriculture by enabling data-driven plant disease monitoring and decision support. Soil-borne mosaic wheat virus (SBWMV) is a soil-transmitted virus disease that poses a serious threat to wheat production across multiple ecological zones. Due to the regional variability in environmental conditions and symptom expressions, accurately evaluating the severity of wheat soil-borne mosaic (WSBM) infections remains a persistent challenge. To address this, the problem is formulated as large-scale group decision-making process (LSGDM), where each planting plot is treated as an independent virtual decision maker, providing its own severity assessments. This modeling approach reflects the spatial heterogeneity of the disease and enables a structured mechanism to reconcile divergent evaluations. First, for each site, field observation of infection symptoms are recorded and represented using intuitionistic fuzzy numbers (IFNs) to capture uncertainty in detection. Second, a Bayesian graph convolutional networks model (Bayesian-GCN) is used to construct a spatial trust propagation mechanism, inferring missing trust values and preserving regional dependencies. Third, an enhanced spectral clustering method is employed to group plots with similar symptoms and assessment behaviors. Fourth, a feedback mechanism is introduced to iteratively adjust plot-level evaluations based on a set of defined agricultural decision indicators sets using a multi-granulation rough set (ADISs-MGRS). Once consensus is reached, final rankings of candidate plots are generated from indicators, providing an interpretable and evidence-based foundation for targeted prevention strategies. By using the WSBM dataset collected in 2017–2018 from Walla Walla Valley, Oregon/Washington State border, the United States of America, and performing data augmentation for validation, along with comparative experiments and sensitivity analysis, this study demonstrates that the AI-driven LSGDM model integrating enhanced spectral clustering and ADISs-MGRS feedback mechanisms outperforms traditional models in terms of consensus efficiency and decision robustness. This provides valuable support for multi-party decision making in complex agricultural contexts. Full article

The increasing urgency of the energy transition, particularly in ecologically sensitive regions, demands spatially informed planning tools to guide renewable energy development. This study presents a Multi-Criteria Decision-Making (MCDM) approach to assess the suitability of the Gargano district in southern Italy for the implementation of Renewable Energy Communities. The analysis combines expert-based weighting and the Weighted Linear Combination method to evaluate seven key criteria grouped into environmental, socioeconomic, and technical dimensions. The resulting suitability scores, calculated at the municipal scale, highlight spatial disparities across the district, revealing that areas with the highest potential for Renewable Energy Community (REC) deployment are largely situated at the boundaries of the Gargano National Park. These zones benefit from stronger infrastructure, higher energy demand, and fewer environmental constraints, particularly with regard to wind energy initiatives. Conversely, municipalities within the park exhibit lower suitability, constrained by strict landscape regulations and lower population density. The findings provide valuable insights for regional planners and policymakers, supporting the adoption of targeted, environmentally compatible strategies for the advancement of citizen-led renewable energy initiatives in complex territorial contexts. Full article

With the nationwide completion of China’s large-scale Poverty Alleviation Relocation (PAR) initiative in 2020, the government’s poverty alleviation efforts have officially entered the “post-poverty era”. However, many regions still lack well-established sustainable development mechanisms and face a potential risk of returning to poverty. To better stabilize the achievements of poverty alleviation, this study examines the potential risk of returning to poverty after the first Five-Year Transition Period (2021–2025) from a livelihood space perspective and proposes optimization directions for PAR policies in future poverty reduction efforts. Research findings indicate that simply altering geographical conditions is insufficient to achieve stable poverty alleviation. The production space of relocated populations is vulnerable to the stability and precision in resource supply, which may lead to recurring poverty due to policy discontinuities and administrative preferences. Meanwhile, improvements in living spaces are constrained by imbalances in household income and expenditure. This study also found that, on the one hand, changes in residential patterns break the original boundaries of administrative villages by incorporating migrants from different villages into concentrated communities, leading to the expansion of weak-tie networks while, on the other hand, the relocation process disrupts some of the migrants’ original strong-tie networks, and the concentration and clustering of impoverished groups in relocation communities further lead to the contraction of these networks. Additionally, the unique characteristics of relocation communities generate exorbitant governance costs and population management difficulties that far exceed the service provision and administrative capacities of community organizations. In the long run, this situation proves detrimental to normalized community governance and dynamic poverty relapse monitoring and interventions. Accordingly, this study proposes relevant policy recommendations from the following four aspects, i.e., strengthening endogenous development capacity, improving social security mechanisms, expanding social support networks, and enhancing organizational governance capabilities, aiming to provide both a theoretical basis and a decision-making reference for future poverty alleviation efforts. Full article

The construction industry plays a key role in economic development but continues to face challenges in promoting employee well-being, particularly mental health and social sustainability. While existing decision-making tools emphasize environmental and economic factors, the social dimension remains largely overlooked, creating a significant gap in both research and practice. To address this, the study develops a decision support tool (DST) to help construction organizations prioritize strategic investments that enhance employee social sustainability. The tool is based on a hybrid multi-criteria decision-making framework, combining the Analytical Hierarchy Process (AHP) with Fuzzy MOORA to integrate both quantitative and qualitative assessments. A literature review, along with findings from a previous empirical study, identified 27 validated criteria, grouped into seven core sustainability alternatives. Additionally, five decision criteria (cost, risk, compatibility, return on investment, and difficulty) were refined through expert interviews. The DST was implemented as a modular Excel-based tool allowing users to input data, conduct pairwise comparisons, evaluate alternatives using linguistic scales, and generate a final ranking through defuzzification. A case study in a private construction company showed Training and Development and Work Environment as top priorities. An online expert focus group confirmed the DST’s clarity, usability, and strategic relevance. By addressing the often-neglected social pillar of sustainability, this tool offers a practical and transparent framework to support decision-making, ultimately enhancing employee well-being and organizational performance in the construction sector. Full article

Negative pressure wound therapy (NPWT) is widely recognized for its efficacy in treating diabetic wounds, but the mechanisms involved in the wound healing process remain unclear. By examining changes in blood cytokine levels as molecular signaling precursors, we aim to provide a comprehensive cytokine profile to support adjunctive therapy research and clinical applications. A diabetic mouse wound model was established to compare cytokine profiles between NPWT-treated and standard dressing groups, identifying key signaling candidates that may facilitate wound healing. By integrating normal mouse data with large-scale cytokine analysis, we developed a time-stratified NPWT approach to track acute-phase cytokine fluctuations in diabetic conditions. NPWT did not significantly enhance coagulation-related cytokine expression but effectively reduced inflammation, albeit with a delayed regulatory effect compared to wild-type mice. A one-sided binomial test revealed that NPWT advanced the cytokine expression peak from 16 to 2 h, partially restoring the early healing pattern seen in normal mice and suggesting its potential role in modulating early-stage wound repair. These findings provide novel insights into early cytokine regulation during wound healing and highlight the potential of NPWT to inform therapeutic strategies. This refined monitoring approach may contribute to improved clinical decision-making and support enhanced wound management in diabetic patients. Full article

The Unit Commitment Problem (UCP) is a critical component of power market decision-making and is typically formulated as Mixed Integer Programming (MIP). Given the complexity of solving MIPs, efficiently solving large-scale UCPs remains a significant challenge. This paper presents a hybrid Graph Neural Network (GNN)–Linear Programming (LP) framework to accelerate the solution of large-scale Unit Commitment Problems (UCPs) while maintaining the quality of solutions. By analyzing variable stability through historical branch-and-bound (B&B) trajectories, we classify MIP variables into dynamically adjustable stable and unstable groups. We adopt an MIP formulation that includes multiple types of binary variables—such as commitment, startup, and shutdown variables—and extract additional information from these auxiliary binary variables. This enriched representation provides more candidates for stable variable fixation, helping to improve variable refinement, mitigate suboptimality, and enhance computational efficiency. A bipartite GNN is trained offline to predict stable variables based on system topology and historical operational patterns. During online optimization, instance-specific root LP solutions refine these predictions, enabling adaptive variable fixation via a dual-threshold mechanism that integrates GNN confidence and LP relaxations. To mitigate suboptimality risks, we introduce temporally flexible fixation strategies—hard fixation for variables with persistent stability and soft fixation allowing limited temporal adjustments—alongside a GNN-guided branching rule to prioritize unstable variables. Numerical experiments demonstrate that jointly fixing commitment, startup, and shutdown variables yields better performance compared to fixing only commitment variables. Ablation studies further validate the importance of hard fixation and customized branching strategies, especially for large-scale systems. Full article