Search Results (38)

Multi-source environmental data are increasingly used for measurement, reporting and verification, and for coordinating low-carbon innovation across interorganizational networks. However, voluntary data sharing remains limited because participants face asymmetric costs, leakage and compliance risks, and uncertainty in value capture. This study develops a network evolutionary game model to examine how cooperative data sharing emerges and stabilizes in green innovation networks. We specify a two-strategy game in which heterogeneous agents choose between sharing and withholding. The payoff structure integrates private innovation gains from their own data, cross-partner synergy, external incentives, fixed governance costs, and stock-scaled sharing and risk burdens. Agents interact on a Barabási–Albert scale-free network and update strategies via local imitation under a Fermi rule. Simulations show that cooperation can diffuse from low initial participation and converge to a high-sharing regime when benefit allocation and incentive intensity jointly offset cost and risk frictions. Several governance levers exhibit threshold-type effects, including the allocation share, the opportunity loss of non-sharing, and the marginal cost–risk burden. Multi-source synergy and subsidies further raise the attainable cooperation level, but with diminishing marginal returns. Degree heterogeneity accelerates diffusion once hub organizations adopt sharing, while also raising fairness concerns when benefits concentrate on central nodes. Overall, the findings provide green-innovation-specific governance conditions that translate threshold regions into implementable design targets for sustainable environmental data sharing. Full article

Nearest-neighbor classifiers are accurate and easy to deploy, but their memory footprint and inference time grow with the size of the reference set. This paper studies an evolutionary prototype selection strategy for k-nearest neighbor (K-NN) classification aimed at extreme, class-balancedreduction. A compact genetic algorithm (GA) evolves a fixed number of prototype indices per class drawn from a disjoint design partition; the selected prototypes are then used by a 1-NN classifier, with fitness defined as the number of correctly classified test instances. To address concerns about generality and baseline strength, we evaluate an experimental suite including synthetic 2D Gaussians ($\sigma =0.5$ and $\sigma =1.0$) and a 3D three-moons geometry, as well as public benchmarks spanning binary and multi-class settings and higher-dimensional data (Breast Cancer Wisconsin, Wine, Reduced MNIST/Digits 8 × 8, Forest CoverType with seven classes, and a 10D five-class spiral benchmark). We compare against K-NN baselines with $k\in \{1,3,5,7\}$ using all design samples, and include GA operator ablations (GA1/GA2/GA3). Each scenario is repeated over 30 independent runs, reporting mean ± std, min/max, per-run distributions, win/tie/loss counts, and non-parametric significance tests (paired Wilcoxon with Holm correction; Friedman where applicable). Across datasets, the GA-selected prototype banks—often orders of magnitude smaller than the full design set—match or improve accuracy, with frequent statistically supported wins against strong K-NN baselines, and in the hardest cases provide substantial compression with no loss relative to the best baseline. These results establish a reproducible baseline for extreme, class-balanced prototype reduction suitable for memory- and latency-constrained deployments and for fair comparison against more elaborate prototype selection methods. Full article

Asymmetries in data distributions and performance across subgroups can induce systematic unfairness in real-world systems. A variety of previous studies have significantly ameliorated the fairness of deep learning models; however, most of them necessarily require additional labels for sensitive attributes, (i.e., ethnicity and gender). Since sensitive attributes often correspond to personal information, collecting such labels can be restricted and may raise privacy concerns. Although recent work has sought to address these issues by training a model without sensitive attribute labels, we point out that it has limitations, as it assumes specific characteristics of sensitive attributes and is validated in simplistic, constrained environments. Therefore, we propose an Unsupervised Fairness-aware Framework (UFF) that trains a fair classification model without pre-defining the characteristics of the sensitive attributes. It includes branches that capture various types of biases and eliminates them through adversarial training. In various scenarios on benchmark datasets, (i.e., CelebA and UTK Face) for facial attribute classification, the proposed method significantly enhances fairness without assuming specific characteristics of sensitive attributes. Moreover, we introduce g-FAT, which is a new metric to measure generalized trade-off performances between classification accuracy and fairness. For example, on CelebA, ours reduces EO from 11.8 to 7.6 for malignant bias and from 15.6 to 9.6 for benign bias, while improving g-FAT from 80.7 to 84.9 and from 79.0 to 85.2, respectively. In terms of g-FAT, our method achieves the highest trade-off performance among the compared methods on the benchmarks. Full article

Stress is a pervasive global health concern that adversely contributes to morbidity and reduced productivity, yet it often remains unquantified due to its subjective and variant presentation. Although artificial intelligence offers an encouraging path toward automated monitoring of mental states, current state-of-the-art approaches are challenged by the reliance on single-source data, sparsity of labeled samples, and significant class imbalance. This paper proposes NeuroStrainSense, a novel deep multimodal stress detection model that integrates three complementary datasets—WESAD, SWELL-KW, and TILES—through a Transformer-based feature fusion architecture combined with a Variational Autoencoder for generative data augmentation. The Transformer architecture employs four encoder layers with eight multi-head attention heads and a hidden dimension of 512 to capture complex inter-modal dependencies across physiological, audio, and behavioral modalities. Our experiments demonstrate that NeuroStrainSense achieves a state-of-the-art performance with accuracies of 87.1%, 88.5%, and 89.8% on the respective datasets, with F1-scores exceeding 0.85 and AUCs greater than 0.89, representing improvements of 2.6–6.6 percentage points over existing baselines. We propose a robust evaluation framework that quantifies discrimination among stress types through clustering validity metrics, achieving a Silhouette Score of 0.75 and Intraclass Correlation Coefficient of 0.76. Comprehensive ablation experiments confirm the utility of each modality and the VAE augmentation module, with physiological features contributing most significantly (average performance decrease of 5.8% when removed), followed by audio (2.8%) and behavioral features (2.1%). Statistical validation confirms all findings at the p < 0.01 significance level. Beyond binary classification, the model identifies five clinically relevant stress profiles—Cognitive Overload, Burnout, Acute Stress, Psychosomatic, and Low-Grade Chronic—with an expert concordance of Cohen’s κ = 0.71 (p < 0.001), demonstrating the strong ecological validity for personalized well-being and occupational health applications. External validation on the MIT Reality Mining dataset confirms the generalizability with minimal performance degradation (accuracy: 0.785, F1-score: 0.752, AUC: 0.849). This work underlines the potential of integrated multimodal learning and demographically aware generative AI for continuous, precise, and fair stress monitoring across diverse populations and environmental contexts. Full article

The increasing use of artificial intelligence (AI) in athlete health monitoring and injury prediction presents both technological opportunities and complex ethical challenges. This narrative review critically examines 24 empirical and conceptual studies focused on AI-driven injury forecasting systems across diverse sports disciplines, including professional, collegiate, youth, and Paralympic contexts. Applying an IMRAD framework, the analysis identifies five dominant ethical concerns: privacy and data protection, algorithmic fairness, informed consent, athlete autonomy, and long-term data governance. While studies commonly report the effectiveness of AI models—such as those employing decision trees, neural networks, and explainability tools like SHAP and HiPrCAM—few offers robust ethical safeguards or athlete-centered governance structures. Power asymmetries persist between athletes and institutions, with limited recognition of data ownership, transparency, and the right to contest predictive outputs. The findings highlight that ethical risks vary by sport type and competitive level, underscoring the need for sport-specific frameworks. Recommendations include establishing enforceable data rights, participatory oversight mechanisms, and regulatory protections to ensure that AI systems align with principles of fairness, transparency, and athlete agency. Without such frameworks, the integration of AI in sports medicine risks reinforcing structural inequalities and undermining the autonomy of those it intends to support. Full article

This article explores how natural wood materials—especially untreated or minimally treated timber—are perceived and experienced during tourist experiences in recreational and tourism-oriented built environments. Drawing on principles of biophilic design and cultural theories of authenticity, the study examines both the psychological and the physiological impacts of wood surfaces on users. One of the objectives of this study is to strengthen the theoretical background and to explore the connections between tourists’ experiences and the material environment. Two pilot studies were conducted: a questionnaire administered to visitors of a national design fair (n = 37) and a physiological experiment measuring user responses to three material types (solid oak, chipboard, and white laminate). The results indicate that natural wood evokes significantly more positive emotional responses and is strongly associated with authenticity, sustainability, and comfort, although concerns about hygiene and surface aging persist. A SWOT analysis is used to summarize the strategic opportunities and risks associated with wood in tourism design. The findings support the inclusion of natural wood as a multisensory design element that enhances atmosphere, emotional engagement, and perceived environmental quality—especially when surface maintenance and cultural framing are appropriately addressed. Full article

This initial exploratory study examined the perceptions of teachers and school leaders in the Republic of Ireland regarding diversity in promotions to school principalship, framed by Equity Theory, Organisational Justice Theory, and Legitimacy Theory. A mixed-methods approach was utilised within this study. Data was collected from 123 participants via an online survey comprising Likert-type statements and open-ended questions. This data was analysed using descriptive statistics and quantitative analysis for the Likert-type statements and thematic analysis was used to examine the qualitative responses, allowing for the identification of recurring patterns and themes to complement the quantitative findings. Findings indicated disparities between perceived and desired prioritisation of diversity, alongside varied perceptions of its impact on school performance and leadership. Disability, social class, and religious diversity were perceived as the least prioritised in promotion practices, while gender and cultural diversity received greater support and were more frequently linked to positive leadership outcomes. Participants reported mixed perceptions across diversity dimensions, with gender, age, and cultural diversity associated with the most positive impacts. Concerns about tokenism and the perceived undermining of merit-based promotion were widespread, reflecting the importance of fairness, transparency, and alignment with stakeholder expectations. The study underscored the need for promotion processes that are both equitable and credible, and for organisational cultures that enable diverse leaders to thrive. These findings provided a foundation for further research and policy development to foster inclusive and representative school leadership in Ireland. Full article

As organizations increasingly turn to machine learning for customer segmentation and targeted marketing, concerns about fairness and algorithmic bias have become more urgent. This study presents a comprehensive fairness audit and mitigation framework for predictive marketing models using the Bank Marketing dataset. We train logistic regression and random forest classifiers to predict customer subscription behavior and evaluate their performance across key demographic groups, including age, education, and job type. Using model explainability techniques such as SHAP and fairness metrics including disparate impact and true positive rate parity, we uncover notable disparities in model behavior that could result in discriminatory targeting. We implement three mitigation strategies—reweighing, threshold adjustment, and feature exclusion—and assess their effectiveness in improving fairness while preserving business-relevant performance metrics. Among these, reweighing produced the most balanced outcome, raising the Disparate Impact Ratio for older individuals from 0.65 to 0.82 and reducing the true positive rate parity gap by over 40%, with only a modest decline in precision (from 0.78 to 0.76). We propose a replicable workflow for embedding fairness auditing into enterprise BI systems and highlight the strategic importance of ethical AI practices in building accountable and inclusive marketing technologies. technologies. Full article

Background and Objectives: Type 2 diabetes mellitus (T2DM) remains a significant public health problem across Gulf Cooperation Council (GCC) nations because of advancements in urbanization alongside behavioural lifestyle changes and genetic predispositions. Specific self-management methods are fundamental in T2DM management because they provide better glycaemic control and decrease complications. Achieving a synthesis of updated evidence about self-management strategies and patient perception within GCC nations represents the primary objective of this narrative review. Materials and Methods: The studies included in the present review were retrieved from the Web of Science, Scopus, Medline, Saudi Digital Library, and Embase. We included peer-reviewed studies that were published from January 2020 to March 2025. The selected studies measured the self-management practices of adult T2DM patients by examining medication adherence, dietary patterns, blood glucose monitoring, and treatment barriers. Results: Research data indicate that patients demonstrate different levels of self-care management behaviours, where medication compliance is fair, but dietary patterns and physical activities remain areas of concern. High levels of knowledge deficits, cultural elements, and economic background substantially impact patients’ self-management practices. Patients indicate their need for enhanced and personalized care, better connections with healthcare providers, and interventions that consider their cultural backgrounds. Conclusions: Patients throughout the GCC region encounter ongoing difficulties that prevent them from performing their best at self-management, even though advanced healthcare facilities exist in this region. Therefore, it is critical to develop culturally sensitive patient-centered care, individualized educational programs, and adopt supportive digital solutions to enhance diabetes-related self-care management. Full article

Background/Objectives: The increasing incidence rates of keratinocyte carcinoma (KC), particularly in fair-skinned populations, call for efforts to intensify health education of the general population in addressing this prevalent skin cancer type. As a preparatory step, this systematic review summarizes the published research on the knowledge and risk perception regarding KC among individuals without medical training. Methods: The review was registered in PROSPERO (CRD42024618851) and adheres to PRISMA guidelines. The databases PubMed, Scopus, Web of Science, PsycArticles, and PsycINFO were searched on 30 July 2024. Studies were eligible if knowledge and/or risk perception was assessed in lay people. Risk of bias (ROB) was assessed with the Joanna Briggs Institute checklist for prevalence studies. Comparable outcomes (e.g., awareness of terms for KC) were meta-analyzed. Results: Included reports (n = 17) were published between 1991 and 2024 with 16,728 individuals assessed. Awareness for the most common type of KC, basal cell carcinoma (BCC), was low (20.75% of respondents (95% confidence interval (CI): 15.24–27.61)), while more respondents were familiar with colloquial terms (60.9–72.8%). Meta-analysis indicated an underestimation of the frequency of KC, with only 7.21% (CI: 4.03–12.58) identifying BCC as the most common type of skin cancer. Furthermore, concern about developing KC as assessed in only two overlapping studies was reported by only 25–30% of respondents, indicating a significant gap in risk awareness and a lack of research on risk perception regarding KC. Conclusions: This review highlights the need for targeted health education interventions to improve knowledge and preventive behaviors regarding KC. Given the limitations of the included studies, characterized by high ROB, heterogeneity of results, and a lack of standardized assessment tools, further research is essential to enhance the understanding and awareness of KC in diverse populations. Full article

The prevalence of artificial intelligence (AI) increases social concern surrounding unethical consumer behavior in human–AI interaction. Existing research has mainly focused on anthropomorphic characteristics of AI and unethical consumer behavior (UCB). However, the role of algorithms in unethical consumer behavior, which is central to AI, is not yet fully understood. Drawing on social exchange theory, this study investigates the impact of algorithmic discrimination on UCB and explores the interrelationships and underlying mechanisms. Through three experiments, this study found that experiencing algorithmic discrimination significantly increases UCB, with anticipatory guilt mediating this relationship. Moreover, consumers’ negative reciprocity beliefs moderated the effects of algorithmic discrimination on anticipatory guilt and UCB. In addition, this study distinguish between active and passive UCB based on their underlying ethical motivations. This enhances the study’s universality by assessing both types of behaviors and highlighting their differences. These insights extend current research on UCB within the purview of AI agents and provide valuable insights into effectively mitigating losses caused by UCB behaviors, offering improved directions for facilitating AI agents to provide fair, reliable, and efficient interactions for both businesses and consumers. Full article

Federated learning (FL) enables deep learning models to be trained locally on devices without the need for data sharing, ensuring data privacy. However, when clients have uneven or imbalanced data distributions, it leads to data heterogeneity. Data heterogeneity can appear in different ways, often due to variations in label, data distributions, feature variations, and structural inconsistencies in the images. This can significantly impact FL performance, as the global model often struggles to achieve optimal convergence. To enhance training efficiency and model performance, a common strategy in FL is to exclude clients with limited data. However, excluding such clients can raise fairness concerns, particularly for smaller populations. To understand the influence of data heterogeneity, a self-evaluating federated learning framework for heterogeneity, Fed-Hetero, was designed to assess the type of heterogeneity associated with the clients and provide recommendations to clients to enhance the global model’s accuracy. Fed-Hetero thus enables the clients with limited data to participate in FL processes by adopting appropriate strategies that enhance model accuracy. The results show that Fed-Hetero identifies the client with heterogeneity and provides personalized recommendations. Full article

Machine learning is regarded as an effective approach in network intrusion detection, and has gained significant attention in recent studies. However, few intrusion detection methods have been successfully applied to detect anomalies in large-scale network traffic data, and low explainability of the complex algorithms has caused concerns about fairness and accountability. A further problem is that many intrusion detection systems need to work with distributed data sources in the cloud. In this paper, we propose an intrusion detection method based on distributed computing to learn the latent representations from large-scale network data with lower computation time while improving the intrusion detection accuracy. Our proposed classifier, based on a novel hierarchical algorithm combining adaptability and visualization ability from a self-structured unsupervised learning algorithm and achieving explainability from self-explainable supervised algorithms, is able to enhance the understanding of the model and data. The experimental results show that our proposed method is effective, efficient, and scalable in capturing the network traffic patterns and detecting detailed network intrusion information such as type of attack with high detection performance, and is an ideal method to be applied in cloud-computing environments. Full article

This paper studies optimal decisions in an authorized remanufacturing closed-loop supply chain (CLSC) consisting of a manufacturer, a retailer, and an authorized third-party remanufacturer with dual-fairness concerns (distributional fairness concerns and peer-induced fairness concerns). Four Stackelberg game models are developed: (i) the dual-fairness concerns are considered by the retailer (model F); (ii) the retailer does not consider both types of fairness concerns (model N); (iii) the retailer only considers the distributional fairness concerns (model D); (iv) the retailer only considers the peer-induced fairness concerns (model P). We use numerical analysis to examine the equilibrium outcomes under dual-fairness concerns. The results show that: (1) The increase in the coefficient of peer-induced fairness concerns will result in more profit for the manufacturer in most cases, while distributional fairness concerns always hurt the manufacturer; (2) In most parameter cases, the increase in the degree of distributional fairness concerns favors the retailer. The retailer considers only peer-induced fairness concerns when the degree of distributional fairness concerns is low and the degree of peer-induced fairness concerns is relatively high, whereas in other cases, two kinds of fairness concerns are ignored; (3) Model P is the most profitable and model D is most disadvantageous for the third party, however, for the manufacturer it is the opposite; (4) The impact of fairness concerns on the environment depends on the retailer’s attitude towards fairness concerns. Model P is the best for the environment, while model D has the highest environmental impact. This study introduces dual-fairness concerns into the authorized remanufacturing CLSC model and provides theoretical references for authorized remanufacturing and sustainability practices. Full article

Scrap steel serves as the primary alternative raw material to iron ore, exerting a significant impact on production costs for steel enterprises. With the annual growth in scrap resources, concerns regarding traditional manual inspection methods, including issues of fairness and safety, gain increasing prominence. Enhancing scrap inspection processes through digital technology is imperative. In response to these concerns, we developed CNIL-Net, a scrap-quality inspection network model based on object detection, and trained and validated it using images obtained during the scrap inspection process. Initially, we deployed a multi-camera integrated system at a steel plant for acquiring scrap images of diverse types, which were subsequently annotated and employed for constructing an enhanced scrap dataset. Then, we enhanced the YOLOv5 model to improve the detection of small-target scraps in inspection scenarios. This was achieved by adding a small-object detection layer (P2) and streamlining the model through the removal of detection layer P5, resulting in the development of a novel three-layer detection network structure termed the Improved Layer (IL) model. A Coordinate Attention mechanism was incorporated into the network to dynamically learn feature weights from various positions, thereby improving the discernment of scrap features. Substituting the traditional non-maximum suppression algorithm (NMS) with Soft-NMS enhanced detection accuracy in dense and overlapping scrap scenarios, thereby mitigating instances of missed detections. Finally, the model underwent training and validation utilizing the augmented dataset of scraps. Throughout this phase, assessments encompassed metrics like mAP, number of network layers, parameters, and inference duration. Experimental findings illustrate that the developed CNIL-Net scrap-quality inspection network model boosted the average precision across all categories from 88.8% to 96.5%. Compared to manual inspection, it demonstrates notable advantages in accuracy and detection speed, rendering it well suited for real-world deployment and addressing issues in scrap inspection like real-time processing and fairness. Full article