NIMS: MagIC - Artigos em revista internacional com arbitragem científica (Peer-Review articles in international journals)
URI permanente para esta coleção:
Navegar
Entradas recentes
- Unification of Closed-Open Industrial Detection ScenariosPublication . Zhang, Zekai; Zhang, Jinglin; Chen, Qinghui; Li, Gang; Chen, Da; Jing, Shuainan; Wang, He; Li, Dagang; Liu, Cong; Bai, Cong; Chen, Shengyong; NOVA Information Management School (NOVA IMS); Information Management Research Center (MagIC) - NOVA Information Management School; IEEE Computer SocietyLarge-scale Visual-Language Models (LVLMs) have achieved remarkable success in natural visual tasks, yet their application to industrial defect detection remains challenging due to two fundamental limitations: (i) the scarcity of large-scale industrial datasets that cover diverse defect categories across multiple domains, and (ii) the reliance on manual prompts (points, boxes, masks) that introduce subjective noise and lack text-visual interaction for fine-grained understanding. To address these challenges, we introduce a Large-Scale Multi-Modal Industrial Open-Closed benchmark (MMIOC-1M) containing over one million samples across 14 super-categories, 29 industrial scenes, and 351 defect subcategories. To our knowledge, MMIOC-1M is the first unified largest benchmark supporting both open-vocabulary and closed-set industrial detection, providing valuable pre-training data for LVLMs in industrial scenarios. Furthermore, we propose a Refined Text-Visual Prompt Network (RTVPNet) that incorporates three key innovations: (1) an expert-assisted domain projection mechanism that enables rapid adaptation of general vision models to industrial domains, (2) an energy-based sparse sampling strategy that automatically generates refined visual prompts without manual intervention, and (3) a bidirectional text-visual interaction module that enhances cross-modal semantic alignment and understanding. Extensive experiments demonstrate that RTVPNet achieves state-of-the-art performance on MMIOC-1M, LVIS, and COCO benchmarks while maintaining computational efficiency. The dataset and code are available at https://github.com/hellozzk/MMIO.
- Entering B2B brands' living roomsPublication . Österle, Benjamin; Sarasvuo, Sonja; Kuhn, Marc; Henseler, Jörg; Information Management Research Center (MagIC) - NOVA Information Management School; Elsevier Science B.V., Amsterdam.Brand worlds are powerful tools for branding and for creating extraordinary customer experiences in B2C markets, and they are increasingly applied in B2B contexts as well. However, the specific characteristics of industrial marketing raise the question of whether brand worlds function similarly in this setting. This study examines how visiting a brand world is related to brand experience and brand equity in industrial marketing. Drawing on data from 218 business visitors, we employed a pretest-posttest quasi-experimental design combined with structural equation modeling. The findings reveal that brand world visits are associated with higher levels of brand experience and brand equity through the multidimensional concept of brand world experience, a higher-order formative construct. Brand world experience mediates the link between pre- and post-visit brand experience, but is not associated with pre-visit brand equity. Post-visit brand equity is related both directly to the brand world experience and indirectly to post-visit brand experience. These findings demonstrate that, when embedded in experiential marketing strategies, brand worlds function as instruments for enhancing brand experience and brand equity in industrial marketing, thereby underscoring their role as the metaphorical “living room of the brand.”
- Asymmetric volatility transmission in cryptocurrency marketsPublication . Santos, Mariana; Iorio, Carmela; Damásio, Bruno; Information Management Research Center (MagIC) - NOVA Information Management School; NOVA Information Management School (NOVA IMS); Elsevier Science B.V., Amsterdam.We examine how risk travels between large-cap and small-cap cryptocurrencies and how major news shocks amplify these linkages. Using daily data for nine large-cap/small-cap pairs from September 2018–March 2023, we combine a multivariate volatility model with an event study of eleven major episodes, including the Terra-Luna collapse. Three results emerge. First, volatility transmission runs mainly from large-cap coins to smaller ones: 7 of 9 high-to-low cross-shock coefficients are statistically significant, versus 3 in the opposite direction. Second, negative events trigger larger abnormal returns and more frequent significant post-event effects than positive events, especially among small-cap coins. Third, conditional correlations rise during stress, pointing to stronger market integration and weaker diversification exactly when it matters most. The implied hedge ratios show that short positions in large-cap coins can partly protect small-cap exposure. As cryptocurrency markets mature, monitoring these transmission channels will remain important for portfolio design and for the regulation of systemic digital-asset risk.
- Online Multi-Task Business Process Prediction Using Dynamic RepresentationPublication . Zhang, Xiwei; Fang, Xianwen; Bao, Wei; Liu, Cong; NOVA Information Management School (NOVA IMS); Information Management Research Center (MagIC) - NOVA Information Management School; Institute of Electrical and Electronics Engineers (IEEE)Existing Predictive Process Monitoring (PPM) methods typically rely on static offline methods, limiting their ability to adapt to dynamic process evolution driven by emerging activities and shifting behavioral patterns. This constraint is particularly critical for multi-task prediction, such as the simultaneous forecasting of the next activity and the remaining process time. To address this challenge, we propose an online multi-task prediction framework based on dynamic graph representations. The framework enables a Graph Neural Network (GNN) to incrementally learn newly emerging activities by leveraging dynamic graph snapshots and an architecture expansion strategy. For efficient online adaptation, the framework incorporates two update strategies, a standard periodic update and a drift-aware adaptive update triggered by the Maximum Mean Discrepancy (MMD2) between subgraph embeddings. Both strategies are integrated with a Prioritized Experience Replay (PER) mechanism, augmented with a rarity-aware bonus, to ensure rapid and robust model adjustments in non-stationary environments. Comprehensive experiments on multiple real-world event logs demonstrate that our framework, when combined with different GNN backbones such as GCN, GAT, and GIN, significantly outperforms state-of-the-art baselines in both next-activity and remaining time prediction. Notably, under concept drift, the proposed drift-aware strategy exhibits strong adaptability, highlighting the framework’s effectiveness and potential for addressing complex online process prediction challenges.
- ATHWPublication . Qiao, Sibo; Liu, Junhao; Guo, Qiang; Liu, Cong; Aldawsari, Hamad; Mumtaz, Shahid; Wang, Min; NOVA Information Management School (NOVA IMS); Information Management Research Center (MagIC) - NOVA Information Management School; IEEE Computer SocietyWith the widespread use of biometric technologies in consumer electronics such as smart locks and wearable devices, securing biometric data transmission across the “home gateway–ISP/Internet–cloud” path has become increasingly important. Existing cross-domain traffic correlation solutions mainly rely on log aggregation or application-layer identifiers, which often suffer from limited timeliness, weak verifiability, and poor scalability. To address these issues, this paper proposes ATHW, an active threat-hunting network flow watermarking method for cross-domain consumer electronics, which aims to establish verifiable associations between gateway events and cloud-side traffic. ATHW employs a hybrid embedding framework that combines sequence-based synchronization and centroid-based modulation. To improve synchronization stability under network jitter and packet loss, a dual-layer synchronization mechanism with threshold-based redundant decisions is introduced. Meanwhile, a controllable time-slot centroid modulation strategy combined with lightweight redundancy coding is applied to reduce sensitivity to per-packet delay variations and improve watermark recovery reliability. Experimental results show that ATHW maintains high extraction accuracy under packet loss and delay perturbations while preserving favorable robustness and invisibility.
- The Embodiment of VulnerabilityPublication . Girão Carrilho, Mariana; Pinto, Diego Costa; Shuqair, Saleh; Maurer Herter, Márcia; Mattila, Anna S.; Information Management Research Center (MagIC) - NOVA Information Management School; NOVA Information Management School (NOVA IMS); WileyEmpathy is central to healthcare, yet its role is evolving as artificial intelligence increasingly delivers forms of care traditionally provided by humans. Drawing on Embodiment Theory and Mind–Body Dualism, this research introduces the concept of the embodiment of vulnerability—the extent to which vulnerability is anchored in the body (embodied) or in the mind (disembodied). We propose that perceptions of empathy for AI care depend on the match between the type of vulnerability and the agent's mode of understanding. When vulnerability is embodied, as in physical pain or discomfort, humans are perceived as more empathetic because empathy judgments are grounded in affective resonance and embodied cues. However, when vulnerability is disembodied, as in mental health contexts characterized by psychological and emotional distress, AI agents achieve comparable perceived empathy because judgments are grounded in linguistic and informational inference. Across three studies, two controlled experiments, and a text mining of health app reviews, we document a vulnerability-contingent dilemma in empathy judgments: humans are favored under embodied vulnerability, whereas AI agents match human providers under disembodied vulnerability. These findings contribute to the literature by showing that the embodiment of vulnerability systematically shapes how consumers infer the capacity for empathic care of human and AI tools.
- Why travellers Share Their Experiences on Social MediaPublication . Catalán, Sara; Marchan, Júlia; Oliveira, Tiago; Information Management Research Center (MagIC) - NOVA Information Management School; NOVA Information Management School (NOVA IMS); De GruyterPrior research on motivations for sharing travel experiences on social media offers fragmented and inconsistent findings due to the ad-hoc selection of constructs, the use of diverse terminologies for the same motivations, the combination of different motivations into single constructs, and the lack of distinction between different social media platforms. To address these limitations, we review existing literature and categorise the motivations for sharing based on two dimensions: the orientation of the motive (i.e. functional, affective and expressive) and the sphere of action (i.e. self-sphere and social-sphere). Then, based on Uses and Gratifications (U&G) theory, we empirically examine the effect of these motivations on actual travel experience sharing. The results identify four key motivations (gratifications) for travellers in profile-based social media (i.e. enjoyment, expressing positive feelings, documentation of experiences, and helping the service provider) and three in content-based social media (i.e. helping the service providers, helping other travellers, and enjoyment). Finally, the implications for encouraging travel experience sharing behaviours in social media are discussed.
- Spatial assessment of forest soil carbon and climate-related value inside and outside protected areas in ChinaPublication . Zhang, Yuxian; Wang, Guojie; Cabral, Pedro; Information Management Research Center (MagIC) - NOVA Information Management School; Springer Science Business MediaProtected areas are widely used as spatial instruments for climate mitigation, yet their contribution to below‐ground carbon storage remains insufficiently quantified at national scales. This study assesses how forest soil organic carbon (SOC) and its climate-related value differ between protected and non-protected areas across China under historical and future climate conditions. Using field-based SOC observations and spatial machine‐learning models, we estimated SOC density at two soil depths (0–20 cm and 0–100 cm) from 2000 to 2100 under multiple Shared Socioeconomic Pathway scenarios. Spatially explicit SOC projections were generated using Random Forest models driven by climatic, vegetative, soil, and topographic variables, and SOC differences associated with protected-area status were evaluated through comparative analysis of forested regions inside and outside established reserves. The results reveal strong spatial differentiation in SOC trajectories, with stability or accumulation under low-emission pathways and widespread losses under high-emission scenarios, particularly in deeper soil layers. Forests within protected areas consistently exhibit higher SOC densities than unprotected forests, with mean differences of 45.5% in topsoil and 33.4% across the full soil profile. Extrapolation to protected areas established after 2000 indicates potentially substantial additional SOC stocks, corresponding to climate-related values ranging from tens to over one hundred billion USD under alternative carbon price assumptions. Although spatially independent validation indicates reduced predictive performance at fine scales, the model robustly captures broad climatic and edaphic gradients. Overall, this study provides a spatially explicit assessment of forest SOC dynamics to support conservation planning and climate-mitigation strategies.
- Comportamiento de los turistas en los hoteles de cuatro y cinco estrellas del Algarve antes y durante la pandemia de COVID-19Publication . Ferreira, Ana; Correia, Marisol B.; Renda, Ana Isabel; António, Nuno; NOVA Information Management School (NOVA IMS); Information Management Research Center (MagIC) - NOVA Information Management School; Universidad de MurciaThis study aims to examine the behaviour of tourists staying in four- and five-star hotels in Portugal’s Algarve region before and during the pandemic and to identify differences between these periods. To achieve this, 17,601 online reviews published on TripAdvisor between January 2018 and April 2023 were analysed using NVivo 14 software. The findings reveal that guest behaviour during the pandemic closely mirrored pre-pandemic patterns, except for variations related to tourists’ continent of origin.
- Climate-Resilient Agriculture and Sustainable Livelihoods in EuropePublication . Goli, Imaneh; Ghazali, Samane; Cabanelas, Pablo; Vieira, Aitor Manuel Couce; Muñoz Dueñas, María del Pilar; Neves, Catarina; Oliveira, Tiago; Azadi, Hossein; Information Management Research Center (MagIC) - NOVA Information Management School; NOVA Information Management School (NOVA IMS); John Wiley and Sons LtdAchieving climate-resilient agriculture (CRA) is a key concern for policymakers and at the core of the European Union's (EU) agenda. Indeed, sustainability influences a wide range of livelihood assets, which can also directly affect CRA in Europe. Therefore, this study used a quantitative meta-analysis of 43 original articles published between 1990 and 2024 to identify effective strategies to enhance the resilience of the European agricultural sector. In this regard, the search was done in the Web of Science, Scopus, and Science Direct databases by the main inclusion criteria on socio-economic and environmental sustainability. For this purpose, livelihood assets and adaptation strategies that help improve or strengthen CRA and sustainability in Europe were examined from three social, economic, and environmental perspectives. According to the meta-regression coefficients, human and financial assets can be significant for achieving better socially sustainable agriculture, suggesting that in Europe, as a developed region, human and financial assets contribute more to a socially sustainable and resilient agriculture than social, natural, and physical assets. Furthermore, social and natural assets follow in terms of importance to achieve more sustainable and economically viable agriculture. Livelihood assets also exhibit significant spatial and temporal impacts on environmental sustainability across Europe. According to the meta-regression findings, advancing agriculture's transformative resilience-building potential requires sustained investment in key livelihood assets, particularly human, financial, social, and natural capital. Since CRA takes a holistic approach that includes some simple farming techniques, the results also suggest focusing on human, social, and natural assets to support inclusive education, fair access to livelihood assets, and a sustainable environment as combined strategies for lasting sustainability.