Search Results (682)

Background: Corporal punishment (CP) remains a common disciplinary practice in many countries, despite evidence of its negative consequences for children’s development. Objective: This study examined the effectiveness of a culturally adapted intervention aimed at reducing parents’ use of CP. Method: Using a 12-month quasi-experimental longitudinal design, the study included an intervention group (n = 21) and a control group (n = 17). We administered standardized instruments at pretest and posttest to assess changes in parenting behavior, emotional regulation, and perceptions of child behavior. Artificial neural networks (ANNs) were used to model nonlinear relationships and classify group membership. Results: The intervention group showed significant improvements in parenting practices and emotion regulation. The ANN model classified participants with 74.6% accuracy. Key predictive variables included emotional suppression, physical punishment, and parental support and acceptance. Conclusions: These findings provide evidence for the effectiveness of the SERES program in reducing harmful parenting behaviors and promoting positive practices. Additionally, the use of AI models proved to be valuable for understanding complex behavioral changes, offering a promising approach for optimizing future interventions aimed at strengthening parenting and preventing family violence. Full article

The sustainable integration of Artificial Intelligence in Education (AIEd) in higher education hinges on students’ prolonged and meaningful adoption. Grounded in the Acceptance of AI Device Usage (AIDUA) framework, this study extends the model by incorporating novelty value and trust to investigate the determinants of students’ willingness to use AIEd Tools sustainably. Data from 400 university students in China were analyzed using Partial Least Squares Structural Equation Modeling (PLS-SEM). The results reveal that novelty value acts as a powerful catalyst, substantially boosting performance expectancy and diminishing effort expectancy. Furthermore, this study delineates a dual-pathway mechanism where performance and effort expectancies shape both emotions and trust, which in turn directly determine adoption intention—with emotion exhibiting the stronger influence. Theoretically, this research validates an extended AIDUA model, highlighting the critical roles of sustained innovation perception and cognitive-affective dual pathways. Practically, it advises higher education institutions to prioritize building robust trust through transparent practices and to design AIEd Tools that deliver lasting innovative value and positive learning experiences to foster sustainable adoption. Full article

Accurate estimation of the state of health (SOH) of lithium-ion batteries is essential for the safe and efficient operation of electric vehicles (EVs). Conventional approaches, including Coulomb counting, electrochemical impedance spectroscopy, and equivalent circuit models, provide useful insights but face practical limitations such as error accumulation, high equipment requirements, and limited applicability across different conditions. These challenges have encouraged the use of machine learning (ML) methods, which can model nonlinear relationships and temporal degradation patterns directly from cycling data. This paper reviews four machine learning algorithms that are widely applied in SOH estimation: support vector regression (SVR), random forest (RF), convolutional neural networks (CNNs), and long short-term memory networks (LSTMs). Their methodologies, advantages, limitations, and recent extensions are discussed with reference to the existing literature. To complement the review, MATLAB-based simulations were carried out using the NASA Prognostics Center of Excellence (PCoE) dataset. Training was performed on three cells (B0006, B0007, B0018), and testing was conducted on an unseen cell (B0005) to evaluate cross-battery generalisation. The results show that the LSTM model achieved the highest accuracy (RMSE = 0.0146, MAE = 0.0118, R² = 0.980), followed by CNN and RF, both of which provided acceptable accuracy with errors below 2% SOH. SVR performed less effectively (RMSE = 0.0457, MAPE = 4.80%), reflecting its difficulty in capturing sequential dependencies. These outcomes are consistent with findings in the literature, indicating that deep learning models are better suited for modelling long-term battery degradation, while ensemble approaches such as RF remain competitive when supported by carefully engineered features. This review also identifies ongoing and future research directions, including the use of optimisation algorithms for hyperparameter tuning, transfer learning for adaptation across battery chemistries, and explainable AI to improve interpretability. Overall, LSTM and hybrid models that combine complementary methods (e.g., CNN-LSTM) show strong potential for deployment in battery management systems, where reliable SOH prediction is important for safety, cost reduction, and extending battery lifetime. Full article

The aim of this paper is to provide some concrete evidence, based on the literature review, about the reliability and validity of various Generative Artificial Intelligence (GenAI) tools in the educational process aiming to cultivate speaking and writing skills of learners of English as a second/foreign language (EFL). For this purpose, the PRISMA methodology was employed to secure an academically accepted and valid overview of the literature on the relevant topic. After the exclusion process, 54 studies, within the years 2024–2025, were carefully analyzed. Our discussion centers around the most well-cited benefits and limitations of GenAI-induced tools in the EFL context. The most important findings highlight the significance of employing GenAI tools alongside human teachers in the learning process, as these tools provide learners with opportunities to practice the foreign language in a stress-free, authentic, and stimulating environment. The results were further discussed by reviewing the main benefits, limitations, and pedagogical implications of the proposed use of GenAI in the educational process. Several limitations were acknowledged so as to provide guidelines for future research in this area. This systematic review has been registered through PROSPERO (ID: 1126543). Full article

Background: Lung cancer remains the leading cause of cancer-related mortality worldwide, with non-small cell lung cancer (NSCLC) accounting for the majority of cases. Radiomics and artificial intelligence (AI) have emerged as promising tools for quantitative imaging analysis and precision staging. This study aimed to evaluate the ability of an AI-based radiomics model to preoperatively predict tumor (T) and nodal (N) stage, lymphovascular invasion (LVI), and postoperative complications in patients with early-stage NSCLC. Material and Methods: This retrospective study included 51 consecutive patients who underwent anatomical lobectomy with systematic lymph node dissection between 2019 and 2024, at the Clinic for Thoracic Surgery of the University Clinical Center of Serbia. Quantitative imaging features were extracted from preoperative CT scans using the Lesion Scout with Auto ID module (syngo.via VB50 MM, Siemens Healthineers). Radiomics and clinical predictors were analyzed using regularized logistic regression (LASSO) with five-fold cross-validation. Model performance was assessed using AUC, accuracy, sensitivity, specificity, precision, and F1 score, and calibration was evaluated using the Hosmer–Lemeshow test. Groups were compared using parametric and non-parametric tests. Correlation between the variables was assessed using Spearman’s rank correlation coefficient. All p-values less than 0.05 were considered significant. Results: The AI-based model showed excellent performance for predicting the T component (training AUC = 0.89; test AUC = 0.86; F1 = 0.81) and acceptable calibration (p = 0.41). Nodal metastasis (OR = 0.108; 95% CI: 0.011–1.069; p = 0.057) and LVI (OR = 0.519; 95% CI: 0.139–1.937; p = 0.329) were not significantly predicted. Emphysema was identified as a significant independent predictor of postoperative complications (χ² = 5.13; p = 0.024). Conclusions: The AI-driven radiomics model demonstrated strong predictive ability for the T component and identified emphysema as a clinically relevant predictor of postoperative complications. Full article

This paper explores the intersection of H.P. Lovecraft’s cosmicism and contemporary artificial intelligence (AI), proposing a philosophical shift from anthropocentric AI development to a “cosmicist” approach. Cosmicism, with its emphasis on humanity’s insignificance in a vast, indifferent universe, offers a provocative lens through which to reassess AI’s purpose, trajectory, and ethical grounding. As AI systems grow in complexity and autonomy, current human-centered frameworks, rooted in utility, alignment, and value-conformity, may prove inadequate for grappling with the emergence of intelligence that is non-human in origin and indifferent in operation. Drawing on Lovecraftian themes of fear, the unknown, and cognitive dissonance in the face of incomprehensible entities, this paper parallels AI with the “Great Old Ones”: systems so alien in logic and scale that they challenge the coherence of human-centric epistemology. We argue that a cosmicist perspective does not dismiss the real risks of AI (environmental, existential, or systemic), but reframes them within a broader ontology, one that accepts our limited place in a vast techno-cosmic continuum. By embracing cosmic humility, we propose an expanded AI ethics: one that centers not on domination or full control, but on coexistence, containment, and stewardship. This cosmicist reframing invites a deeper rethinking of intelligence, ethics, and the future: not just of humanity, but of all possible minds. Full article

This paper reports a study conducting an in-depth analysis of the impacts of ethical training on the adoption of AI tools among computer science students in higher vocational colleges. These students will serve as the pivotal human factor for advancing the field of AI. Aiming to explore practical models for integrating AI ethics into computer science education, the research seeks to promote more responsible and effective AI application and therefore become a positive influence in the field. Employing a mixed-methods approach, the study included 105 students aged 20–24 from a vocational college in Guangdong Province, a developed region in China. Based on the Unified Theory of Acceptance and Use of Technology 2 (UTAUT2) model, a five-point Likert scale was used to evaluate the participants’ perceptions of AI tool usage based on ethical principles. The Structural Equation Modeling (SEM) results indicate that while participants are motivated to adopt AI technologies in certain aspects, performance expectancy negatively impacts their intention and actual usage. After systematically studying and understanding AI ethics, participants attribute a high proportion of responsibility (84.89%) to objective factors and prioritized safety (27.11%) among eight ethical principles. Statistical analysis shows that habit (β = 0.478, p < 0.001) and hedonic motivation (β = 0.239, p = 0.004) significantly influence behavioral intention. Additionally, social influence (β = 0.234, p = 0.008) affects use behavior. Findings regarding factors that influence AI usage can inform a strategic framework for the integration of ethical instruction in AI applications. These findings have significant implications for curriculum design, policy formulation, and the establishment of ethical guidelines for AI deployment in higher educational contexts. Full article

Using big data for risk analysis of construction projects is a largely unexplored area. In this traditional industry, risk identification is often based either on so-called domain expert knowledge, in other words on experience, or on different statistical and quantitative analysis of individual past projects. The motivation of this research is based on the implemented and evaluated data-driven and AI-based DARIA approach to identify financial risks in the execution phase of transportation infrastructure construction projects that shows exceptional results at an early stage of the project execution phase and has already been deployed into enterprise-wide production within the STRABAG group. Due to DARIA’s productive use, concern and doubts about the trustworthiness of its ML algorithm are certainly possible, especially when DARIA identifies risky projects while all conventional metrics within the STRABAG controlling system do not identify any problems. “If AI systems do not prove to be worthy of trust, their widespread acceptance and adoption will be hindered, and the potentially vast societal and economic benefits will not be fully realized”. Thus, and based on the results of a user study during DARIA’s successful deployment into enterprise-wide production, this paper focuses on the identification of suitable indicators to measure the trustworthiness of the DARIA ML algorithm in the interaction between individuals and systems as well as on the modeling of the reproducibility of the internal state of DARIA’s ML model. Full article

As grids decarbonize and end-use sectors electrify, the rapid penetration of artificial intelligence (AI) and hyperscale data centers reshapes the electrical load profile and power quality requirements. This leads not only to higher consumption but also coincident demand in constrained urban nodes, steeper ramps and tighter power quality constraints. The article investigates to what extent a compute-additionality covenant can reduce resource inadequacy (LOLE) at an acceptable $/kW-yr under realistic grid constraints, tying interconnection/capacity releases to auditable contributions (ELCC-accredited firm-clean MW in-zone or verified PCC-level services such as FFR/VAR/black-start). Using two worked cases (mature market and EMDE context) the way in which tranche-gated interconnection, ELCC accreditation and PCC-level services can hold LOLE at the planning target while delivering auditable FFR/VAR/ride-through performance at acceptable normalized costs is illustrated. Enforcement relies on standards-based telemetry and cybersecurity (IEC 61850/62351/62443) and PCC compliance (e.g., IEEE/IEC). Supply and network-side options are screened with stage-gates and indicative ELCC/PCC contributions. In a representative mature case, adequacy at 0.1 day·yr⁻¹ is maintained at ≈$200 per compute-kW-yr. A covenant term sheet (tranche sizing, benefit–risk sharing, compliance workflow) is developed along an integration roadmap. Taken together, this perspective outlines a governance mechanism that aligns rapid compute growth with system adequacy and decarbonization. Full article

This paper systematically reviewed studies on the integration of Artificial Intelligence (AI) into infrastructure management to support sustainable urban planning across three primary domains: predictive maintenance and energy optimization, traffic and mobility systems, and public participation with ethical considerations. Findings from thirty peer-reviewed studies underscore how AI-driven models enhance operational efficiency, sustainability, and governance in smart cities. Effective management of AI-driven smart infrastructure can transform urban planning by optimizing resources efficiency and predictive maintenance, including 15% energy savings, 25–30% cost reductions, 25% congestion reduction, and 18% decrease in travel times. Similarly, participatory digital twins and citizen-centric approaches are found to enhance public participation and help address ethical issues. The findings further reveal that AI-based predictive maintenance frameworks improve system reliability, while deep learning and hybrid models achieve up to 92% accuracy in traffic forecasting. Nonetheless, obstacles to equitable implementation, including the digital divide, privacy infringements, and algorithmic bias, persist. Establishing ethical and participatory frameworks, anchored in responsible AI governance, is therefore vital to promote transparency, accountability, and inclusivity. This study demonstrates that AI-enabled smart infrastructure management strengthens urban planning by enhancing efficiency, sustainability, and social responsiveness. It concludes that achieving sustainable and socially accepted smart cities depends on striking a balance between technological innovation, ethical responsibility, and inclusive governance. Full article

Background and Objectives: Artificial intelligence (AI) and extended reality (XR) are reshaping telemedicine, yet physician-level adoption depends on perceived value, training needs, and specialty context. We quantified attitudes toward AI/XR, identified barriers/benefits, and tested advanced relationships (moderation and mediation). Methods: Cross-sectional survey of Romanian physicians (n = 43) across anesthesiology and ICU, surgical, medical, and dentistry. Items were translated into English and mapped to 5-point scales. A 10-item Telemedicine Acceptance Index (TAI; α = 0.86) and a 2-item XR Utility Index (XUI) were computed. Moderation by specialty (Training Priority × Specialty) and bootstrap mediation (2000 resamples) of Future Potential → XUI → TAI were performed. Results: Overall acceptance and perceived utility of XR were moderate to high across specialties; participants most frequently identified technical and financial constraints as barriers and time efficiency and improved access as key benefits. Acceptance patterns were similar across specialties and aligned most strongly with beliefs about future system-level potential and the priority assigned to hands-on training. Conclusions: Physicians reported favorable acceptance of AI/XR-enabled telemedicine. Perceived future system-level value and prioritization of hands-on training were the most consistent correlates of acceptance across specialties. Technical and financial constraints remained the primary barriers, while time efficiency and access emerged as leading perceived benefits. Acceptance appears to be driven more by beliefs about system-level potential and practical upskilling than by specialty identity. Full article

Background and Objectives: As artificial intelligence (AI) and extended reality (XR) enter routine care, understanding patient acceptance is essential. We assessed attitudes toward AI/XR-enabled telemedicine among Romanian patients and examined correlates of acceptance. Methods: We analyzed 198 survey responses to a 20-item questionnaire. Ordinal items were encoded 1–4. The Acceptance Index measured trust in AI, perceived improvement in care, and willingness to choose AI-assisted visits (on a 1–4 scale). Results: Respondents were predominantly 31–50 years old (62.6%) and university educated (76.2%); 27.3% reported prior experience with AI/XR. Acceptance averaged 3.27 ± 0.59 (α = 0.780) and did not differ by age (p = 0.922). Prior users showed higher acceptance than non-users (3.47 ± 0.47 vs. 3.19 ± 0.59; p = 0.0011). Knowledge (ρ = 0.189, p = 0.048) and perceived accessibility (ρ = 0.229, p = 0.016) correlated with acceptance; privacy concern did not (ρ = 0.072, p = 0.455). Subgroups: Prior use was associated with higher acceptance across education levels, with a significant effect in secondary education (Holm-adjusted p = 0.029; Cliff’s δ = 0.56). Ordinal logistic model: higher willingness to pay (OR 6.81, 95% CI 3.39–13.66, p < 0.001) and greater perceived accessibility (OR 1.83, 95% CI 1.03–3.24, p = 0.040) independently predicted choosing AI-assisted visits. Conclusions: Patient acceptance of AI/XR-enabled telemedicine was moderate to high, strongest among prior users, and increased when access felt easy. Knowledge modestly supported acceptance; privacy concerns did not diminish it. Clear value propositions, streamlined access, and optional exposure pathways may enhance informed uptake. Full article

Modern AI systems can strategically misreport information when incentives diverge from truthfulness, posing risks for oversight and deployment. Prior studies often examine this behavior within a single paradigm; systematic, cross-architecture evidence under a unified protocol has been limited. We introduce the Strategy Elicitation Battery (SEB), a standardized probe suite for measuring deceptive reporting across large language models (LLMs), reinforcement-learning agents, vision-only classifiers, multimodal encoders, state-space models, and diffusion models. SEB uses Bayesian inference tasks with persona-controlled instructions, schema-constrained outputs, deterministic decoding where supported, and a probe mix (near-threshold, repeats, neutralized, cross-checks). Estimates use clustered bootstrap intervals, and significance is assessed with a logistic regression by architecture; a mixed-effects analysis is planned once the per-round agent/episode traces are exported. On the latest pre-correction runs, SEB shows a consistent cross-architecture pattern in deception rates: ViT $80.0\%$, CLIP $15.0\%$, Mamba $10.0\%$, RL agents $10.0\%$, Stable Diffusion $10.0\%$, and LLMs $5.0\%$ (20 scenarios/architecture). A logistic regression on per-scenario flags finds a significant overall architecture effect (likelihood-ratio test vs. intercept-only: ${\chi }^2\left(5\right)=41.56$, $p=7.22\times {10}^{-8}$). Holm-adjusted contrasts indicate ViT is significantly higher than all other architectures in this snapshot; the remaining pairs are not significant. Post-correction acceptance decisions are evaluated separately using residual deception and override rates under SEB-Correct. Latency varies by architecture (sub-second to minutes), enabling pre-deployment screening broadly and real-time auditing for low-latency classes. Results indicate that SEB-Detect deception flags are not confined to any one paradigm, that distinct architectures can converge to similar levels under a common interface, and that reporting interfaces and incentive framing are central levers for mitigation. We operationalize “deception” as reward-sensitive misreport flags, and we separate detection from intervention via a correction wrapper (SEB-Correct), supporting principled acceptance decisions for deployment. Full article

Dementia and mild cognitive impairment (MCI) are growing health concerns in Canada’s aging population. Over 700,000 Canadians currently live with dementia, and this number is expected to rise. As the older adult population increases, coupled with an already strained healthcare system, there is a pressing need for innovative tools that support aging in place. This study explored the feasibility and acceptability of using a Digital Human (DH) conversational agent, combined with AI-driven speech analysis, to monitor cognitive function, anxiety, and depression in cognitively healthy community-dwelling older adults (CDOA) aged 65 and older. Sixty older adults participated in up to three in-person sessions over six months, interacting with the DH through journaling and picture description tasks. Afterward, 51 of the participants completed structured interviews about their experiences and perceptions of the DH and AI more generally. Findings showed that 84% enjoyed interacting with the DH, and 96% expressed interest in learning more about AI in healthcare. While participants were open and curious about AI, 67% voiced concerns about AI replacing human interaction in healthcare. Most found the DH friendly, though reactions to its appearance varied. Overall, participants viewed AI as a promising tool, provided it complements, rather than replaces, human interactions. Full article

The increasing availability of User-Generated Content during large-scale events is transforming spectators into active co-creators of live narratives while simultaneously introducing challenges in managing heterogeneous sources, ensuring content quality, and orchestrating distributed infrastructures. A trial was conducted to evaluate automated orchestration, media enrichment, and real-time quality assessment in a live sporting scenario. A key innovation of this work is the use of a cloud-native architecture based on Kubernetes, enabling dynamic and scalable integration of smartphone streams and remote production tools into a unified workflow. The system also included advanced cognitive services, such as a Video Quality Probe for estimating perceived visual quality and an AI Engine based on YOLO models for detection and recognition of runners and bib numbers. Together, these components enable a fully automated workflow for live production, combining real-time analysis and quality monitoring, capabilities that previously required manual or offline processing. The results demonstrated consistently high Mean Opinion Score (MOS) values above 3 72.92% of the time, confirming acceptable perceived quality under real network conditions, while the AI Engine achieved strong performance with a Precision of 93.6% and Recall of 80.4%. Full article