46870 research outputs found
Sort by
Developing Artificial Intelligence Explanations for Technology Enhanced Learning with and for Special Educational Needs Children and Teachers
No full textThis paper describes a participatory design approach involving children with special education needs (SEN) and their teachers in the design of AI explanations for a maths learning environment. Findings from these design activities indicate that the children were particularly curious about how the AI ‘learned’ maths. The teachers wanted not only information about the AI algorithm but also information about the data used by the AI and ethical considerations. These findings could provide practical insights to inform further design of transparent and accessible AIED systems especially for SEN children.</p
A Quantitative Methodology for Systemic Impact Assessment of Cyber Threats in Connected Vehicles
Get PDFThe increasing integration of digital technologies in connected vehicles introduces cybersecurity risks that extend beyond individual vehicles, with the potential to disrupt entire transportation systems. Current practice (e.g., ISO/SAE~21434 TARA) focuses on threat identification and qualitative impact ratings at the vehicle boundary, with limited systemic quantification. This study presents a systematic, simulation-based methodology for quantifying the systemic operational and safety impacts of cyber threats on connected vehicles, evaluating cascading effects across the transport network. Three representative scenarios are examined: (I) telematics-induced sudden braking causing a cascading collision, (II) remote disabling on a motorway (M25) segment, and (III) a compromised Roadside Unit (RSU) spoofing Variable Speed Limit (VSL) and phantom lane closure messages to connected and automated vehicles (CAVs). The results highlight the potential for cascading safety incidents and systemic operational degradation, as evidenced by the defined systemic operational and safety vectors, factors that are insufficiently addressed in the current scope of the ISO/SAE 21434 standard, which primarily focuses on individual vehicle-level threats. The findings underscore the need to incorporate systemic evaluation into existing frameworks to enhance cyber resilience across connected vehicle ecosystems. The framework complements ISO/SAE~21434 by supplying quantitative, reproducible evidence for the impact rating step at a systemic scale, reducing assessor subjectivity and supporting policy and operations, enabling more data-driven evaluations of systemic cyber risks
Intermediaries in Agricultural Supply Chains:Trends and Insights
Get PDFThe role of intermediaries in the agricultural supply chain has become a significant topic of interest due to their influence on efficiency, market access, and value addition. This study presents a bibliometric analysis aimed at getting a deeper understanding of the evolution of research on agricultural supply chain intermediaries. The analysis intends to identify key trends, influential studies, and emerging areas of interest that will contribute to the field of research. We retrieved metadata from the Scopus database, which included 1.074 articles published between 2014 and 2025. Statistical analysis was conducted to discover the leading publishers and authors in this field. A co-occurrence network and overlay visualization of author keywords were generated using VOS viewer to map the structure and progression of the research landscape. The analysis also presented emerging keywords and research issues corresponding to network visualization, highlighting this field's dynamic and evolving nature. These insights are valuable for researchers, policymakers, and practitioners seeking to understand and enhance the relationship between intermediaries and the agricultural supply chain
The effects of isothermic heat acclimation on simple and complex cognitive performance in the heat
Get PDFLonger heat acclimation (HA) protocols more effectively improve physical performance than shorter ones, but the effect of HA duration on cognitive performance remains unclear. Twelve participants performed a 45-min cycling heat stress test [(HST) 40%W max; 40°C; 50% RH] on the first (HST 1), seventh (HST 7), and thirteenth (HST 13) day of testing with five consecutive days of isothermic HA (60-min; rectal temperature ~38.5°C) between each HST. Simple (five-choice reaction time [RT]) and complex (spatial working memory [SWM]) tests were completed before and after each HST. Reaction and Movement times were slower before HST 13 than HST 1. Fewer errors were made in the SWM test before HST 13 in the 6- (0.0v2.7), 8- (1.8v7.6) and 12- (18v31) box tests and before HST 7 in the 6- and 8-box tests (1.9v7.6) compared to HST 1. Search strategy was improved before HST 7 (4.5v6.8) and HST 13 (4.3v6.8). Fewer errors were made in the 8-box test after HST 7 (1.6v8.8) and HST 13 (1.1v8.6). No other differences were observed (p > 0.05). HA improved performance in some of the more challenging tasks but had no effect on the most complex task (12-box) when physiological strain was highest. 10-days of HA was more effective than 5-days at improving some aspects of cognitive performance.</p
Large language model-based multiagent collaboration for abstract screening toward automated systematic reviews
Get PDFSystematic reviews (SRs) are essential for evidence-based practice but remain labor-intensive, especially during abstract screening. This study evaluates whether multiple large language models (multi-LLMs) collaboration can improve the efficiency and reduce costs for abstract screening. Abstract screening was framed as a question-answering (QA) task using cost-effective LLMs. Three multi-LLM collaboration strategies were evaluated, including majority voting by averaging opinions of peers, multi-agent debate for answer refinement, and LLM-based adjudication against answers of individual QA baselines. These strategies were evaluated on 28 SRs of the CLEF eHealth 2019 technology-assisted review benchmark using standard performance metrics such as mean average precision (MAP) and work saved over sampling at 95% recall (work saved over sampling WSS@95%). Multi-LLM collaboration significantly outperformed QA baselines. Majority voting was overall the best strategy, achieving the highest MAP 0.462 and 0.341 on subsets of SRs about clinical intervention and diagnostic technology assessment, respectively, with WSS@95% 0.606 and 0.680, enabling in theory up to 68% workload reduction at 95% recall of all relevant studies. Multi-agent debate improved weaker models most. Our own adjudicator-as-a-ranker method was the second strongest approach, surpassing adjudicator-as-a-judge, but at a significantly higher cost than majority voting and debating. Multi-LLM collaboration substantially improves abstract screening efficiency, and the success lies in model diversity. Making the best use of diversity, majority voting stands out in terms of both excellent performance and low cost compared to adjudication. Despite context-dependent gains and diminishing model diversity, multi-agent debate is still a cost-effective strategy and a potential direction of further research
Machine Learning or Deep Learning? The Role of Ice Sensors and Weather Forecasts in Wind Turbine Icing Prediction
No full textAtmospheric icing on wind turbine blades remains a major barrier to reliable wind energy production in cold climates, reducing annual yields by up to 20%. In addition to production losses, ice shedding from blades creates safety hazards for personnel and infrastructure, prompting mandatory curtailments. Reliable forecasting of icing formation would allow operators to anticipate events before losses occur, preventing blade damage, reducing downtime, and improving the accuracy of day-ahead energy trading.Predicting icing accretion is challenging because it depends on diverse atmospheric and turbine operating conditions, as well as microphysical parameters such as liquid water content (LWC) and droplet size, which are difficult to measure. These variables can fluctuate rapidly and are only partially observed by SCADA systems and conventional weather stations. Prior studies have largely been restricted to very short forecasting horizons using limited data sources, leaving a gap between research model capabilities and the operational needs of wind farm operators.This research presents the first systematic benchmarking of machine learning (ML) and deep learning (DL) models for icing prediction across multiple horizons and input configurations. The models integrate SCADA signals, meteorological measurements, turbine-mounted icing sensors, and weather forecasts. We compare ML ensembles, including Random Forest, Extreme Gradient Boosting, and Light Gradient Boosting Machine, with a convolutional neural network–long short-term memory (CNN-LSTM) model. Models are evaluated at 1-, 6-, and 24-hour horizons using high-frequency turbine data recorded at 1-second resolution.To assess the contribution of different data sources, three input configurations are tested: Class A (SCADA plus historical weather), Class B (Class A plus icing sensor data), and Class C (Class A plus forecasted weather including LWC). Performance is measured using the F1 score, which balances precision, avoiding false alarms that cause unnecessary shutdowns, with recall, capturing as many real icing events as possible.Random Forest emerged as the best-performing ML model and, with Class C inputs, performed comparably to CNN-LSTM across all horizons, achieving high F1 scores at 1, 6, and 24 hours. Crucially, Random Forest executes significantly faster than CNN-LSTM, making it highly suitable for real-time deployment. Ablation analysis demonstrates that including icing sensor data significantly improves short-term, 1-hour forecasts, increasing the F1 score. At the day-ahead horizon, incorporating weather forecast data in Class C is essential for maintaining strong predictive performance.These findings demonstrate that enriched input data matter more than model complexity. ML ensembles, when supplied with icing-relevant measurements and forecasts, can rival deep learning performance while remaining interpretable and computationally efficient. This enables proactive turbine control in the short term and more reliable energy trading strategies in cold-climate wind farms
Game-based strategies for data literacy:exploring agency in adult learning
Get PDFIn an increasingly data-driven world, supporting adults in developing data literacy is essential for informed participation in society. For learning to be relevant and impactful, adults need to experience a sense of agency in the process. Game-based learning provides a safe, engaging, and experiential space that enables adults to explore and develop data-related knowledge and skills in meaningful, situated ways. Building on this premise, the Erasmus + project Data Literacy for Citizenship (DALI) explored how game-based learning experiences, originally designed to foster Data Literacy, promote agency among adult learners in both formal and informal continuing education contexts. A cross-national sample of 338 participants from Spain, the UK, Germany, and Norway played purpose-designed DALI games and completed an online survey. Using a quantitative, descriptive–correlational design, we analyse how individual factors (age, prior gaming experience) and perceived game quality shaped opportunities for enacting agency within these learning environments. Results show that the game-based strategies of the non-digital DALI games allowed agency activation, regardless of adult age and game experience. The perceived fun, along with game quality, and the clarity of visual texts emerged as drivers of agency in game-based learning. Implications for instructional design, game development and policy are discussed
Remote touch: Chronic pain participants’ experiences with touch-focused audio recordings
No full textPeople living with chronic pain often face barriers to accessing supportive care, including limited mobility, touch sensitivity and the emotional toll of ongoing symptoms. While touch-based interventions like massage or proprioceptive movement can support relief, they are not always accessible or appropriate. In response, ‘Audio Snacks for People Living with Chronic Pain’ explored how remotely delivered, touch-focused audio recordings might support individuals living with chronic pain, not by promising a reduction in physical symptoms but by inviting new forms of sensory engagement that could shift the felt experience of pain. Drawing on somatic approaches, including release-based dance methodologies and approaches that emphasize sensory awareness, the recordings framed touch as an embodied language, allowing participants to explore it through self-directed movement or guided mental imagery. Ten participants with chronic pain engaged with guided audio recordings designed to remotely activate their sense of touch. Through qualitative surveys, a focus group interview and creative responses, participants described feeling more connected to their bodies, supported during overwhelm and able to meet pain with greater softness and agency. Although gathered over a short period, participants’ reflections point to promising possibilities for further development
High resolution assessment of the impact of solar radiation modification on future Caribbean wind and solar energy sources
Get PDFThis study employed the Weather Research and Forecasting (WRF) model to dynamically downscale outputs from the HadGEM2-ES global climate model for the Caribbean at resolutions of 40 km and 8 km. Simulations were conducted for a historical period (1980–1990) and two future periods corresponding to global warming limits of 1.5 °C (2024–2034) and 2 °C (2038–2048) derived from the representative concentration pathway (RCP) 4.5 projection. The future projections were from the RCP4.5 scenario and the solar radiation modification (SRM) G4 scenario from the Geoengineering Model Intercomparison Project, focusing on variables relevant to wind and solar energy assessments. Three bias-correction methods were independently applied to the downscaled outputs to evaluate their effectiveness in reducing bias while preserving projected climate change signals. The Quantile Delta Mapping and Delta method produced the best outputs and were subsequently used to assess the potential influence of SRM on solar and wind energy resources at the island scale. Results indicate that wind speeds under the G4 scenario generally decrease across much of the Caribbean, with parts of southern Jamaica and Hispaniola seeing the most notable increases. Changes in solar irradiance appear minimal; however, this finding remains inconclusive due to limitations in validating the more variable historical distribution of the WRF-derived outputs. These findings demonstrate the feasibility of conducting sub-regional and local-scale wind energy assessments in the Caribbean while underscoring the need for improved observational datasets to enhance solar resource validation