Science – Page 89 – Minority Mindset

Played for Suckers: How Scammers Exploit Our Psychology

28.01.2026 by qfx

New research reveals the behavioral cues that make people vulnerable to online job scams, leading to significant financial loss.

Predicting Soccer Injuries Before They Happen

28.01.2026 by qfx

A DeepHit model, trained with a leave-one-patient-out method, predicts injury risk over time, with observed injury events indicated by vertical, red dotted lines.

New research shows how machine learning can forecast time-to-injury for elite female soccer players, offering a proactive approach to athlete health.

Predicting the Future with Polynomial Networks

28.01.2026 by qfx

The architecture dissects temporal dependencies through a stacked series of Hahn-KAN blocks-each leveraging Hahn polynomials within intra- and inter-patch layers-and refines the resulting sequence via a bottleneck structure, effectively establishing a system where channel independence, reversible normalization, and patching converge to produce forecasts.

A new framework combines Hahn polynomials and Kolmogorov-Arnold networks for more accurate and efficient time series forecasting.

Untangling AI Failures: A Statistical Approach to Root Cause Analysis

28.01.2026 by qfx

The autonomous railway system underwent rigorous testing against a deliberately expanded synthetic dataset, subjected to a spectrum of environmental disturbances - including simulated zoom blur, glass distortion, snowfall, frost, fog, and Gaussian noise - to assess its resilience under adverse conditions and expose potential failure modes.

As artificial intelligence systems grow in complexity, pinpointing the source of errors becomes increasingly difficult, and this research introduces a new framework for statistically attributing failures to specific components.

When AI Does the Thinking: The Hidden Costs for Software Engineering Research

28.01.2026 by qfx

A thought experiment explores how over-dependence on generative AI tools could subtly undermine core technical competencies and erode the foundations of trustworthy research in software engineering.

Mapping Aneurysm Risk with AI

28.01.2026 by qfx

The study presents a qualitative comparison of computational fluid dynamics (CFD) and deep learning (DL) derived fields - time-averaged wall shear stress (TAWSS), oscillatory shear index (OSI), and residence time ratio (RRT) - suggesting a correspondence between these traditionally modeled hemodynamic parameters and those predicted through machine learning approaches.

A new deep learning framework dramatically accelerates the prediction of blood flow dynamics within brain aneurysms, offering a faster path to risk assessment.

Beyond Black Boxes: Smarter Energy Forecasts

28.01.2026 by qfx

New research demonstrates that statistically rigorous economic modeling can rival the predictive power of machine learning in energy markets.

Predicting Corporate Risk with AI Foresight

28.01.2026 by qfx

The analysis of predicted risk probabilities against empirical materialization rates demonstrates a calibration of confidence, revealing how well the system’s assessment of risk aligns with actual outcomes on the test set.

New research demonstrates how artificial intelligence can anticipate the likelihood of disclosed corporate risks becoming real-world problems.

Finding a Voice: How AI Chatbots Are Changing the Conversation for Autistic Users

28.01.2026 by qfx

New research explores the complex relationship between autistic individuals and AI chatbots like ChatGPT, revealing both empowering benefits and potential pitfalls.

Future-Proofing Cities: AI Navigates the Rising Tide of Flood Risk

27.01.2026 by qfx

Under a RCP4.5 climate scenario spanning 2024-2100, a reinforcement learning policy demonstrably reduces adaptation costs-measured in Danish Kroner-with greater stability and significantly lower expenditures compared to a Random Control strategy, despite the latter’s reliance on high and persistent investment.

A new reinforcement learning framework helps urban planners proactively design resilient transportation systems capable of weathering long-term climate change and minimizing disruption from flooding.