explainable ai

Privacy-aware adversarial defense with explainable AI for adversarial robustness in AI model

The Attention Concentration Score (ACS) is introduced, which measures how DP training shifts Transformer attention away from task-critical features toward non-functional ones, providing a mechanistic explanation of the trade-off.

A Flexible-Horizon Clinical Decision Support Model for Dementia Early Detection and Risk Prediction in Secondary Care: A Responsible AI Approach

The findings support the feasibility of flexible-horizon, clinically-informed and responsible ML-based decision support for dementia early detection; however, external validation, recalibration and prospective clinical evaluation are required before deployment.

A hybrid deep learning framework for early autism screening

A reliability-oriented hybrid deep learning framework that provides a low-cost, scalable, non-invasive, and AI-assisted pre-screening tool for early ASD risk indication and referral support is proposed.

Building the Wings and Flying Too Close to the Sun? A Daedalus–Icarus Framework for GenAI, Trust, and Sustainable Marketing

Generative artificial intelligence (GenAI) is reshaping digital marketing by expanding opportunities for personalization, content generation, automation, and consumer interaction, while simultaneously raising concerns about intrusion, manipulation, authenticity, autonomy, and trust. This conceptual study examines how G...

When is AI-mediated institutional action ethically warranted? A feasibility-first framework for admissible-state reasoning

A feasibility-first framework for admissible-state reasoning within Deterministic Systems Intelligence (DSI) is developed, which distinguishes continuity with earlier DSI release-governance work from a further theoretical question: whether an institution is justified in exercising consequential authority through a prop...

Artificial intelligence guided nanomaterials for sustainable environmental remediation advances and future perspectives

Abstract Environmental pollution by heavy metals, pharmaceuticals, and emerging contaminants has been identified as a serious global issue owing to their persistence, toxicity, and difficulty of removal using conventional methods. AI is changing the paradigm of nanotechnology through the rapid design and optimization o...

Artificial intelligence in higher education: The interplay of competence, perception, and artificial intelligence influence on self-learning outcomes

The quick adoption of artificial intelligence (AI) in higher education has changed how students learn and cultivate their capacity for self-directed learning. Although previous research has looked at the adoption of AI, few have investigated the ways in which perception, competency, and AI's behavioural effect, all wor...

Artificial intelligence-based integration of imaging, exposome, and multi-omics data for immune-related biomarker discovery and precision prevention in breast cancer

Breast cancer management still depends on early detection, risk assessment, and individualized treatment. Imaging is used throughout screening, diagnosis, treatment evaluation, and follow-up. For this reason, artificial intelligence (AI) has become an active area in breast cancer imaging, especially in mammography, ult...

Diagnostic Performance of Agentic AI for Rare Disease Diagnosis: A Systematic Review, Meta-analysis, Workflow Development, and Benchmark-based Validation

PREreview of "A Modular Platform for Purification of Organelle-associated Mitochondria Reveals Functional Specialization at Organelle Contact Sites"

This Zenodo record is a permanently preserved version of a PREreview. You can view the complete PREreview at https://prereview.org/reviews/22755975. Otto et al. have developed a proximity labelling method called Organelle Contact-dependent Affinity Purification (ORCA) to systematically separate subpopulations of mitoch...

Analysis Code for "Do Standardized Residential Energy Models Represent the Variables That Matter? Evidence from Explainable Machine Learning"

Title: Analysis Code for “Do Standardized Residential Energy Models Represent the Variables That Matter? Evidence from Explainable Machine Learning” Creators: Jie Li, Guido Cervone, José P. Duarte, Ute Poerschke, and Lisa D. Iulo Description: This repository contains the analysis code supporting the study “Do Standardi...

Analysis Code for "Do Standardized Residential Energy Models Represent the Variables That Matter? Evidence from Explainable Machine Learning"

Title: Analysis Code for “Do Standardized Residential Energy Models Represent the Variables That Matter? Evidence from Explainable Machine Learning” Creators: Jie Li, Guido Cervone, José P. Duarte, Ute Poerschke, and Lisa D. Iulo Description: This repository contains the analysis code supporting the study “Do Standardi...