explainable ai

Smart healthcare systems with improved cybersecurity by AI integration

Prediction of Brain Stroke Risk Using Machine Learning and Deep Learning: An Hybrid XGBoost-ResNet-18 CDSS

Stroke continues to be one of the major causes of global deaths and neurologic impairment. Conventional clinical scoring system such as CHADS₂ scores static and additive in nature and unable to process high dimensional multi-modal data. This paper proposes a hybrid artificial intelligence (AI) based clinical decision s...

Federated Cognitive Parliament: A Democratic Framework for Agentic Decision-Making Over Data

As more autonomous AI agents are deployed in the form of distributed data ecosystems, there is an increased pressure on the necessity of having transparent, responsible, and ethically consistent decisions. Classical frameworks of governance in dealing with complexity of federated and setting where stakeholders possess...

Spatiotemporal evolution and drivers of eco-environmental quality for sustainable rural tourism in China’s Yangtze River Basin: an explainable AI approach

Balancing tourism-driven growth (SDG 8.9) with terrestrial ecosystem conservation (SDG 15) is vital for sustainable watershed management. Focusing on 409 Key Rural Tourism Villages in China’s Yangtze River Basin, this study integrates Google Earth Engine and MODIS data to assess eco-environmental quality (EEQ) from 200...

Governing the Algorithm

AI (Artificial Intelligence) has transformed adaptive learning by enhancing student engagement, automating assessments and customizing education. But a formal regulatory structure is essential because of the ethical restrictions of AI governance such as algorithmic bias, data privacy problems, transparency gaps, and ac...

Building Ethical AI Competencies in STEM Education

The importance of AI ethics in STEM education is to train future technologists on how to create socially useful and responsible AI systems. It focuses on the incorporation of governance systems, transparency, and responsible innovation into the school curricula. Governance guarantees responsible behavior and ethical co...

Loss-Aware Residual Learning for Imbalanced Multi-Class Diabetic Retinopathy Diagnosis

Diabetic Retinopathy (DR) is a severe complication of diabetes that can lead to vision impairment or blindness, making early detection crucial. Traditional deep learning models often struggle with class imbalance in medical datasets, leading to poor performance for minority classes. This study proposes a novel deep...

Marketing Analytics for Gastrointestinal Cancer Prevention and Early Detection: Emerging Trends, Analytical Frameworks and Research Directions

Gastrointestinal (GI) cancers, such as colorectal, gastric, liver, pancreatic, and oesophageal cancers, continue to represent a serious public health concern because of their high prevalence and mortality and frequent delayed diagnosis. The evolution of marketing analytics offers new opportunities to address existing b...

Clinically Actionable Explainable Artificial Intelligence: A Risk-Aware Framework for Translating Model Explanations into Medical Decisions

Explainable Artificial Intelligence is now widely used in the healthcare sector in order to increase transparency in AI prediction models which can be used for diagnosis, risk prediction, and decision-making. Although currently used explainability techniques can justify predictions, in most cases they do not effectivel...

Artificial Intelligence Derived from Ancient Indian Practices in Chemistry

This chapter explores the intersection between the Ancient Indian Practices (AIP) and Artificial Intelligence (AI), highlighting the relevance of the traditional Indian Knowledge System (IKS) to the advancement of chemical sciences. The vast data of the Indian Knowledge System are available in the form of textual mater...

Ethical AI in Practice

The swift incorporation of artificial intelligence (AI) into science, technology, engineering, and mathematics (STEM) education has generated revolutionary prospects for customized learning, intelligent tutoring, predictive analytics, and automated evaluation. But with these benefits come important ethical issues that...

Investigating AI/ML Models that Learn the Preferences and Constraints of Human Decision-Makers to Develop Interactive or Tools that Suggest Optimized Solutions While Allowing for Human Override and Incorporating Expert Judgment

The growing adoption of Artificial Intelligence and Machine Learning (AI/ML) systems in very complicated and sensitive decision-making areas have had a big impact on the issues of transparency, trust, and ethical accountability. The optimization-based AI systems were mainly focusing on maximizing the computational effi...