explainable ai

AI-driven collision risk prediction and debris optimization in low earth orbit

Debris congestion and collision in low Earth orbit have become a major point of concern due to the rapid expansion of activities in that region. In this work, an AI-driven framework is developed and deployed to predict, analyze, and optimize collision risk across the altitude inclination space. Local debris object popu...

XAI2CSI: Interpreting CSI with eXplainable AI for Human Activity Recognition

This paper introduces XAI2CSI, a framework that leverages eXplainable Artificial Intelligence (XAI) to analyze DL-based CSI sensing systems and employs SAGE, a model-agnostic explainability method, to quantify temporal, spectral, and spatial CSI contributions to HAR decisions under nominal and cross-context evaluations...

Explainable Artificial Intelligence through Symbolic Reasoning Framework

This paper proposes a framework for achieving explainable artificial intelligence (XAI) by integrating deep learning with symbolic reasoning. The core claim is to translate the predictions of deep learning models into interpretable symbolic rules and then leverage these rules for symbolic reasoning. This framework util...

XMER: An Explainable Multimodal Emotion Recognition Framework for Trustworthy Human–AI Collaboration

Exploring the influence mechanisms of global hydro-climatic factors on vegetation carbon sinks using geospatial interpretable AI models

Explainable Artificial Intelligence through Symbolic Reasoning Framework

This paper proposes a framework for achieving explainable artificial intelligence (XAI) by integrating deep learning with symbolic reasoning. The core claim is to translate the predictions of deep learning models into interpretable symbolic rules and then leverage these rules for symbolic reasoning. This framework util...

English Language Testing and Assessment in the AI Era: Research Guidelines for School-Based Mixed-Methods Studies

This research guide is for the course Current Issues in English Language Education. It focuses on English language testing and assessment in the AI era. Students work in small research teams. Each team has two students and one lecturer. All teams use one shared questionnaire, but each team has a different research topi...

Explainable Artificial Intelligence via Causal Intervention Methods

This paper proposes a novel approach to explainable artificial intelligence (XAI) by leveraging causal intervention methods. The core idea is to model systems using causal graphs and then employ techniques like do-calculus for precise intervention and control. Traditional intervention methods often lack interpretabilit...

The Mechanism Before the Mind: An Engineering Standard for Causal Claims About Machine Learning Behavior

Machine learning research routinely treats a behavioral description as if it were a demonstrated internal mechanism, calling something "intention" or "preference" and then reasoning as though that label had been independently established rather than just applied. This paper draws that boundary formally: an observed beh...

Explainable AI for food safety risk prediction with uncertainty quantification using RASFF data

Food safety incidents pose significant public health risks globally, necessitating robust predictive frameworks for identifying high-risk contamination notifications. This study presents an explainable artificial intelligence framework for food safety risk prediction that integrates SHAP-based feature attribution, temp...

The Sovereign Stack: Architecture, Discipline, and Evidence from One Desk

A sealed, dated research record: an AI factory reached from the other end, one operator and one consumer GPU against an eleven-layer governed stack, with a receipt for every claim. Compiled from the maintained sources of the living record at https://osintelligence-llc.gitbook.io/osintelligence. Every chapter carries it...

Algorithmic Transparency via Interpretable Representation Learning for Deep Neural Networks

Deep neural networks have achieved remarkable success in various domains, including image recognition, natural language processing, and game playing. However, their inherent complexity often leads to a "black box" problem, where the reasoning behind their predictions remains opaque to humans. This research investigates...