Muhammad Umair Danish — Research Updates https://umairdanish.com/ 2026-08-07T19:30:00-04:00 Muhammad Umair Danishhttps://umairdanish.com/ Cognitive Effects of Textual, Graphical, and Interactive Explanations in Explainable Artificial Intelligence https://umairdanish.com/publications/cognitive-effects-xai/ 2026-08-05T12:00:00-04:00 Examines how textual, graphical, and interactive explanation modalities shape cognitive processing, understanding, and user experience in explainable-AI systems. Human-Centered Explainable Artificial Intelligence and the Effects of Explanation Modalities on Trust, Understanding, and Decision Making https://umairdanish.com/publications/human-centered-xai-explanation-modalities/ 2026-08-05T12:00:00-04:00 Investigates how explanation modalities influence trust, understanding, and decision making, placing human outcomes at the centre of explainable-AI evaluation. Dispersity Measures Within Sessions During Improvised Active Music Therapy with Clients with Parkinson’s Disease https://umairdanish.com/publications/dispersity-measures-music-therapy/ 2026-01-01T12:00:00-04:00 Examines within-session dispersity measures in improvised active music therapy with clients with Parkinson’s disease. MidiPy: A Python Application for Processing MIDI Data in Improvised Active Music Therapy https://umairdanish.com/publications/midipy/ 2026-01-01T12:00:00-04:00 Presents open-source Python research software for transforming MIDI event streams into reproducible measures and visual analytics for music-therapy research. Statistically-Guided Kernel Regression: Embedding Feature Relevance into Kernel Learning https://umairdanish.com/publications/statistically-guided-kernel-regression/ 2026-01-01T12:00:00-04:00 Embeds statistically estimated feature relevance directly into kernel learning for regression. Any-Class Presence Likelihood for Robust Multi-Label Classification with Abundant Negative Data https://umairdanish.com/publications/any-class-presence-likelihood/ 2026-01-01T12:00:00-04:00 Improves multi-label classification when datasets contain many examples in which none of the target classes is present. Conditional Denoising Diffusion Model for Missing Value Imputation in Smart Meter Data https://umairdanish.com/publications/conditional-diffusion-imputation/ 2026-01-01T12:00:00-04:00 Applies conditional denoising diffusion to reconstruct missing smart-meter observations in high-resolution energy data. Linear Lens: A Human-Centered, Non-Interventional Mechanistic Approach to Explainable AI https://umairdanish.com/publications/linear-lens/ 2026-01-01T12:00:00-04:00 Introduces a non-interventional framework for tracing predictive information through neural networks and translating internal representations into human-centered evidence. Monotone Delta: An Order-Theoretic Tournament Graph Approach for Internal Consistency Assessment https://umairdanish.com/publications/monotone-delta/ 2026-01-01T12:00:00-04:00 Develops an order-theoretic tournament-graph method for assessing internal consistency in structured comparative settings.