output
20152026
most citedA Perspective on Explainable Artificial Intelligence Methods: SHAP and LIME

805 citations

10 papers

astro-ph.GA2026

Single-Parameter Exponential Model Outperforms Standard Dark Matter and Modified Newtonian Frameworks in Predicting Galactic Rotation Curves

Mohammed Guhdar

The functional forms of galactic rotation curves provide a fundamental test for models of gravity and dark matter. In this work, we conduct a rigorous statistical comparison of fiv…

cs.CV2026★ 1 cited

Curvelet-Based Frequency-Aware Feature Enhancement for Deepfake Detection

Salar Adel Sabri, Ramadhan J. Mstafa

The proliferation of sophisticated generative models has significantly advanced the realism of synthetic facial content, known as deepfakes, raising serious concerns about digital…

eess.IV2025★ 8 cited

Optimizing Region of Interest Selection for Effective Embedding in Video Steganography Based on Genetic Algorithms

Nizheen A. Ali, Ramadhan J. Mstafa

With the widespread use of the internet, there is an increasing need to ensure the security and privacy of transmitted data. This has led to an intensified focus on the study of vi…

cs.MM2025★ 7 cited

Reversible Video Steganography Using Quick Response Codes and Modified ElGamal Cryptosystem

Ramadhan J. Mstafa

The rapid transmission of multimedia information has been achieved mainly by recent advancements in the Internet's speed and information technology. In spite of this, advancements…

cs.CV2025★ 4 cited

A Study of Gender Classification Techniques Based on Iris Images: A Deep Survey and Analysis

Basna Mohammed Salih Hasan, Ramadhan J. Mstafa

Gender classification is attractive in a range of applications, including surveillance and monitoring, corporate profiling, and human-computer interaction. Individuals' identities…

cs.LG2025★ 4 cited

Hybrid Deep Learning Model for epileptic seizure classification by using 1D-CNN with multi-head attention mechanism

Mohammed Guhdar, Ramadhan J. Mstafa, Abdulhakeem O. Mohammed

Epilepsy is a prevalent neurological disorder globally, impacting around 50 million people \cite{WHO_epilepsy_50million}. Epileptic seizures result from sudden abnormal electrical…

stat.ML2023★ 805 cited

A Perspective on Explainable Artificial Intelligence Methods: SHAP and LIME

Ahmed Salih, Zahra Raisi-Estabragh, Ilaria Boscolo Galazzo +4

eXplainable artificial intelligence (XAI) methods have emerged to convert the black box of machine learning (ML) models into a more digestible form. These methods help to communica…

stat.ML2023★ 25 cited

Characterizing the contribution of dependent features in XAI methods

Ahmed Salih, Ilaria Boscolo Galazzo, Zahra Raisi-Estabragh +3

Explainable Artificial Intelligence (XAI) provides tools to help understanding how the machine learning models work and reach a specific outcome. It helps to increase the interpret…

math.GM2019

A New Type of Weakly Commutative Groups

Hariwan Z. Ibrahim, Muwafaq M. Salih

The aim of the present paper is to define and study a new class of groups, namely Wm-groups with a single binary operation based on axioms of semi commutativity, right identity and…

math.GN2015★ 1 cited

On Pre-γ-I-Open Sets In Ideal Topological Spaces

Hariwan Z. Ibrahim

In this paper, the author introduce and study the notion of pre-γ-I-open sets in ideal topological space.