Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Videos

KFASL: a variance-stable explainable AI framework for high-dimensional anomaly detection.

Hassam Tahir¹, Mohammad Reza Jabbarpour², Bao Quoc Vo²

¹School of Science, Computing and Engineering Technologies, Swinburne University of Technology, Hawthorn, VIC, 3122, Australia. htahir@swin.edu.au.

Scientific Reports

|May 4, 2026

Summary

Related Concept Videos

Variability: Analysis

Variability: Analysis

Measures of variability are statistical metrics that reveal the dispersion pattern within a dataset. They are pivotal in biostatistics, providing insights into the heterogeneity within health and biological data. Variability signifies the degree to which data points diverge from one another, helping researchers understand the potential range of values and associated uncertainty within the data.
The range is a simple measure of variability, indicating the difference between the highest and...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Correction: Rubber intercropping with arboreal and herbaceous species alleviated the global warming potential through the reduction of soil greenhouse gas emissions.

Scientific reports·2026

Same author

Cardiac arrest as initial presentation of Kawasaki disease with giant coronary aneurysms: A case report and review of literature.

World journal of clinical cases·2026

Same author

Funding Distributions, Trends, Gaps, and Policy Implications for Spinal Cord Injury Research: A Systematic Analysis of U.S. Federal Funds.

Journal of neurotrauma·2025

Same author

A genome-wide analysis of ascorbate oxidase gene family and hormonal activity in mango exposed to enhanced UV-B radiation.

BMC plant biology·2025

Same author

Genome-Wide Identification and Expression Profiling of Pyruvate Kinase Genes in Litchi Under Calcium-Magnesium Foliar Treatment.

Plants (Basel, Switzerland)·2025

Same author

Physiological Mechanisms of the Enhanced UV-B Radiation Triggering Plant-Specific Peroxidase-Mediated Antioxidant Defences.

Antioxidants (Basel, Switzerland)·2025

Same journal

Application of ephrin-B2 loaded glycol chitosan-silk fibroin hydrogel in the treatment of diabetic refractory wounds.

Scientific reports·2026

Same journal

International expert Delphi consensus on thromboprophylaxis in metabolic and bariatric surgery.

Scientific reports·2026

Same journal

Assessing the cross-region knowledge transfer capability of selected deep learning building vectorization methods in the context of available training datasets.

Scientific reports·2026

Same journal

Feasibility and preliminary effects of outdoor versus indoor cognitive-motor therapy in women with Alzheimer's disease: A randomized single-blind pilot study.

Scientific reports·2026

Same journal

Hallmarks of social action in the vocal turn-taking of wild common marmosets (Callithrix jacchus).

Scientific reports·2026

Same journal

Role and mechanism of AOPPs-induced NOX4-mediated ferroptosis in intervertebral disc degeneration.

Scientific reports·2026

See all related articles

This summary is machine-generated.

A new explainable artificial intelligence (XAI) framework, KFASL, offers stable and efficient feature attributions for anomaly detection in complex sensor systems. It overcomes computational costs and limitations of existing methods, enabling practical deployment.

Area of Science:

Artificial Intelligence
Machine Learning
Data Science

Background:

Explainable AI (XAI) is crucial for anomaly detection in high-dimensional, safety-critical sensor systems.
Existing post-hoc XAI methods face challenges like high computational cost, unstable attributions, and poor performance in unsupervised settings.

Purpose of the Study:

To introduce KFASL, a novel, computationally efficient, and variance-stable XAI framework.
To approximate Shapley-based feature attributions using a variance-optimized weighting strategy for improved anomaly detection.

Main Methods:

KFASL integrates local and global explanations with causality-aware regularization.
It approximates Shapley attributions with reduced complexity from exponential to polynomial time.
Employs a variance-optimized weighting strategy for enhanced stability and efficiency.

Keywords:

Anomaly detection Causal reasoning Explainable artificial intelligence Safety-critical systems Satellite constellation

Related Experiment Videos

Main Results:

KFASL demonstrates improved attribution stability, explanation fidelity, and runtime efficiency.
Outperforms existing XAI techniques like SHAP, Kernel SHAP, LIME, and Anchors in evaluations.
Successfully applied to spacecraft telemetry data for anomaly detection.

Conclusions:

KFASL provides a general and practical solution for explainable anomaly detection in complex sensor systems.
The framework is scalable and suitable for resource-constrained and safety-critical environments.
Offers a significant advancement over current XAI methods for anomaly detection.