Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Variability: Analysis01:11

Variability: Analysis

191
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...
191
Survival Tree01:19

Survival Tree

163
Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
 Building a Survival Tree
Constructing a...
163
Propagation of Uncertainty from Systematic Error01:10

Propagation of Uncertainty from Systematic Error

890
The atomic mass of an element varies due to the relative ratio of its isotopes. A sample's relative proportion of oxygen isotopes influences its average atomic mass. For instance, if we were to measure the atomic mass of oxygen from a sample, the mass would be a weighted average of the isotopic masses of oxygen in that sample. Since a single sample is not likely to perfectly reflect the true atomic mass of oxygen for all the molecules of oxygen on Earth, the mass we obtain from this...
890
Attribution Theory00:56

Attribution Theory

13.4K
Behavior is a product of both the situation (e.g., cultural influences, social roles, and the presence of bystanders) and of the person (e.g., personality characteristics). Subfields of psychology tend to focus on one influence or behavior over others. Situationism is the view that our behavior and actions are determined by our immediate environment and surroundings. In contrast, dispositionism holds that our behavior is determined by internal factors (Heider, 1958).
13.4K
Classification of Systems-I01:26

Classification of Systems-I

313
Linearity is a system property characterized by a direct input-output relationship, combining homogeneity and additivity.
Homogeneity dictates that if an input x(t) is multiplied by a constant c, the output y(t) is multiplied by the same constant. Mathematically, this is expressed as:
313
Classification of Signals01:30

Classification of Signals

899
In signal processing, signals are classified based on various characteristics: continuous-time versus discrete-time, periodic versus aperiodic, analog versus digital, and causal versus noncausal. Each category highlights distinct properties crucial for understanding and manipulating signals.
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
899
  1. Home
  3. Research Domains
  5. Information And Computing Sciences
  7. Artificial Intelligence
  9. Knowledge Representation And Reasoning
  11. A Comprehensive Analysis Of Perturbation Methods In Explainable Ai Feature Attribution Validation For Neural Time Series Classifiers

A comprehensive analysis of perturbation methods in explainable AI feature attribution validation for neural time series classifiers

Ilija Šimić1,2, Eduardo Veas3,4, Vedran Sabol4

  • 1Graz University of Technology, Graz, Austria. isimic@know-center.at.

Scientific Reports
|July 22, 2025

Related Experiment Videos

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
05:47

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

586
Using Informational Connectivity to Measure the Synchronous Emergence of fMRI Multi-voxel Information Across Time
07:12

Using Informational Connectivity to Measure the Synchronous Emergence of fMRI Multi-voxel Information Across Time

Published on: July 1, 2014

12.4K
Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks
11:18

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Published on: March 2, 2015

10.4K

View abstract on PubMed

Summary
This summary is machine-generated.

This study introduces a new metric, the Consistency-Magnitude-Index, for validating feature attribution methods in explainable AI (XAI). It offers improved faithfulness assessment for AI model explanations, especially for time series data.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Data Science

Background:

  • Explainable AI (XAI) is crucial in high-stakes domains like medicine and finance.
  • Feature attribution methods (AMs) are common for identifying influential features in AI models.
  • Current validation metrics for AMs have shown flaws, particularly with time series data.

Purpose of the Study:

  • To address the need for rigorous validation of explanation methods in AI.
  • To introduce a novel metric for faithful assessment of feature importance attribution.
  • To develop an adapted methodology for robust faithfulness evaluation of AMs.

Main Methods:

  • Introduction of the Consistency-Magnitude-Index metric for AM validation.
  • Development of an adapted methodology using diverse perturbation methods for faithfulness evaluation.
Keywords:
Attribution methodsCMIDDSDeep learning

Related Experiment Videos

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
05:47

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

586
Using Informational Connectivity to Measure the Synchronous Emergence of fMRI Multi-voxel Information Across Time
07:12

Using Informational Connectivity to Measure the Synchronous Emergence of fMRI Multi-voxel Information Across Time

Published on: July 1, 2014

12.4K
Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks
11:18

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Published on: March 2, 2015

10.4K
  • Extended evaluation of AMs on time series data, considering perturbation methods and region size.

    • Main Results:

    • The Consistency-Magnitude-Index facilitates a more faithful assessment of feature importance.
    • Perturbation methods and region size significantly influence AM evaluation on time series data.
    • Guidelines for future AM faithfulness assessments are provided based on extensive evaluation.

    Conclusions:

    • The proposed metric and methodology enhance the trustworthiness of AI explanations.
    • The study provides practical insights for evaluating AMs in time series analysis.
    • Demonstration of the methodology on a multivariate time series example validates its utility.
    Evaluation
    Explainable AI
    PES
    Time series