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

Prediction Intervals01:03

Prediction Intervals

The interval estimate of any variable is known as the prediction interval. It helps decide if a point estimate is dependable.
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y. 
The...
Classification of Signals01:30

Classification of Signals

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...
Classification of Systems-I01:26

Classification of Systems-I

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:
Classification of Systems-II01:31

Classification of Systems-II

Continuous-time systems have continuous input and output signals, with time measured continuously. These systems are generally defined by differential or algebraic equations. For instance, in an RC circuit, the relationship between input and output voltage is expressed through a differential equation derived from Ohm's law and the capacitor relation,
Per-Unit Sequence Models01:26

Per-Unit Sequence Models

An ideal Y-Y transformer, grounded through neutral impedances, displays per-unit sequence networks akin to those of a single-phase ideal transformer when subjected to balanced positive- or negative-sequence currents. These currents do not produce neutral currents, and their associated voltage drops.
Zero-sequence currents, which are identical in magnitude and phase, generate a neutral current, resulting in voltage drops across the neutral impedance and the low-voltage winding. If the...
Aggregates Classification01:29

Aggregates Classification

Aggregate classification is generally based on its size, petrographic characteristics, weight, and source. Size classification ranges from coarse to fine aggregates, defined by the size of the particles. Coarse aggregates are particles that do not pass through ASTM sieve No. 4, and aggregates that pass through the sieve are fine aggregates.
Petrographic classification groups aggregates based on common mineralogical characteristics. Some of the common mineral groups found in aggregates are...

You might also read

Related Articles

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

Sort by
Same author

Ten-year progression of Caroli's disease with portal hypertension despite endoscopic and pharmacological therapy: Implications for liver transplantation-A case report.

SAGE open medical case reports·2026
Same author

Interfacial Electron Engineering for Nitrate-to-Ammonia Electrocatalysis: Mechanistic Insights and Design Strategies.

Nanomaterials (Basel, Switzerland)·2026
Same author

Ten-year update on the European Association of Urology Robotic Section (ERUS) fellowship training for robot-assisted radical prostatectomy.

BJUI compass·2026
Same author

Author Correction: Electrostatic potentials of atomic nanostructures at metal surfaces quantified by scanning quantum dot microscopy.

Nature communications·2026
Same author

Tumour-macrophage crosstalk initiated by NFIC/METTL3 negative feedback loop via exosomal miR-194-5p promotes NSCLC progression.

Clinical and translational medicine·2026
Same author

C1 pedicle screw placement risks in patients with ponticulus posticus: a CTA retrospective simulation study.

Journal of orthopaedic surgery and research·2026

Related Experiment Video

Updated: Jul 13, 2026

The Mouse Cremaster Muscle Preparation for Intravital Imaging of the Microcirculation
07:19

The Mouse Cremaster Muscle Preparation for Intravital Imaging of the Microcirculation

Published on: June 10, 2011

32.4K

SEGAL time series classification - Stable explanations using a generative model and an adaptive weighting method for

Han Meng1, Christian Wagner2, Isaac Triguero3

  • 1College of Information Science and Engineering/College of Artificial Intelligence, China University of Petroleum (Beijing), Beijing, 102249, China; Computational Optimisation and Learning (COL) Lab, School of Computer Science, University of Nottingham, Nottingham, United Kingdom; The Lab for Uncertainty in Data and Decision Making (LUCID), School of Computer Science, University of Nottingham, Nottingham, United Kingdom.

Neural Networks : the Official Journal of the International Neural Network Society
|May 11, 2024
PubMed
Summary

This study addresses the instability of Local Interpretability Model-agnostic Explanations (LIME) in time series classification. We introduce a new method using generative models and adaptive weighting to create more reliable and stable explanations.

Keywords:
Explainable artificial intelligenceFeature importanceLIMEMultivariate time series classificationStability

More Related Videos

Microiontophoresis and Micromanipulation for Intravital Fluorescence Imaging of the Microcirculation
06:02

Microiontophoresis and Micromanipulation for Intravital Fluorescence Imaging of the Microcirculation

Published on: June 10, 2011

14.5K
Development of Knock-Out Muscle Cell Lines using Lentivirus-Mediated CRISPR/Cas9 Gene Editing
10:12

Development of Knock-Out Muscle Cell Lines using Lentivirus-Mediated CRISPR/Cas9 Gene Editing

Published on: June 16, 2022

4.2K

Related Experiment Videos

Last Updated: Jul 13, 2026

The Mouse Cremaster Muscle Preparation for Intravital Imaging of the Microcirculation
07:19

The Mouse Cremaster Muscle Preparation for Intravital Imaging of the Microcirculation

Published on: June 10, 2011

32.4K
Microiontophoresis and Micromanipulation for Intravital Fluorescence Imaging of the Microcirculation
06:02

Microiontophoresis and Micromanipulation for Intravital Fluorescence Imaging of the Microcirculation

Published on: June 10, 2011

14.5K
Development of Knock-Out Muscle Cell Lines using Lentivirus-Mediated CRISPR/Cas9 Gene Editing
10:12

Development of Knock-Out Muscle Cell Lines using Lentivirus-Mediated CRISPR/Cas9 Gene Editing

Published on: June 16, 2022

4.2K

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Data Science

Background:

  • Local Interpretability Model-agnostic Explanations (LIME) is a popular post-hoc method for explaining black-box models.
  • Recent studies indicate potential instability in LIME explanations, questioning their reliability, especially for complex data like time series.

Purpose of the Study:

  • To investigate the stability of LIME when applied to multivariate time series classification.
  • To identify the causes of LIME instability in time series data, including out-of-distribution neighbors and hyperparameter sensitivity.

Main Methods:

  • A generative model is used to create in-distribution neighbors for LIME, improving sample quality.
  • An adaptive weighting method is proposed to simplify hyperparameter tuning and enhance explanation stability.

Main Results:

  • The proposed method significantly enhances the stability of LIME explanations for multivariate time series classification.
  • Out-of-distribution neighbors generated by traditional LIME methods were identified as a key source of instability.

Conclusions:

  • The novel approach effectively addresses LIME instability in time series classification.
  • The findings offer a more robust framework for interpreting complex time series models.