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

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving01:29

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

253
Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
253
Mechanistic Models: Compartment Models in Individual and Population Analysis01:23

Mechanistic Models: Compartment Models in Individual and Population Analysis

221
Mechanistic models are utilized in individual analysis using single-source data, but imperfections arise due to data collection errors, preventing perfect prediction of observed data. The mathematical equation involves known values (Xi), observed concentrations (Ci), measurement errors (εi), model parameters (ϕj), and the related function (ƒi) for i number of values. Different least-squares metrics quantify differences between predicted and observed values. The ordinary least...
221
Linear time-invariant Systems01:23

Linear time-invariant Systems

832
A system is linear if it displays the characteristics of homogeneity and additivity, together termed the superposition property. This principle is fundamental in all linear systems. Linear time-invariant (LTI) systems include systems with linear elements and constant parameters.
The input-output behavior of an LTI system can be fully defined by its response to an impulsive excitation at its input. Once this impulse response is known, the system's reaction to any other input can be...
832
Linear Approximation in Time Domain01:21

Linear Approximation in Time Domain

310
Nonlinear systems often require sophisticated approaches for accurate modeling and analysis, with state-space representation being particularly effective. This method is especially useful for systems where variables and parameters vary with time or operating conditions, such as in a simple pendulum or a translational mechanical system with nonlinear springs.
For a simple pendulum with a mass evenly distributed along its length and the center of mass located at half the pendulum's length,...
310
Classification of Systems-I01:26

Classification of Systems-I

528
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:
528
Parameters Affecting Nonlinear Elimination: Zero-Order Input, First-Order Absorption and Two-Compartment Model01:13

Parameters Affecting Nonlinear Elimination: Zero-Order Input, First-Order Absorption and Two-Compartment Model

267
Drugs administered through various routes can lead to nonlinear elimination, resulting in complex pharmacokinetic behaviors crucial to understanding efficacious drug dosing.
When a drug is administered through a constant intravenous infusion and eliminated via nonlinear pharmacokinetics, it follows zero-order input. For example, oral drugs undergo first-order absorption upon administration and are eliminated through nonlinear pharmacokinetics.
In the case of subcutaneously administered drugs,...
267

You might also read

Related Articles

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

Sort by
Same author

Graph autoencoder with mirror temporal convolutional networks for traffic anomaly detection.

Scientific reports·2024
Same author

Dual-feature Fusion Attention Network for Small Object Segmentation.

Computers in biology and medicine·2023
Same author

Cardiac MR segmentation based on sequence propagation by deep learning.

PloS one·2020
Same author

Comparison of inlet geometry in microfluidic cell affinity chromatography.

Analytical chemistry·2011
Same author

Ion-exchange synthesis of a micro/mesoporous Zn2GeO4 photocatalyst at room temperature for photoreduction of CO2.

Chemical communications (Cambridge, England)·2011
Same author

A microarray-based approach identifies ADP ribosylation factor-like protein 2 as a target of microRNA-16.

The Journal of biological chemistry·2011
Same journal

Change-Prior-Guided Unsupervised Change Detection of Heterogeneous Remote Sensing Images.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

AgonicDreamer: Enhancing Multi-View Consistency in Text-to-3D Generation via Rectified Score Distillation.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

BiCM-Prompt: Bidirectional Cross-Modal Prompt Tuning for Class-Incremental Learning on Multisource Remote Sensing Images.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

GoP-based Quality Enhancement on Video Compression.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

Align then Tensorize: Multi-Level Consistent Anchor Graph Learning for Scalable Multi-View Clustering.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same journal

Beyond Fidelity: Diverse Image Synthesis via Retrieval-Augmented Diffusion.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
See all related articles

Related Experiment Video

Updated: Jan 6, 2026

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

1.2K

An Explanation Method Based on Interpretable Linear Model With Four Key Characteristics.

Yuecan Yuan, Zhan Ao Huang, Peng Li

    IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
    |September 24, 2025
    PubMed
    Summary
    This summary is machine-generated.

    This study introduces a new method for explaining deep neural networks (DNNs) in visual tasks. It enhances interpretability by creating more robust and semantically meaningful saliency maps for better feature attribution analysis.

    More Related Videos

    Development of an Individual-Tree Basal Area Increment Model using a Linear Mixed-Effects Approach
    04:35

    Development of an Individual-Tree Basal Area Increment Model using a Linear Mixed-Effects Approach

    Published on: July 3, 2020

    3.7K
    Using Cholesky Decomposition to Explore Individual Differences in Longitudinal Relations between Reading Skills
    06:52

    Using Cholesky Decomposition to Explore Individual Differences in Longitudinal Relations between Reading Skills

    Published on: September 17, 2019

    6.7K

    Related Experiment Videos

    Last Updated: Jan 6, 2026

    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

    1.2K
    Development of an Individual-Tree Basal Area Increment Model using a Linear Mixed-Effects Approach
    04:35

    Development of an Individual-Tree Basal Area Increment Model using a Linear Mixed-Effects Approach

    Published on: July 3, 2020

    3.7K
    Using Cholesky Decomposition to Explore Individual Differences in Longitudinal Relations between Reading Skills
    06:52

    Using Cholesky Decomposition to Explore Individual Differences in Longitudinal Relations between Reading Skills

    Published on: September 17, 2019

    6.7K

    Area of Science:

    • Computer Science
    • Artificial Intelligence
    • Machine Learning

    Background:

    • Existing deep neural network (DNN) explanation methods often rely on linear relationships between outputs and inputs, leading to potential inaccuracies.
    • These methods can lack robustness, provide misleading explanations, and fail to offer feature attributions with identifiable semantics, especially when conflicting with human visual inspection.

    Purpose of the Study:

    • To propose four key characteristics (richness, adaptivity, exclusiveness, fairness) for evaluating DNN explanation methods.
    • To develop a novel, interpretable linear model-based explanation method that satisfies these characteristics.
    • To enhance the robustness and semantic interpretability of saliency maps in visual-related DNN tasks.

    Main Methods:

    • Formalized four key characteristics: richness, adaptivity, exclusiveness, and fairness.
    • Developed a novel explanation method based on an interpretable linear model.
    • Utilized Nonnegative Matrix Factorization (NMF) to extract exclusive semantic features.
    • Employed an information entropy model for adaptive feature determination and richness assessment.
    • Applied an approximate Shapley algorithm for fair weight assignment to generate saliency maps.

    Main Results:

    • The proposed method generates more convincing and robust explanations compared to state-of-the-art techniques across various datasets and DNNs.
    • Evaluated robustness using metrics like Average Drop (AD), Average Increase (AI), Deletions (Del), and Insertions (Ins).
    • Supplementary experiments confirmed the feasibility of feature attribution analysis and improved explanation quality.

    Conclusions:

    • The developed method, guided by richness, adaptivity, exclusiveness, and fairness, significantly enhances the interpretability and robustness of DNN explanations.
    • The approach provides reliable feature attribution, addressing limitations of existing linear relation-based methods.
    • This work offers a more trustworthy tool for analyzing and understanding DNN behavior in visual tasks.