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 Experiment Video

Updated: Dec 15, 2025

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

1.1K

Robustness testing framework for RUL prediction Deep LSTM networks.

Mohamed Sayah1, Djillali Guebli1, Zeina Al Masry2

  • 1University Oran1, Laboratory LITIO, FSEA Faculty, Computer Science Department, Oran Algeria, Algeria.

ISA Transactions
|July 11, 2020
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

Long-term Potentiation01:35

Long-term Potentiation

57.7K
Long-term potentiation, or LTP, is one of the ways by which synaptic plasticity—changes in the strength of chemical synapses—can occur in the brain. LTP is the process of synaptic strengthening that occurs over time between pre- and postsynaptic neuronal connections. The synaptic strengthening of LTP works in opposition to the synaptic weakening of long-term depression (LTD) and together are the main mechanisms that underlie learning and memory.
57.7K

You might also read

Related Articles

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

Sort by
Same author

Modernizing the Staging of Parkinson Disease Using Digital Health Technology.

Journal of medical Internet research·2025
Same author

A Comprehensive Multifunctional Approach for Measuring Parkinson's Disease Severity.

Applied clinical informatics·2024
Same author

A new methodology to predict the oncotype scores based on clinico-pathological data with similar tumor profiles.

Breast cancer research and treatment·2023
Same author

Confounding Effects on the Performance of Machine Learning Analysis of Static Functional Connectivity Computed from rs-fMRI Multi-site Data.

Neuroinformatics·2023
Same author

An Explainable AI Approach for Breast Cancer Metastasis Prediction Based on Clinicopathological Data.

IEEE transactions on bio-medical engineering·2023
Same author

Metabolic syndrome screening in adolescents: New scores AI_METS based on artificial intelligence techniques.

Nutrition, metabolism, and cardiovascular diseases : NMCD·2022

This study introduces a framework to test the robustness of Deep Long Short Term Memory (LSTM) models for predicting remaining useful life (RUL). The proposed method ensures stable, high-quality RUL predictions, even with model variations.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Predictive Maintenance

Background:

  • Accurate remaining useful life (RUL) prediction is vital for system health monitoring and maintenance scheduling.
  • Deep Long Short Term Memory (LSTM) networks are commonly used for RUL prediction but their robustness requires thorough evaluation.
  • Assessing model performance solely on test datasets may not fully capture reliability under varying conditions.

Purpose of the Study:

  • To propose and validate a novel framework for assessing the robustness and quality of Deep LSTM models in RUL prediction.
  • To investigate the impact of induced stresses on Deep LSTM model performance for RUL estimation.
  • To determine the stability and test accuracy of Deep LSTM models in proximity to the trained model.

Main Methods:

Keywords:
-RobustnessFuzzy Deep LSTM networkLSTM modelMutant modelRUL predictionRobustness

Related Experiment Videos

Last Updated: Dec 15, 2025

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

1.1K
  • Development of a framework to test the robustness of Deep LSTM architectures for RUL prediction.
  • Application of stress functions to evaluate the resiliency of Deep LSTM networks.
  • Comparative analysis of original Deep LSTM models against mutant, fuzzed Deep LSTM networks.
  • Utilizing φ-stress operators to assess model stability and data independence.

Main Results:

  • The proposed framework effectively evaluates the robustness of Deep LSTM models for RUL prediction.
  • Stress testing revealed the impact of variations on model performance, highlighting areas for improvement.
  • Mutant fuzzed Deep LSTM networks showed performance variations compared to the original model, aiding quality assessment.
  • φ-stress operators demonstrated the potential to create stable and data-independent Deep LSTM models.

Conclusions:

  • The developed framework enhances confidence in Deep LSTM models for RUL prediction by ensuring better quality and reliability.
  • Stable and data-independent Deep LSTM models for RUL prediction can be achieved using φ-stress operators.
  • The framework's validation on the C-MAPSS dataset confirms its efficacy in real-world RUL prediction scenarios.