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 Videos

Carbon price forecasting based on modified ensemble empirical mode decomposition and long short-term memory optimized

Shaomei Yang1, Dongjiu Chen1, Shengli Li2

  • 1Department of Economics and Management, North China Electric Power University, Baoding, China.

The Science of the Total Environment
|February 21, 2020
PubMed
Summary

Related Concept Videos

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

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

235
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...
235

You might also read

Related Articles

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

Sort by
Same author

Three-Month Functional Exercise Reduces Upper Limb Lymphedema After Breast Cancer Surgery: A Prospective Randomized Controlled Trial.

The Tohoku journal of experimental medicine·2025
Same author

Alpha-linolenic acid reshapes the gastrointestinal ecology to enhance immune function in dairy cows: insights from microbiome and metabolome profiling.

Frontiers in microbiology·2025
Same author

Analysis of risk factors for recurrence of Budd-Chiari syndrome: A retrospective study with zero-inflated model.

Medicine·2025
Same author

Mendelian Randomization Unlocks Stroke Therapeutics: Dioscin Inhibits CD27-Driven Neuroinflammation via Gut Microbiota Modulation.

Molecular neurobiology·2025
Same author

Anti-BCMA/CD19 CAR T cell therapy in patients with refractory generalized myasthenia gravis: a single-arm, phase 1 trial.

EClinicalMedicine·2025
Same author

A mouse model of bilateral acute inner-ear (labyrinthine) injury with vestibular involvement reveals functional, behavioral, and histological correlates of vestibular compensation.

Neuroscience research·2025

Accurate carbon price forecasting is challenging. A novel hybrid model using modified ensemble empirical mode decomposition (MEEMD) and improved whale optimization algorithm (IWOA)-optimized long short-term memory (LSTM) significantly enhances prediction accuracy.

Area of Science:

  • Environmental Economics
  • Computational Finance
  • Time Series Analysis

Background:

  • Accurate carbon price prediction is crucial for industry and government policy-making.
  • Carbon prices exhibit complex nonlinear and non-stationary characteristics, posing forecasting challenges.

Purpose of the Study:

  • To develop a novel hybrid model for accurate carbon price forecasting.
  • To address the nonlinear and non-stationary nature of carbon price data.

Main Methods:

  • Modified Ensemble Empirical Mode Decomposition (MEEMD) for data decomposition.
  • Long Short-Term Memory (LSTM) neural network for prediction.
  • Improved Whale Optimization Algorithm (IWOA) for LSTM optimization.
  • Random Forest for input variable selection.
Keywords:
Carbon price forecastingImproved whale optimization algorithmLong short-term memoryModified ensemble empirical mode decomposition

Related Experiment Videos

Main Results:

  • The proposed MEEMD-LSTM-IWOA model demonstrated superior prediction performance compared to 11 benchmark models.
  • Decomposition of carbon price data effectively improved prediction accuracy.
  • The IWOA-optimized LSTM model proved highly suitable for time series forecasting.

Conclusions:

  • The hybrid model offers a novel and effective tool for carbon price forecasting.
  • Decomposition techniques enhance the accuracy of carbon price prediction models.
  • Optimized LSTM networks provide robust solutions for complex time series data.