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

Downsampling01:20

Downsampling

264
When considering a sampled sequence with zero values between sampling instants, one can replace it by taking every N-th value of the sequence. At these integer multiples of N, the original and sampled sequences coincide. This process, known as decimation, involves extracting every N-th sample from a sequence, thereby creating a more efficient sequence.
The Fourier transform of the decimated sequence reveals a combination of scaled and shifted versions of the original spectrum. This...
264
Discrete-Time Fourier Series01:20

Discrete-Time Fourier Series

373
The Discrete-Time Fourier Series (DTFS) is a fundamental concept in signal processing, serving as the discrete-time counterpart to the continuous-time Fourier series. It allows for the representation and analysis of discrete-time periodic signals in terms of their frequency components. Unlike its continuous counterpart, which utilizes integrals, the calculation of DTFS expansion coefficients involves summations due to the discrete nature of the signal.
For a discrete-time periodic signal x[n]...
373
Linear Approximation in Time Domain01:21

Linear Approximation in Time Domain

129
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,...
129
Difference Equation Solution using z-Transform01:24

Difference Equation Solution using z-Transform

381
The z-transform is a powerful tool for analyzing practical discrete-time systems, often represented by linear difference equations. Solving a higher-order difference equation requires knowledge of the input signal and the initial conditions up to one term less than the order of the equation.
The z-transform facilitates handling delayed signals by shifting the signal in the z-domain, which corresponds to delaying the signal in the time domain, and advancing signals by similarly shifting in the...
381
Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving01:29

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

103
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...
103
Prediction Intervals01:03

Prediction Intervals

2.3K
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. 
2.3K

You might also read

Related Articles

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

Sort by
Same author

Ribonucleic acid binding protein-mediated regulation of luteinizing hormone receptor expression in granulosa cells: relationship to sterol metabolism.

Molecular endocrinology (Baltimore, Md.)·2007
Same author

Psychological stress-induced oxidative stress as a model of sub-healthy condition and the effect of TCM.

Evidence-based complementary and alternative medicine : eCAM·2007
Same author

Overexpression of OsCOIN, a putative cold inducible zinc finger protein, increased tolerance to chilling, salt and drought, and enhanced proline level in rice.

Planta·2007
Same author

Edge-based scoring and searching method for identifying condition-responsive protein-protein interaction sub-network.

Bioinformatics (Oxford, England)·2007
Same author

[The value of long-term postoperative follow-up after curative resection of lung cancer and common problems associated with it].

Nihon Geka Gakkai zasshi·2007
Same author

Identification of a type III thioesterase reveals the function of an operon crucial for Mtb virulence.

Chemistry & biology·2007

Related Experiment Video

Updated: Sep 17, 2025

A Method of Trigonometric Modelling of Seasonal Variation Demonstrated with Multiple Sclerosis Relapse Data
10:46

A Method of Trigonometric Modelling of Seasonal Variation Demonstrated with Multiple Sclerosis Relapse Data

Published on: December 9, 2015

10.8K

A novel LLM time series forecasting method based on integer-decimal decomposition.

Lei Wang1, Keyao Dong2, Xiaoyong Zhao1

  • 1School of Management Science and Engineering, Beijing Information Science and Technology University, Beijing, 100192, China.

Scientific Reports
|July 2, 2025
PubMed
Summary
This summary is machine-generated.

This study introduces IDDLLM, a novel framework for time series forecasting using large language models (LLMs). IDDLLM enhances LLM capabilities for time series data, achieving superior long-term forecasting performance.

Keywords:
Artificial intelligenceDeep learningLarge Language modelsTime series forecasting

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

3.4K
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

6.4K

Related Experiment Videos

Last Updated: Sep 17, 2025

A Method of Trigonometric Modelling of Seasonal Variation Demonstrated with Multiple Sclerosis Relapse Data
10:46

A Method of Trigonometric Modelling of Seasonal Variation Demonstrated with Multiple Sclerosis Relapse Data

Published on: December 9, 2015

10.8K
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

3.4K
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

6.4K

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Data Science

Background:

  • Traditional deep learning models struggle with generalization in time series forecasting due to domain specificity.
  • Large language models (LLMs) show promise for time series forecasting, but adapting sequential data to LLM architectures is challenging.
  • Existing methods face difficulties in effectively bridging the gap between time series data and the capabilities of LLMs.

Purpose of the Study:

  • To propose an innovative framework, IDDLLM (Integer-Decimal Decomposition and cross-modal fine-tuning for LLMs), to enhance time series forecasting.
  • To address the limitations of current LLM adaptations for time series data.
  • To improve the generalization and performance of LLMs in time series forecasting tasks.

Main Methods:

  • Developed the Splitting time series Data Cross-attention (SDC) module to decompose time series into integer and decimal components for improved pattern recognition.
  • Implemented a dual cross-attention mechanism to align time series and text modalities, facilitating better LLM integration.
  • Employed a cross-modal fine-tuning strategy to adapt LLMs for time series forecasting.

Main Results:

  • The proposed IDDLLM framework significantly outperformed state-of-the-art models in long-term time series forecasting, achieving top rankings in 34 out of 46 experimental settings.
  • IDDLLM demonstrated robust and competitive performance in few-shot and zero-shot time series forecasting scenarios.
  • The SDC module and dual cross-attention mechanism proved effective in enhancing the model's understanding of time series patterns and cross-modal alignment.

Conclusions:

  • IDDLLM represents a significant advancement in leveraging LLMs for time series forecasting, overcoming previous adaptation challenges.
  • The framework's ability to handle complex time series patterns and its strong performance in various settings highlight its potential for real-world applications.
  • IDDLLM offers a promising direction for future research in cross-modal learning and advanced time series analysis.