Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Videos

Visual prediction method based on time series-driven LSTM model.

Huxidan Jumahong^1,2, Yongjie Wang³, Abuduwaili Aili¹

¹School of Network Security and Information Technology, YiLi Normal University, Yining, 835000, China.

Scientific Reports

|October 31, 2025

Summary

Related Concept Videos

End Point Prediction: Gran Plot

End Point Prediction: Gran Plot

A Gran plot is used to predict the equivalence volume or endpoint of a potentiometric or acid-base titration without reaching the endpoint. Typically, titration data is collected as a function of the titrant's volume up to a point less than the equivalence volume and then transformed into a linear format. The straight line is extended to the x-axis, indicating the necessary titrant volume to achieve the equivalence point.
For potentiometric titration, the Gran plot is created by plotting...

Prediction Intervals

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.

You might also read

Related Articles

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

Sort by

Same author

Reliability and reproducibility of the modified thoracolumbar injury classification and severity score and the thoracolumbar AO spine injury score for guiding surgical decision-making in thoracolumbar fractures.

Frontiers in surgery·2026

Same author

Exploring healthcare professionals' views on integrative Chinese-Western medicine in the nutritional management of cancer patients: a qualitative study.

Frontiers in nutrition·2026

Same author

Limb cold therapy for preventing paclitaxel-induced peripheral neuropathy in breast cancer patients: a randomized controlled study.

World journal of surgical oncology·2026

Same author

The impact of early integrated palliative care on symptom burden and quality of life in patients with advanced breast cancer.

Frontiers in oncology·2026

Same author

Echinococcus multilocularis serine protease inhibitor 1 (EmSPI-1): a highly effective serodiagnostic antigen for alveolar echinococcosis.

Clinica chimica acta; international journal of clinical chemistry·2026

Same author

Network pharmacology and Mendelian randomization analysis to unravel the mechanism of Qingwen Baidu Decoction in sepsis treatment.

Medicine·2026

This study introduces a new visual prediction framework integrating time series forecasting and image processing. The novel method effectively analyzes spatio-temporal features for accurate image prediction, outperforming existing approaches.

Area of Science:

Computer Vision
Artificial Intelligence
Data Science

Background:

Traditional image processing and time series prediction studies often operate in isolation.
Existing algorithms face limitations in accurately inferring temporal dynamics within image sequences.

Purpose of the Study:

To propose a novel visual prediction framework that integrates time series forecasting models for enhanced image temporal inference.
To leverage spatio-temporal features for predicting single or multi-frame images.

Main Methods:

Utilized a Vision Transformer (ViT) for image feature extraction via masked image reconstruction.
Developed a time series construction module to adapt features for Long Short-Term Memory (LSTM) networks.
Employed LSTM for time series prediction and transformed results back into predicted images.

Keywords:

Image processing Masked autoencoders Time series forecasting Vision transformer Visual prediction

Related Experiment Videos

Main Results:

Experimental validation on three cloud image datasets demonstrated the framework's effectiveness.
The proposed method showed significant improvements in image prediction performance.
Results indicate the feasibility of integrating time series models for visual prediction tasks.

Conclusions:

The novel framework successfully bridges the gap between time series forecasting and image processing.
The approach offers a viable solution for complex image temporal inference problems.
This research highlights the potential of spatio-temporal feature analysis for advanced visual prediction.