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

Related Concept Videos

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.

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...

You might also read

Related Articles

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

Sort by

Same author

Adapting general representations of pretrained vision foundation models to seismic understanding.

Communications engineering·2026

Same author

A benchmark dataset and baseline methods for rock microstructure interpretation in SEM images.

Scientific data·2025

Same journal

In-situ enhancement of autotrophic nitrogen removal in coking wastewater using staged diatomite and pyrite strategy.

Communications engineering·2026

Same journal

Thermo-mechanical behavior and thermal regulation measures of subgrade layer in roads under stochastic periodic thermal disturbance.

Communications engineering·2026

Same journal

Network architecture follows coupling in multiphysics systems: single vs. multiple branches in DeepONet and S-DeepONet.

Communications engineering·2026

Same journal

A robust GaN p-FET with unconventional electron conduction.

Communications engineering·2026

Same journal

Mobile charges in MoS<sub>2</sub>/high-k oxide transistors: from abnormal instabilities to transient negative differential resistance.

Communications engineering·2026

Same journal

Bubble-raft inspired shape-assembly in flying robot swarm for uniform formation and obstacle traversal.

Communications engineering·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Jan 7, 2026

Author Spotlight: Three-Dimensional Cephalometric Landmark Annotation Demonstration on Human Cone Beam Computed Tomography Scans

Author Spotlight: Three-Dimensional Cephalometric Landmark Annotation Demonstration on Human Cone Beam Computed Tomography Scans

Published on: September 8, 2023

Memory-efficient full-volume inference for large-scale 3D dense prediction without performance degradation.

Jintao Li^1,2,3, Xinming Wu^4,5

¹State Key Laboratory of Ocean Sensing & Ocean College, Zhejiang University, Zhoushan, Zhejiang, China.

Communications Engineering

|January 3, 2026

Summary

This summary is machine-generated.

This study introduces a novel framework for efficient, large-volume 3D dense prediction in deep learning. The retraining-free approach optimizes inference for industrial applications, overcoming memory limitations without performance loss.

More Related Videos

High-resolution, High-speed, Three-dimensional Video Imaging with Digital Fringe Projection Techniques

High-resolution, High-speed, Three-dimensional Video Imaging with Digital Fringe Projection Techniques

Published on: December 3, 2013

Three-Dimensional Shape Modeling and Analysis of Brain Structures

Three-Dimensional Shape Modeling and Analysis of Brain Structures

Published on: November 14, 2019

Related Experiment Videos

Last Updated: Jan 7, 2026

Author Spotlight: Three-Dimensional Cephalometric Landmark Annotation Demonstration on Human Cone Beam Computed Tomography Scans

Author Spotlight: Three-Dimensional Cephalometric Landmark Annotation Demonstration on Human Cone Beam Computed Tomography Scans

Published on: September 8, 2023

High-resolution, High-speed, Three-dimensional Video Imaging with Digital Fringe Projection Techniques

High-resolution, High-speed, Three-dimensional Video Imaging with Digital Fringe Projection Techniques

Published on: December 3, 2013

Three-Dimensional Shape Modeling and Analysis of Brain Structures

Three-Dimensional Shape Modeling and Analysis of Brain Structures

Published on: November 14, 2019

Area of Science:

Computer Vision
Deep Learning
Scientific Computing

Background:

Large-volume 3D dense prediction is crucial for energy exploration and medical imaging.
Current deep learning models face memory and efficiency challenges with full-size volumetric data.
Existing solutions like tiling or compression often degrade accuracy or require retraining.

Purpose of the Study:

To develop a retraining-free framework for accurate and efficient whole-volume 3D dense prediction.
To overcome memory constraints and operator inefficiencies in deep learning inference.
To enable large-scale 3D model deployment in industrial domains.

Main Methods:

Integration of operator spatial tiling and fusion.
Normalization statistic aggregation for improved efficiency.
On-demand feature recomputation to reduce memory footprint and accelerate runtime.

Main Results:

The framework enables accurate, whole-volume inference on volumes exceeding 1024³ voxels.
Achieved 13x increase in volume size handling (1024³ vs 448³) on seismic data with no performance loss.
Demonstrated 7.5-second inference for a 1024³ volume using 27.6 GB memory.

Conclusions:

The proposed framework offers a generalizable and engineering-friendly solution for large-scale 3D deep learning inference.
Preserves global structural coherence, suitable for tasks incompatible with patch-wise processing.
Significantly enhances the feasibility of deploying 3D models in demanding industrial applications.