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

Convolution: Math, Graphics, and Discrete Signals01:24

Convolution: Math, Graphics, and Discrete Signals

361
In any LTI (Linear Time-Invariant) system, the convolution of two signals is denoted using a convolution operator, assuming all initial conditions are zero. The convolution integral can be divided into two parts: the zero-input or natural response and the zero-state or forced response, with t0 indicating the initial time.
To simplify the convolution integral, it is assumed that both the input signal and impulse response are zero for negative time values. The graphical convolution process...
361
Force Classification01:22

Force Classification

1.4K
Forces play a crucial role in the study of physics and engineering. They are essential in describing the motion, behavior, and equilibrium of objects in the physical world. Forces can be classified based on their origin, type, and direction of action.
Contact and non-contact forces are two of the most widely used categories of forces. As the name suggests, contact forces require physical contact between two objects to act upon each other. Examples of contact forces include frictional,...
1.4K
Convolution Properties II01:17

Convolution Properties II

271
The important convolution properties include width, area, differentiation, and integration properties.
The width property indicates that if the durations of input signals are T1 and T2, then the width of the output response equals the sum of both durations, irrespective of the shapes of the two functions. For instance, convolving two rectangular pulses with durations of 2 seconds and 1 second results in a function with a width of 3 seconds.
The area property asserts that the area under the...
271
Convolution Properties I01:20

Convolution Properties I

222
Convolution computations can be simplified by utilizing their inherent properties.
The commutative property reveals that the input and the impulse response of an LTI (Linear Time-Invariant) system can be interchanged without affecting the output:
222
Classification of Systems-II01:31

Classification of Systems-II

221
Continuous-time systems have continuous input and output signals, with time measured continuously. These systems are generally defined by differential or algebraic equations. For instance, in an RC circuit, the relationship between input and output voltage is expressed through a differential equation derived from Ohm's law and the capacitor relation,
221
Deconvolution01:20

Deconvolution

239
Deconvolution, also known as inverse filtering, is the process of extracting the impulse response from known input and output signals. This technique is vital in scenarios where the system's characteristics are unknown, and they must be inferred from the observable signals.
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...
239

You might also read

Related Articles

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

Sort by
Same author

Corylin promotes healthy aging via RAGA-mTOR suppression and sex-dependent activation of SIRT3.

Nature communications·2026
Same author

Impact of deubiquitination of Epstein-Barr virus Rta and Zta on lytic development.

Microbiology spectrum·2026
Same author

Refining deep learning segmentation in gallium-68-prostate-specific membrane antigen-11 positron emission tomography: evaluation of small lesion filtering and intersection-over-union thresholds.

Nuclear medicine communications·2026
Same author

Magnolol suppresses TKI-resistant EGFR-mutant lung cancer by inhibiting EGFR and AXL-cMyc.

European journal of pharmacology·2026
Same author

Emotional Distress and Attitudinal Changes in Nursing Students During the Psychiatric Practicum: Impact of Patient Aggression.

Journal of psychiatric and mental health nursing·2026
Same author

Corylin attenuates oral squamous cell carcinoma progression through c-Myc inhibition.

Journal of dental sciences·2025
Same journal

Composite fault-tolerant predictive control strategy for PMSM demagnetization faults.

ISA transactions·2026
Same journal

Bias-compensated Q-learning for optimal tracking control under denial-of-service attacks.

ISA transactions·2026
Same journal

Motion prediction for leader manipulator of teleoperation system with large time delay based on inverse optimal control.

ISA transactions·2026
Same journal

Neural network parameter identification-based prescribed-time adaptive control for morphing glide aircraft.

ISA transactions·2026
Same journal

Nonlinear system-guided continuous-time generalization for cross-aircraft engine state monitoring.

ISA transactions·2026
Same journal

Predefined-time distributed optimal formation control for constrained UAV-UGV systems.

ISA transactions·2026
See all related articles

Related Experiment Video

Updated: Aug 30, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

616

MiniNet: Dense squeeze with depthwise separable convolutions for image classification in resource-constrained

Fan-Hsun Tseng1, Kuo-Hui Yeh2, Fan-Yi Kao3

  • 1Department of Computer Science and Information Engineering, National Cheng Kung University, Tainan, Taiwan.

ISA Transactions
|August 29, 2022
PubMed
Summary
This summary is machine-generated.

A new AI model, MiniNet, significantly reduces computation and training time while maintaining high accuracy. This efficient deep learning approach excels on smaller datasets, outperforming existing models.

Keywords:
Convolutional neural networkDeep learningDenseNetDepthwise separable convolutionMobileNetSENet

More Related Videos

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

486
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.9K

Related Experiment Videos

Last Updated: Aug 30, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

616
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

486
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.9K

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Deep Learning

Background:

  • Artificial intelligence (AI) development faces challenges with computational demands and training time on limited hardware.
  • Optimizing AI models for efficiency without sacrificing accuracy is crucial for widespread autonomous application deployment.

Purpose of the Study:

  • To propose MiniNet, a novel deep learning model based on MobileNet architecture.
  • To enhance computational efficiency and reduce training time for AI applications.

Main Methods:

  • Developed MiniNet using depthwise separable convolutions, dense connections, and Squeeze-and-Excitation operations.
  • Implemented and experimented with the MiniNet model using Keras.
  • Compared MiniNet against DenseNet, MobileNet, and SE-Inception-Resnet-v1 on datasets of varying sizes.

Main Results:

  • MiniNet demonstrated a significant reduction in the number of parameters and training time.
  • The model achieved superior performance in terms of parameter count, training duration, and accuracy, particularly on small datasets.
  • Experimental results validated MiniNet's efficiency compared to established models.

Conclusions:

  • MiniNet offers an efficient deep learning solution for resource-constrained environments.
  • The proposed model provides a favorable trade-off between computational cost, training efficiency, and predictive accuracy.
  • MiniNet presents a promising advancement for AI autonomous applications requiring optimized performance.