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

One-Compartment Open Model: Wagner-Nelson and Loo Riegelman Method for ka Estimation01:24

One-Compartment Open Model: Wagner-Nelson and Loo Riegelman Method for ka Estimation

890
This lesson introduces two critical methods in pharmacokinetics, the Wagner-Nelson and Loo-Riegelman methods, used for estimating the absorption rate constant (ka) for drugs administered via non-intravenous routes. The Wagner-Nelson method relates ka to the plasma concentration derived from the slope of a semilog percent unabsorbed time plot. However, it is limited to drugs with one-compartment kinetics and can be impacted by factors like gastrointestinal motility or enzymatic degradation.
On...
890
Estimation of k and VD of Aminoglycosides01:20

Estimation of k and VD of Aminoglycosides

76
Aminoglycosides are a class of antibiotics used to treat various bacterial infections. Clinicians must determine the elimination rate constant (k) and volume of distribution (VD) to optimize therapeutic efficacy and minimize toxicity. The k value represents the rate at which the drug is removed from the body, and the VD reflects the degree to which the drug distributes into body tissues. Accurately estimating these parameters allows healthcare professionals to tailor drug dosing to individual...
76
Deconvolution01:20

Deconvolution

402
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...
402

You might also read

Related Articles

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

Sort by
Same author

Frequency selective binary metasurface with two high-selectivity transmission passbands and wideband RCS reduction.

Optics express·2025
Same author

Advancing Stepped-Waveform Radar Jamming Techniques for Robust False-Target Generation against LFM-CFAR Systems.

Sensors (Basel, Switzerland)·2023
Same author

The use of intravenous amiodarone in patients with atrial fibrillation and Wolff-Parkinson-White syndrome.

Pacing and clinical electrophysiology : PACE·2020
Same author

Assessment of Quality of Life of Free Anterolateral Thigh Flap for Reconstruction of Tissue Defects of Total or Near-Total Glossectomy.

Journal of oncology·2020
Same author

A hybrid and scalable brain-inspired robotic platform.

Scientific reports·2020
Same author

<i>AUREA</i> maintains the balance between chlorophyll synthesis and adventitious root formation in tomato.

Horticulture research·2020

Related Experiment Video

Updated: Nov 12, 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

764

Multi-DOA estimation based on the KR image tensor and improved estimation network.

Ye Yuan1, Shuang Wu2, Yong Yang3

  • 1State Key Laboratory of Complex Electromagnetic Environment Elects on Electronics and Information System, National University of Defense Technology, Changsha, 410073, China.

Scientific Reports
|March 19, 2021
PubMed
Summary

This study introduces an improved deep neural network for multi-direction-of-arrival (DOA) estimation, enhancing accuracy and resolution in challenging environments. The novel CurriculumNet training scheme improves generalization and performance, even with limited data.

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

641

Related Experiment Videos

Last Updated: Nov 12, 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

764
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

641

Area of Science:

  • Signal Processing
  • Machine Learning
  • Array Signal Processing

Background:

  • Deep neural networks (DNNs) excel at single Direction-of-Arrival (DOA) estimation.
  • Existing DNNs struggle with the complexities of multi-DOA estimation problems.
  • Advanced antenna array processing is crucial for accurate spatial signal localization.

Purpose of the Study:

  • To develop a novel deep neural network architecture for accurate multi-DOA estimation.
  • To enhance the degree of freedom in antenna arrays using the Khatri-Rao product.
  • To improve the generalization and accuracy of DOA estimation networks through innovative training strategies.

Main Methods:

  • Utilized the Khatri-Rao product to augment antenna array degrees of freedom.
  • Developed an improved estimation network to process covariance matrix image tensors.
  • Implemented a CurriculumNet training scheme incorporating curriculum learning and partial label strategies.

Main Results:

  • Achieved high-resolution DOA estimation, distinguishing signals with an angular difference of [Formula: see text].
  • Demonstrated a root mean square estimation error below [Formula: see text] at a signal-to-noise ratio of [Formula: see text].
  • Accurate DOA estimation was achieved using as few as 8 snapshots, outperforming prior DNN-based methods.

Conclusions:

  • The proposed network and CurriculumNet training scheme significantly improve multi-DOA estimation accuracy and generalization.
  • The method effectively handles hostile environments and limited snapshots, outperforming existing DNN approaches.
  • This work offers a robust solution for high-resolution multi-DOA estimation in complex scenarios.