Jove
Visualize
Contact Us

Related Concept Videos

Sample Handling01:02

Sample Handling

100
Transportation of samples from the collection point to the laboratory, as well as storage and preservation techniques, are crucial for maintaining sample integrity and ensuring accurate and reliable test results.
Samples should be transported carefully from collection points to the laboratory. They should be properly sealed and clearly labeled to prevent cross-contamination. To preserve the sample integrity, optimal temperature conditions during transport are essential. This could involve using...
100
Quantifying and Rejecting Outliers: The Grubbs Test01:02

Quantifying and Rejecting Outliers: The Grubbs Test

1.6K
Sometimes, a data set can have a recorded numerical observation that greatly  deviates from the rest of the data. Assuming that the data is normally distributed, a statistical method called the Grubbs test can be used to determine whether the observation is truly an outlier.  To perform a two-tailed Grubbs test, first, calculate the absolute difference between the outlier and the mean. Then, calculate the ratio between this difference and the standard deviation of the sample. This...
1.6K
Positive, Negative, and Zero Work00:58

Positive, Negative, and Zero Work

18.8K
Work is done on an object when energy is transferred to the object. In other words, work is done when a force acts on a body that undergoes a displacement from one position to another. By definition, the work done by a force is the integral of the force with respect to the displacement along its path. Forces can vary as a function of position, and displacements can occur along various paths between two points. The magnitude of a force multiplied by the cosine of the angle that the force makes...
18.8K
Downsampling01:20

Downsampling

154
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...
154
Difference from Background: Limit of Detection01:05

Difference from Background: Limit of Detection

6.3K
The limit of detection (LOD) is the smallest amount of analyte that can be distinguished from the background noise. The LOD value corresponds to the concentration at which the analyte signal is three times larger than the standard deviation of the blank signal. Below this value, the analyte signal cannot be differentiated from the background noise. It is calculated by dividing the calibration slope by 3 times the standard deviation of the blank signals.
The LOD indicates the presence or absence...
6.3K
Sampling Theorem01:15

Sampling Theorem

328
In signal processing, the analysis of continuous-time signals, denoted as x(t), often involves sampling techniques to convert these signals into discrete-time signals. This process is essential for digital representation and manipulation. A critical component in sampling is the train of impulses, characterized by the sampling interval and the sampling frequency. The relationship between these parameters and the original signal's properties dictates the success of the sampling process.
328

You might also read

Related Articles

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

Sort by
Same author

Rational design of next-generation vaccine adjuvants: From molecular mechanisms to hybrid delivery platforms.

Human vaccines & immunotherapeutics·2026
Same author

Broadening the horizon: The promise of PROTACs in non-malignant disorders.

European journal of medicinal chemistry·2026
Same author

MERBench: A Unified Evaluation Benchmark for Multimodal Emotion Recognition.

IEEE transactions on pattern analysis and machine intelligence·2026
Same author

SpeechPalette: A Comprehensive Speech Editing Method for Text-Based Speech Editing, One-Shot TTS and Attributes Editing.

IEEE transactions on pattern analysis and machine intelligence·2025
Same author

IRNet: Iterative Refinement Network for Noisy Partial Label Learning.

IEEE transactions on pattern analysis and machine intelligence·2025
Same author

Source-Free Object Detection With Detection Transformer.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2025
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 Experiment Video

Updated: Jun 25, 2025

A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports
07:35

A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports

Published on: October 13, 2023

1.6K

M2ixKG: Mixing for harder negative samples in knowledge graph.

Feihu Che1, Jianhua Tao2

  • 1Department of Automation, Tsinghua University, Beijing, China.

Neural Networks : the Official Journal of the International Neural Network Society
|May 28, 2024
PubMed
Summary

This study introduces M²ixKG, a novel mixing strategy for knowledge graph embeddings (KGE). M²ixKG generates higher-quality negative samples, significantly improving KGE model performance and robustness.

Keywords:
Hard negativesKnowledge graphMixing operationNegative sampling

More Related Videos

A Strategy for Sensitive, Large Scale Quantitative Metabolomics
14:18

A Strategy for Sensitive, Large Scale Quantitative Metabolomics

Published on: May 27, 2014

20.9K
Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction
06:19

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

Published on: August 16, 2024

418

Related Experiment Videos

Last Updated: Jun 25, 2025

A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports
07:35

A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports

Published on: October 13, 2023

1.6K
A Strategy for Sensitive, Large Scale Quantitative Metabolomics
14:18

A Strategy for Sensitive, Large Scale Quantitative Metabolomics

Published on: May 27, 2014

20.9K
Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction
06:19

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

Published on: August 16, 2024

418

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Data Science

Background:

  • Knowledge Graph Embedding (KGE) maps entities and relations to low-dimensional vectors.
  • Effective KGE relies on distinguishing positive from negative triplets.
  • Current KGE methods struggle to generate high-quality negative samples, hindering model performance.

Purpose of the Study:

  • To address the limitations of existing negative sampling strategies in KGE.
  • To introduce a novel mixing strategy, M²ixKG, for generating harder negative samples.
  • To enhance the robustness and generalization capabilities of KGE models.

Main Methods:

  • M²ixKG employs a mixing strategy for generating negative samples in knowledge graphs.
  • It involves mixing heads and tails within triplets sharing the same relation.
  • It also mixes high-scoring negative samples to create more challenging ones.

Main Results:

  • Experiments on three datasets demonstrate M²ixKG's superior performance.
  • M²ixKG significantly outperforms previous negative sampling algorithms.
  • The strategy enhances the robustness and generalization of entity embeddings.

Conclusions:

  • M²ixKG offers a significant advancement in negative sampling for KGE.
  • The proposed mixing strategy effectively generates harder negatives, improving model performance.
  • This approach provides a more robust and generalizable solution for knowledge graph embedding.