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

The Y-to-Y Circuit01:19

The Y-to-Y Circuit

521
In a balanced four-wire wye-to-wye system, the arrangement involves wye-connected sinusoidal voltage sources and loads, connected through a neutral wire that links the neutral nodes of the source and load. The load impedance is connected across each phase of the load. The wye-connected source can be connected to the wye-connected load in four-wire and three-wire arrangements. A three-phase system is considered balanced when the load on each phase is equal, leading to uniform current flow and...
521
IR Frequency Region: X–H Stretching01:24

IR Frequency Region: X–H Stretching

1.1K
In IR spectroscopy, signals produced by the X−H bonds (such as C−H, O−H, or N−H) can be observed in the frequency range of  2700–4000 cm–1. The C−H stretching vibration forms sharp bands in the region 2850–3000 cm–1. The presence of the O−H stretching vibration leads to the forming of an absorption band in the frequency range 3650–3200 cm−1. At the same time, N−H stretching can be confirmed by absorption bands in...
1.1K
IR Spectrum Peak Splitting: Symmetric vs Asymmetric Vibrations01:08

IR Spectrum Peak Splitting: Symmetric vs Asymmetric Vibrations

1.3K
Identical bonds within a polyatomic group can stretch symmetrically (in-phase) or asymmetrically (out-of-phase). Similar to hydrogen bonding, these vibrations also influence the shape of the IR peak. Generally, asymmetric stretching frequencies are higher than symmetric stretching frequencies. For example, primary amines exhibit two distinct IR peaks between 3300–3500 cm−1 corresponding to the symmetric and asymmetric N-H stretching, while secondary amines exhibit a single...
1.3K
Uniform Depth Channel Flow01:27

Uniform Depth Channel Flow

199
Uniform depth channel flow keeps fluid depth consistent along channels such as irrigation canals. In natural channels, such as rivers, approximate uniform flow is often assumed. This condition occurs when the channel’s bottom slope matches the energy slope, balancing potential energy lost from gravity with head loss due to shear stress. This balance prevents depth changes along the channel length, resulting in a steady, uniform flow.Uniform flow in open channels with a constant cross-section...
199
Classification of Signals01:30

Classification of Signals

1.0K
In signal processing, signals are classified based on various characteristics: continuous-time versus discrete-time, periodic versus aperiodic, analog versus digital, and causal versus noncausal. Each category highlights distinct properties crucial for understanding and manipulating signals.
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
1.0K
Downsampling01:20

Downsampling

297
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...
297

You might also read

Related Articles

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

Sort by
Same author

Support for the Vulnerability Management Process Using Conversion CVSS Base Score 2.0 to 3.x.

Sensors (Basel, Switzerland)·2023
Same author

Cost-Efficient Coverage of Wastewater Networks by IoT Monitoring Devices.

Sensors (Basel, Switzerland)·2022
Same author

Machine Learning Algorithms for Prediction of the Quality of Transmission in Optical Networks.

Entropy (Basel, Switzerland)·2020
Same author

Infrared Laser Application to Wood Cutting.

Materials (Basel, Switzerland)·2020

Related Experiment Video

Updated: Oct 12, 2025

Transmission of Multiple Signals through an Optical Fiber Using Wavefront Shaping
09:43

Transmission of Multiple Signals through an Optical Fiber Using Wavefront Shaping

Published on: March 20, 2017

10.0K

Learning to Classify DWDM Optical Channels from Tiny and Imbalanced Data.

Paweł Cichosz1, Stanisław Kozdrowski1, Sławomir Sujecki2,3

  • 1Computer Science Institute, Warsaw University of Technology, Nowowiejska 15/19, 00-665 Warsaw, Poland.

Entropy (Basel, Switzerland)
|November 27, 2021
PubMed
Summary

Machine learning for optical network quality faces challenges with small, imbalanced datasets. One-class classification significantly outperforms binary methods, offering more practical models for assessing transmission quality.

Keywords:
imbalanced datamachine learningone-class classificationoptical networks

More Related Videos

Quasi-light Storage for Optical Data Packets
07:45

Quasi-light Storage for Optical Data Packets

Published on: February 6, 2014

11.0K
Design and Fabrication of an Optical Fiber Made of Water
08:06

Design and Fabrication of an Optical Fiber Made of Water

Published on: November 8, 2018

8.3K

Related Experiment Videos

Last Updated: Oct 12, 2025

Transmission of Multiple Signals through an Optical Fiber Using Wavefront Shaping
09:43

Transmission of Multiple Signals through an Optical Fiber Using Wavefront Shaping

Published on: March 20, 2017

10.0K
Quasi-light Storage for Optical Data Packets
07:45

Quasi-light Storage for Optical Data Packets

Published on: February 6, 2014

11.0K
Design and Fabrication of an Optical Fiber Made of Water
08:06

Design and Fabrication of an Optical Fiber Made of Water

Published on: November 8, 2018

8.3K

Area of Science:

  • Telecommunications Engineering
  • Machine Learning Applications
  • Network Performance Monitoring

Background:

  • Optical networks, particularly Dense Wavelength Division Multiplexing (DWDM), present challenges in assessing transmission quality due to small and imbalanced datasets.
  • Traditional binary classification methods struggle with limited data, necessitating imbalance compensation techniques.

Purpose of the Study:

  • To evaluate the effectiveness of one-class classification versus binary classification with imbalance handling for optical network transmission quality assessment.
  • To compare the performance of specific algorithms within each classification approach using a real-world dataset.

Main Methods:

  • Utilized a real-world imbalanced dataset from a DWDM network operator.
  • Implemented binary classification with Random Forest and Extreme Gradient Boosting, combined with instance weighting and synthetic minority class instance generation.
  • Compared these with one-class classification algorithms: One-class SVM, One-class Naive Bayes, Isolation Forest, and Maximum Entropy Modeling.

Main Results:

  • One-class classification algorithms demonstrated superior performance compared to binary classification methods.
  • Specifically, one-class approaches achieved higher classification precision, yielding more practical models.
  • The study confirmed the challenges posed by small and imbalanced datasets in this domain.

Conclusions:

  • One-class classification is a more effective strategy for assessing optical network transmission quality with imbalanced data.
  • The findings suggest that one-class models provide more reliable and actionable insights for network operators.
  • Further research into one-class algorithms can enhance network monitoring and quality assurance.