Learning to Classify DWDM Optical Channels from Tiny and Imbalanced Data
Applying machine learning algorithms for assessing the transmission quality in optical networks is associated with substantial challenges. Datasets that could provide training instances tend to be small and heavily imbalanced. This requires applying imbalanced compensation techniques when using binary classification algorithms, but it also makes one-class classification, learning only from instances of the majority class, a noteworthy alternative. This work examines the utility of both these approaches using a real dataset from a Dense Wavelength Division Multiplexing network operator, gathered through the network control plane. The dataset is indeed of a very small size and contains very few examples of "bad" paths that do not deliver the required level of transmission quality. Two binary classification algorithms, random forest and extreme gradient boosting, are used in combination with two imbalance handling methods, instance weighting and synthetic minority class instance generation. Their predictive performance is compared with that of four one-class classification algorithms: One-class SVM, one-class naive Bayes classifier, isolation forest, and maximum entropy modeling. The one-class approach turns out to be clearly superior, particularly with respect to the level of classification precision, making it possible to obtain more practically useful models.
Medienart: |
E-Artikel |
---|
Erscheinungsjahr: |
2021 |
---|---|
Erschienen: |
2021 |
Enthalten in: |
Zur Gesamtaufnahme - volume:23 |
---|---|
Enthalten in: |
Entropy (Basel, Switzerland) - 23(2021), 11 vom: 13. Nov. |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Cichosz, Paweł [VerfasserIn] |
---|
Links: |
---|
Themen: |
Imbalanced data |
---|
Anmerkungen: |
Date Revised 29.11.2021 published: Electronic Citation Status PubMed-not-MEDLINE |
---|
doi: |
10.3390/e23111504 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM333653254 |
---|
LEADER | 01000naa a22002652 4500 | ||
---|---|---|---|
001 | NLM333653254 | ||
003 | DE-627 | ||
005 | 20231225222106.0 | ||
007 | cr uuu---uuuuu | ||
008 | 231225s2021 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.3390/e23111504 |2 doi | |
028 | 5 | 2 | |a pubmed24n1112.xml |
035 | |a (DE-627)NLM333653254 | ||
035 | |a (NLM)34828202 | ||
035 | |a (PII)1504 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Cichosz, Paweł |e verfasserin |4 aut | |
245 | 1 | 0 | |a Learning to Classify DWDM Optical Channels from Tiny and Imbalanced Data |
264 | 1 | |c 2021 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a ƒaComputermedien |b c |2 rdamedia | ||
338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
500 | |a Date Revised 29.11.2021 | ||
500 | |a published: Electronic | ||
500 | |a Citation Status PubMed-not-MEDLINE | ||
520 | |a Applying machine learning algorithms for assessing the transmission quality in optical networks is associated with substantial challenges. Datasets that could provide training instances tend to be small and heavily imbalanced. This requires applying imbalanced compensation techniques when using binary classification algorithms, but it also makes one-class classification, learning only from instances of the majority class, a noteworthy alternative. This work examines the utility of both these approaches using a real dataset from a Dense Wavelength Division Multiplexing network operator, gathered through the network control plane. The dataset is indeed of a very small size and contains very few examples of "bad" paths that do not deliver the required level of transmission quality. Two binary classification algorithms, random forest and extreme gradient boosting, are used in combination with two imbalance handling methods, instance weighting and synthetic minority class instance generation. Their predictive performance is compared with that of four one-class classification algorithms: One-class SVM, one-class naive Bayes classifier, isolation forest, and maximum entropy modeling. The one-class approach turns out to be clearly superior, particularly with respect to the level of classification precision, making it possible to obtain more practically useful models | ||
650 | 4 | |a Journal Article | |
650 | 4 | |a imbalanced data | |
650 | 4 | |a machine learning | |
650 | 4 | |a one-class classification | |
650 | 4 | |a optical networks | |
700 | 1 | |a Kozdrowski, Stanisław |e verfasserin |4 aut | |
700 | 1 | |a Sujecki, Sławomir |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t Entropy (Basel, Switzerland) |d 2008 |g 23(2021), 11 vom: 13. Nov. |w (DE-627)NLM191572098 |x 1099-4300 |7 nnns |
773 | 1 | 8 | |g volume:23 |g year:2021 |g number:11 |g day:13 |g month:11 |
856 | 4 | 0 | |u http://dx.doi.org/10.3390/e23111504 |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |d 23 |j 2021 |e 11 |b 13 |c 11 |