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

Kozdrowski, Stanisław; Cichosz, Paweł; Paziewski, Piotr; Sujecki, S.

doi:10.3390/e23010007

Cited by 16 publications

(11 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Tree algorithm is a hierarchical structure that Internal Tree nodes represent splits applied to decompose the domain into regions, and terminal nodes assign class labels or class probabilities to regions believed to be sufficiently small or sufficiently uniform [32]. Pruning was done by using tenfold cross-validation.…”

Section: Treementioning

confidence: 99%

A Systematic Evaluation of Methods for Cell Phenotype Classification Using Single-Cell RNA Sequencing Data

Cao

Xing

Majd

et al. 2021

Preprint

View full text Add to dashboard Cite

Background: Single-cell RNA sequencing (scRNA-seq) yields valuable insights about gene expression and gives critical information about complex tissue cellular composition. In the analysis of single-cell RNA sequencing, the annotations of cell subtypes are often done manually, which is time-consuming and irreproducible. Garnett is a cell-type annotation software based the on elastic net method. Beside cell-type annotation, supervised machine learning methods can also be applied to predict other cell phenotypes from genomic data. Despite the popularity of such applications, there is no existing study to systematically investigate the performance of those supervised algorithms in various sizes of scRNA-seq data sets. Methods and Results: This study evaluates 13 popular supervised machine learning algorithms to classify cell phenotypes, using published real and simulated data sets with diverse cell sizes. The benchmark contained two parts. In the first part, we used real data sets to assess the popular supervised algorithms’ computing speed and cell phenotype classification performance. The classification performances were evaluated using AUC statistics, F1-score, precision, recall, and false-positive rate. In the second part, we evaluated gene selection performance using published simulated data sets with a known list of real genes. Conclusion: The study outcomes showed that ElasticNet with interactions performed best in small and medium data sets. NB was another appropriate method for medium data sets. In large data sets, XGB works excellent. Ensemble algorithms were not significantly superior to individual machine learning methods. Adding interactions to ElasticNet can help, and the improvement was significant in small data sets.

show abstract

Section: Treementioning

confidence: 99%

A Systematic Evaluation of Methods for Cell Phenotype Classification Using Single-Cell RNA Sequencing Data

Cao

Xing

Majd

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Applying additional aggregation functions to edge properties, such as the minimum, the maximum, the median, the first quartile, the third quartile, or the linear correlation coefficient with the ordinal number of the edge in the path, as in our prior work [14], may create some additional predictively useful attributes. However, this would make the dimensionality of this representation relatively high in comparison to the size of the available dataset, considerably increasing the risk of overfitting.…”

Section: Vector Representationmentioning

confidence: 99%

“…Any standard classification algorithm can be used to predict channel "good"/"bad" class labels or probabilities. In this work we limit our attention to the two algorithms that performed the best in our previous study [14]: Random forest and extreme gradient boosting. They belong to the most successful learning algorithms for tabular data and it is very unlikely that their performance could be beaten by other algorithms using the same vector path representation.…”

Section: Binary Classificationmentioning

confidence: 99%

“…As already mentioned this makes the ML problem considered in this contribution clearly different from those considered so far in most of the available literature [6,7,12,13]. Expanding upon our previous work [14,15], we compare the predictive performance of the most successful binary classification algorithms combined with different techniques for class imbalance compensation and that of one-class classification algorithms that learn from majority class instances only.…”

Section: Introductionmentioning

confidence: 97%

See 1 more Smart Citation

Learning to Classify DWDM Optical Channels from Tiny and Imbalanced Data

Cichosz

Kozdrowski

Sujecki

2021

Entropy

Self Cite

View full text Add to dashboard Cite

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.

show abstract

“…A particularly promising domain is the network management. Researchers have used Machine Learning (ML) to automate the management of network resources in relation to routing or network traffic optimization [20][21][22][23][24]. In loT networks, we expect network conditions to vary over time and space.…”

mentioning

confidence: 99%

Artificial Intelligence Control Logic in Next-Generation Programmable Networks

et al. 2021

Self Cite

View full text Add to dashboard Cite

The new generation of programmable networks allow mechanisms to be deployed for the efficient control of dynamic bandwidth allocation and ensure Quality of Service (QoS) in terms of Key Performance Indicators (KPIs) for delay or loss sensitive Internet of Things (IoT) services. To achieve flexible, dynamic and automated network resource management in Software-Defined Networking (SDN), Artificial Intelligence (AI) algorithms can provide an effective solution. In the paper, we propose the solution for network resources allocation, where the AI algorithm is responsible for controlling intent-based routing in SDN. The paper focuses on the problem of optimal switching of intents between two designated paths using the Deep-Q-Learning approach based on an artificial neural network. The proposed algorithm is the main novelty of this paper. The Developed Networked Application Emulation System (NAPES) allows the AI solution to be tested with different patterns to evaluate the performance of the proposed solution. The AI algorithm was trained to maximize the total throughput in the network and effective network utilization. The results presented confirm the validity of applied AI approach to the problem of improving network performance in next-generation networks and the usefulness of the NAPES traffic generator for efficient economical and technical deployment in IoT networking systems evaluation.

show abstract

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

Cited by 16 publications

References 54 publications

A Systematic Evaluation of Methods for Cell Phenotype Classification Using Single-Cell RNA Sequencing Data

A Systematic Evaluation of Methods for Cell Phenotype Classification Using Single-Cell RNA Sequencing Data

Learning to Classify DWDM Optical Channels from Tiny and Imbalanced Data

Artificial Intelligence Control Logic in Next-Generation Programmable Networks

Contact Info

Product

Resources

About