XPySom: High-Performance Self-Organizing Maps

Mancini, Riccardo; Ritacco, Antonio; Lanciano, Giacomo; Cucinotta, Tommaso

doi:10.1109/sbac-pad49847.2020.00037

Cited by 5 publications

(5 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Three data sets and grid sizes are used to test the efficiency of the SOM models. The quantisation error is the metric evaluation recommended by [11,[22][23][24]. The error can prove the accuracy because it measures the fitting of the neural map towards the data.…”

Section: Analysis and Discussionmentioning

confidence: 99%

Implementing Self Organising Map to Organise the Unstructured Data

Lim

Lee

Tan

et al. 2021

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

Surface reconstruction is significant in reverse engineering because it should present the correct surface with minimum error using the data available. It has become a challenging process when the data are in the unstructured type and the existing methods are still suffering from accuracy issues. The unstructured data will produce an incorrect surface because there is no connectivity information among the data. So, the unstructured data should undergo the organising process to obtain the correct shape. The Self Organising Map (SOM) has been extensively applied in previous works to solve surface reconstruction problems. However, the performance of the SOM models has remained uncertain. It can be evaluated and tested using different types of data sets. The objectives of this research are to examine the performance and to determine the weaknesses of SOM models. 2D SOM, 3D SOM, and Cube Kohonen (CK) SOM models are investigated and tested using three data sets in this research. As shown in the experimental results, the CKSOM model has proved to perform better because it can represent the correct closed surface with the lowest minimum error.

show abstract

Section: Analysis and Discussionmentioning

confidence: 99%

Implementing Self Organising Map to Organise the Unstructured Data

Lim

Lee

Tan

et al. 2021

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

show abstract

“…The size of the map is chosen as a trade‐off between the level of information reduction, and the accuracy of the clustering. We use the XPySom package (Mancini et al., 2020) run in a batch mode (using all the vectors in data sequentially, in opposition to a random training), in order to obtain a reproducible result. Each node being associated with a subset of the input data, we can then use the time‐steps associated with a node (called Best Matching Units BMUs) to compute composites of other variables (“conditional average”) and investigate the link between the nodes and those variables.…”

Section: Data Sets and Methodsmentioning

confidence: 99%

East Australian Current System: Frontal Barrier and Fine‐Scale Control of Chlorophyll‐a Distribution

Bourg,

Schaeffer,

Molcard

2024

JGR Oceans

View full text Add to dashboard Cite

The East Australian Current (EAC), as the western boundary current of the South Pacific Gyre, governs the mesoscale circulation dynamics along the East Coast of Australia. It also exhibits meandering and instabilities that generate fine‐scale structures. Understanding the interplay between these fine‐scale processes and the larger‐scale EAC patterns is crucial in regards to chlorophyll‐a distribution, a key indicator of phytoplankton abundance and an essential component of marine ecosystems. However, the link between fine‐scale and large‐scale variability in the EAC's separation dynamics and its impact on chlorophyll‐a distribution remains poorly understood. In this study, we investigate this relationship using a clustering of high‐frequency radar data near the EAC's coherent jet and separation point, combined with satellite data on chlorophyll‐a concentration, sea surface temperature, and altimetry. Our findings reveal that the EAC acts as a frontal barrier for water‐mass and chlorophyll‐a concentration. The EAC separation enhances shelf‐offshore exchange and off‐shelf chlorophyll‐a concentration. In contrast, the extension of the current is characterized by fine‐scale structures with cyclonic vorticity and elevated strain, consequently contributing to an elevation of chlorophyll‐a levels in the region. In conclusion, the impact of separation dynamics on chlorophyll‐a distribution involves a complex interplay between large‐scale and fine‐scale processes, which may possibly compete under certain scenarios. Considering the implications of our findings in the context of future climate conditions, it becomes evident that purely dynamical changes in the separation latitude of the East Australian Current may hold consequences for chlorophyll‐a concentration distribution off the east coast of Australia.

show abstract

“…Such accelerations have been proved to be necessary in order to reach a satisfactory performance when tackling the massive data set provided by Vodafone. In the future, we plan to switch to a new implementation we recently realized performing even better [23].…”

Section: Som Implementationmentioning

confidence: 99%

Using Self-Organizing Maps for the Behavioral Analysis of Virtualized Network Functions

Lanciano

Ritacco

Brau

et al. 2021

Communications in Computer and Information Science

Self Cite

View full text Add to dashboard Cite

Detecting anomalous behaviors in a network function virtualization infrastructure is of the utmost importance for network operators. In this paper, we propose a technique, based on Self-Organizing Maps, to address such problem by leveraging on the massive amount of historical system data that is typically available in these infrastructures. Indeed, our method consists of a joint analysis of system-level metrics, provided by the virtualized infrastructure monitoring system and referring to resource consumption patterns of the physical hosts and the virtual machines (or containers) that run on top of them, and application-level metrics, provided by the individual virtualized network functions monitoring subsystems and related to the performance levels of the individual applications. The implementation of our approach has been validated on real data coming from a subset of the Vodafone infrastructure for network function virtualization, where it is currently employed to support the decisions of data center operators. Experimental results show that our technique is capable of identifying specific points in space (i.e., components of the infrastructure) and time of the recent evolution of the monitored infrastructure that are worth to be investigated by human operators in order to keep the system running under expected conditions.

show abstract

XPySom: High-Performance Self-Organizing Maps

Cited by 5 publications

References 25 publications

Implementing Self Organising Map to Organise the Unstructured Data

Implementing Self Organising Map to Organise the Unstructured Data

East Australian Current System: Frontal Barrier and Fine‐Scale Control of Chlorophyll‐a Distribution

Using Self-Organizing Maps for the Behavioral Analysis of Virtualized Network Functions

Contact Info

Product

Resources

About