A Novel Methodology Based on Orthogonal Projections for a Mobile Network Data Set Analysis

Cortés-Polo, David; Gil, Libertad Sánchez; Calle-Cancho, Jesús; González-Sánchez, José-Luis

doi:10.1109/access.2019.2949804

Cited by 5 publications

(18 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…where Y is the complete data set, U are the comportment arrays in matrix form, α are the weights matrix, and e ∈ R is a matrix that represents the error introduced during the process. The methodology uses the Orthogonal Projections algorithm (OSP) [15] to select the reference vectors of the comportments. In order to establish a relationship between each class defined by a comportment and every sub-area, y n , in the data set Y, a Euclidean distance-based technique is performed, assigning each sub-area to the closest comportment c l ∈ U.…”

Section: Proposed Methodologymentioning

confidence: 99%

“…The province is divided using a grid of square cells of 1000 m per side, covering an area of 6000 km 2 with a total population of~0.5 million. In comparison with Milan data set [15], it covers more extensions, the cells are larger, and it also introduces an irregular pattern in the disposition of the information collected by adjusting to the shape of the province. The data is obtained in 10 min intervals to collect the aforementioned information from each cell in the grid as an activity level.…”

Section: Description Of the Used Data Setsmentioning

confidence: 99%

“…The analysis process started using the same methodology as presented in [15], choosing the same date (Thursday, 14 November 2013) for Milan and the Trento province data sets. On this date, various intervals (8:00 h, 15:00 h and 20:00 h) have been analyzed to cover different network behaviors during the day.…”

Section: Analysis Conducted Of the Data Setmentioning

confidence: 99%

“…Two data sets are analyzed in order to prove the methodology introduced in [15]. These real data sets are provided by Telecom Italia and cover different areas of Italy.…”

mentioning

confidence: 99%

See 3 more Smart Citations

A Methodology for Network Analysis to Improve the Cyber-Physicals Communications in Next-Generation Networks

Cortés-Polo¹,

Gil²,

González-Sánchez³

et al. 2020

Sensors

Self Cite

View full text Add to dashboard Cite

Cyber-physical systems allow creating new applications and services which will bring people, data, processes, and things together. The network is the backbone that interconnects this new paradigm, especially 5G networks that will expand the coverage, reduce the latency, and enhance the data rate. In this sense, network analytics will increase the knowledge about the network and its interconnected devices, being a key feature especially with the increment in the number of physical things (sensors, actuators, smartphones, tablets, and so on). With this increment, the usage of online networking services and applications will grow, and network operators require to detect and analyze all issues related to the network. In this article, a methodology to analyze real network information provided by a network operator and acquire knowledge of the communications is presented. Various real data sets, provided by Telecom Italia, are analyzed to compare two different zones: one located in the urban area of Milan, Italy, and its surroundings, and the second in the province of Trento, Italy. These data sets describe different areas and shapes that cover a metropolitan area in the first case and a mainly rural area in the second case, which implies that these areas will have different comportments. To compare these comportments and group them in a single cluster set, a new technique is presented in this paper to establish a relationship between them and reduce those that could be similar.

show abstract

Section: Proposed Methodologymentioning

confidence: 99%

Section: Description Of the Used Data Setsmentioning

confidence: 99%

Section: Analysis Conducted Of the Data Setmentioning

confidence: 99%

“…Two data sets are analyzed in order to prove the methodology introduced in [15]. These real data sets are provided by Telecom Italia and cover different areas of Italy.…”

mentioning

confidence: 99%

See 2 more Smart Citations

A Methodology for Network Analysis to Improve the Cyber-Physicals Communications in Next-Generation Networks

Cortés-Polo¹,

Gil²,

González-Sánchez³

et al. 2020

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…In previous works [7], [8], a novel unsupervised methodology which exploits call detailed record information collected from the core network of a real mobile cellular network was presented. This methodology uses the linear mixture model [9]- [12] in order to describe a particular data set based on the network information in the metropolitan area of Milan.…”

Section: Introductionmentioning

confidence: 99%

A Quantitative and Comparative Evaluation of Key Points Selection Algorithms for Mobile Network Data Sets Analysis

et al. 2021

Self Cite

View full text Add to dashboard Cite

Currently, network operators are receiving an avalanche of data due to the increasing number of mobile network subscribers, network services and device signalling. This trend will be increased with the deployment of 5G that will provide advanced connectivity to wireless devices and develop new services. Network analytics must allow telecommunications operators to improve their services and the infrastructure extracting useful information from large amounts of data. A methodology based on orthogonal projections was developed in order to analyze the network information and facilitate the management and the operations to network providers. In the current study, different key points selection algorithms are investigated in order to make a comparative evaluation and analyze the performance of those algorithms which use different approaches to select these points, which will be utilized in the methodology. A novel synthetic data set has also been developed to statistically evaluate the effect of the key points selection algorithms in the clustering, as well as, measure the performance of the aforementioned methodology. Finally, these key points selection algorithms are used in a real scenario to evaluate the impact of the different approaches in the analysis.INDEX TERMS 5G, data analysis, mobile networks, network analytic

show abstract

Orthogonal projection for anomaly detection in networking datasets

Cortés-Polo

Jiménez

Paoletti

et al. 2023

J Ambient Intell Human Comput

Self Cite

View full text Add to dashboard Cite

In recent years, the impressive growth of new wireless technologies, together with the appearance of new requirements in applications and services, is progressively changing the use of networks. Due to the high mobility required, the network must adapt to the infrastructure to meet the demands of the users. As a result, service providers currently have to over-provision network capacity, which is costly. In addition, considering efficient resource planning in advance involves a lot of labor-intensive efforts. Consequently, network usage analysis is a very useful tool that allows network administrators to find patterns and anomalies. Whilst pattern detection provides administrators the ability to define the infrastructure, anomaly detection provides rich and valuable information for certain applications, for example, to avoid network saturation in urban areas during peak hours. This article proposes a new methodology based on orthogonal projections over Call Detail Records (CDR) for anomaly detection to help in the dynamic management of the network in an urban area. The method is evaluated in a real scenario provided by an Italian telecommunications operator, considering different locations in the Milan metropolitan area, differentiated by the geographic resolution of the data, reaching F1 scores above 0.8. In addition, a new ground truth is presented, hoping it will become a reference data set for the community, in the form of a set of locations that have been corroborated for use in evaluating anomaly detection techniques.

show abstract

A Novel Methodology Based on Orthogonal Projections for a Mobile Network Data Set Analysis

Cited by 5 publications

References 18 publications

A Methodology for Network Analysis to Improve the Cyber-Physicals Communications in Next-Generation Networks

A Methodology for Network Analysis to Improve the Cyber-Physicals Communications in Next-Generation Networks

A Quantitative and Comparative Evaluation of Key Points Selection Algorithms for Mobile Network Data Sets Analysis

Orthogonal projection for anomaly detection in networking datasets

Contact Info

Product

Resources

About