Node Centrality Metrics for Hotspots Analysis in Telecom Big Data

Mededovic, Emil; Douros, Vaggelis G.; Mähönen, Petri

doi:10.1109/infcomw.2019.8845204

Cited by 13 publications

(9 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They identified different metrics that are more applicable to this specific type of communication networks. Mededovic et al discussed the node centrality metrics, and concluded that they are significantly helpful in the analysis of hotspots in the telecom domain [26]. In this study, they performed an analysis of telecom data for two weeks.…”

Section: Related Workmentioning

confidence: 95%

Hotspots Analysis Using Cyber-Physical-Social System for a Smart City

Amin

Choi

2020

IEEE Access

View full text Add to dashboard Cite

Internet of things plays a vital role in providing various services to users. Significant volumes of data are generated from the communication between a large numbers of heterogeneous devices over the Internet. Big data technology is generally used to handle the large volume of data. Complex networks are graphs (networks) having non-trivial topological features, such as random graphs and lattices. Big data of complex networks concerns big data methods that can be used to analyze massive structural data sets, including considerably large networks and sets of graphs. This study is based on the critical phenomenon arising in complex networks that enable us to analytically predict the hotspots in smart cities. Hotspots are places with significantly high communication traffic relative to others. In this study, we propose a cyber-physical-social system for the analysis of high communication traffic hotspots using telecom data. The proposed model constructs a graph, and perform social network analysis on it. The process of hotspot extraction is performed, followed by social network analysis, which is conducted by quantifying the importance of each hotspot based on network metrics. These metrics aid in determining the importance of each hotspot in a telecom data network. Our objective is to prioritize different areas and detect hotspots quickly. Our results indicate that the proposed model has an efficiency comparable with that of state of the art methods. This research study will be helpful for urban planning and development, as well as in upgrading telecommunication infrastructure.

show abstract

Section: Related Workmentioning

confidence: 95%

Hotspots Analysis Using Cyber-Physical-Social System for a Smart City

Amin

Choi

2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The dataset has log data for 2 months (62 days) from November 1, 2013 to January 1, 2014. 41 Although this dataset was collected between 2013 and 2014, it still proves to be quite valuable for researchers exploring mobile traffic prediction, and it has been used in a number of recently published articles (see, e.g., other studies [42][43][44] ). The Telecom Italia dataset adopted in this study in fact is one of the few telecommunication datasets that are publicly available in contrast to the large number of datasets that are typically accessible to a restricted number of researchers under non-disclosure agreements (NDAs), or by third parties that have a contractual relationship with telecommunication providers.…”

Section: Datasetmentioning

confidence: 99%

Predicting short‐term mobile Internet traffic from Internet activity using recurrent neural networks

et al. 2021

View full text Add to dashboard Cite

Mobile network traffic prediction is an important input into network capacity planning and optimization. Existing approaches may lack the speed and computational complexity to account for bursting, non-linear patterns, or other important correlations in time series mobile network data. We compare the performance of two deep learning (DL) architectures, long short-term memory (LSTM) and gated recurrent unit (GRU), and two conventional machine learning (ML) architectures-Random Forest and Decision Tree-for predicting mobile Internet traffic using 2 months of Telecom Italia data for Milan.K-Means clustering was used a priori to group cells based on Internet activity, and the Grid Search method was used to identify the best configurations for each model. The predictive quality of the models was evaluated using root mean squared error and mean absolute error. Both DL algorithms were effective in modeling Internet activity and seasonality, both within days and across 2 months. We find variations in performance across clusters within the city. Overall, the DL models outperformed the conventional ML models, and the LSTM outperformed the GRU in our experiments.

show abstract

“…Some stateof-the-art research work present to involve mobile network data such as Call Detail Records (CDRs) and User Detail Records (UDRs) to make accurate hotspot analysis. Mededovic et al [13] make analysis on datasets of Telecom Italia for Milan and Trento and then identify the hotspots with high communication traffic through graph centrality measurement. Seufert et al [14] make analysis on a public WiFi dataset and then bring forward a simple WiFi hotspot model in smart city.…”

Section: B Urban Hotspot Analysis Schemesmentioning

confidence: 99%

“…The graph theory based techniques are helpful in modeling highly connected systems and capture the structural information inside. Mededovic et al [13] utilize the graph model and make analysis on node centrality metrics to identify hotspots with high communication traffic by measuring the node interactions. Some of the studies address the hotspot analysis based on centrality calculation measurements [22] such as closeness, degree and PageRank, etc.…”

Section: B Urban Hotspot Analysis Schemesmentioning

confidence: 99%

Edge Oriented Urban Hotspot Prediction for Human-Centric Internet of Things

Zeng

Xiang

2021

IEEE Access

View full text Add to dashboard Cite

Mobile edge computing works well with the rapid growth of human-centric IoT applications by providing timely and in-situ data caching and processing. Edge oriented urban hotspot prediction is to predict the high traffic regions in case to provide basis for further deployment and replenishment of edge servers. Most of the existing hotspot analysis work is not well suited for human-centric IoT application scenarios especially for large-scale urban city areas. Instead, in this paper we propose edge-oriented hotspot prediction scheme based on information Interactive Graph Attention Networks (I-GAN) for urban city within the human-centric IoT and MEC application scenarios. I-GAN makes reasoning on the user service needs by learning the interactive relations of multifaceted human-centric factors: including online human behavior and offline crowd flow through graph attention networks. On the other hand, I-GAN makes representation of urban-scale edge service capability by graph embeddings through inductive learning with distributed multi-layer graph convolutions. Based on it, I-GAN makes matching between them and then predicts the edge-oriented hotspots with time variance. The performance evaluations are based on realistic dataset of a southern city of China provided by China Unicom. I-GAN is compared with the other related hotspot analysis schemes. The results show that I-GAN is with much better prediction accuracy with multiple time dimensions.

show abstract

Node Centrality Metrics for Hotspots Analysis in Telecom Big Data

Cited by 13 publications

References 9 publications

Hotspots Analysis Using Cyber-Physical-Social System for a Smart City

Hotspots Analysis Using Cyber-Physical-Social System for a Smart City

Predicting short‐term mobile Internet traffic from Internet activity using recurrent neural networks

Edge Oriented Urban Hotspot Prediction for Human-Centric Internet of Things

Contact Info

Product

Resources

About