A novel urban mobility classification approach based on convolutional neural networks and mobility-to-image encoding

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989100%3A27240%2F23%3A10252791" target="_blank" >RIV/61989100:27240/23:10252791 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/61989100:27740/23:10252791

Výsledek na webu

<a href="https://www.sciencedirect.com/science/article/pii/S1319157823001076" target="_blank" >https://www.sciencedirect.com/science/article/pii/S1319157823001076</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1016/j.jksuci.2023.101561" target="_blank" >10.1016/j.jksuci.2023.101561</a>

Jazyk výsledku

angličtina

Název v původním jazyce

A novel urban mobility classification approach based on convolutional neural networks and mobility-to-image encoding

Popis výsledku v původním jazyce

Over the last few decades, the classification and prediction of mobility trajectories in dynamic networks have become major research topics. Switching of mobility areas (hand-over) in modern cellular networks is frequent due to restricted coverage area and node speeds (urban, highway, etc.). Accurate management of hand-over events is highly desirable to improve the system&apos;s quality of service. We have exploited the high accuracy of machine learning to classify user mobility from mobility traces which we encoded into images. The method delivers high performance in mobility classification/prediction (exceeding 95%) and avoids the need to study and implement a dedicated neural network structure. The technique requires the conversion of mobility traces into image structures and the subsequent application of a convolutional neural network. We propose a novel approach to classifying mobility that involves data-to-image encoding and machine learning for image classification. Numerous simulations were performed to demonstrate the benefits of the proposed technique and to illustrate the variance in the accuracy of the functions of many encoding/classification parameters. The work represents a first preliminary step towards a new mobility prediction approach. We demonstrate that it is possible to achieve a very high level of prediction accuracy with low computational complexity, exploiting the strength of neural networks in image recognition. (C) 2023 The Author(s)

Název v anglickém jazyce

A novel urban mobility classification approach based on convolutional neural networks and mobility-to-image encoding

Popis výsledku anglicky

Over the last few decades, the classification and prediction of mobility trajectories in dynamic networks have become major research topics. Switching of mobility areas (hand-over) in modern cellular networks is frequent due to restricted coverage area and node speeds (urban, highway, etc.). Accurate management of hand-over events is highly desirable to improve the system&apos;s quality of service. We have exploited the high accuracy of machine learning to classify user mobility from mobility traces which we encoded into images. The method delivers high performance in mobility classification/prediction (exceeding 95%) and avoids the need to study and implement a dedicated neural network structure. The technique requires the conversion of mobility traces into image structures and the subsequent application of a convolutional neural network. We propose a novel approach to classifying mobility that involves data-to-image encoding and machine learning for image classification. Numerous simulations were performed to demonstrate the benefits of the proposed technique and to illustrate the variance in the accuracy of the functions of many encoding/classification parameters. The work represents a first preliminary step towards a new mobility prediction approach. We demonstrate that it is possible to achieve a very high level of prediction accuracy with low computational complexity, exploiting the strength of neural networks in image recognition. (C) 2023 The Author(s)

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

20203 - Telecommunications

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2023

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Journal of King Saud University - Computer and Information Sciences

ISSN

1319-1578

e-ISSN

—

Svazek periodika

35

Číslo periodika v rámci svazku

6

Stát vydavatele periodika

SA - Království Saúdská Arábie

Počet stran výsledku

13

Strana od-do

—

Kód UT WoS článku

001042923200001

EID výsledku v databázi Scopus

2-s2.0-85158045553