Leveraging Personalized Customer Experiences in Mobile Edge Computing Through Split Learning Using Smart Data-Driven Modeling

The rapid growth and opportunities of Mobile Edge Computing (MEC) technology have transformed smart consumer electronics like smartphones and wearable devices that produce massive and complicated data sets. Analyzing consumer electronics data to understand customers is difficult because of its vast...

Full description

Saved in:
Bibliographic Details
Main Authors: V. Vinoth Kumar, K. M. Karthick Raghunath, Iyappan Perumal, K. Manikandan
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10892096/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849339856150331392
author V. Vinoth Kumar
K. M. Karthick Raghunath
Iyappan Perumal
K. Manikandan
author_facet V. Vinoth Kumar
K. M. Karthick Raghunath
Iyappan Perumal
K. Manikandan
author_sort V. Vinoth Kumar
collection DOAJ
description The rapid growth and opportunities of Mobile Edge Computing (MEC) technology have transformed smart consumer electronics like smartphones and wearable devices that produce massive and complicated data sets. Analyzing consumer electronics data to understand customers is difficult because of its vast scale and detailed content. To solve these issues, we present Enhanced Smart Data-Driven Modeling (ESDDM), which combines Smart Data-Driven Modeling (SDDM) with modern Deep Learning (DL). ESDDM combines multiple data streams to better understand consumer electronics systems beyond the normal Machine Learning (ML) capabilities. ESDDM’s integration with Split Learning (SL) protects data by lessening transmission risks and avoiding central cloud storage while keeping sensitive information secure on user devices and delivering better system performance. The prediction results from ESDDM show its strength with a low Mean Squared Error (MSE) of 0.267, which reveals its capability to reshape the MEC domain while creating business possibilities and better customer outcomes.
format Article
id doaj-art-a11bdfd3a66e4e8a9d95183944674802
institution Kabale University
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-a11bdfd3a66e4e8a9d951839446748022025-08-20T03:44:02ZengIEEEIEEE Access2169-35362025-01-0113344353444810.1109/ACCESS.2025.354357710892096Leveraging Personalized Customer Experiences in Mobile Edge Computing Through Split Learning Using Smart Data-Driven ModelingV. Vinoth Kumar0https://orcid.org/0000-0003-1070-3212K. M. Karthick Raghunath1Iyappan Perumal2https://orcid.org/0000-0003-3104-8149K. Manikandan3School of Computer Science Engineering and Information Systems (SCORE), Vellore Institute of Technology, Vellore, Tamil Nadu, IndiaDepartment of Computer Science and Engineering, JAIN (Deemed-to-be University), Bengaluru, Karnataka, IndiaSchool of Computer Science and Engineering (SCOPE), Vellore Institute of Technology, Vellore, Tamil Nadu, IndiaSchool of Computer Science and Engineering (SCOPE), Vellore Institute of Technology, Vellore, Tamil Nadu, IndiaThe rapid growth and opportunities of Mobile Edge Computing (MEC) technology have transformed smart consumer electronics like smartphones and wearable devices that produce massive and complicated data sets. Analyzing consumer electronics data to understand customers is difficult because of its vast scale and detailed content. To solve these issues, we present Enhanced Smart Data-Driven Modeling (ESDDM), which combines Smart Data-Driven Modeling (SDDM) with modern Deep Learning (DL). ESDDM combines multiple data streams to better understand consumer electronics systems beyond the normal Machine Learning (ML) capabilities. ESDDM’s integration with Split Learning (SL) protects data by lessening transmission risks and avoiding central cloud storage while keeping sensitive information secure on user devices and delivering better system performance. The prediction results from ESDDM show its strength with a low Mean Squared Error (MSE) of 0.267, which reveals its capability to reshape the MEC domain while creating business possibilities and better customer outcomes.https://ieeexplore.ieee.org/document/10892096/Contextual adaptationfeature engineeringmobile edge computingpredictive analyticssplit learning
spellingShingle V. Vinoth Kumar
K. M. Karthick Raghunath
Iyappan Perumal
K. Manikandan
Leveraging Personalized Customer Experiences in Mobile Edge Computing Through Split Learning Using Smart Data-Driven Modeling
IEEE Access
Contextual adaptation
feature engineering
mobile edge computing
predictive analytics
split learning
title Leveraging Personalized Customer Experiences in Mobile Edge Computing Through Split Learning Using Smart Data-Driven Modeling
title_full Leveraging Personalized Customer Experiences in Mobile Edge Computing Through Split Learning Using Smart Data-Driven Modeling
title_fullStr Leveraging Personalized Customer Experiences in Mobile Edge Computing Through Split Learning Using Smart Data-Driven Modeling
title_full_unstemmed Leveraging Personalized Customer Experiences in Mobile Edge Computing Through Split Learning Using Smart Data-Driven Modeling
title_short Leveraging Personalized Customer Experiences in Mobile Edge Computing Through Split Learning Using Smart Data-Driven Modeling
title_sort leveraging personalized customer experiences in mobile edge computing through split learning using smart data driven modeling
topic Contextual adaptation
feature engineering
mobile edge computing
predictive analytics
split learning
url https://ieeexplore.ieee.org/document/10892096/
work_keys_str_mv AT vvinothkumar leveragingpersonalizedcustomerexperiencesinmobileedgecomputingthroughsplitlearningusingsmartdatadrivenmodeling
AT kmkarthickraghunath leveragingpersonalizedcustomerexperiencesinmobileedgecomputingthroughsplitlearningusingsmartdatadrivenmodeling
AT iyappanperumal leveragingpersonalizedcustomerexperiencesinmobileedgecomputingthroughsplitlearningusingsmartdatadrivenmodeling
AT kmanikandan leveragingpersonalizedcustomerexperiencesinmobileedgecomputingthroughsplitlearningusingsmartdatadrivenmodeling