Exploring Smartphone-Based Edge AI Inferences Using Real Testbeds

Na minha lista:
Detalhes bibliográficos
Publicado no:Sensors vol. 25, no. 9 (2025), p. 2875
Autor principal: Hirsch, Matías
Outros Autores: Mateos Cristian, Majchrzak, Tim A
Publicado em:
MDPI AG
Assuntos:
Acesso em linha:Citation/Abstract
Full Text + Graphics
Full Text - PDF
Tags: Adicionar Tag
Sem tags, seja o primeiro a adicionar uma tag!

MARC

LEADER 00000nab a2200000uu 4500
001 3203248129
003 UK-CbPIL
022 |a 1424-8220 
024 7 |a 10.3390/s25092875  |2 doi 
035 |a 3203248129 
045 2 |b d20250101  |b d20251231 
084 |a 231630  |2 nlm 
100 1 |a Hirsch, Matías  |u ISISTAN (UNICEN-CONICET), Tandil 7000, Buenos Aires, Argentina; matias.hirsch@isistan.unicen.edu.ar (M.H.); cristian.mateos@isistan.unicen.edu.ar (C.M.) 
245 1 |a Exploring Smartphone-Based Edge AI Inferences Using Real Testbeds 
260 |b MDPI AG  |c 2025 
513 |a Journal Article 
520 3 |a The increasing availability of lightweight pre-trained models and AI execution frameworks is causing edge AI to become ubiquitous. Particularly, deep learning (DL) models are being used in computer vision (CV) for performing object recognition and image classification tasks in various application domains requiring prompt inferences. Regarding edge AI task execution platforms, some approaches show a strong dependency on cloud resources to complement the computing power offered by local nodes. Other approaches distribute workload horizontally, i.e., by harnessing the power of nearby edge nodes. Many of these efforts experiment with real settings comprising SBC (Single-Board Computer)-like edge nodes only, but few of these consider nomadic hardware such as smartphones. Given the huge popularity of smartphones worldwide and the unlimited scenarios where smartphone clusters could be exploited for providing computing power, this paper sheds some light in answering the following question: Is smartphone-based edge AI a competitive approach for real-time CV inferences? To empirically answer this, we use three pre-trained DL models and eight heterogeneous edge nodes including five low/mid-end smartphones and three SBCs, and compare the performance achieved using workloads from three image stream processing scenarios. Experiments were run with the help of a toolset designed for reproducing battery-driven edge computing tests. We compared latency and energy efficiency achieved by using either several smartphone clusters testbeds or SBCs only. Additionally, for battery-driven settings, we include metrics to measure how workload execution impacts smartphone battery levels. As per the computing capability shown in our experiments, we conclude that edge AI based on smartphone clusters can help in providing valuable resources to contribute to the expansion of edge AI in application scenarios requiring real-time performance. 
653 |a Architecture 
653 |a Remote computing 
653 |a Collaboration 
653 |a Smartphones 
653 |a Infrastructure 
653 |a Cloud computing 
653 |a Communication 
653 |a Workloads 
653 |a Power 
653 |a Energy consumption 
653 |a Neural networks 
653 |a Distributed processing 
700 1 |a Mateos Cristian  |u ISISTAN (UNICEN-CONICET), Tandil 7000, Buenos Aires, Argentina; matias.hirsch@isistan.unicen.edu.ar (M.H.); cristian.mateos@isistan.unicen.edu.ar (C.M.) 
700 1 |a Majchrzak, Tim A  |u Faculty of Computer Science, Ruhr University, 44801 Bochum, Germany 
773 0 |t Sensors  |g vol. 25, no. 9 (2025), p. 2875 
786 0 |d ProQuest  |t Health & Medical Collection 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3203248129/abstract/embedded/L8HZQI7Z43R0LA5T?source=fedsrch 
856 4 0 |3 Full Text + Graphics  |u https://www.proquest.com/docview/3203248129/fulltextwithgraphics/embedded/L8HZQI7Z43R0LA5T?source=fedsrch 
856 4 0 |3 Full Text - PDF  |u https://www.proquest.com/docview/3203248129/fulltextPDF/embedded/L8HZQI7Z43R0LA5T?source=fedsrch