Edge Intelligence: A Review of Deep Neural Network Inference in Resource-Limited Environments

Guardat en:
Dades bibliogràfiques
Publicat a:Electronics vol. 14, no. 12 (2025), p. 2495-2549
Autor principal: Ngo Dat
Altres autors: Park, Hyun-Cheol, Kang Bongsoon
Publicat:
MDPI AG
Matèries:
Accés en línia:Citation/Abstract
Full Text + Graphics
Full Text - PDF
Etiquetes: Afegir etiqueta
Sense etiquetes, Sigues el primer a etiquetar aquest registre!

MARC

LEADER 00000nab a2200000uu 4500
001 3223908949
003 UK-CbPIL
022 |a 2079-9292 
024 7 |a 10.3390/electronics14122495  |2 doi 
035 |a 3223908949 
045 2 |b d20250101  |b d20251231 
084 |a 231458  |2 nlm 
100 1 |a Ngo Dat  |u Department of Computer Engineering, Korea National University of Transportation, Chungju 27469, Republic of Korea; datngo@ut.ac.kr (D.N.); hc.park@ut.ac.kr (H.-C.P.) 
245 1 |a Edge Intelligence: A Review of Deep Neural Network Inference in Resource-Limited Environments 
260 |b MDPI AG  |c 2025 
513 |a Journal Article 
520 3 |a Deploying deep neural networks (DNNs) in resource-limited environments—such as smartwatches, IoT nodes, and intelligent sensors—poses significant challenges due to constraints in memory, computing power, and energy budgets. This paper presents a comprehensive review of recent advances in accelerating DNN inference on edge platforms, with a focus on model compression, compiler optimizations, and hardware–software co-design. We analyze the trade-offs between latency, energy, and accuracy across various techniques, highlighting practical deployment strategies on real-world devices. In particular, we categorize existing frameworks based on their architectural targets and adaptation mechanisms and discuss open challenges such as runtime adaptability and hardware-aware scheduling. This review aims to guide the development of efficient and scalable edge intelligence solutions. 
653 |a Deep learning 
653 |a Smartphones 
653 |a Hardware 
653 |a Bandwidths 
653 |a Optimization techniques 
653 |a Artificial neural networks 
653 |a Data processing 
653 |a Software upgrading 
653 |a Co-design 
653 |a Privacy 
653 |a Energy consumption 
653 |a Efficiency 
653 |a Energy budget 
653 |a Neurons 
653 |a Embedded systems 
653 |a Artificial intelligence 
653 |a Edge computing 
653 |a Power 
653 |a Sensors 
653 |a Decision making 
653 |a Autonomous vehicles 
653 |a Neural networks 
653 |a Inference 
653 |a Network latency 
653 |a Remote computing 
653 |a Connectivity 
653 |a Intelligence 
653 |a Algorithms 
653 |a Surveillance 
700 1 |a Park, Hyun-Cheol  |u Department of Computer Engineering, Korea National University of Transportation, Chungju 27469, Republic of Korea; datngo@ut.ac.kr (D.N.); hc.park@ut.ac.kr (H.-C.P.) 
700 1 |a Kang Bongsoon  |u Department of Electronics Engineering, Dong-A University, Busan 49315, Republic of Korea 
773 0 |t Electronics  |g vol. 14, no. 12 (2025), p. 2495-2549 
786 0 |d ProQuest  |t Advanced Technologies & Aerospace Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3223908949/abstract/embedded/L8HZQI7Z43R0LA5T?source=fedsrch 
856 4 0 |3 Full Text + Graphics  |u https://www.proquest.com/docview/3223908949/fulltextwithgraphics/embedded/L8HZQI7Z43R0LA5T?source=fedsrch 
856 4 0 |3 Full Text - PDF  |u https://www.proquest.com/docview/3223908949/fulltextPDF/embedded/L8HZQI7Z43R0LA5T?source=fedsrch