Ata uhi

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

I tiakina i:
I whakaputaina i:Electronics vol. 14, no. 12 (2025), p. 2495-2549
Kaituhi matua: Ngo Dat
Ētahi atu kaituhi: Park, Hyun-Cheol, Kang Bongsoon
I whakaputaina:
MDPI AG
Ngā marau:
Deep learning
Smartphones
Hardware
Bandwidths
Optimization techniques
Artificial neural networks
Data processing
Software upgrading
Co-design
Privacy
Energy consumption
Efficiency
Energy budget
Neurons
Embedded systems
Artificial intelligence
Edge computing
Power
Sensors
Decision making
Autonomous vehicles
Neural networks
Inference
Network latency
Remote computing
Connectivity
Intelligence
Algorithms
Surveillance
Urunga tuihono:Citation/Abstract
Full Text + Graphics
Full Text - PDF
Ngā Tūtohu: Tāpirihia he Tūtohu
Kāore He Tūtohu, Me noho koe te mea tuatahi ki te tūtohu i tēnei pūkete!
Whakarāpopotonga: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.
ISSN:2079-9292
DOI:10.3390/electronics14122495
Puna:Advanced Technologies & Aerospace Database