Synapse
⌘+K
Synapse
PulseExploreJournal ClubResearchersJournals
Instagram
HomeJournal ClubExplore
September 10, 2025SensorsOpen Access

Comprehensive Analysis of Neural Network Inference on Embedded Systems: Response Time, Calibration, and Model Optimisation

View Full Paper
Ask AI
Bookmark
Share

Authors

PHPatrick HuberUGUlrich GöhnerMTMario Trapp

Discussion

Loading...

Member takes

Overview

This analysis reveals response time and calibration challenges in embedded systems, highlighting model optimisation needs.

Key Points

  • Response time performance is critical in embedded systems, especially for predictive maintenance applications.
  • The study highlights the impact of network parameters and threading on response times in ANN applications.
  • Analysis includes hardware influences and model calibration quantified with Expected Calibration Error (ECE).
  • Optimisation across platforms requires precise parameter coordination, revealing limitations in automatic operations of frameworks.

Cite This Study

Huber et al. (2025) studied this question.

synapsesocial.com/papers/68c1afd354b1d3bfb60e8272https://doi.org/10.3390/s25154769
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Optimization and Benchmarking of Lightweight Neural Networks for Efficient Embedded <scp>AI</scp> Deployment2026 · 1 citations
  2. 2Benchmarking Deep Learning Models on NVIDIA Jetson Nano for Real-Time Systems: An Empirical Investigation2024 · 1 citations
  3. 3Edge AI in Practice: A Survey and Deployment Framework for Neural Networks on Embedded Systems2025 · 38 citations
  4. 4Model Optimization Techniques for Embedded Artificial Intelligence2025
  5. 5Evolutionary Perspectives on Neural Network Generations: A Critical Examination of Models and Design Strategies2024