Model Optimization for Edge Devices
Research gap analysis derived from 2 computer_science papers in our local library.
The gap
There is a need to optimize deep learning models using techniques such as pruning, quantization, and knowledge distillation specifically for deployment on mobile and edge devices, including ARM-based processors and embedded systems.
Consensus across the literature
The papers collectively establish that current models are not optimized for real-time and resource-constrained environments but leave open the specific optimization techniques and their performance on these devices.
Research trend
Emerging — attention growing, methods still coalescing.
Supporting evidence — 2 representative gaps
- Research On Text Generated Images Based on GAN And Diffusion (2026) · doi
Develop model compression and acceleration technologies for mobile and edge devices through combination optimization of pruning, low-rank decomposition, and quantization.
Keywords: develop model compression acceleration technologies mobile edge devices combination optimization pruning rank decomposition quantization - Real-Time Facial Emotion Detection Using Deep Learning and AI (2026) · doi
The system can also be made faster and smaller for mobile and IoT devices using model optimization techniques.
Keywords: system made faster smaller mobile devices using model optimization techniques
Explore this gap further
Search “Model Optimization for Edge Devices” across open scholarly engines for the latest related literature.
Working on this gap? Publish with us.
Science AI Journal reviews manuscripts in under 15 minutes with 8 specialised AI reviewers calibrated on 23,000+ real peer reviews. Open access, CC BY 4.0.
Free tools for your next paper
Related gaps in Computer Science
- Finally, we identify gaps in the knowledge of sex differences in athletic performance and the underlying mechanisms, providing substantial opportunities for high-impact studies.Finally, we identify gaps in the knowledge of sex differences in athletic performance and the underlying mechanisms, providing substantial o…
- For verbal working memory, these near-transfer effects were not sustained at follow-up, whereas for visuospatial working memory, limited evidence suggested that such effects might be maintained.For verbal working memory, these near-transfer effects were not sustained at follow-up, whereas for visuospatial working memory, limited evi…
- Although large language models often produce impressive outputs, it remains unclear how they perform in real-world scenarios requiring strong reasoning skills and expert domain knowledge.Although large language models often produce impressive outputs, it remains unclear how they perform in real-world scenarios requiring stron…
- In deep learning (DL), the deep generative model is helpful for data augmentation objectives to tackle the lack of datasets that have a significant impact on learning performance.In deep learning (DL), the deep generative model is helpful for data augmentation objectives to tackle the lack of datasets that have a sign…