Energy-aware metaheuristics use an EI/J score to dynamically pick operators that maximize fitness gain per unit energy, reaching comparable fitness with substantially less energy than standard versions on knapsack, NK-landscapes, and error-correcting code problems.
Lightweight deep learning for resource-constrained environments: A survey
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
Experimental benchmarks show ESP-NOW protocol yields lowest latency in TinyML split learning on ESP32-S3, with a beam search optimizer achieving near-optimal split points in 0.1 seconds for small device groups.
Decision-level fusion with WBF outperforms feature-level fusion for occlusion-robust detection on ultra-low-end hardware, with gains up to +0.3827 mAP across three views and on-device execution on Coral boards.
citing papers explorer
-
Energy-Aware Metaheuristics
Energy-aware metaheuristics use an EI/J score to dynamically pick operators that maximize fitness gain per unit energy, reaching comparable fitness with substantially less energy than standard versions on knapsack, NK-landscapes, and error-correcting code problems.
-
Optimizing Split Learning Latency in TinyML-Based IoT Systems
Experimental benchmarks show ESP-NOW protocol yields lowest latency in TinyML split learning on ESP32-S3, with a beam search optimizer achieving near-optimal split points in 0.1 seconds for small device groups.
-
Tiny Collaborative Inference for Occlusion-Robust Object Detection
Decision-level fusion with WBF outperforms feature-level fusion for occlusion-robust detection on ultra-low-end hardware, with gains up to +0.3827 mAP across three views and on-device execution on Coral boards.