Edge Intelligence for Low-Power IoT Sensing: Balancing Accuracy and Energy through Model Compression

The proliferation of Internet of Things (IoT) devices necessitates processing paradigms that move beyond traditional cloud-centric models, particularly for low-power embedded sensing where connectivity, latency, and energy budgets are tightly constrained. This paper presents an extended investigation of edge intelligence for low-power IoT sensing, focusing on the integration of machine learning (ML) directly on resource-constrained devices and the resulting trade-off between computational accuracy and energy consumption. We evaluate five edge-deployable model configurations — a Baseline CNN, ResNet-50, MobileNetV2 (INT8), a pruned SqueezeNet, and a Proposed Method combining quantization, structured pruning, and a depth-wise separable architecture — on the CIFAR-10 benchmark, and profile each model's per-inference energy consumption on a representative Cortex-M7 microcontroller. The Proposed Method achieved the highest accuracy (0.934) and F1-score (0.928) while consuming only 15.7 mJ per inference, 8.4 times less energy than ResNet-50. A bit-width sweep further shows that INT8 quantization preserves accuracy within 1.3 percentage points of full-precision inference while cutting energy consumption by roughly 88%. This revised edition extends the technical evaluation with an illustrative organizational validation study: a simulated survey of embedded/IoT engineering stakeholders (N = 213) analyzed with reliability, validity, and PLS-SEM-style structural path techniques comparable to those conducted in SmartPLS, R, or SPSS/AMOS, demonstrating how perceived compression benefits translate into perceived deployment value, realized energy savings, and organizational adoption intention for on-device inference pipelines