Low-Resource Scenario Classification Through Model Pruning Toward Refined Edge Intelligence

Xiaofeng Shan

doi:10.1109/JIOT.2023.3347665

Low-Resource Scenario Classification Through Model Pruning Toward Refined Edge Intelligence

2024-11-01

1

PRE

AI

DOI：10.1109/JIOT.2023.3347665

Original

Original request for help

Save

Abstract

En 中文

The implementation of scenario classification (SC) plays a pivotal role in various edge intelligence applications, notably in fields, such as autonomous driving, navigation, and remote sensing. With recent advancements, deep learning (DL) techniques have substantially improved SC, delivering remarkable results in classification tasks. However, the integration of DL in SC brings significant computational demands, posing challenges for deployment on edge devices where resources are constrained. Addressing this issue, we propose a novel low-resource SC (LR-SC) approach, primarily focused on model pruning. This strategy aims to reduce computational power and storage needs, thus optimizing resource utilization in edge intelligence applications. Our approach involves the application of an & ell;(2) regularization and a threshold-based pruning method, which selectively eliminates nonessential connections. This is followed by a systematic process of alternating pruning and fine-tuning to mitigate any performance loss due to the pruning. Experimental evaluations of the LR-SC method have shown its effectiveness; it substantially lowers the parameter count to merely 24% of the original model, while simultaneously achieving a 0.42% increase in classification accuracy.

Keywords:

Computational modeling

Internet of Things

Feature extraction

Data models

Channel estimation

Adaptation models

Wireless communication

& ell

(2) regularization

low-resource

model pruning

refined edge intelligence

scenario classification (SC)

Low-Resource Scenario Classification Through Model Pruning Toward Refined Edge Intelligence

Abstract

Journal

Organization