Developing Compact Models Using Regression Confidence Forge Knowledge Distillation for IMU-Based Indoor Positioning System

IF 1.7 4区计算机科学 Q3 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

IEEE Embedded Systems Letters Pub Date : 2024-10-28 DOI:10.1109/LES.2024.3487236

Nur Achmad Sulistyo Putro;Jenq-Shiou Leu;Nias Ananto;Cries Avian;Muhammad Izzuddin Mahali;Setya Widyawan Prakosa

引用次数: 0

Abstract

This letter focuses on developing practical and resource-efficient solutions for indoor positioning systems using inertial measurement unit sensors (IMU) by introducing a compact and efficient model. The model, derived from the robust neural inertial navigation (RoNIN) architecture, features a lightweight model that is achieved by reducing the number of filters. A specific knowledge distillation (KD) method, regression confidence forge (ReCoF) KD, is proposed and employed to address potential performance implications, enhancing the efficacy of the streamlined model. The smallest proposed model exhibits an 86% size reduction from RoNIN Resnet, leading to an 18.8% acceleration in inference time and 56% more power efficiency on the edge. Notably, the proposed model maintains high performance, as evidenced by its absolute trajectory error (ATE) and relative trajectory error (RTE).

查看原文本刊更多论文

基于回归置信度锻造知识精馏的室内定位系统紧凑模型研究

这封信的重点是通过介绍一种紧凑和高效的模型，为使用惯性测量单元传感器（IMU）的室内定位系统开发实用和资源高效的解决方案。该模型源自鲁棒神经惯性导航（RoNIN）架构，其特点是通过减少滤波器数量来实现轻量级模型。提出了一种特殊的知识蒸馏（KD）方法，即回归置信锻造（ReCoF） KD，并采用该方法来解决潜在的性能影响，增强了精简模型的有效性。最小的模型显示出比RoNIN Resnet减少86%的尺寸，导致推理时间加速18.8%，边缘功率效率提高56%。值得注意的是，该模型的绝对轨迹误差（ATE）和相对轨迹误差（RTE）均保持了较高的性能。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

IEEE Embedded Systems Letters Engineering-Control and Systems Engineering

CiteScore

3.30

自引率

0.00%

发文量

期刊介绍： The IEEE Embedded Systems Letters (ESL), provides a forum for rapid dissemination of latest technical advances in embedded systems and related areas in embedded software. The emphasis is on models, methods, and tools that ensure secure, correct, efficient and robust design of embedded systems and their applications.