Search research articles

关于 JoVE

概览领导团队博客 JoVE 帮助中心

作者

出版流程编辑委员会范围与政策同行评审常见问题投稿

图书馆员

用户评价订阅访问资源图书馆顾问委员会常见问题

研究

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments 存档

教育

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual 教师资源中心教师网站

使用条款与条件

相关概念视频

Design Example: Identifying the Locations of Monuments in the Field Using Global Positioning System Device

Design Example: Identifying the Locations of Monuments in the Field Using Global Positioning System Device

Surveyors use Global Positioning System (GPS) technology to measure the precise location and elevation of points on Earth. In a recent survey, GPS receivers were used to determine the coordinates and elevations of two park monuments. The process involved careful mission planning, data collection, and correction to ensure accuracy. The survey began with mission planning to identify optimal satellite visibility and minimize Position Dilution of Precision (PDOP). A geodetic control point...

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序

Same author

An energy aware Q-learning framework for comprehensive coverage path planning in unknown complex environments.

Scientific reports·2025

Same author

Cloud-native simulation framework for gossip protocol: Modeling and analyzing network dynamics.

PloS one·2025

Same author

Artificial Tactile Sensory Finger for Contact Pattern Identification Based on High Spatiotemporal Piezoresistive Sensor Array.

ACS applied materials & interfaces·2024

Same author

A high-dimensional, multi-transceiver channel state information dataset for enhanced human activity recognition.

Data in brief·2024

Same author

Effect of titanium dioxide nanoparticles and co-composted biochar on growth and Cd uptake by wheat plants: A field study.

Environmental research·2023

Same author

Zinc oxide nanoparticles coated urea enhances nitrogen efficiency and zinc bioavailability in wheat in alkaline calcareous soils.

Environmental science and pollution research international·2023

Search research articles

相关实验视频

Updated: Jan 12, 2026

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

精确的室内定位使用轻量级的2D-CNN与自适应温度引导的代自我知识蒸.

Muhammad Rizwan¹, Yin Hoe Ng², Hin-Yong Wong¹

¹Faculty of Artificial Intelligence and Engineering, Multimedia University, 63100, Cyberjaya, Malaysia.

Scientific reports

|November 7, 2025

概括

这项研究引入了一种新的轻量级卷积神经网络 (CNN),用于使用Wi-Fi和蓝牙信号准确的室内定位. 该方法可将定位精度提高8%以上,并将误差降低到2.24m,使其适用于资源有限的设备.

关键词:

3D卷积神经网络是一个3D卷积神经网络.计算复杂性计算复杂性室内本地化室内本地化知识的蒸知识的蒸.接收器的信号强度指示器.

更多相关视频

Visualization Method for Proprioceptive Drift on a 2D Plane Using Support Vector Machine

Visualization Method for Proprioceptive Drift on a 2D Plane Using Support Vector Machine

Published on: October 27, 2016

相关实验视频

Last Updated: Jan 12, 2026

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Visualization Method for Proprioceptive Drift on a 2D Plane Using Support Vector Machine

Visualization Method for Proprioceptive Drift on a 2D Plane Using Support Vector Machine

Published on: October 27, 2016

科学领域:

计算机科学计算机科学
电气工程电气工程
信号处理信号处理

背景情况:

使用Wi-Fi和蓝牙RSS进行基于指纹的室内定位至关重要,但在部署约束下面临准确性挑战.
深度卷积神经网络 (CNN) 提供了更高的准确性,但对于资源有限的设备来说太复杂了.
知识蒸 (KD) 能够将知识从复杂模型转移到更简单的模型,但通常需要单独的教师-学生架构.

研究的目的:

提出一种新的轻量级二维CNN架构,以减少基础设施的室内本地化.
整合挤压和激发 (SE) 模块和自适应温度引导的代自我知识蒸 (SKD) 以提高准确性和效率.
在资源有限的平台上实现实用,实时的室内定位.

主要方法:

开发了一个轻量级的2D CNN,结合SE模块进行动态特征重新校准.
在单一模型中实施了一种代的SKD策略,消除了对单独教师模型的需求.
在HDLC公共数据集上评估拟议的架构,以确定室内定位的准确性.

主要成果:

没有SKD的CNN架构比传统CNN提高了8.32%的定位精度,实现了2.60m的3D平均定位误差 (APE).
整合代SKD进一步提高了1.66%的定位精度,将3DAPE降低到2.24m.
拟议的方法证明了室内定位的显著效率和准确性.

结论:

具有SE模块和代SKD的新型轻量级CNN提供了一个资源高效和实用的解决方案,用于准确的室内定位.
与传统的KD方法相比,单模型KD方法显著降低了计算开销.
该框架可在具有有限计算能力的设备上提供实时室内定位应用.