.png){kind=icon}
返回
.png){kind=icon}
.png){kind=icon}
摘要
En 中文
This study presents a proof-of-concept demonstration of a demodulation technique using a seven-core fiber (SCF) and machine learning (ML) algorithms for multimode fiber (MMF)-based tactile sensing. By condensing high-resolution images into vectors of seven power values from the cores of the MMF, dataset size is significantly reduced compared to conventional specklegram sensors, mitigating post-processing workload. This downsampling approach, akin to machine learning pooling layers, boosts computational efficiency without compromising accuracy. Leveraging power measurements from the seven cores along with a Gaussian process regression model, the proposed sensor achieves a spatial resolution of 0.075 mm (1 mm sampling) for detecting normal force distribution, outperforming conventional ML algorithms used in MMF specklegram sensors with 20 times less computation time. Moreover, the sensor design enables simultaneous measurement of contact force and position with over 96% accuracy. This study underscores the potential of SCF-based sensors to streamline data acquisition and storage while preserving signal quality, potentially eliminating the need for free-space coupling and cameras commonly used in MMF specklegram setups, thus paving the way for all-fiber-based, high-speed, cost-effective, multi-parameter tactile sensors.
Keyword:
VECTOR MACHINE
期刊
IF:
3.3
论文数:
6.1W
被引数:
14.3W
机构
引用论文
Fast and robust demodulation of temperature from sparse sapphire fiber Bragg grating spectra with machine learning.png)
OPTICS EXPRESS.png)
OAAI
OPTICS EXPRESSIF3.3
OAAI.png){kind=icon}
分享.png){kind=icon}
收藏Public perspectives on the use of different data types for prediction in healthcare公众对医疗保健中不同数据类型用于预测的看法
OAAI
OAAI分享收藏分享收藏Machine learning for sensing with a multimode exposed core fiber specklegram sensorOPTICS EXPRESSOAAI
OPTICS EXPRESSIF3.3
OAAI分享收藏Machine-Learning-Enabled Multimode Fiber Specklegram Sensors: A Review支持机器学习的多模光纤散斑图传感器: 综述IEEE SENSORS JOURNAL
IEEE SENSORS JOURNALIF4.5
PREAI
分享收藏
查看更多内容