期刊
IEEE SENSORS LETTERS
卷 7, 期 5, 页码 -出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/LSENS.2023.3273733
关键词
Computational efficiency; Computer architecture; Sensors; Pipelines; Convolutional neural networks; Computational modeling; Standards; Sensor applications; convolutional neural networks (CNNs); neural architecture search (NAS); smart sensors; tactile systems; touch modality classification
This letter introduces a neural architecture search method to optimize tactile elaboration systems, considering the computational cost of the entire pipeline including data preprocessing and a convolutional neural network (CNN) model for information extraction. The strategy is applied to train standard 1-D CNNs and binary CNNs on a three-class touch modality classification dataset. Experimental results show that systems based on standard CNNs outperform state-of-the-art techniques in terms of accuracy and computational cost, while those based on binary CNNs further reduce computational cost with a slight accuracy drop.
This letter presents a neural architecture search to optimize tactile elaboration systems taking into account the computational cost of the whole pipeline consisting of data preprocessing and a convolutional neural network (CNN) model to extract information. The strategy is exploited to train standard 1-D CNNs and binary CNNs on a three-class touch modality classification dataset. The experimental results show that systems based on standard CNNs outperform state-of-the-art techniques in terms of accuracy and computational cost, while the ones based on binary CNNs further reduce the computational cost with a small accuracy drop.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据