论文标题
帕金森氏病检测中的1D信号的变压器从步态检测
Transformers for 1D Signals in Parkinson's Disease Detection from Gait
论文作者
论文摘要
本文的重点是基于对患者步态的分析来检测帕金森氏病。在自然语言处理和图像识别中，变形金刚网络的日益普及和成功促使我们基于通过变压器提取自动特征来为此问题开发新的方法。在1D信号中使用变压器并不是很普遍，但是我们在本文中表明它们有效从1D信号中提取相关功能。由于变压器需要大量内存，我们将时间和空间信息解耦以使模型较小。我们的体系结构使用了颞变压器，缩小层来减少数据的维度，空间变压器，两个完全连接的层和一个输出层作为最终预测。我们的模型的表现优于当前的最新算法，其精度为95.2 \％，可以将帕金森氏症患者与Physionet数据集中的健康患者区分开来。从这项工作中学习的一个关键学习是，变形金刚可以在结果中提高稳定性。源代码和预训练的模型在https://github.com/ducminhdimitringuyen/transformers-for-1d-signals-in-parkinson-s-parkinson-s-disease-detection-gait.git.git.git.git中
This paper focuses on the detection of Parkinson's disease based on the analysis of a patient's gait. The growing popularity and success of Transformer networks in natural language processing and image recognition motivated us to develop a novel method for this problem based on an automatic features extraction via Transformers. The use of Transformers in 1D signal is not really widespread yet, but we show in this paper that they are effective in extracting relevant features from 1D signals. As Transformers require a lot of memory, we decoupled temporal and spatial information to make the model smaller. Our architecture used temporal Transformers, dimension reduction layers to reduce the dimension of the data, a spatial Transformer, two fully connected layers and an output layer for the final prediction. Our model outperforms the current state-of-the-art algorithm with 95.2\% accuracy in distinguishing a Parkinsonian patient from a healthy one on the Physionet dataset. A key learning from this work is that Transformers allow for greater stability in results. The source code and pre-trained models are released in https://github.com/DucMinhDimitriNguyen/Transformers-for-1D-signals-in-Parkinson-s-disease-detection-from-gait.git
