如果发现问题,请联系我
No Truce With Furies
自适应傅里叶分解 (AFD) 是传统傅里叶分解的扩展。 通过匹配追踪生成自适应基,AFD 实现了分解过程中的快速能量收敛。
这个工具箱旨在方便用户使用与改进 AFD 算法。此工具箱提供了 AFD 的传统计算版本(计算速度较慢)和FFT加速版本(计算速度较快)。其中包括 Matlab 与 Python 两个版本。
AFD算法与加速版本的简介可以在《自适应傅里叶分解 (AFD) 简介》和《快速自适应傅里叶分解 (Fast AFD) 简介》中找到。
Python 版本有一个简单的在线演示,第一次尝试 AFD 的用户可以尝试此演示来理解 AFD 的分解过程。
一个用来学习与测试 SSVEP 识别算法的 Python 包。目标是让研究人员快速熟悉 SSVEP 信号和相关识别算法,并缩短准备时间来专注于改进算法。
数据库:
SSVEP 识别算法:
This study is intended to achieve a general stimulus-stimulus transfer of SSVEP signals.
To achieve the stimulus-stimulus transfer, this study proposes a new perspective to analyze the SSVEP signals, which is the time-frequency-joint representation. In this representation, the SSVEP signals of different stimuli are synchronized according to the stimulus frequencies and phases. Then, the common components of different stimuli can be emphasied and become possible to be characterized and extracted. From the time-frequency-joint-representation point of view, a new SSVEP signal model is proposed for the stimulus-stimuls transfer. Moreover, an adaptive decomposition approach based on the multi-channel adaptive Fourier decomposition (MAFD) is designed to estimate components in the porposed SSVEP model, which is the MAFD with different phases (DP-MAFD).
Codes in this repository implement the simulations for the Benchmark Dataset. Simulation results show the classification performance of SSVEP templates constructed by the proposed stimulus-stimulus trnasfer.
Ze Wang et al., "Stimulus-stimulus transfer based on time-frequency-joint representation in SSVEP-based BCIs," IEEE Trans. Biomed. Eng., 2022. DOI: 10.1109/TBME.2022.3198639.
使用 Matlab 建立的一个 6 自由度 3D Yaskawa 模型演示。
此演示中包括两个 demo,一个是控制机器臂绘制 “UM” 字样,一个是控制控制机器臂绘制一个圆形。