En este artículo, analizaremos la aplicación de filtros digitales a series temporales representadas en el dominio de la frecuencia con el fin de extraer características únicas que puedan resultar útiles para los modelos de predicción.
In the article "Practical Implementation of Digital Filters in MQL5 for Beginners" the author, presented digital filters applied in the time domain, through convolution. The series is multiplied with a unique set of weights of varying length, depending on the filter type and its parameters. The number of weights define a moving window that is convolved with corresponding series values as the filter is applied over the extent of the data. Moving averages also work in the same manner.
In this article, we will apply filters in the frequency domain. The basic steps involved are as follows:
First the series is preprocessed in preparation of a DFT operation.
Next we manipulate the waveform of the series in whatever way we deem necessary. That is to say, a filter is applied, thereby modifying the original waveform of the series.
An inverse DFT operation is done on the modified waveform, converting it back to the familiar time domain.
Lastly we undo any effects brought on by operations conducted at the initial preprocessing step.
Para iniciar sesión y usar el sitio web MQL5.com es necesario permitir el uso de Сookies.
Por favor, active este ajuste en su navegador, de lo contrario, no podrá iniciar sesión.
Ha iniciado sesión. La autenticación de dos factores se ha desactivado. Vuelva a configurarla y escanee un nuevo código QR, o continúe con la autenticación de dos factores desactivada.
Artículo publicado Filtrado y extracción de características en el dominio de la frecuencia:
En este artículo, analizaremos la aplicación de filtros digitales a series temporales representadas en el dominio de la frecuencia con el fin de extraer características únicas que puedan resultar útiles para los modelos de predicción.
In the article "Practical Implementation of Digital Filters in MQL5 for Beginners" the author, presented digital filters applied in the time domain, through convolution. The series is multiplied with a unique set of weights of varying length, depending on the filter type and its parameters. The number of weights define a moving window that is convolved with corresponding series values as the filter is applied over the extent of the data. Moving averages also work in the same manner.
In this article, we will apply filters in the frequency domain. The basic steps involved are as follows:
Autor: Francis Dube