This paper gives a description of various signal processing techniques that are in use for processing time series databases for extracting relevant features for pattern recognition. In addition to describe the normally used signal processing methods, we also present a novel signal processing technique, which is a modification of the well-known Short-Time Fourier Transform (STFT) and Wavelet Transform for extracting suitable features for both visual and automatic classification of non-stationary time-series databases [3][5]. Although the new signal processing technique is useful for speech, medical, financial, and other types of time varying databases, only the power network disturbance time series is used for computing features for visual and automatic recognition.

No abstract

No abstract

No abstract

No abstract