System and method for reducing size of raw data by performing time-frequency data analysis

A system for reducing size of the raw data based on spectral and statistical properties of the raw data by performing time-frequency data analysis to identify relevant categories of events from the raw data, the system comprises:

• a processor;
• a memory coupled to the processor, wherein the processor is capable for executing programmed instructions stored in the memory to:
• calculate Wigner Ville Distributions (WVD's) for a plurality of windows of the raw data, wherein a window of the plurality of windows comprises a predefined number of samples of the raw data;
• compute Renyi entropies over the WVD's for the plurality of windows;
• compute a distribution of magnitudes of the Renyi entropies over the plurality of windows;
• identify a first set of windows from the plurality of windows based upon a Renyi entropy threshold and upon the distribution of magnitudes of the Renyi entropies, wherein the Renyi entropy threshold is related to a complexity of the raw data, and wherein the complexity indicates an amount of information present in the raw data;
• compute Wigner Ville Spectrum (WVS) of the first set of windows, wherein the WVS is indicative of an average of the WVD's of all windows present in the first set of windows, and wherein the WVS is stored in form of a Time-Frequency matrix;
• compute a Renyi divergence using the WVS and the WVD's for the first set of windows;
• compute a distribution of the Renyi divergence over the first set of windows;
• prepare a dataset comprising a second set of windows selected from the first set of windows, wherein the second set of windows has the Renyi divergence lower than a predefined divergence threshold, and wherein the predefined divergence threshold is selected based on time-frequency test statistics;
• calculate Eigen values for the Time-Frequency matrix of the WVS of the second set of windows, wherein the Eigen values are indicative of spectral features of the second set of windows;
• identify a third set of windows from the second set of windows, wherein the third set of windows has the Eigen values greater than a predefined Eigen threshold;
• cluster the Eigen values of the third set of windows into clusters of Eigen values based upon a nearest neighbour rule;
• compute centroids of the clusters of Eigen values, wherein the centroids are indicative of the relevant categories of events;
• and
• classify at least one window, of the third set of windows, with the Eigen values having a nearest distance to one of the centroids, thereby reducing size of the raw data.

A non-transitory computer readable medium embodying a program executable in a computing device for reducing size of the raw data based on spectral and statistical properties of the raw data by performing time-frequency data analysis to identify relevant categories of events from the raw data, the program comprising:

• a program code for calculating Wigner Ville Distributions (WVD's) for a plurality of windows of the raw data, wherein a window of the plurality of windows comprises a predefined number of samples of the raw data;
• a program code for computing Renyi entropies over the WVD's for the plurality of windows;
• a program code for computing a distribution of magnitudes of the Renyi entropies over the plurality of windows;
• a program code for identifying a first set of windows from the plurality of windows based upon a Renyi entropy threshold and upon the distribution of magnitudes of the Renyi entropies, wherein the Renyi entropy threshold is related to a complexity of the raw data, and wherein the complexity indicates an amount of information present in the raw data;
• a program code for computing a Wigner Ville Spectrum (WVS) of the first set of windows, wherein the WVS is indicative of an average of the WVD's of all windows present in the first set of windows, and wherein the WVS is stored in form of a Time-Frequency matrix;
• a program code for computing a Renyi divergence using the WVS and the WVD's for the first set of windows;
• a program code for computing a distribution of the Renyi divergence over the first set of windows;
• a program code for preparing a dataset comprising a second set of windows selected from the first set of windows, wherein the second set of windows has the Renyi divergence lower than a predefined divergence threshold, and wherein the predefined divergence threshold is selected based on time-frequency test statistics;
• a program code for calculating Eigen values for the Time-Frequency matrix of the WVS of the second set of windows, wherein the Eigen values are indicative of spectral features of the second set of windows;
• a program code for identifying a third set of windows from the second set of windows, wherein the third set of windows has the Eigen values greater than a predefined Eigen threshold;
• a program code for clustering the Eigen values of the third set of windows into clusters of Eigen values based upon a nearest neighbour rule;
• a program code for computing centroids of the clusters of Eigen values, wherein the centroids are indicative of the relevant categories of events;
• and
• a program code for classifying at least one window, of the third set of windows, with the Eigen values having a nearest distance to one of the centroids, thereby reducing size of the raw data.