Approximate entropy (ApEn) is a technique used to quantify the unpredictability and regularity of fluctuations in time-series data. It reflects the likelihood that similar patterns will not be followed by additional similar observations. ApEn is useful for relatively short, noisy time-series data, as it can be applied to small sample sizes. ApEn has been used to distinguish patient groups in medical applications like endocrine hormone secretion where traditional statistics did not show differences. It has also been used to detect epileptic seizures from EEG data with over 96% accuracy when combined with discrete wavelet transforms.
Approximate entropy (ApEn) is a technique used to quantify the unpredictability and regularity of fluctuations in time-series data. It reflects the likelihood that similar patterns will not be followed by additional similar observations. ApEn is useful for relatively short, noisy time-series data, as it can be applied to small sample sizes. ApEn has been used to distinguish patient groups in medical applications like endocrine hormone secretion where traditional statistics did not show differences. It has also been used to detect epileptic seizures from EEG data with over 96% accuracy when combined with discrete wavelet transforms.
Approximate entropy (ApEn) is a technique used to quantify the unpredictability and regularity of fluctuations in time-series data. It reflects the likelihood that similar patterns will not be followed by additional similar observations. ApEn is useful for relatively short, noisy time-series data, as it can be applied to small sample sizes. ApEn has been used to distinguish patient groups in medical applications like endocrine hormone secretion where traditional statistics did not show differences. It has also been used to detect epileptic seizures from EEG data with over 96% accuracy when combined with discrete wavelet transforms.
Approximate entropy (ApEn) is a technique used to quantify the unpredictability and regularity of fluctuations in time-series data. It reflects the likelihood that similar patterns will not be followed by additional similar observations. ApEn is useful for relatively short, noisy time-series data, as it can be applied to small sample sizes. ApEn has been used to distinguish patient groups in medical applications like endocrine hormone secretion where traditional statistics did not show differences. It has also been used to detect epileptic seizures from EEG data with over 96% accuracy when combined with discrete wavelet transforms.
Download as PPTX, PDF, TXT or read online from Scribd
Download as pptx, pdf, or txt
You are on page 1of 19
APPROXIMATE
ENTROPY (ApEn)
Submitted to: Submitted by:
Prof. R. Kanda GAURAV KUMAR SHARMA Department of Mechanical ME17209004 Engineering Keywords • Deterministic Model: No randomness in development of future states.(i/p = same o/p) • Stochastic: having a random prob distribution or pattern that may be analyzed statistically but may not be predicted precisely. • Information Theory: studies quantification, storage and communication of info. • Entropy (statically): it quantifies the amount of regularity or uncertainty involved in value of random variable or the outcome of a random process • Dynamic system: fn describes time dependence of aa point in a geometric space. Eg flow of water in a pipe. Introduction • Developed by Steve M. Pincus • an approximate entropy (ApEn) is a technique used to quantify the amount of regularity and the unpredictability of fluctuations over time-series data, which appears to have potential application to a wide variety of relatively short (range 50-5000) and noisy time-series data. • motivated by data length constraints commonly encountered, e.g., in heart rate, EEG, and endocrine hormone secretion data sets. • Findings have discriminated groups of subjects via ApEn, in instances where classical [mean, standard deviation (SD)] statistics did not show clear group distinctions Cont… • ApEn reflects the likelihood that similar patterns of observations will not be followed by additional similar observations. A time series containing many repetitive patterns has a relatively small ApEn; a less predictable process has a higher ApEn. • KS entropy : true dynamic system • ApEn : general system (stochastic+deterministic) Cont… • In applications to endocrine hormone secretion data based on as few as N =72 points, ApEn has provided vivid distinctions between actively diseased subjects and normals, with nearly 100% specificity and sensitivity. Algorithm Cont… Example Cont… Cont.. Cont… Coding. • Python Other examples 2nd 3rd • detecting epileptic seizures from electro-encephalo-gram (EEG) data recorded from normal subjects and epileptic patients. • Seizure detection was accomplished in two stages. In the first stage, EEG signals were decomposed into approximation and detail coefficients using DWT. In the second stage, ApEn values of the approximation and detail coefficients were computed. • Significant differences were found between the ApEn values of the epileptic and the normal EEG allowing us to detect seizures with over 96% accuracy. Without DWT as preprocessing step, it was shown that the detection rate was reduced to 73%. Cont.. • during seizure activity EEG had lower ApEn values compared to normal EEG. This suggested that epileptic EEG was more predictable or less complex than the normal EEG. Cont… Advantages & applications • Advantages • Lower computational demand. ApEn can be designed to work for small data samples (n < 50 points) and can be applied in real time. • Less effect from noise. If data are noisy, the ApEn measure can be compared to the noise level in the data to determine what quality of true information may be present in the data. • Applications • ApEn has been applied to classify EEG in psychiatric diseases, such as schizophrenia, epilepsy, and addiction THANK YOU….