Expectation-maximization algorithm for amplitude estimation of saturated optical transient signals

Area of Science:

• Optical transient signal analysis
• Statistical signal processing
• Data analysis with censoring

Background:

• Parameter estimation is crucial for understanding optical transient signals.
• Received data often suffers from right-censoring, complicating analysis.
• Additive background counts and measurement saturation further challenge accurate estimation.

Purpose of the Study:

• To develop a robust expectation-maximization (EM) algorithm for parameter estimation of optical transient signals.
• To specifically address challenges posed by right-censored data, signal saturation, and background noise.
• To evaluate the performance of the proposed algorithm against existing methods.

Main Methods:

• Development of a novel expectation-maximization (EM) algorithm tailored for right-censored optical transient data.
• Incorporation of a Poisson intensity model with known shape, accounting for additive background counts.
• Modeling of measurement saturation effects within the estimation framework.
• Comparative analysis against a standard EM algorithm that ignores data censoring.

Main Results:

• The developed EM algorithm effectively estimates signal amplitude under right-censoring and saturation.
• The proposed method demonstrates improved accuracy compared to an EM algorithm that does not account for censoring.
• The algorithm provides reliable parameter estimates in the presence of background counts.

Conclusions:

• The novel EM algorithm offers a significant advancement for analyzing right-censored optical transient signals.
• Accounting for censoring and saturation effects is critical for accurate parameter estimation.
• This work provides a valuable tool for researchers in optical transient detection and analysis.