Extracting the most relevant information from biophotonic data: a Constrained Maximum Entropy methodology

This paper presents a novel approach, the Constrained Maximum Entropy (CME) methodology, for extracting knowledge from biophotonic data. More specifically, we discuss the main issues related to this new type of data and demonstrate the potential of the CME methodology to incorporate both a priori knowledge and data constraints to efficiently analyze biophotonic data. The key advantage lies in its ability to determine the most “unbiased” biophoton distribution - one with maximum entropy among distributions that satisfy given constraints while remaining uncommitted to unavailable information. Furthermore, we advance the discussion by proposing that the CME formulation, enriched with quantitative and qualitative constraints derived from precise biophoton emissions, serves as a powerful new tool for monitoring changes in biological systems. It holds the potential to identify unstable states and assess the impact of novel treatments on these systems. An empirical application for the plant study based on imaging sensors and AI mathematical algorithms is also provided.