System and method for designing optimum modified atmosphere packaging

A system comprising:

• at least one memory storing programmed instructions;
• one or more Input/Output (I/O) interfaces;
• and one or more hardware processors operatively coupled to the at least one memory, wherein the one or more hardware processors are configured by the programmed instructions to:
• receive a plurality of timeseries data pertaining to a storage environment of a product to be packed and a plurality of time invariant package data comprising a plurality of Modified Atmosphere Packaging (MAP) design parameters,
• predict a plurality of temporal vectors associated with the plurality of timeseries data using a Long Short Term Memory (LSTM) neural network layer;
• compute a plurality of design vectors based on the plurality of time invariant package data using a two layered Artificial Neural Network (ANN) stack;
• generate a concatenated prediction vectors based on the plurality of temporal vectors and the plurality of design vectors using a concatenation layer;
• predict shelf-life period of the product to be packed based on the concatenated prediction vectors using a dense layer;
• and
• compute a plurality of optimum package design parameters for maximum shelf-life based on predicted shelf-life period of the product and environmental storage parameters using Bayesian optimization algorithm.

One or more non-transitory machine-readable information storage mediums comprising one or more instructions which when executed by one or more hardware processors cause:

• receiving, a plurality of timeseries data pertaining to a storage environment of a product to be packed and a plurality of time invariant package data comprising a plurality of Modified Atmosphere Packaging (MAP) design parameters,
• predicting, a plurality of temporal vectors associated with the plurality of timeseries data using a Long Short Term Memory (LSTM) neural network layer;
• computing, a plurality of design vectors based on the plurality of time invariant package data using a two layered Artificial Neural Network (ANN) stack;
• generating, a concatenated prediction vectors based on the plurality of temporal vectors and the plurality of design vectors using a concatenation layer;
• predicting, shelf-life period of the product to be packed based on the concatenated prediction vectors using a dense layer;
• and
• computing, a plurality of optimum package design parameters for maximum shelf-life based on predicted shelf-life period of the product and environmental storage parameters using Bayesian optimization algorithm.