In this feasibility study, BlakBear will build a Machine Learning AI model to make real-time food freshness predictions for salmon, with the goal of reducing food waste.
This SIF Feasibility Study has enabled BlakBear to focus on developing our AI engine to turn BlakBear’s proprietary sensors into a predictive analysis tool, which is the self-improving aspect of our technology that predicts future spoilage.
BlakBear sensors directly measure spoilage directly and digitally, sending real-time data to the cloud that feeds into an AI engine to predict food freshness. From taking part in SIF, multiple supply chain simulations were conducted in-house to gather large sets of salmon spoilage data to train our self-improving shelf-life predictive feature of our suite of technologies.
Spoilage data was processed using signal processing techniques and was analysed using machine learning to predict freshness and shelf-life of a wide range of foods, where SIF enabled BlakBear to particularly focus on analysing data from fish, notably salmon.
SIF has also driven BlakBear to evaluate the commercial feasibility of the application of our technology in the seafood industry, from evaluating competitor risk to engaging with key players in the industry to determine the value that can be added to current sector needs across complex supply chains. This project has also driven the improvement of our spoilage data which in turn can be applied to the seafood industry, to improve quality control to better manage the cold chain.