Discussion
As shown above, this method combining biosensors and deep learning has
many advantages such as high efficiency, low cost, and automation, and
is expected to be applied in the field of food quality assessment.
However, there are many challenges in these applications. First, in the
long run, it is necessary to develop effective sensing systems that are
cheap, reliable, and fully functional. Since different foods contain
different nutrients, how to choose A suitable biosensor to construct a
sensing system is still a problem, which needs to be selected according
to the needs of users, or according to the general formula for food
quality evaluation. Second, the generation of predictive models requires
a large amount of training data. Different models may need to be trained
for different types of food. Therefore, the amount of data is huge,
which requires specific hardware for data processing, model training and
evaluation. Therefore, combining technologies such as cloud computing,
5G networks can effectively address the challenges.