Abstract:
The Paper titled “Analyzing the adaption of organic fertilizer in aquaculture by using
embedded technology” is a comprehensive review that delves into the transformative
role of machine learning and IoT in Aquaculture. This study also deals with assessing
water purifying, Pond Plankton growth, and specific Ph and TDS determination for fish
farming for some selective ponds. The Paper proceeds with a detailed analysis of
machine learning and IoT applications across various aquaculture domains. As our
country is a riverine country, we get most of the fish from here. Which we can eat and
sell to earn domestic and foreign exchange. So, we need to protect these fish. But day
by day the population is increasing. As a result, new problems arise and new
requirements are needed. As the increased population fulfills the protein requirement
people have developed fish farming for the fish's natural growth. The nutrition level of
the fish in the river is very good but over time, the condition of the river is deteriorating
due to which the amount of fish farming in the pond is increasing day by day. Fish
needs extra care to get good quality fish. Chemical fertilizers are used to increase the
growth rate of fish but we want to increase the growth rate naturally. Plankton is a type
of organic food for fish. Use organic fertilizers to increase plankton growth. The use of
modern technology will be a successful development and fulfill people’s needs also
there are various drawbacks in cage-culture. If we recover this problem with a modern
system, it’ll be very helpful for this aqua species and enhance our economic state. We
implemented and evaluated several models to predict plankton growth, achieving
varying degrees of accuracy. Our Random Forest Classifier model from accuracy of
100%. In machine learning, the Logistic Regression accuracy rates of 99.30%, the K-
Nearest Neighbors (KNN) model yielded an accuracy of 95.12%, the Gradient Boost
accuracy rates of 100%, while the Support Vector Machine (SVM) model reached an
accuracy of 61.85%. These results indicate that machine learning models, particularly
Random Forest and Gradient Boost, can provide highly reliable plankton growth
predictions based on the sensor data collected. The high accuracy rates of our models
demonstrate the potential for such IoT-based systems to offer precise and efficient
water quality monitoring solutions, contributing to the Adoption of organic fertilizer
in aquaculture by using embedded technology.
