The Water Potability Prediction Based on Active Support Vector Machine and Artificial Neural Network
Rui Jie Zhao · 2021
The total amount of water on the planet is approximately 1.4 billion cubic kilometers, but only 2.5% of it is fresh water. Among freshwater resources, human drinkable water resources account for only 0.3 % of them. In Africa, hundreds of thousands of people fall ill or even die from drinking unclean water every year. If the water potability can be predicted accurately, then it can save a lot of the human, material and financial resources of the country and the region on the drinkability of water resources, which is an important step for the application of machine learning in water resources monitoring. In the technology field, today's machine learning technology has become mature, and it has been applied in many fields such as finance, biology, and medical care. The algorithms in machine learning can be used to help humans quickly identify whether water can be drunk so that the efficiency of identifying water availability is greatly improved. Among the many machine learning methods, artificial neural networks and support vector machine algorithms became popular in machine learning due to their large processing data and fast calculation speed. Therefore, selecting the above two algorithms to judge the drinking ability of water resources is expected to better achieve the desired purpose. In conclusion, after constant tuning of parameters and changing the calculation mode, a high-precision artificial neural network model and SVM prediction model were obtained, which make judgments in an extremely efficient manner and predictions highly accurate.