Application of K-means algorithm in amino acid data set of different jujube cultivars

Jujube is an important food in our life. It is divided into three types: fresh, dried and processed jujube food. It is rich in nutrients and has certain health care functions and medicinal values. Shanxi Province is one of the main production areas of jujube, and its annual output ranks forefront of our country. Shanxi jujubes have a wide variety and are rich in amino acids and other nutrients. Although they are all produced in Shanxi, due to different cultivars, the contents of various amino acids in each cultivar of jujube are different. Based on this situation, according to the amounts of various amino acids in different cultivars of jujube, we use k-means clustering algorithm to cluster them. After clustering, the contents of various amino acids in each category of jujube are similar, while the contents of amino acids in different categories of jujube are quite different. According to this classification result, we can quantitatively analyze the nutritional values of jujube. According to the demand, we can also extract the high contents of amino acids from specific cultivars of jujube for production research and so on.