High-Dimensional Data Integration Model to Improve the Plants Quality

High Dimensional Data is data that has many dimensions or features with the aim of providing more complete and detailed information about an object or phenomenon. Plant images are objects that have data with many dimensions or features. Plant images can be analyzed to determine plant quality. For example, coffee plant images can be analyzed to determine the quality of coffee plants. Determination of coffee plant quality in previous studies only used one object such as leaves or stems and or fruit. In this study, the quality of coffee plants is measured using leaves, stems, fruit, and hypotheses from coffee plant experts. Analysis of coffee plant images can produce information in the form of size, color and health of plants. This information can be found by extracting image features. However, the large number of features is an obstacle in grouping. Clustering techniques are used to group the large amount of data in the dataset. Expert hypotheses will be used to validate the dataset, determine centroid values ​​and determine weight values ​​to determine plant quality. The obstacle in analyzing multidimensional data is the difficulty of visualizing the number of variables because the available methods generally only process low-dimensional data. The purpose of this study is to produce an integration model for analyzing plant quality datasets by optimizing machine learning to group high-dimensional data.