Oil palm plant diseases typically manifest themselves on the leaves, resulting in reduced crop quality. It is necessary to solve this issue as the need for premium-quality palm oil keeps growing. Despite the fact that various automatic detection models for oil palm leaf disease have been developed, their performance was frequently inadequate due to the similarity of class characteristics. This work proposes a method that automatically detects the oil palm leaf disease on a natural background to distinguish between infected and healthy leaf classes. The method was developed using deep learning based on Convolution Neural Network (CNN) model. The private dataset consists of 600 oil palm leaf images (300 healthy and 300 infected) on a natural background. In order to decrease the computation time, pre-processing was carried out, which consists of resizing and normalizing the image, followed by augmentation. Augmentation was applied by rotation, flip, shear, and zooming techniques. Furthermore, the CNN model was employed to detect oil palm leaf disease using Tensorflow 2.5.0 framework with $224\ \times\ 224$ input data. The proposed method successfully achieved the highest performance, revealed by the accuracy value of 1.

To achieve the objectives of the Internal Quality Assurance System, the Quality Standard document must be socialized to each work unit, and the existence of information technology will greatly assist in the distribution and socialization of these documents. This study aims to design and build a data model for storage and management of SPMI documents, especially Standard documents, which are generally in the form of files in print or digital format with a complete structure as a collection of text. With the data model designed, the Standard document is stored in a divided state into a number of entities that represent sub-sections of the document and are structured. This research produces a data model design with a relational system, so that it will produce optimal performance when create, retrieve, update and delete operations are carried out on Standard Documents, and still produce complete information about standard documents, as well as one aspect or context. in Standard documents and their linkages, through application programs and information systems. Testing was carried out by the black-box method of the SPMI document information system prototype which indicated that the data model was successfully implemented and worked well in its application.

The problem at PT. TMCI is that the lab part is still confused in determining the quality of some cocoa beans, because there is no average calculation. So that the quality of cocoa depends only on the specified parameters, and the moisture content, the count of cocoa beans as the first determinant of quality. The purpose of this study is to make a decision model in a decision making with the Multidimensional Scaling method, and a decision support system as a decision maker in determining the quality of cocoa beans, and implementing a decision support system and calculation of MDS metrics with several parameters, namely based on moisture content, moudly, broken beans, weight of waste, number of cocoa beans and flat cocoa beans. Then apply the MDS method in an Android-based application system, so that from the calculation results can determine which quality is good and which will be mixed again. Data collection is done by observing conditions directly, and conducting interviews. From the results of testing implementation, interviews and testing applications, that the application works properly when used. In terms of appearance and function the application can help the lab and the owner at the time of supplying supplier data. So it was concluded that this application could be well received and answer the problems of the lab and the owner.