Mango contains about 20 vitamins and minerals such as iron, copper, potassium, phosphorus, zinc, and calcium. The freshness of the ripe mango will taste sweet. The level of ripeness of the mango fruit can be seen from the texture of the skin and skin color. Ripe mangoes have a bright, fragrant color and a smooth skin texture. The problem found in mango segmentation is that the image of the mango fruit is influenced by several factors, such as noise and environmental objects. In measuring the maturity of mangoes traditionally, it can be seen from image analysis based on skin color. The mango peel segmentation process is needed so that the classification or pattern recognition process can be carried out better. The segmented mango image will read the feature extraction value of an object that has been separated from the background. The procedure on the image that has been analyzed will analyze the pattern recognition process. In this process, the segmented image is divided into several parts according to the desired object acquisition. Clustering is a technique for segmenting images by grouping data according to class and partitioning the data into mango datasets. This study uses the Fuzzy C Means method to produce optimal results in determining the clustering-based image segmentation. The final result of Fuzzy C-based mango segmentation processing means that the available feature extraction value or equal to the maximum number of iterations (MaxIter) is 31 iterations, error (x) = 0.00000001, and the image computation testing time is 2444.913636

During the Covid-19 pandemic, teachers and students carried out the online teaching and learning process from home. Distance learning has several problems including the limitations of teachers and students in the world of information and communication technology, the facilities and infrastructure they have, and environmental conditions that are less supportive. The use of laptops and the internet every day are used by students and teachers as the main means of the online teaching and learning process. Continuous use without proper maintenance and lack of knowledge in overcoming the problem of damage to laptops makes teachers and students unable to identify the location of the damage and how to deal with it. Therefore, this expert system application was created to assist teachers and students in detecting the symptoms of laptop damage experienced and solutions to overcome the damage. In the development of this expert system using the Naive Bayes method, this method only requires a small amount of training data to determine parameter estimates during the classification process. The results of the application of the nave Bayes method produce appropriate calculations based on the symptoms of damage and a predetermined list of damage so that it can make it easier for users when analyzing the beginning by using existing symptoms with a system that has been built with very efficient time and has an accuracy rate of 100%.