Machine learning is an alternative tool for classifying animal species, especially feral cats. In this research, we use a machine learning algorithm to classify three species of feral cats: American Wildcat, Black-footed Cat, and European Wildcat. We also use a transfer learning model using the VGG-19 network for extracting the features in the feral cat images. By combining the VGG-19 and logistic regression algorithm, we build six models and compare which one is the best to solve the problem. We evaluate and analyze all models using a 5-fold, 10-fold, and 20- fold cross-validation, with accuracy, precision, and recall as the base performance value. The best result obtained is a model with a lasso regularization and cost parameter value of 1, with an accuracy value of 0.846667, a precision value of 0.845389, and a recall value of 0.846667. We also tune the C parameter in each LR model with values such as 0.1, 0.5, and 1. The most optimum C value for the lasso and ridge regularization is one, resulting in an average value of accuracy = 0.813, precision = 0.812, and recall = 0.813.

Tomato Leaf Disease is one of the common things for farmers in growing tomatoes. Tomatoes are one of the popular crops that can grow in low and high areas but are susceptible to disease. For this reason, farmers take precautions by looking at the characteristics and texture of tomato leaves. However, this requires more time and money and a long process. One of the efforts that can be made is to classify tomato leaf diseases. This research aims to classify using the Support Vector Machine and K-Nearest Neighbor methods. The dataset used is tomato leaf image data with 4 classes of leaves affected by disease and 1 healthy leaf. We evaluate and analyze all models using 5-Fold, 10-Fold, and 20-Fold Cross Validation with accuracy, precision, and recall for the best accuracy. The best results of this study are accuracy in the SVM method of 0.953 or 95.3%, Precision of 0.953 or 95.3%, and Recall of 0.953 or 95.3% with 10-Fold Cross-Validation. Compared to the K-NN method, it only obtained an accuracy of 0.907 or 90.7%, a Precision of 0.908 or 90.8%, and a Recall of 0.907 or 90.7% with 10-Fold Cross-Validation.