The recognition of herbs and spices among young generation is still low. Based on research in SMK 9 Bandung, showed that there are 47% of students that did not recognize herbs and spices. The method that can be used to overcome this problem is automatic digital sorting of herbs and spices using Convolutional Neural Network (CNN) algorithm. In this study, there are 300 images of herbs and spices that will be classified into 3 categories. It’s ginseng, ginger and galangal. Data in each category is divided into two, training data and testing data with a ratio of 80%: 20%. CNN model used in classification of digital images of herbs and spices is a model with 2 convolutional layers, where the first convolutional layer has 10 filters and the second convolutional layer has 20 filters. Each filter has a kernel matrix with a size of 3x3. The filter size at the pooling layer is 3x3 and the number of neurons in the hidden layer is 10. The activation function at the convolutional layer and hidden layer is tanh, and the activation function at the output layer is softmax. In this model, the accuracy of training data is 0.9875 and the loss value is 0.0769. The accuracy of testing data is 0.85 and the loss value is 0.4773. Meanwhile, testing new data with 3 images for each category produces an accuracy of 88.89%. Keywords: image classification, herbs and spices, CNN.

Hepatitis causes around 1.4 million people die every year. This number makes hepatitis to be the largest contagious disease in the number of deaths after tuberculosis. Liver biopsy is still the best method for diagnosing the stage of hepatitis C, but this method is an invasive, painful, expensive, and can cause complications. Non-invasively method needs to be developed, one of non-invasif method is machine learning. Random Forest and XGboost are classification methods that are often used, since they have many advantages over classical classification methods. The SMOTE algorithm can be used to improve the accuracy of predictions from imbalanced data. the data in this study have 24 independent variables in the form of patients self-data, hepatitis C symptoms, and laboratory test results. The dependent variable in this study is a binary category, namely the level of hepatitis C disease (fibrosis and cirrhosis). The results showed that the random forest and XGboost had an accuracy of around 74% but the recall value was less than 2%. SMOTE random forest dan SMOTE XGboost have an accuracy & recall value more than 75%. SMOTE random forest has a higher accuracy for predicting fibrosis class while SMOTE XGboost is better in cirrhosis class. Variables that are more influental in determining hepatitis C stage are variables from laboratory test. Keyword : Fibrosis, Cirrhosis, Random Forest, SMOTE, XGboost

No abstract

The k-medoids method is a non-hierarchical clustering to classify n object into k clusters that have the same characteristics. This clustering algorithm uses the medoid as its cluster center. Medoid is the most centrally located object in a cluster, so it’s robust to outliers. In cluster analysis the objects are grouped by the similarity. To measure the similarity, it can be used distance measures, euclidean distance and cityblock distance. The distance that is used in cluster analysis can affect the clustering results. Then, to determine the quality of the clustering results can be used the internal criteria with silhouette width and C-index. In this research the k-medoids method to classify of regencies/cities in Central Java based on type and number of crimes. The optimal cluster at k= 4 use euclidean distance, where the silhouette index= 0,3862593 and C-index= 0,043893. Keywords: Clustering, k-Medoids, Euclidean distance, Cityblock distance, Silhouette index, C-index, Crime

The research was conducted to measure rural banks (Bank Perkreditan Rakyat / BPR) efficiency level in Semarang city. The measurement was done using non parametric approach with Data Envolepment Analysis (DEA) method constant return to scale assumption (CCR model). The research was using all rural banks in Semarang (16 rural banks). The result indicated that 6 rural banks were efficient and 10 rurals banks were inefficient.