Sugarcane mosaic virus (SCMV) is one among many viruses that infect sugarcane, cause yield loss, and become serious disease agents on sugarcane plantations. Since the morphological symptoms of SCMV are similar to other symptoms caused by Sugarcane streak mosaic virus (SCSMV) or nitrogen deficiency, the detection of SCMV is important through accurate diagnostic-like ELISA or RT-PCR. This research aimed to study the causative mosaic pathogen of SCMV in East Java, Indonesia, including mosaic development. The results showed that the mosaic symptom is present in all sugarcane plantations with 78% and 65% disease incidence and severity, respectively. Moreover, the detection procedure based on an amplification of cDNA of the coat protein gene sequence confirmed that SCMV was the causative agent of mosaic disease on sugarcane. Re-inoculation of healthy sugarcane plants with plant sap from a symptomatic leaf from the field showed similar mosaic or yellowish chlorotic areas on the leaf blade, and appeared on the fourth leaves upward from the inoculation leaf, in addition to showing different levels of peroxidase but not total phenol. Mosaic also correlated with the amount of total chlorophyll. Although Sucrose phosphate synthase (SPS) protein accumulation and activity were at a lower level in infected leaves, sucrose accumulation was at a higher level in the same leaves.

General elections are an important part of the political process so that many political figures participate in the process. Electability is one of the concerns, various things are done to be able to increase the electability of political figures who participate in general elections. Media has become one of the important tools used to increase electability, one of which is online news media. Reader comments can be used as an assessment of political figures in the form of sentiment analysis. However, it is not easy to analyze sentiments from comments on online news media, because comments contain unstructured text, especially in Indonesian text. Text pre-processing in text mining is an important part of getting the basic information contained in the comments. This research uses Indonesian text pre-processing using the Gata Framework Tetmining. Then proceed with extracting information using the Naïve Bayes classification algorithm and Support Vector Machine which are optimized using Particle Swarm Optimization. Tests carried out with both methods get the results that, Particle Swarm Optimization based on Support Vector Machine is the best method with an accuracy of 78.40% and AUC 0.850. This study found an algorithm that was effective in classifying positive and negative comments related to political figures from online news media.

No abstract

The intense competition in the sale of goods and services in the digital era of e-commerce requires to manage customers optimally. Some online shops try to improve their marketing strategies by classifying their customers. This study aims to determine potential customers, namely loyal customers. Potential customers can be determined by customer segmentation. Sampling from several online shops in Indonesia. The model used for segmentation is RFM (Recency, Frequency, and Monetary) and data mining techniques, namely clustering method with the K-Means algorithm. The results of this segmentation research divide the customer into 2 clusters. The best number of clusters is determined based on the Davies Bouldin index. The first cluster is cluster 0 consisting of 261 customers with RFM Score between 111–543. The first cluster includes the Everyday Shopper group. The second cluster, cluster 1 consists of 102 customers with RFM Score 443–555. The second cluster includes the Golden Customer group. With the existence of research on customer segmentation, it is expected to help in grouping customers so that companies can determine the right strategy for each group of customers.

There are more than 80 species of fish caught by fishermen in the sea of Indonesia. To find out what kinds of fish mostly caught, it is necessary to analyse the data pattern of fish being caught. The activities of searching and associating the data pattern are closely related to data mining technique that being used to discover the rules of association of items. In this associative rule method, there are two process can be used: the process of generating frequent itemset and finding associative rules. The Frequent Itemset Generation is a process to get the connection of the itemset and the value of the association based on the value of support and confidence. The algorithm used to generate the frequent itemset is Apriori Algorithm. The Apriori Algorithm has a weakness in the extraction of the appropriate feature of the used attributes. This condition causes the rules formed in large number. This research applies Apriori Algorithm based on principal component analysis to obtain more optimal rules. After the experiments using the apriori algorithm applied with the magnitude ˚ = 30, minimum Support 80% and Confidence 80%, the result of the rule formed are totally 82 rules.