Muhammad Subianto

Instability of classifiers on categorical data

In this paper we study the local behaviour of arbitrary classifiers using the instability of that classifier in a data point. Moreover, we introduce two algorithms. The first to find highly unstable points, the second to find islands of stability.

Periodic update and automatic extraction of web data for creating a Google Earth based tool

A lot of tropical disease cases that occurred in Indonesia are reported online in Indonesian news portals. Online news portals are now becoming great sources of information because online news articles are updated frequently. A rule-based, combined with machine learning algorithm, to identify the location of the cases has been developed. In this paper, a complete flow to routinely search, crawl, clean, classify, extract, and integrate the extracted entities into Google Earth is presented. The algorithm is started by searching for Indonesian news articles using a set of selected queries and Google Site Search API, and then crawling them. After the articles are crawled, they are cleaned and classified. The articles that discuss about tropical disease cases (classified as positive) are further examined to extract the locution of the incidence and to determine the sentences containing the date of occurrence and the number of casualties. The extracted entities are then stored in a relational database and annotated in an XML keyhole markup language notation to create a geographic visualization in Google Earth. The evaluation shows that it takes approximately 6 minutes to search, crawl, clean, classify, extract, and annotate the extracted entities into an XML keyhole markup language notation from 5 Web articles. In other words, it takes about 72.40 seconds to process a new page.

Understanding Discrete Classifiers with a Case Study in Gene Prediction

The requirement that the models resulting from data mining should be understandable is an uncontroversial requirement. In the data mining literature, however, it plays hardly any role, if at all. In practice, though, understandability is often even more important than, e.g., accuracy. Understandability does not mean that models should be simple. It means that one should be able to understand the predictions of models. In this paper we introduce tools to understand arbitrary classifiers defined on discrete data. More in particular, we introduce Explanations that provide insight at a local level. They explain why a classifier classifies a data point as it does. For global insight, we introduce attribute weights. The higher the weight of an attribute, the more often it is decisive in the classification of a data point. To illustrate our tools, we describe a case study in the prediction of small genes. This is a notoriously hard problem in bioinformatics.

A web-based agricultural commodity price information system for Aceh region, Indonesia

Agricultural commodity is one of important livelihoods for people in Aceh region. The basic meaning of commodity is something sold and bought so commodity price is a necessity information for farmers, buyers, traders, investors and consumers. This paper proposes a web-based information system to provide agricultural commodity price information specific to Aceh region. The system was named KomoditiAceh and designed to be accessible for public who need agricultural commodity price information. The development of KomoditiAceh implemented Rapid Applications Development (RAD) model by applying the steps from System Development Life Cycle (SDLC). RAD model applies several iterations to generate prototype for fulfilling system requirements. There are three entities in KomoditiAceh, they are public, author and administrator. Each entity has its own role so the interface can be slightly different. After the final prototype was completely developed, the usability of KomoditiAceh was analyzed by using System Usability Scale (SUS) method. SUS questionnaire has 10 questions and the questionnaires was distributed to 30 respondents. The result obtained from this questionnaire was calculated using SUS method and got SUS score 81 or B grade scale. That score means KomoditiAceh is regarded as excellent system and acceptable to use as a web-based agricultural commodity price for Aceh region.

Interactive statistics learning with RWikiStat

RWikiStat is a web based statistics learning. It is built by using Rweb (a web based interface for R statistical software) and Wiki Technology (MediaWiki). Rweb can be seen as a bridge between content and user in learning process, while MediaWiki is to guarantee the sustainability of the program. The output of this research are a website which can be accessed through intranet or internet, a start up CD/DVD for interactive statistics learning, and statistics modules for learning process.