Capsicum is a genus of flowering plants in the Solanaceae family in which the members are well known to have a high economic value. The Capsicum fruits, which are popularly known as peppers or chili, have been widely used by people worldwide. It serves as a spice and raw material for many products such as sauce, food coloring, and medicine. For many years, scientists have studied this plant to optimize its production. A tremendous amount of knowledge has been obtained and shared, as reflected in multiple knowledge-based systems, databases, or information systems. An approach to knowledge-sharing is through the adoption of a common ontology to eliminate knowledge understanding discrepancy. Unfortunately, most of the knowledge-sharing solutions are intended for scientists who are familiar with the subject. On the other hand, there are groups of potential users that could benefit from such systems but have minimal knowledge of the subject. For these non-expert users, finding relevant information from a less familiar knowledge base would be daunting. More than that, users have various degrees of understanding of the available content in the knowledge base. This understanding discrepancy raises a personalization problem. In this paper, we introduce a solution to overcome this challenge. First, we developed an ontology to facilitate knowledge-sharing about Capsicum to non-expert users. Second, we developed a personalized faceted search algorithm that provides multiple structured ways to explore the knowledge base. The algorithm addresses the personalization problem by identifying the degree of understanding about the subject from each user. In this way, non-expert users could explore a knowledge base of Capsicum efficiently. Our solution characterized users into four groups. As a result, our faceted search algorithm defines four types of matching mechanisms, including three ranking mechanisms as the core of our solution. In order to evaluate the proposed method, we measured the predictability degree of produced list of facets. Our findings indicated that the proposed matching mechanisms could tolerate various query types, and a high degree of predictability can be achieved by combining multiple ranking mechanisms. Furthermore, it demonstrates that our approach has a high potential contribution to biodiversity science in general, where many knowledge-based systems have been developed with limited access to users outside of the domain.
11 June 2019 in Computer Engineering and Applications Journal
Recommender system aims to provide on something that likely most suitable and attractive for users. Many researches on the book recommender system for library have already been done. One of them used association rule mining. However, the system was not optimal in providing recommendations that appropriate to the user's preferences and achieving the goal of recommender system. This research proposed a book recommender system for the library that optimizes association rule mining using genetic algorithm. Data used in this research has taken from Yogyakarta City Library during 2015 until 2016. The experimental results of the association rule mining study show that 0.01 for the greatest value of minimum support and 0.4359 for the average confidence value due to a lot of data and uneven distribution of data. Furthermore, other results are 0.499471 for the average of Laplace value, 30.7527 for the average of lift value and 1.91534252 for the average of conviction value, which those values indicate that rules have good enough level of confidence, quite interesting and dependent which indicates existing relation between antecedent and consequent. Optimization using genetic algorithm requires longer execution time, but it was able to produce book recommendations better than only using association rule mining. In Addition, the system got 77.5% for achieving the goal of recommender system, namely relevance, novelty, serendipity and increasing recommendation diversity.
In the last decade, our capability to collect data has been improved significantly. A new era of big data has emerged as indicated by five characteristics of data: volume, variety, veracity, velocity, and value. The adoption of open-science approach is important in order to manage and exploit the available data appropriately. An open science approach enables curation, discovery, linking, and reusability of data across the globe. The challenge lies in the data heterogeneity, limitation of data interface, and conventional data visualization practices. In this work, we introduce a solution to overcome the challenges by using the Linked Data approach. The solution enables data to be represented in a machine-readable format and linked to or from external data sets, in a way that can be easily integrated, allow search optimization, as well as open the possibility to obtain new knowledge. Our solution consists of a schema construction to uniformly represent biodiversity data (mostly biological specimen data). After that, mapping rules were defined to align data from multiple biodiversity information systems that are available on the Web to the constructed schema. Finally, an engine will consume the mapping rules and generate linked data in a common format. Our results indicate that despite multiple data structures have been utilized by multiple systems, the mapping rules provide flexibility to accommodate every one of them. Further, we successfully demonstrated the possibility to deliver linked biodiversity data across multiple sources as our first step to harness big data biodiversity.
Indonesian Government Budget Appropriations or Outlays for Research and Development (GBAORD) is one of component from Indonesian Gross Expenditure on Research and Development (GERD). Calculation of GBAORD are made by classifying each government expenditure budget. Classification is done manually so that there are frequent inconsistencies. This study proposed an automated classification using decision tree and Naive bayes algorithm to handle problem in previous method. The result of study have conclusion that an automated classification using Naive bayes is more accurate than using decision tree. The highest average accuracy score given by Naive Bayes model in this experiment is 98.462 while decision tree gives about 90.236. This can be related to the number of features involved in classification process. Naive Bayes uses most of the features in data while decision tree only uses one feature. Although decision tree model only uses one feature, the accuracy score produced by the model is considered as high.