An expert system as an expert knowledge-based information system has been widely used by interested parties to consult their problems. Therefore, an expert system should be well designed so as to meet the requirements for a software to store knowledge, explain problems, and recommend solutions. The purpose of the present study is to develop a systematic design of an expert system using Unified Modeling Language (UML), which is one of popular object-oriented modeling languages. The research method was a literature review as the main source for analyzing the expert system requirements. The developed design was then clarified, verified, and validated in a Focus Group Discussion (FGD). To evaluate the model, a review of some related studies was conducted. The research respondents were informatics lecturers at UIN Sunan Gunung Djati Bandung. The results of the study revealed that the systematic design of expert system was well-developed because it was user-friendly, flexible, easy to be modified, and able to propose solutions for various problems.
11 September 2020 in International Journal of Emerging Technologies in Learning (iJET)
This study aims to analyse the Key Success Factors (KSFs) of e-learning implementation, so that e-learning can work well and provide maximum benefits for learning activities process in higher education. The method used in this research is begin from investigate the determinant factors based on the results of literature studies and survey techniques. To obtain a more in-depth analysis, then the factors are weighted using the Multi-Attribute Utility Theory (MAUT) method. The results showed that the determinant factors that need to be used as the main consideration in the implementation of e-learning at higher education are organizational factors, technology, and human resources. The dominant factor that needs attention in realizing the effectiveness of the implementation of e-learning in higher education is the organizational aspect which is realized in the form of creating a work culture and setting policies that are binding on the academic community to carry out e-learning.
24 January 2018 in IOP Conference Series: Materials Science and Engineering
Many organisations (government of non-government) use websites to share information of new recruitment for the workers. This information overflows on thousands of sites with various attributes and criteria. However, this availability forms a complex puzzle in the selection process and lead to inefficient runtime. This study proposes a simple method for job searching simplification through a construction and collaboration of web scraping technique and classification using Naïve Bayes on search engine. This study is resulting an effective and efficient application for users to seek a potential job that fit in with their interests.
24 January 2018 in IOP Conference Series: Materials Science and Engineering
In a scientific work, an abstract always contains main information of an article including at least a researched problem, aim(s), methodology, and result of the study. Writing an abstract requires a conscientious analysis since the contents would affect both the readers' interestedness and disinterestedness on a particular or overall research topic. However, people generally write manually by summarizing the article. The aim of this study is constructing automation for summarizing Indonesian articles as an alternative approach to an This is involving two methods to summarize an article. A Term Frequency-inverse Document Frequency is used to get a keyword and weight terms, and a Vector Space Model is utilized to represent abstract text into a vector that used to identify the linkage of documents. From this method, the result of the summary can be generated from documents. Supporting this research, we used several journal articles written by a manual The results of this application show that the automatic summarization produces a paragraph which consists of more than three same sentences constantly as compared to manual paragraphing.
24 January 2018 in IOP Conference Series: Materials Science and Engineering
Pregnancy is an important moment of growth of the human being. In many case women do not know that she is being pregnant, this is one of the causes of miscarriage. For healthy pregnancy also need to be guarded by knowing abnormalities early in pregnancy. There are several early pregnancy disorder among others hyperemesis gravidarum, pre-eclampsia and eclampsia, hydatidiform mole, and ectopic pregnancy. In this research, we propose an expert system using Artificial Neural Network (ANN) and Back Propagation algorithm for predicting the pregnancy with disorders early. We used 172 medical records of patient with 17 input parameters and 5 output classes, among others normal early pregnancy, and 4 classes for pregnancy disorders. The experiment with training and testing process showed that ANN could be applied to predict the disorders pregnancy with percentage of accuracy around 78,248%. The percentage is got by 0,1 of learning rate value, 17 of neuron input layers, 50 of neuron hidden layers, 5 of neuron output layers, and 0,01 of error value.