Sebastianus A S Mola
Unknown Affiliation

Published : 4 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 4 Documents
Search

Sistem pakar mendiagnosa penyakit pada balita usia 0 – 60 bulan menggunakan metode Dempster-Shafer Jesica Cecilia Djami Manu; Sebastianus A S Mola; Adriana Fanggidae
J-Icon : Jurnal Komputer dan Informatika Vol 8 No 1 (2020): Maret 2020
Publisher : Universitas Nusa Cendana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35508/jicon.v8i1.2026

Abstract

Toddlers are susceptible to germs and viruses so that they are susceptible to various types of diseases because the immune system that has not been built properly. Most parents don't know about the symptoms and diseases suffered by toddlers, which is why sometimes the disease gets worse. The solution to the disease experienced by toddlers can be overcome is to take them to a hospital or health center. Binaus Health Center located in Mollo Tengah District, TTS Regency is one of the community health centers where most of the patients are toddlers. The obstacle of Binaus Community Health Center in operating is the specialist doctor of children or toddlers is not available, so an expert system was created as a media for consultation and monitoring of toddlers with the Dempster-Shafer Method whose end result was the diagnosis of diseases suffered by toddlers. Comparison of expert diagnosis results with expert systems obtained an average range of trust of 92.86% for appropriate testing experts above the threshold value and testing below the threshold value obtained miss-classification 7.14%. The expert system does not provide 100% results according to expert diagnosis not because of inference errors but the inappropriate value of expert density. Data testing based on case studies taken from medical record data at the Binaus Health Center, Kec. Mollo Tengah, Kab. TTS has a 100% accuracy rate.
PENALARAN BERBASIS KASUS UNTUK MENDIAGNOSA PENYAKIT INFEKSI MENULAR SEKSUAL (IMS) MENGGUNAKAN ALGORITMA WEIGHTED EUCLIDEAN DISTANCE Derin N Liu; Sebastianus A S Mola; Yelly Y Nabuasa
J-Icon : Jurnal Komputer dan Informatika Vol 8 No 2 (2020): Oktober 2020
Publisher : Universitas Nusa Cendana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35508/jicon.v8i2.2799

Abstract

Case-based reasoning is a methodology for solving problems by utilizing previous experience. In this study the authors apply case-based reasoning to diagnose sexually transmitted infection using the weighted Euclidean distance method. Source of the knowledge base was obtained by collecting medical record of patients with sexually transmitted infections in 2016-2017. The process of finding a solution starts with eliminating irrelevant data using the C4.5 method and continues with the calculation of the similarity value using the Weighted Euclidean Distance algorithm. This system can diagnose 5 types of sexually transmitted infections based on 123 existing symptoms. System result in the form of sexually transmitted infections based on symptoms experienced by the patient, treatment solution and presentation of similarities between new cases and old cases. Based on the result of testing with 127 cases of sexually transmitted infections obtained result: testing uses the K-Fold Cross Validation scenario, the total data is divided into 10fold and the testing process is divided into 2 parts, namely testing using indexing and testing without using indexing. For testing using the highest accuracy indexing obtained at 90.84% in the second fold, and the average accuracy of the entire fold is 88.55% with the average time generated 9498 ms (millisecond), while testing without using the highest accuracy indexing obtained by 63.03% in the second fold, and the average accuracy of the entire fold is 53.48% with the average time generated 9975 ms (millisecond).
EKSTRASI CIRI WARNA HSV DAN CIRI BENTUK MOMENT INVARIANT UNTUK KLASIFIKASI BUAH APEL MERAH Nikotesa Eko Rianto Pah; Sebastianus A S Mola; Arfan Y Mauko
J-Icon : Jurnal Komputer dan Informatika Vol 9 No 2 (2021): Oktober 2021
Publisher : Universitas Nusa Cendana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35508/jicon.v9i2.5043

Abstract

Red apple is one of the fruit plants with a lot of enthusiasts so it is very popular in the market. Red apples also have several types that at first glance look similar to one another. This is what makes it difficult for people to distinguish between red apples that are consumed, especially since there is no information label to explain these apples. Therefore, in this study a classification of red apples was carried out based on their shape and color characteristics. Image data used is secondary data in * JPG format with a size of 100 x 100 pixels. The method used is the extraction of the Mean HSV color feature (the output value is 3) and the Moment Invariant form feature (the output value is 7) so that each image has 10 values. Image classification results were obtained using Euclidean Distance. Meanwhile, the test scenario used K-Fold Cross Validation where 1,710 image data were divided into 10-folds with 171 images in each subset. From 10-fold tested 50 times, so that an average accuracy of 98.82% was obtained. The highest accuracy was obtained in the 46th test of 99.12% and the lowest accuracy was in the 48th test of 98.54%.
PEMBOBOTAN DINAMIS BERBASIS POSISI PADA APPROXIMATE STRING MATCHING Sebastianus A S Mola; Meiton Boru; Emerensye Sofia Yublina Pandie
J-Icon : Jurnal Komputer dan Informatika Vol 9 No 2 (2021): Oktober 2021
Publisher : Universitas Nusa Cendana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35508/jicon.v9i2.5149

Abstract

Written communication in social media that emphasizes the speed of information dissemination, the phenomenon of using non-standard language often occurs at the level of sentences, clauses, phrases and words. As a source of data, social media with this phenomenon presents challenges in the process of extracting information. Normalization of non-standard language into standard language begins in the word normalization process where non-standard words (NSW) are normalized to standard forms (standard words (SW)). The normalization process using edit distance has limitations in the process of weighting the static mismatch, match, and gap values. In calculating the mismatch value, statida weighting cannot provide a weight difference due to incorrect keystrokes on the keyboard, especially adjacent keys. Due to the limited edit distance weighting, this research proposes a dynamic weighting method for mismatch weights. The result of this research is that there is a new method of dynamic weighting based on the position of the keyboard keys that can be used to normalize NSW using the approximate string matching method.