Article Per Year (5 Year)
p-Index From 2019 - 2024
0.23
P-Index
This Author published in this journals
All Journal ICON-CSE BRITech : Jurnal Ilmiah Ilmu Komputer, Sains dan Teknologi Terapan
Rifka Widyastuti
Unknown Affiliation
Computer Science & IT Engineering

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
KLASIFIKASI CIRI FITUR KAYU MERBAU DAN KAYU JATI MENGGUNAKAN SUPPORT VECTOR MACHINE (SVM) Rifka Widyastuti; Basri, Hasan
BRITech, Jurnal Ilmiah Ilmu Komputer, Sains dan Teknologi Terapan Vol 1 No 2 (2020): Periode Januari
Publisher : Institute Teknologi dan Bisnis Bank Rakyat Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Indonesia has the biggest forest area which is almost 2/3 of the total area. Around 4000 types of wood are spread in the all areas of Indonesia?s forests. Wood identification has important benefits in determining quality of wood, that is developing in the wood industry. Manually, identifying wood species can only be done by a number of wood experts so the process take so much time and also has complex methods that cannot be done in shortly. Therefore, we need a system that can solve identification of wood types which is the process to be short and accurate. In this study, we used the method of support vector machine (SVM) to do classification of wood types which the resulting level of accuracy is 95%. This result also obtained by looking at the value of k-fold cross validation and confusion matrix.
Simplification Complex Sentences in Indonesia Language using Rule-Based Reasoning Rifka Widyastuti; M Fachrurrozi; Novi Yusliani
ICON-CSE Vol 1, No 1 (2014)
Publisher : ICON-CSE

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Complex sentence consist of two or more single sentence and one or more conjunctions. Complex sentences have many meaning, so that is quite difficult to be simplified because the results of simplification complex sentence does not match the original sentence. To solve this problem, this research using Rule-Based Reasoning method and Surface Expression Rules. Because Rule-Based Reasoning method can be adapted to the rules of surface expression that can look for patterns of complex sentences, so thus simplifying precise and accurate results. The results of researchis the Rule-Based Reasoning methods used in accordance with the accuracy of 93.8% and an assessment of questionnaires obtained values 76-100
Co-Authors Hasan Basri M Fachrurrozi Novi Yusliani