Claim Missing Document
Check
Articles

Found 4 Documents
Search
Journal : Gaung Informatika

PENGUKURAN PERFORMA SUPPORT VECTOR MACHINE DAN NEURAL NETWOK DALAM MERAMALKAN TINGKAT CURAH HUJAN Ruswanti, Diyah
JURNAL GAUNG INFORMATIKA Vol 13 No 1 (2020): Jurnal Gaung Informatika Januari - Juni 2020
Publisher : Prodi Teknik Informatika Universitas Sahid Surakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (408.132 KB)

Abstract

Prediction models using Neural Network or Support Vector Machine have been developed in many areas of rainfall. In this studi we have compared the performance of NN and SVM models, in predition of monthly rainfall at R-17 station Kecepit Pemalang. The analyzed using NN and SVM in which testing with Root Mean Square Error (RMSE) for get the performance is done. The data obtained for 2009 to 2018 monthly rainfall were used as modelling and forecasting sample. The results showed that NN obtained smallest error rate compared to SVM. the recognized value of RMSE for SVM is 176,374, Neural Network is 22,289. In RMSE the smallest error rate showed the best performance of algorithm.
PENGUKURAN PERFORMA SUPPORT VECTOR MACHINE DAN NEURAL NETWOK DALAM MERAMALKAN TINGKAT CURAH HUJAN Diyah Ruswanti
JURNAL GAUNG INFORMATIKA Vol 13 No 1 (2020): Jurnal Gaung Informatika Vol 13 No 1 Januari 2020
Publisher : Universitas Sahid Surakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47942/gi.v13i1.455

Abstract

Prediction models using Neural Network or Support Vector Machine have been developed in many areas of rainfall. In this studi we have compared the performance of NN and SVM models, in predition of monthly rainfall at R-17 station Kecepit Pemalang. The analyzed using NN and SVM in which testing with Root Mean Square Error (RMSE) for get the performance is done. The data obtained for 2009 to 2018 monthly rainfall were used as modelling and forecasting sample. The results showed that NN obtained smallest error rate compared to SVM. the recognized value of RMSE for SVM is 176,374, Neural Network is 22,289. In RMSE the smallest error rate showed the best performance of algorithm.
PERANCANGAN SISTEM PENDUKUNG KEPUTUSAN MENGGUNAKAN METODE PROMETHEE Diyah Ruswanti
JURNAL GAUNG INFORMATIKA Vol 12 No 1 (2019): Jurnal Gaung Informatika Vol.12 No 1 Januari 2019
Publisher : Universitas Sahid Surakarta

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

Abstract

Decision Support System Using the Promethee Method is a solution for selecting partners in an Event Organizer service company. In determining the selection of work partners in this system, it is based on ratings or rankings taken from the calculation results of each criterion. From the results of these calculations, a rating of 1 (one) to 3 (three) is taken, to determine the ranking used 5 (five) criteria. The object of this research is an event organizer service company that will determine its partners. This development will affect the company's consideration of choosing a partner offered by an EO because partners are one of the important parts that play a role in running an event, namely those that provide facilities such as for parties, workshops, seminars, exhibitions, and others.
KLASTERING KOTA DAN KABUPATEN DI INDONESIA BERDASARKAN UMUR HARAPAN HIDUP SAAT LAHIR DENGAN K-MEDOIDS Astri Charolina; Diyah Ruswanti
JURNAL GAUNG INFORMATIKA Vol 12 No 1 (2019): Jurnal Gaung Informatika Vol.12 No 1 Januari 2019
Publisher : Universitas Sahid Surakarta

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

Abstract

One of the uses of cluster analysis is to predict the state of objects, and in this study, 514 provinces in Indonesia are grouped into four clusters based on LifeExpectancy at birth. The historical data used is sourced from BPS for a period of 11 years, from 2010 to 2019. The purpose of this provincial grouping is to provide input to local governments and policy makers regarding provincial clusters in their area. With the hope of making improvements or increasing efforts to increase life expectancy at birth and reduce mortality at birth. The algorithm used is K-Medoids which can perform clusters with the advantage of being able to overcome noise and oulier in large data. The results obtained are Cluster 1 as many as 125 provinces, Cluster 2 as many as 119 provinces, Cluster 3 as many as 137 provinces and Cluster 4 as many as 133 provinces. Life expectancy is one of the components in calculating the Human Development Index.