Muhammad Ali Ridla
Universitas Ibrahimy

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

Found 2 Documents
Search
Journal : Scientific Journal of Informatics

PARTICLE SWARM OPTIMIZATION SEBAGAI PENENTU NILAI BOBOT PADA ARTIFICIAL NEURAL NETWORK BERBASIS BACKPROPAGATION UNTUK PREDIKSI TINGKAT PENJUALAN MINYAK PELUMAS PERTAMINA Muhammad Ali Ridla
Jurnal Ilmiah Informatika Vol. 3 No. 1 (2018): Jurnal Imliah Informatika
Publisher : Department of Science and Technology Ibrahimy University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35316/jimi.v3i1.473

Abstract

The lubricating oil industry is one part of the oil and gas sector which is still one of the main pillars of economic growth in Indonesia. Sales predictions are needed by companies and policy makers as planning materials and economic development strategies to increase income in the future. Predictions that have a better level of accuracy can provide appropriate decisions. Various methods have been used, the Artificial Neural Network algorithm is one of the most widely used, especially in the Backpropagation (BPNN) structure which can predict non linear time series data. Backpropagation has been proven to have a better level of accuracy compared to econometric methods such as ARIMA. The integration of Backpropagation algorithm with other algorithms needs to be done to overcome the shortcomings and improve the ability of the National Land Agency itself. Particle Swarm Optimization (PSO) which is used as an optimization determinant of attribute weight values in the network structure of BPNN shows good results. After testing, BPNN without PSO has a Squared Error (SE) level of 0.012 and a Root Mean Aquared Error (RMSE) of 0.111. While BPNN with PSO has SE levels of 0.004 and RMSE of 0.059. This shows that there is a significant decrease in the error rate after the PSO algorithm is added to the BPNN structure which is 46.85%.
Perancangan dan Implementasi Sistem Informasi Pelayanan Jam'iyah Umroh Hafas Irma Yunita; Muhammad Ali Ridla
Jurnal Ilmiah Informatika Vol. 4 No. 2 (2019): Jurnal Imliah Informatika
Publisher : Department of Science and Technology Ibrahimy University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35316/jimi.v4i2.533

Abstract

The servicing done by jam'iyah umroh hafas (a group which provide umrah service) still use conventional procedure, namely by using form paper during the registration which obliges pilgrims to meet with the organizer. Also in the next process all is done with a face to face model, so that for the management of pilgrims each package the officer must carefully sort it out. This greatly affects the service process, in which officers must be really careful to group installments from pilgrims, as well as prepare data for processing to passports and travel. Therefore, in an effort to provide optimal, fast and appropriate services for hafas pilgrims, it is necessary to adopt the Customer Relationship Management contained in e-business, as well as to engineer software that can facilitate officers in completing all pilgrims administrative who will go to makkah. Designing this system uses the V-Model method in which each stage is validated and verified so that the system that is produced really meets the needs of the users and helps the officers to better administer the needs of the pilgrims.