Claim Missing Document
Check
Articles

Found 3 Documents
Search
Journal : Journal of Environmental Engineering and Sustainable Technology

IMPLEMENTASI FUZZY INFERENCE SYSTEM (FIS) METODE TSUKAMOTO PADA SISTEM PENDUKUNG KEPUTUSAN PENENTUAN KUALITAS AIR SUNGAI Galuh Mazenda; Arief Andy Soebroto; Candra Dewi
Journal of Environmental Engineering and Sustainable Technology Vol 1, No 2 (2014)
Publisher : Lembaga Penelitian dan Pengabdian kepada Masyarakat Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (283.785 KB) | DOI: 10.21776/ub.jeest.2014.001.02.4

Abstract

Water was one resource that has a very important function for life and human life. River was the main channel as water flowing from upstream to downstream, has many domestic and industrial activity along the stream. The flow dynamics lead to changes in the quality and quantity of the river significantly. Water quality was maintained by analyzing the quality of the river water. Decision Support System (DSS) was a system designed to simplify the determination of water quality officer in making decisions. Inputs are parameter water quality test that consists of physical parameters and chemical parameters.The process of water quality analysis was conducted using Fuzzy Inference System Tsukamoto method. Fuzzy tsukamoto method used to determine the water quality of the river into four (4) classes which meet quality standards (good condition), lightly polluted, contaminated medium, and heavy polluted. The results of tested scenarios obtained an accuracy rate between the results of the calculation method of Fuzzy Tsukamoto with the calculated water quality STORET method at 90%.
IDENTIFICATION OF PATCHOULI PLANTS USING LANDSAT-8 SATELLITE IMAGERY AND IMPROVED K-MEANS METHOD Candra Dewi; Muhammad Syaifuddin Zuhri; Achmad Basuki; Budi Darma Setiawan
Journal of Environmental Engineering and Sustainable Technology Vol 3, No 2 (2016)
Publisher : Lembaga Penelitian dan Pengabdian kepada Masyarakat Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (517.806 KB) | DOI: 10.21776/ub.jeest.2016.003.02.1

Abstract

To maintain the availability of the patchouli plants required monitoring the spread of patchouli plantation. This study performed the identification of patchouli plant through Landsat-8 satellite imagery and Improved K-Means method. Improved was done on this study include the process of determining the initial cluster by specifying the closeness between the data and the determination of the number of cluster (K) by using the histogram equalization technique. The result of internal criteria testing shows that determining the number of clusters using the histogram is less effective because it produces the lower value of the silhouette. On almost all image data test found the best value of the silhouette's coefficient is 75.089% at K=2 and data in February. Furthermore, based on the results of testing the external criteria known the highest purity value in February data with a number of cluster 5 is 0.6829268. The test results also show that the use of the Improved K-Means on the Landsat-8 image has not been able to recognize the difference patchouli plants with other crops due to the limited resolution of imagery data and also the minimum number and variation of test data. But, visually the patchouli plant cluster is found for February data while the age of the rice crop surrounding the patchouli is still in the early phase of planting.
PENGARUH ARSITEKTUR ANFIS PADA PERAMALAN CUACA Candra Dewi
Journal of Environmental Engineering and Sustainable Technology Vol 2, No 1 (2015)
Publisher : Lembaga Penelitian dan Pengabdian kepada Masyarakat Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (165.935 KB) | DOI: 10.21776/ub.jeest.2015.002.01.3

Abstract

Dalam proses pembelajaran dengan Adaptive Neuro Fuzzy Inference System (ANFIS), selain parameter laju pembelajaran dan error harap, jumlah neuron dalam tiap lapisan juga sangat mempengaruhi hasil pembelajaran. Dengan demikian, pengujian untuk mendapatkan arsitektur jaringan yang optimal perlu untuk dilakukan. Adapun dalam arsitektur  ANFIS, bagian lapisan yang memegang peranan adalah lapisan pertama dan lapisan kedua, dimana lapisan pertama yang merupakan fuzzyfikasi dari input dan lapisan kedua mewakili jumlah aturan fuzzy dalam proses inferensi. Pada penelitian ini diimplementasikan pengujian arsitektur ANFIS untuk peramalan cuaca, terutama untuk mengetahui jumlah neuron yang paling baik pada lapisan pertama dan kedua.Hasil uji coba menunjukkan bahwa kombinasi persentase 40%, 50% dan 60% data latih menghasilkan nilai akurasi dan RMSE yang cukup stabil pada beberapa kombinasi neuron (antara 2 sampai 6) pada lapisan pertama dan kedua. Disamping itu dapat diketahui bahwa kombinasi jumlah neuron yang optimal adalah antara 2 sampai 4.