Penerapan Extreme Learning Machine (ELM) untuk Peramalan Laju Inflasi di Indonesia

Abstract

AbstrakInflasi merupakan salah satu indikator untuk mengukur perkembangan suatu bangsa. Apabila inflasi tidak terkontrol akan memberikan banyak dampak negative terhadap masyarakat disuatu negara. Ada banyak cara untuk mengendalikan inflasi, salah satunya dengan peramalan. Peramalan adalah suatu aktivitas untuk mengetahui kejadian di masa mendatang berdasarkan data masa lalu. Pada penelitian ini menggunakan metode kecerdasan buatan yakni extreme learning machine (ELM). Kelebihan ELM yaitu cepat dalam proses pembelajaran. Berdasarkan penggujian yang dilakukan metode ELM mendapatkan nilai kesalahan sebesar 0.0202008, lebih kecil dibandingkan dengan metode backpropagation sebesar 1.16035821. Hal tersebut membuktikan bahwa metode ELM sangat cocok digunakan untuk peramalan.Kata kunci: inflasi, extreme learning machine, backpropagation, jaringan syaraf tiruan. AbstractInflation is one indicator to measure the development of a nation. If inflation is not controlled will give many negative impacts to the people in a country. There are many ways to control inflation, one with forecasting. Forecasting is an activity to know future events based on past data. In this research using artificial intelligence method is extreme learning machine (ELM). The advantages of ELM are fast in the learning process. Based on ELM testing gets obtained an error value of 0.0202008, smaller than the backpropagation method of 1.16035821. It proves that ELM method is very suitable for forecasting.

Penerapan Extreme Learning Machine Dalam Meramalkan Harga Minyak Sawit Mentah

“…Metode ELM merupakan modifikasi dari metode Jaringan Syaraf Tiruan (JST) feedforward sederhana dengan menggunakan konsep Single Hidden Layer Feedforward Neural Networks (SLFns). Kelebihan metode ini adalah parameter yang digunakan seperti input bobot dan bias yang diambil secara acak, kinerja pada learning speed pada metode ini lebih cepat dan kinerja generalisasi yang dihasilkan lebih baik [4].…”

Implementation of the Step Function Intervention and Extreme Learning Machine for Forecasting the Passenger’s Airport in Sorong

“…Several related studies include research by Alfiyatin et al [5] using the ELM and backpropagation methods to predict Indonesia's inflation rate. Fransiska [6] forecasts monthly rainfall in Bengkulu City with the Seasonal Autoregressive Integrated Moving Average (SARIMA).…”

Leukaemia Identification based on Texture Analysis of Microscopic Peripheral Blood Images using Feed-Forward Neural Network

“…In recent years, there have been developments of machine learning, one of which is an Feed-Forward Neural Network. Extreme Learning Machine (ELM) is a neural network that has a feedforward structure with a single hidden layer [14]. ELM is widely used to complete classification.…”

“…Nemissi uses ELM for the classification of breast cancer with excellent results. Besides, ELM has also been used to solve problems such as forecasting the inflation rate in Indonesia [14], the detection of dengue fever [15], the diagnosis of breast cancer [16], and others showing results with an average accuracy rate above 90%. Gowthaman compares SVM with ELM.…”