Claim Missing Document
Check
Articles

Found 5 Documents
Search
Journal : Jurnal Lebesgue : Jurnal Ilmiah Pendidikan Matematika, Matematika dan Statistika

ANALISIS CONDITIONAL RESTRICTED BOLTZMAN MACHINE UNTUK MEMPREDIKSI HARGA SAHAM BANK SYARIAH INDONESIA Indiko Prima; Defri Ahmad
Jurnal Lebesgue : Jurnal Ilmiah Pendidikan Matematika, Matematika dan Statistika Vol. 4 No. 1 (2023): Jurnal Lebesgue : Jurnal Ilmiah Pendidikan Matematika, Matematika dan Statistik
Publisher : LPPM Universitas Bina Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46306/lb.v4i1.266

Abstract

This study aims to predict the movement of Bank Syariah Indonesia shares (BRIS.JK) prices using the Conditional Restricted Boltzmann Machine (CRBM) method. Prediction is needed in conducting share transactions, because the increase or decrease in share price movements is very difficult to predict. The CRBM method is a machine learning algorithm used to model the probability distribution of data associated with variables and inputs. CRBM is a type of Restricted Boltzman Machine (RBM) that consists of two layers, namely the input layer and the hidden layer. CRBM is a type of Boltzmann machine model equipped with a conditioned unit that is used to perform analysis and learning on data that has conditional properties. In this research, the first step is to divide several research scenarios. Then conduct CRBM tests to get prediction results. The data used is daily close data. Based on the research that has been done, it is obtained that the best prediction accuracy is in July - August with MAPE below 5%.
IMPLEMENTASI FUZZY TIME SERIES LOGIKA LEE UNTUK PERAMALAN INFLASI DI INDONESIA Aulia Fitri Fireza; Defri Ahmad
Jurnal Lebesgue : Jurnal Ilmiah Pendidikan Matematika, Matematika dan Statistika Vol. 4 No. 2 (2023): Jurnal Lebesgue : Jurnal Ilmiah Pendidikan Matematika, Matematika dan Statistik
Publisher : LPPM Universitas Bina Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46306/lb.v4i2.386

Abstract

Inflation is a process of continuous increase in the price of goods or an economic situation that shows a tendency to increase the price level in general. One way to control inflation is to use forecasting. Forecasting is an activity to predict future events. Related to forecasting, the method that can be used in forecasting inflation time series data in Indonesia is the fuzzy time series method of Lee's logic. This study aims to apply Lee's Fuzzy Time Series method in forecasting inflation in Indonesia in the period January 2014 to December 2022. The forecasting results of the method are then measured using MAE and MAPE. In this study, the results of inflation forecasting in Indonesia follow the pattern of actual data. Meanwhile, the forecasting accuracy value obtained a MAE value of 0.0043 and a MAPE value of 11.7%, so that inflation forecasting in Indonesia using the Fuzzy Time Series Lee method based on MAPE criteria is good
ALGORITMA K-NEAREST NEIGHBOR TERHADAP PELUANG MAHASISWA MENJADI AKTIVIS KAMPUS PADA JURUSAN MATEMATIKA UNIVERSITAS NEGERI PADANG Muhammad Fadhli Gusvino; Defri Ahmad
Jurnal Lebesgue : Jurnal Ilmiah Pendidikan Matematika, Matematika dan Statistika Vol. 4 No. 2 (2023): Jurnal Lebesgue : Jurnal Ilmiah Pendidikan Matematika, Matematika dan Statistik
Publisher : LPPM Universitas Bina Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46306/lb.v4i2.401

Abstract

The purpose of this study was to predict whether mathematics students at Padang State University have the opportunity to become campus activists using the K-Nearest Neighbor Algorithm (KNN). This research will be used as a benchmark to calculate how many mathematics students can become activists at Padang State University. The K-Nearest Neighbor Algorithm (KNN) is a machine learning algorithm that has resistance to training data where there is a lot of noise and is more effective for large data. The K-Nearest Neighbor Algorithm itself is a distance-based data classification process for determining the closeness between different data. become the closest neighbor data and choose a class or category based on the K category of nearest neighbors. In this research, for the first step, data was collected on mathematics students based on several factors that influenced them to become activists, and an analysis of finding distance using the Euclidean distance was carried out. 46% are not activists
ANALISIS HASIL PREDIKSI MAGNITUDO GEMPA DI WILAYAH KOTA PADANG MENGGUNAKAN TEKNIK RANDOM FOREST Ade Fauzan; Defri Ahmad
Jurnal Lebesgue : Jurnal Ilmiah Pendidikan Matematika, Matematika dan Statistika Vol. 4 No. 3 (2023): Jurnal Lebesgue : Jurnal Ilmiah Pendidikan Matematika, Matematika dan Statistik
Publisher : LPPM Universitas Bina Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46306/lb.v4i3.450

Abstract

The topic of earthquake prediction is an interesting one to research. As one of the natural disasters, earthquakes are included in natural disasters that can cause considerable damage. The damage caused not only affects the economy but also the life of an area. Several studies on earthquake prediction have been conducted so far, one of which is Machine Learning and using the Random forest method. The purpose of the research is to determine the analysis of earthquake magnitude prediction results in the Padang City area using machine learning techniques. The variables used in this study are time, latitude, longitude, and magnitude. Earthquake data is obtained from the United States Geological Survey (USGS) website. This research produces an RMSE value of 0.31758 and an MSE value of 0.10085
MODEL EVAKUASI KERAMAIAN DALAM GEDUNG MEMILIKI BEBERAPA PINTU KELUAR DENGAN MEMPERHATIKAN KEPANIKAN INDIVIDU Ghaitsa Deiwa Karufa; Defri Ahmad
Jurnal Lebesgue : Jurnal Ilmiah Pendidikan Matematika, Matematika dan Statistika Vol. 4 No. 3 (2023): Jurnal Lebesgue : Jurnal Ilmiah Pendidikan Matematika, Matematika dan Statistik
Publisher : LPPM Universitas Bina Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46306/lb.v4i3.458

Abstract

The purpose of this study is to determine the effect of panic on evacuation time. Evacuation is the movement of individuals from a place in danger to a safer place. Evacuation is usually done when there is an emergency such as an earthquake, fire or attack, which will make the movement of individuals difficult. Individuals who are in an emergency will feel panic. The panic that occurs will cause individuals to lose their way to a safer place such as an exit. This research is a basic or theoretical research. The evacuation model uses cellular automata that simulates the behavior of individuals in cells for the evacuation process. This model considers the panic factor in the evacuation process which will affect the steps taken by individuals. Individual steps based on transition probabilities will obtain evacuation time. The parameters used are static coefficient, dynamic coefficient, and panic coefficient. Simulation using software by entering the grid size, obstacle position, exit position, individual position and parameters. Based on the simulation results, it is obtained that the increase in individual panic, the longer the evacuation time