Claim Missing Document
Check
Articles

Found 4 Documents
Search
Journal : Indonesian Journal of Electrical Engineering and Computer Science

Downscaling Modeling Using Support Vector Regression for Rainfall Prediction Sanusi Sanusi; Agus Buono; Imas S Sitanggang; Akhmad Faqih
Indonesian Journal of Electrical Engineering and Computer Science Vol 12, No 8: August 2014
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v12.i8.pp6423-6430

Abstract

Statistical downscaling is an effort to link global scale to local scale variable. It uses GCM model which usually used as a prime instrument in learning system of various climate. The purpose of this study is as a SD model by using SVR in order to predict the rainfall in dry season; a case study at Indramayu. Through the model of SD, SVR is created with linear kernel and RBF kernel. The results showed that the GCM models can be used to predict rainfall in the dry season. The best SVR model is obtained at Cikedung rain station in a linear kernel function with correlation 0.744 and RMSE 23.937, while the minimum prediction result is gained at Cidempet rain station with correlation 0.401 and RMSE 36.964. This accuracy is still not high, the selection of parameter values for each kernel function need to be done with other optimization techniques.
Density Based Clustering of Hotspots in Peatland with Road and River as Physical Obstacles Prima Trie Wijaya; Imas Sukaesih Sitanggang; Lailan Syaufina
Indonesian Journal of Electrical Engineering and Computer Science Vol 3, No 3: September 2016
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v3.i3.pp714-720

Abstract

Indonesia has the largest peatland area among tropical countries, covering about 21 milions ha, which spread mainly in Sumatera, Kalimantan, and Papua. Land and forest fires occur almost every year in peatland areas in Indonesia. One of indicators for forest and land fires is hotspot. The objective of this study is to group hotspots with road and river as obstacles using the CPO-WCC (Clustering in Presence of Obstacles with Computed number of Cells) algorithm. Clusters of hotspot data were analyzed based on peatland area distribution. This study also evaluates the results of clustering on peatlands in order to obtain the best clusters. Clustering using CPO-WCC algorithm produces three clusters of hotspot. The area of dense cluster is 10202.10 km2 with number of hotspots per km2 is 0.985. The higest number of hotspots occurrence is found in peatland with type of Hemists /Saprists (60/40) and depth greater than 400 cm.
Face recognition based on Siamese convolutional neural network using Kivy framework Yazid Aufar; Imas Sukaesih Sitanggang
Indonesian Journal of Electrical Engineering and Computer Science Vol 26, No 2: May 2022
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v26.i2.pp764-772

Abstract

Human face recognition is a vital biometric sign that has remained owing to its many levels of applications in society. This study is complex for free faces globally because human faces may vary significantly due to lighting, emotion, and facial stance. This study developed a mobile application for face recognition and implemented one of the convolutional neural network (CNN) architectures, namely the Siamese CNN for face recognition. Siamese CNN can learn the similarity between two object representations. Siamese CNN is one of the most common techniques for one-shot learning tasks. Our participation in this study determined the efficiency of the Siamese CNN architecture with the enormous quantity of face data employed. The findings demonstrated that the suggested strategy is both practical and accurate. The method with augmentation produces the best results with a total data set of 9000 face images, a buffer size of 10000, and epochs of 5, producing the minimum loss of 0.002, recall of 0.996, the precision of 0.999, and F1-score of 0.672. The proposed method gets the best accuracy of 98% with test data. The Siamese CNN model is successfully implemented in Python, and a user interface and executables are built using the Kivy framework.
Estimation of biomass of forage sorghum (sorghum bicolor) Cv. Samurai-2 using support vector regression Kahfi Heryandi Suradiradja; Imas Sukaesih Sitanggang; Luki Abdullah; Irman Hermadi
Indonesian Journal of Electrical Engineering and Computer Science Vol 30, No 3: June 2023
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v30.i3.pp1786-1794

Abstract

One alternative to improve feed quality is to combine the main feed with forages which are more economical in cost but contain high protein sources, such as sorghum. Production estimation is essential because it will determine the sustainability of the feed. This study aimed to estimate the amount of sorghum production using support vector regression (SVR). Several stages of this research are collecting data, preprocessing, modelling, and evaluation. The dataset used and the input for this SVR algorithm model is field observation data. The kernels used in the SVR algorithm modelling are linear, Polynomial, and RBF. Sorghum production estimation using SVR has a performance evaluation value that refers to the root mean square error (RMSE). The result of this research is that the model obtained from the SVR algorithm can estimate sorghum production with performance evaluation values using R2, mean absolute error (MAE), mean absolute percentage error (MAPE), and RMSE. The best results on the Polynomial kernel are R2=0.7841, MAE=0.0681, MAPE=0.46641, and RMSE=0.1006. This study shows that the classification model obtained from the SVR algorithm with Kernel Polynomial is the best model for estimating sorghum production.