Claim Missing Document
Check
Articles

Found 3 Documents
Search
Journal : Jurnal Ilmu Komputer dan Agri-Informatika

Model Spasial untuk Prediksi Konsentrasi Polutan Kabut Asap Kebakaran Lahan Gambut Menggunakan Support Vector Regression Muhammad Asyhar Agmalaro; Imas Sukaesih Sitanggang; Lailan Sahrina Hasibuan; Muhammad Murtadha Ramadhan
Jurnal Ilmu Komputer & Agri-Informatika Vol. 5 No. 2 (2018)
Publisher : Departemen Ilmu Komputer - IPB University

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (498.701 KB) | DOI: 10.29244/jika.5.2.119-127

Abstract

Kabut asap dari kebakaran lahan gambut mengandung berbagai macam polutan seperti CO dan CO2. Polutan tersebut dapat berimplikasi buruk pada kesehatan masyarakat sekitar peristiwa itu terjadi yang berupa Infeksi Saluran Pernafasan Atas (ISPA). Penelitian ini bertujuan untuk membuat model spasial untuk prediksi konsentrasi polutan kabut asap yang berupa CO dan CO2 dari kebakaran lahan gambut di Sumatra tahun 2015. Model spasial dibentuk menggunakan algoritme support vector regression (SVR) dengan kernel radial basis function (RBF) dengan melihat konsentrasi polutan dari beberapa titik tetangga. Parameter tuning dilakukan untuk mendapatkan nilai parameter paling optimal dari SVR. Hasil penelitian menunjukkan bahwa model spasial prediksi konsentrasi CO terbaik didapatkan pada gamma dengan nilai 20 yang menghasilkan root mean squared error (RMSE) dan nilai koefisien korelasi sebesar 1,174242×10-8 dan 0,5879287. Model spasial prediksi konsentrasi CO2 terbaik dibentuk pada gamma dengan nilai 10 yang menghasilkan RMSE dan nilai koefisien korelasi sebesar 9,843717×10-8 dan 0,6058418. Hasil prediksi dari model yang dibentuk telah dapat mengikuti pola nilai aktual konsentrasi polutan. Kata Kunci: CO, CO2, kabut asap, model spasial, support vector regression.
Pemodelan Berbasis Jaringan untuk Pengklasifikasian Kanker Payudara Berdasarkan Data Molekuler Mushthofa; Chamdan L Abdulbaaqiy; Sony Hartono Wijaya; Muhammad Asyhar Agmalaro; Lailan Sahrina Hasibuan
Jurnal Ilmu Komputer dan Agri-Informatika Vol 9 No 1 (2022)
Publisher : Departemen Ilmu Komputer, Institut Pertanian Bogor

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29244/jika.9.1.101-113

Abstract

Cancer is a disease characterized by uncontrolled cell growth. One of the characteristics of uncontrolled growth is the presence of estrogen-receptor-positive (ER+). About 67% of breast cancer test results have ER+. Breast cancer profiles are divided into 4 subtypes, namely: Luminal A, Luminal B, basal-like, and HER-2 enriched. Each category has a different effect on adjuvant chemotherapy. In this study, a network-based approach was used to select features/molecular biomarkers that have the potential to assist modeling and classifying sub-types of breast cancer. The molecular features used are Copy Number Alteration (CNA) and gene expression. The feature selection results were compared with the PAM50 feature-based accuracy from the literature study. The results indicate that the features selected from this network-based approach can obtain a comparable performance w.r.t the original PAM50 features, and can be used as alternative to perform breast cancer subtyping.
Prediksi Harga Minyak Goreng Curah dan Kemasan Menggunakan Algoritme Long Short-Term Memory (LSTM) Lailan Sahrina Hasibuan; Yanda Novialdi
Jurnal Ilmu Komputer dan Agri-Informatika Vol 9 No 2 (2022)
Publisher : Departemen Ilmu Komputer, Institut Pertanian Bogor

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29244/jika.9.2.149-157

Abstract

A very significant increase in the price of basic necessities will affect the economy of the Indonesian people, such as lowering purchasing power. Based on the monitoring of the Strategic Food Price Information Center from November 2021 to August 2022, cooking oil is a necessities that experienced a very significant increase of price in Indonesia. This increase was spread evenly across 34 provinces of Indonesia, including the province of West Java. This significant increase can be prevented by taking preventive actions before, if this increase has been predicted. Deep Learning is a supervised learning method that is widely used today because of its reliability in solving various problems in the field of data mining. Deep learning can predict future cooking oil prices using time series data. This study develops a model to predict the price of cooking oil in bulk and packaged form using deep learning that specifically manages time series data, namely Long Short Term Memory (LSTM). Based on the NRMSE evaluation metric, the model built is able to recognize the price fluctuation of cooking oil in the form of bulk and packaging. The NRMSE value of the LSTM model in the training process is 0.019 for bulk cooking oil data training, and 0.037 for packaged cooking oil data.