Article Per Year (5 Year)
p-Index From 2021 - 2026
0.444
P-Index
This Author published in this journals
All Journal SemanTIK : Teknik Informasi Scientific Journal of Informatics Journal of Artificial Intelligence and Digital Business
Subardin Subardin
Universitas Halu Oleo
Computer Science & IT Control & Systems Engineering Economics, Econometrics & Finance Electrical & Electronics Engineering Engineering

Published : 4 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 4 Documents
Search

 1 
PERANCANGAN DAN IMPLEMENTASI SISTEM REPLIKASI DATABASE TERDISTRIBUSI PADA FAKULTAS TEKNIK UNIVERSITAS HALU OLEO Muhammad Hidayat Darmawan; Isnawaty Isnawaty; Subardin Subardin
semanTIK Vol 4, No 2 (2018): semanTIK
Publisher : Informatics Engineering Department of Halu Oleo University

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1012.596 KB) | DOI: 10.55679/semantik.v4i2.4715

Abstract

Current technological developments are very influential on the process of data distribution that is demanded fast because every second of information can change. One of the methods used in data exchange is to use data replication in a distributed database. The speed of the process and the number of rows that can be replicated in units of time are some of the things that can be taken into consideration when trying to determine how to replicate data in a distributed database.In replication, a software is used to find or more precisely track changes that occur in a database. After changes in one database are identified and known, then changes are made so that all databases are the same as other databases.This study implements two computers consisting of master and slave, each of which is a database server that is connected to each other in the network. The test results obtained in this study are that with the database replication, every data that is stored periodically always backups the slave computer.Keywords—Replication, Database, Distributed Database DOI : 10.5281/zenodo.1493829
MONITORING SUHU DAN KELEMBABAN PROSES DEKOMPOSISI PUPUK KOMPOS BERBASIS ANDROID Fitri Amaliah; Isnawaty Isnawaty; Subardin Subardin
semanTIK Vol 6, No 1 (2020): semanTIK
Publisher : Informatics Engineering Department of Halu Oleo University

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (590.635 KB) | DOI: 10.55679/semantik.v6i1.7521

Abstract

Kelembaban memegang peranan penting dalam proses dekomposisi pupuk sehingga kelembaban ideal harus dijaga pada kisaran 40% hingga 60% sedangkan suhu pupuk pada kisaran 30°C hingga 60°C. Masalah yang sering terjadi dalam pembuatan pupuk kompos adalah tingkat kematangan pupuk yang belum sempurna yang disebabkan oleh tingkat kelembaban dan suhu dalam proses pembuatan tidak stabil. Umumnya pemantauan suhu dan kelembaban pada proses dekomposisi dilakukan secara manual yaitu dengan mengikuti kebiasaan para petani pupuk sehingga waktu dan kinerja tidak efisien. Namun dengan menggunakan komponen mikrokontroler berbasis android pada proses dekomposisi pupuk dapat memberikan kemudahan untuk memperoleh nilai suhu dan kelembaban pupuk kompos secara lebih akurat. Sensor DHT22 digunakan untuk mengukur suhu dan kelembaban sedangkan NodeMcu ESP8266 sebagai mikrokontroler board untuk mengolah data yang didapatkan dari sensor. Dengan implementasi perangkat lunak menggunakan framework ionic untuk smartphone android, dan arduino untuk mikrokontroler. Proses monitoring suhu dan kelembaban pupuk yang menerapkan monitoring realtime dapat berjalan dengan baik melalui internet dengan latency yang sangat kecil.Kata kunci; Monitoring, Dekomposisi, Mikrokontroler, Realtime, Android
Prediksi Popularitas Novel Berbasis Fitur-Fitur Teks Menggunakan Metode Random Forest Nadya Elfareta Azarin; Rizal Adi Saputra; Subardin Subardin
Jurnal Ilmiah Informatika Vol. 9 No. 1 (2024): Jurnal Ilmiah Informatika
Publisher : Department of Science and Technology Ibrahimy University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35316/jimi.v9i1.57-62

Abstract

In today's digital era, a novel's popularity is often measured by reader response and sales. This research aims to develop a novel popularity prediction model based on text features to provide insights to authors and publishers about the factors that influence reader acceptance. The method used in this research is Random Forest, a machine learning algorithm that can handle classification and regression well. The main goal of this research is to develop a predictive model that can identify key factors that contribute to the popularity of novels. The proposed method integrates text features, such as keyword extraction and sentiment analysis, in a Random Forest framework to predict popularity with high accuracy. The dataset used consists of various novel information, including title, genre, number of pages, and text features such as summary or description. Data is preprocessed to address issues such as missing values ​​and duplicates. Feature extraction is carried out by applying tokenization, stemming, and converting text into TF-IDF vectors. A Random Forest model was built incorporating these features, and the model parameters were optimized through a cross-validation process. The dataset used consists of various novel information, including title, genre, number of pages, and text features such as summary or description. Data is preprocessed to address issues such as missing values ​​and duplicates. Feature extraction is carried out by applying tokenization, stemming, and converting text into TF-IDF vectors. A Random Forest model was built incorporating these features, and the model parameters were optimized through a cross-validation process. The experimental results show that the Random Forest model is able to predict the popularity of novels with a satisfactory level of accuracy. Text features, such as keyword frequency and sentiment analysis, proved significant in their contribution to the predictive ability of the model. These findings provide valuable insight to authors and publishers in understanding reader preferences and the potential success of a novel.
Implementasi Algoritma Xgboost dengan Bayesian Optimization pada Sistem Rekomendasi Pemilihan Atlet Bola Voli Pantai Sulawesi Tenggara untuk Meningkatkan Efektivitas Keputusan Muhammad Akbar Perdana Ramadhan; Laode Muhammad Golok Jaya; Adha Mashur Sajiah; Bambang Pramono; Sutardi Sutardi; Subardin Subardin
RIGGS: Journal of Artificial Intelligence and Digital Business Vol. 5 No. 2 (2026): Mei-Juli
Publisher : Prodi Bisnis Digital Universitas Pahlawan Tuanku Tambusai

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31004/riggs.v5i2.11572

Abstract

Seleksi atlet bola voli pantai di Sulawesi Tenggara masih dilakukan secara konvensional dan bergantung pada penilaian subjektif pelatih, sehingga rentan menimbulkan inkonsistensi dan pengambilan keputusan yang kurang optimal di tengah meningkatnya jumlah calon atlet dan kompleksitas kriteria evaluasi. Kondisi ini berpotensi menghasilkan keputusan yang kurang tepat dan menghambat pengembangan atlet potensial. Penelitian ini mengimplementasikan algoritma Extreme Gradient Boosting (XGBoost) yang dioptimasi menggunakan Bayesian Optimization untuk membangun sistem rekomendasi pemilihan atlet yang objektif dan berbasis data. Dataset yang digunakan berjumlah 320 data atlet dengan 13 kriteria penilaian, dibagi menjadi 80% data pelatihan dan 20% data pengujian. Ketiga belas kriteria tersebut mencakup tinggi badan, kekuatan otot, kecepatan, kelincahan, teknik servis, smash, dan aspek psikologis. Evaluasi model dilakukan menggunakan metrik MAE, MSE, RMSE, R², dan MAPE. Hasil penelitian menunjukkan bahwa Bayesian Optimization mampu meningkatkan performa model secara signifikan, dengan nilai MAE menurun dari 1,2878 menjadi 0,9074, MSE dari 2,3796 menjadi 1,2547, RMSE dari 1,5426 menjadi 1,1201, serta R² meningkat dari 0,9412 menjadi 0,9852. Model akhir mencapai MAPE sebesar 2,61%, yang tergolong kategori sangat akurat berdasarkan kriteria Lewis (1982). Nilai MAPE di bawah 10% menunjukkan akurasi peramalan yang sangat tinggi. Sistem berhasil diimplementasikan sebagai aplikasi web berbasis Flask dan telah divalidasi secara kualitatif oleh pakar bola voli pantai. Hasil pengujian black box menunjukkan seluruh fitur sistem berjalan sesuai fungsi yang dirancang. Dengan demikian, sistem ini dapat diandalkan untuk mendukung seleksi atlet yang lebih transparan dan akurat.
Co-Authors Adha Mashur Sajiah Bambang Pramono Fitri Amaliah Golok Jaya, La Ode Muhammad Isnawaty Isnawaty Muhammad Akbar Perdana Ramadhan Muhammad Hidayat Darmawan Nadya Elfareta Azarin Rizal Adi Saputra Sutardi Sutardi