Claim Missing Document
Check
Articles

Found 4 Documents
Search

Prediksi Cacat Perangkat Lunak Dengan Optimasi Naive Bayes Menggunakan Pemilihan Fitur Gain Ratio Muhammad Sonhaji Akbar; Siti Rochimah
Jurnal Sistem dan Informatika (JSI) Vol 11 No 1 (2016)
Publisher : Bagian Perpustakaan dan Publikasi Ilmiah - Institut Teknologi dan Bisnis (ITB) STIKOM Bali

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (106.799 KB)

Abstract

Dalam prediksi cacat perangkat lunak, terjadinya kesalahan prediksi cacat perangkat lunak merupakan hal yang sangat fatal karena data yang salah prediksi dapat menimbulkan pengaruh terhadap perangkat lunak itu sendiri. Kurang optimalnya metode prediksi yang digunakan. Masih terdapat kesalahan dalam memprediksi cacat perangkat lunak. Dalam metode Naive Bayes juga masih terdapat kekurangan ketika terjadi kesalahan klasifikasi. Kesalahan klasifikasi ini dapat memperlambat proses prediksi cacat perangkat lunak. Dibutuhkan metode yang dapat mengatasi kesalahan klasifikasi ini. Dalam penelitian ini disusulkan optimasi metode Naive Bayes menggunakan Gain Ratio. Pemilihan fitur menggunakan Gain Ratio pada Naïve Bayes dapat mengurangi dampak kegagalan prediksi. Penggunaan Gain Ratio dapat meningkatkan performa prediksi. Penghitungan Gain Ratio dapat dirumuskan yaitu dari setiap atribut Gain Ratio dikali jumlah data n kemudian dibagi dengan rata-rata Gain Ratio semua atribut. Atribut dari Gain Ratio sendiri merupakan hasil bagi dari Mutual Information dan Entropy. Mutual Information (MI) merupakan nilai ukur yang menyatakan keterikatan atau ketergantungan antara dua variabel atau lebih. Selain MI, Entropy digunakan sebagai pembagi dari MI yang digunakan untuk menentukan atribut mana yang terbaik atau optimal. Maka dari itu penghitungan Gain Ratio adalah hasil dari penghitungan Mutual Information dibagi dengan hasil penghitungan Entropy Penghitungan Gain Ratio. Hasil penelitian menunjukkan akurasi sebesar 87,55% untuk metode usulan dan 85,34% untuk metode Naïve Bayes biasa.
Analisis Sentimen Performansi Operator Telekomunikasi di Indonesia Menggunakan Metode Text Mining Ersha Aisyah Elfaiz; Prayoga, Riza Akhsani Setyo; Monica Cinthya; Muhammad Sonhaji Akbar; Rizky Basatha
SATESI: Jurnal Sains Teknologi dan Sistem Informasi Vol. 5 No. 1 (2025): April 2025
Publisher : Yayasan Pendidikan Penelitian Pengabdian ALGERO

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54259/satesi.v5i1.4024

Abstract

The telecommunications sector in Indonesia has experienced rapid development in recent years, characterized by the increasing number of telecommunications operators offering various services and products. Therefore, there is competitive rivalry among operators. The right strategy is needed to survive and compete effectively. One of the efforts that can be made by telecommunication companies is to evaluate operational performance. This research aims to analyze the sentiment of X users towards telecommunication operational performance, at Telkomsel and Tri operators using text mining methods, namely Naïve Bayes, Support Vector Machine (SVM) and Decision Tree Learning (DTL). The research data is obtained by crawling from the X application, then the data is processed to remove unnecessary words or affixes. Then data modeling and validation is carried out using split validation and cross validation techniques. In the split validation technique, the data is divided into 70% training data and 30% testing data, while in the cross-validation technique the fold parameter is set to determine which fold has the highest accuracy. The results of the study show that the SVM method has the highest accuracy, where in split validation the accuracy is 84.29% for Telkomsel data and 75.70% for Tri data. Similarly, in cross validation, the accuracy is 82.15% on fold 4, 7 for Telkomsel data and 61.41% on fold 9 for Tri data. In addition, it is known that Telkomsel data has 18.64% positive sentiment and 81.36% negative sentiment. While Tri data has 61.11% positive sentiment and 38.89% negative sentiment.
The Optimisation of Stock Management: Design of an AI-Driven Inventory System Putra, Cendra Devayana; Utami, Ardhini Warih; Dwi, I Kadek; Prayoga, Riza Akhsani Setyo; Basatha, Rizky; Muhammad Sonhaji Akbar
SISFOTENIKA Vol. 15 No. 2 (2025): SISFOTENIKA
Publisher : STMIK PONTIANAK

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30700/sisfotenika.v15i2.543

Abstract

The frozen food industry has witnessed remarkable growth in recent years, driven by increasing urbanization and the demand for convenient, ready-to-eat meals. Despite this upward trend, many businesses in the sector struggle with inefficient stock management, particularly in forecasting daily demand due to fluctuating consumer behavior and unpredictable external factors. This study proposes an end-to-end artificial intelligence-based stock forecasting system aimed at optimizing inventory management for frozen food businesses. By adopting the Design Thinking approach, this research places users—both consumers and internal stakeholders—at the center of the problem-solving process to uncover key operational pain points. The study explores recent technological advancements, including augmented reality, RFID, and blockchain, and integrates them into a practical framework tailored to small and medium enterprises (SMEs). Through qualitative analysis and system prototyping, the research identifies essential features for an intelligent stock management system and demonstrates how a user-centric approach can drive innovation and improve business performance. The findings offer valuable insights into the development of adaptive, data-driven solutions in the rapidly evolving frozen food sector.
Pemanfaatan Deep Learning dalam Kurikulum Pembelajaran Abad 21: Sebuah Tinjauan Literatur Zain, Muhammad; Muhammad Sonhaji Akbar
SISFOTENIKA Vol. 15 No. 2 (2025): SISFOTENIKA
Publisher : STMIK PONTIANAK

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30700/sisfotenika.v15i2.577

Abstract

The transformation of education today is highly dependent on the use of technology, aiming to prepare students who are skilled, adaptive, and ready to compete in the industrial world. This study aims to systematically examine the use, role, and challenges of implementing Deep Learning as part of Artificial Intelligence in the renewed educational curriculum. The study employs a Systematic Literature Review, and its data comes from 28 scientific articles, journals, and research reports that examine the application of Deep Learning technology in education. The research data were analyzed based on themes to identify roles, uses, benefits for 21st-century skills, and difficulties in implementation. The results of the study indicate that Deep Learning plays a significant role in learning that is tailored to student needs through an adaptive system, helps develop appropriate skills in the 21st century (4C), and improves methods for analyzing educational data for early intervention.