Article Per Year (5 Year)
p-Index From 2021 - 2026
2.87
P-Index
This Author published in this journals
All Journal Journal of Software Engineering Jurnal Pilar Nusa Mandiri Information System for Educators and Professionals : Journal of Information System JITK (Jurnal Ilmu Pengetahuan dan Komputer) Jurnal Nasional Komputasi dan Teknologi Informasi JURIKOM (Jurnal Riset Komputer) JISICOM (Journal of Information System, Infomatics and Computing) Journal of Information System, Applied, Management, Accounting and Research Jurnal Mantik INTI Nusa Mandiri Computer Science (CO-SCIENCE) INSANtek – Jurnal Inovasi dan Sains Teknik Elektro Journal Automation Computer Information System (JACIS) Malcom: Indonesian Journal of Machine Learning and Computer Science INFORMATION SYSTEM FOR EDUCATORS AND PROFESSIONALS : Journal of Information System
Harsih Rianto
Universitas Bina Sarana Informatika
Aerospace Engineering Automotive Engineering Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Electrical & Electronics Engineering Engineering Languange, Linguistic, Communication & Media Neuroscience Transportation Other

Published : 24 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 24 Documents
Search

 1   2   3 
Prediksi ISPU Jakarta Menggunakan Random Forest Roris, Renaldi Putra; Saputra, Andhika; Fahrizal, Ahmad; Susilowati, Susi; Rianto, Harsih; Nuryamin, Yamin
Journal Automation Computer Information System Vol. 5 No. 2 (2025): November
Publisher : Indonesian Journal Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47134/jacis.v5i2.139

Abstract

Polusi udara Jakarta memerlukan sistem prediksi akurat untuk peringatan dini kesehatan publik. Penelitian ini mengembangkan model machine learning untuk memprediksi Indeks Standar Pencemar Udara (ISPU) harian maksimum menggunakan dataset 3.045 observasi dari lima stasiun pemantauan (Januari–Agustus 2024) dengan enam parameter polutan (PM10, PM2.5, SO2, CO, O3, NO2). Tiga algoritma dievaluasi: Linear Regression, Random Forest, dan Gradient Boosting. Random Forest mencapai kinerja terbaik dengan R² = 0,9575, RMSE = 4,44, dan MAE = 0,82, melampaui studi sejenis (R² = 0,78–0,89). Analisis feature importance mengungkapkan PM2.5 mendominasi prediksi ISPU dengan kontribusi 87,11%, jauh melebihi NO2 (4,94%) dan SO2 (2,84%). Penelitian memberikan tiga kontribusi: (1) model prediksi ISPU akurasi tertinggi untuk implementasi sistem peringatan dini operasional; (2) identifikasi PM2.5 sebagai target prioritas kebijakan pengendalian polusi berbasis bukti; dan (3) bukti empiris bahwa polusi bersifat kronis dan menyeluruh, memerlukan intervensi komprehensif untuk melindungi kesehatan 10+ juta penduduk Jakarta
Optimalisasi Pengelolaan Tagihan Melalui Sistem Notifikasi WhatsApp Berbasis Framework Laravel dan Metode Rapid Application Development Harsih Rianto; Tyas Setiyorini
Jurnal Nasional Komputasi dan Teknologi Informasi (JNKTI) Vol 7, No 6 (2024): Desember 2024
Publisher : Program Studi Teknik Komputer, Fakultas Teknik. Universitas Serambi Mekkah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32672/jnkti.v7i6.8391

Abstract

Abstrak - Pengelolaan tagihan atau invoice yang tidak efisien dapat menimbulkan dampak serius bagi perusahaan, seperti keterlambatan penerimaan pembayaran, konflik dengan pelanggan, dan kerugian finansial. Untuk mengatasi masalah ini, sistem pengelolaan tagihan berbasis web yang dilengkapi dengan notifikasi otomatis menjadi solusi yang relevan. Salah satu media komunikasi yang efektif untuk notifikasi tagihan adalah WhatsApp, karena keunggulannya dalam aksesibilitas, kecepatan, dan kemampuan untuk menyampaikan informasi secara interaktif. Dalam penelitian ini, pengembangan sistem dilakukan menggunakan framework Laravel 10, yang menawarkan fleksibilitas, dokumentasi lengkap, dan fitur bawaan untuk mempermudah proses pengembangan. Selain itu, metode Rapid Application Development (RAD) digunakan untuk mempercepat proses pembangunan sistem dengan pendekatan iteratif dan umpan balik pengguna yang berkelanjutan. Sistem ini dirancang untuk meningkatkan efisiensi pengelolaan tagihan, memastikan pelanggan menerima informasi dengan cepat, dan meminimalkan kesalahan dalam pencatatan. Hasil pengembangan diharapkan dapat memberikan solusi inovatif bagi perusahaan dalam mengelola tagihan secara lebih efektif, meningkatkan arus kas, dan membangun hubungan yang lebih baik dengan pelanggan. Studi ini juga mengisi gap penelitian terkait pengelolaan tagihan otomatis berbasis WhatsApp dengan menggunakan Laravel dan metode RAD.Kata kunci: Pengelolaan Tagihan, Notifikasi Tagihan, WhatsApp, Laravel, Rapid Application Development (RAD) Abstract - Inefficient management of invoices can cause significant issues for companies, including delayed payments, customer conflicts, and financial losses. To address these challenges, a web-based invoice management system equipped with automated notifications offers a relevant solution. WhatsApp emerges as an effective medium for invoice notifications due to its accessibility, speed, and ability to deliver interactive information. This study develops a system using the Laravel 10 framework, which provides flexibility, comprehensive documentation, and built-in features that simplify the development process. Additionally, the Rapid Application Development (RAD) method is applied to accelerate system creation through iterative approaches and continuous user feedback. The system is designed to enhance invoice management efficiency, ensure timely delivery of information to customers, and minimize recording errors. The development outcome aims to provide innovative solutions for companies to manage invoices more effectively, improve cash flow, and foster better customer relationships. This study also addresses a research gap in developing automated invoice management systems via WhatsApp using Laravel and the RAD methodology.Keywords: Invoice Management, Invoice Notification, WhatsApp, Laravel, Rapid Application Development (RAD)
Perbandingan Neural Network dan K-Fold Cross Validation dengan Neural Network dan Sliding Window Validation untuk Estimasi Kuat Tekan Beton Tyas Setiyorini; Harsih Rianto
Jurnal Nasional Komputasi dan Teknologi Informasi (JNKTI) Vol 8, No 3 (2025): Juni 2025
Publisher : Program Studi Teknik Komputer, Fakultas Teknik. Universitas Serambi Mekkah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32672/jnkti.v8i3.9128

Abstract

Abstrak – Beton menjadi bahan yang penting dan banyak digunakan untuk pembangunan seperti perumahan, gedung, jembatan, jalan dan lain-lain. Beton banyak digunakan karena memiliki kuat tekan yang tinggi dan fleksibel sesuai kebutuhan jenis pembangunannya. Oleh karena itu pengukuran kuat tekan beton menjadi hal yang sangat penting. Namun pengukuran kuat tekan beton saat ini masih dilakukan dengan cara konvensional dan menggunakan rumus standar yang ada dalam ilmu Teknik Sipil. Cara tersebut masih kurang efektif dan kurang akurat karena banyak faktor yang mempengaruhi kuat tekan beton. Oleh karena itu pengukuran kuat tekan beton menjadi hal yang sangat penting dalam dunia Teknik Sipil. Seperti pada penelitian sebelumnya data kuat tekan beton bersifat nonlinear dan memiliki varians yang tinggi. Metode Neural Network sangat cocok untuk mengatasi masalah nonlinear. K-Fold Cross Validation merupakan salah satu metode yang mampu mengurangi varians yang tinggi sehingga dapat meningkatakan akurasi. Pada penelitian ini, diperoleh hasil RMSE sebesar 0,388 pada penerapan Neural Network dan K-Fold Cross Validation, dan RMSE sebesar 0,499 pada penerapan Neural Network dan Sliding Window Validation. Nilai RMSE menunjukkan penggunaan K-Fold Cross Validation lebih rendah dibanding Sliding Window Validation. Hal tersebut membuktikan bahwa K-Fold Cross Validation mampu meningkatkan kinerja yang lebih baik dengan mengurangi varians yang tinggi pada estimasi kuat tekan beton.Kata kunci: Kuat Tekan Beton; Estimation; Neural Network; K-Fold Cross Validation; Sliding Window Validation. Abstract - Concrete is an important material and is widely used for construction such as housing, buildings, bridges, roads and others. Concrete is widely used because it has high compressive strength and is flexible according to the needs of the type of construction. Therefore, measuring the compressive strength of concrete is very important. However, measuring the compressive strength of concrete is currently still done conventionally and using standard formulas in Civil Engineering. This method is still less effective and less accurate because many factors affect the compressive strength of concrete. Therefore, measuring the compressive strength of concrete is very important in the world of Civil Engineering. As in previous studies, concrete compressive strength data is nonlinear and has high variance. The Neural Network method is very suitable for overcoming nonlinear problems. K-Fold Cross Validation is one method that can reduce high variance so that it can increase accuracy. In this study, the RMSE results were obtained of 0.388 in the application of Neural Network and K-Fold Cross Validation, and RMSE of 0.499 in the application of Neural Network and Sliding Window Validation. The RMSE value shows that the use of K-Fold Cross Validation is lower than Sliding Window Validation. This proves that K-Fold Cross Validation is able to improve better performance by reducing high variance in concrete compressive strength estimates.Keywords: Concrete Compressive Strength; Estimation; Neural Network; K-Fold Cross Validation; Sliding Window Validation.
SOFTWARE DEFECT PREDICTION TRENDS: A BIBLIOMETRIC ANALYSIS OF MACHINE AND DEEP LEARNING Rianto, Harsih; Pahlevi, Omar; Desmulyati; Amrin; Budiman, Ade Surya; Supriyadi, Budi
JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer) Vol. 11 No. 3 (2026): JITK Issue February 2026
Publisher : LPPM Nusa Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/jitk.v11i3.7351

Abstract

This study provides a comprehensive bibliometric mapping of global research trends and emerging frontiers in Software Defect Prediction (SDP), emphasizing the integration of machine learning (ML) and deep learning (DL) approaches. Unlike previous bibliometric surveys that focused narrowly on metric-based or short-term analyses, this work offers a broader and more integrated perspective on the intellectual evolution, collaboration patterns, and thematic directions in SDP research. Using data retrieved from the Scopus database and analyzed through Bibliometrix and VOSviewer, the study systematically applied the PRISMA protocol to ensure transparency and replicability. A total of 1,549 publications were examined, revealing a steady increase in scientific output dominated by China, India, and the United States. Thematic and keyword analyses identified five core clusters that trace the paradigm shift from traditional statistical models to advanced ML- and DL-driven predictive frameworks. Emerging topics such as transfer learning, cross-project prediction, and explainable AI (XAI) were identified as promising frontiers shaping the next phase of software quality prediction research. Beyond mapping academic progress, this study contributes strategic insights for researchers seeking to identify research gaps, industry practitioners developing intelligent defect prediction tools, and policymakers designing AI-driven software quality initiatives
Co-Authors Adika May Sari Afiandri, Dhea Aulia AHMAD FAHRIZAL Alfian Alfian Alief, Rafli Naufal amrin Amrin Amrin Astriana Mulyani Bimo Tri Cahyo Budiman, Ade Surya Cahyani Budihartanti Citra Radita Utami Desmulyati Dwiza Riana Eka Wulansari Fridayanthie, Eka Wulansari Firstianty Wahyuhening Fibriany Hasan Basri Juarni Siregar khairul rizal Linda Marlinda Mohammad Syamsul Azis Noer Hikmah Nur Fadillah, Nur Omar Pahlevi Rahmat Tirta Kusuma Rana, Dipo Yudhis Romi Satria Wahono Roris, Renaldi Putra Sahamony, Nur Fitriyani Saputra, Andhika Sari Dewi Siti Chaerul Fadilah Supriyadi, Budi Susi Susilowati, Susi Syamsiar, Syamsiar Syarifah, Asyifa Raudha Terttiaavini, Terttiaavini Tri Hartati Tyas Setiyorini Tyas Setiyorini Yamin Nuryamin Yesni Malau Yumi Novita Dewi