Claim Missing Document
Check
Articles

Found 6 Documents
Search

Evaluasi Estimasi Biaya Perangkat Lunak melalui Ekstraksi Katalog Dari Dokumen Spesifikasi Kebutuhan luqman fanani mz; Andi Ikmal Rachman; Suriansyah B; Gita Pratiwi; Agus Halid; Alviadi Nur Risal
Jurnal Ilmiah Sistem Informasi dan Teknik Informatika (JISTI) Vol 7 No 1 (2024): Jurnal Ilmiah Sistem Informasi dan Teknik Informatika (JISTI)
Publisher : Lembaga Penelitian dan Pengabdian Masyarakat Universitas Lamappapoleonro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57093/jisti.v7i1.198

Abstract

Software cost estimation is an important early stage in the software development cycle. This process requires careful analysis of the project, taking into account various factors that affect cost and time to completion such as errors in the initial identification of what kind of software will be built and its utilization. One of the main challenges in budgeting is the lack of clear reference prices, which often results in the use of historical data as the basis for calculations. This research proposes a combination of methods to improve the accuracy and reliability of cost estimation, including text summarization and word2vec for sentence analysis and weighting, and catalog extraction to identify SRS documents as system features, including ambiguity features. The goal is to provide a more effective tool for future software project budgeting, ensuring cost estimation that matches the complexity of the project and proper assignment of experts. With this method, it is expected that companies can reduce the risk of miscalculation and inappropriate assignment of experts, thereby avoiding financial losses and project delays.
Peningkatan Kinerja Database melalui Teknik Batch Loading dan Parallel Processing pada Proses Load Data Suriansyah B; Andi Ikmal Rachman; Luqman Fanani; Agus Halid; Gita Pratiwi
Jurnal Ilmiah Sistem Informasi dan Teknik Informatika (JISTI) Vol 7 No 1 (2024): Jurnal Ilmiah Sistem Informasi dan Teknik Informatika (JISTI)
Publisher : Lembaga Penelitian dan Pengabdian Masyarakat Universitas Lamappapoleonro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57093/jisti.v7i1.199

Abstract

Penelitian ini menganalisis berbagai teknik optimasi untuk meningkatkan performansi proses load data ke dalam sistem database. Teknik yang dievaluasi meliputi indexing, partitioning, parallel processing, dan batch loading. Studi ini bertujuan untuk menentukan teknik yang paling efektif dalam meningkatkan throughput, mengurangi penggunaan CPU dan memori, serta meningkatkan efisiensi I/O.Pada pengukuran baseline tanpa optimasi, waktu load data tercatat 120 detik dengan throughput 40.000 baris per menit, penggunaan CPU sebesar 75%, penggunaan memori 60%, dan efisiensi I/O sebesar 50 MB/s. Hasil eksperimen menunjukkan bahwa penerapan indexing meningkatkan throughput menjadi 54.500 baris per menit dan sedikit mengurangi penggunaan CPU menjadi 70%, tetapi meningkatkan penggunaan memori menjadi 62%. Partitioning menghasilkan throughput 66.700 baris per menit, penggunaan CPU 65%, penggunaan memori 58%, dan efisiensi I/O meningkat menjadi 46 MB/s. Parallel processing signifikan meningkatkan throughput menjadi 85.700 baris per menit dan efisiensi I/O menjadi 60 MB/s, meskipun meningkatkan penggunaan CPU dan memori masing-masing menjadi 80% dan 75%. Teknik batch loading menunjukkan peningkatan performansi terbaik dengan throughput 90.000 baris per menit, penggunaan CPU 78%, penggunaan memori 70%, dan efisiensi I/O mencapai 65 MB/s.Hasil penelitian ini mengindikasikan bahwa batch loading dan parallel processing adalah teknik paling efektif dalam meningkatkan throughput dan efisiensi I/O, meskipun dengan peningkatan penggunaan sumber daya sistem. Partitioning efektif untuk mengurangi penggunaan memori dan CPU, sementara indexing memberikan manfaat tambahan dalam performansi query. Pemilihan teknik optimasi harus disesuaikan dengan karakteristik data dan kapasitas sumber daya sistem yang tersedia
Pertukaran Data Pada Rumah Sakit Di Makassar Berbasis Xml Based andi ikmal rachman; Luqman Fanani Mz; Agus Halid; Suriansyah B; Gita Pratiwi
Jurnal Ilmiah Sistem Informasi dan Teknik Informatika (JISTI) Vol 7 No 1 (2024): Jurnal Ilmiah Sistem Informasi dan Teknik Informatika (JISTI)
Publisher : Lembaga Penelitian dan Pengabdian Masyarakat Universitas Lamappapoleonro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57093/jisti.v7i1.200

Abstract

Data exchange in hospitals plays an important role in hospital information systems. The problem then arises when there are different systems in two places that want to be connected. The technology used must sacrifice business, cost and development, now a method of interoperability with XML (eXtensible Markup Language) has been proposed. This method can be applied in many distributed computing technologies and problems, especially for data exchange with different platforms. XML-based data exchange is becoming one of the standards in developing frameworks for information systems. This is done to find out whether the programming algorithms used in each program in the system are correct or there are still errors, besides that, what is even more important is whether the system built can meet its objectives. From the design process that has been carried out, it can be concluded that a method can be built that uses a data exchange system between two systems by utilizing XML Based data computing. The data must be easily understood by both parties so as not to cause communication errors so that when the system process can run smoothly.
Analisa Implementasi Sistem Informasi Dalam Demand Side Management Pada Gardu Induk Terhadap Faktor Beban Gita Pratiwi; Andi Ikmal Rachman; Agus Halid; Luqman Mz; Suriansyah -
Jurnal Ilmiah Sistem Informasi dan Teknik Informatika (JISTI) Vol 7 No 1 (2024): Jurnal Ilmiah Sistem Informasi dan Teknik Informatika (JISTI)
Publisher : Lembaga Penelitian dan Pengabdian Masyarakat Universitas Lamappapoleonro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57093/jisti.v7i1.203

Abstract

In Demand Side Management (DSM) of Substation (GI), the application of information system can improve operational efficiency and optimize the distribution of electrical load. Siantan Substation (GI) is part of the Equatorial System, which is the electricity network in West Kalimantan. In 2019, GI Siantan's electricity usage by customers was still inefficient. This is especially true during peak load time (WBP), which is at 19.00. This research analyzes the implementation of information systems in demand side management (DSM) at Siantan Substation and its effect on load factor. The research shows that the implementation of DSM can improve the operational efficiency and stability of the substation by reducing peak loads and organizing load distribution evenly. The low load factor value is definitely caused by the high energy usage during WBP, which is 0.843. However, there was a decrease in the peak load value after simulating the implementation of Demand Side Management (DSM) with the load shifting method, which resulted in the load factor value increasing to 0.9045. Although there are constraints in training and system integration, the financial and operational benefits are substantial.
Explainable Machine Learning for Predicting the Mental Health Impact of AI and Digital Platform Usage among Students Agus Halid; Dwi Amalia Purnamasari; Ade Chandra Saputra; Nicodemus Mardanus Setiohardjo
International Journal of Artificial Intelligence in Medical Issues Vol. 4 No. 1 (2026): International Journal of Artificial Intelligence in Medical Issues
Publisher : Yocto Brain

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56705/pxn6qg39

Abstract

The increasing use of artificial intelligence and digital platforms among students has created new opportunities for learning support, academic assistance, and digital interaction. However, intensive platform usage may also be associated with mental health concerns, sleep disruption, and negative effects on students’ daily life. This study aims to develop and evaluate machine learning models for predicting the overall impact of AI and digital platform usage among students by integrating demographic, behavioral, sleep-related, and mental health-related variables. The dataset consisted of 1,705 student records with features including age, gender, academiclevel, country, average daily usage hours, most-used platform, sleep hours per night, and mental health score. The target variable was Overall_Impact, categorized into Negative, Neutral, and Positive classes. Six supervised machine learning algorithms were evaluated: Logistic Regression, Decision Tree, Random Forest, Support Vector Machine, K-Nearest Neighbors, and Gradient Boosting. Model performance was assessed using accuracy, precision, recall, F1-score, Cohen’s Kappa, MAE, RMSE, ROC-AUC, and confusion matrix. The results showed that Random Forest achieved the best performance, with an accuracy of 99.71%, F1-macro of 99.52%, Cohen’s Kappa of 0.9950, and ROC-AUC of 0.9994 on the testing set. Feature importance analysis revealed that Mental_Health_Score, Sleep_Hours_Per_Night, and Avg_Daily_Usage_Hours were the most influential predictors. The findings indicate that machine learning can effectively predict the impact of digital platform usage and provide useful insights for AI-driven health informatics and student well-being monitoring. However, further validation using longitudinal and clinically grounded datasets is recommended.
Perbandingan Implementasi Layer CNN Untuk Akurasi Optimal Dalam Klasifikasi Jenis Sampah Organik dan Non Organik Nurzaenab Nurzaenab; Sulfahmi Sulfahmi; Agus Halid; Fitriana M. Sabir; Andi Sumardin; Asrul Asrul; Andi Ahmad Zacky Mulya
Jurnal Minfo Polgan Vol. 14 No. 2 (2025): Artikel Penelitian
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/jmp.v14i2.15867

Abstract

Permasalahan pengelolaan sampah menjadi isu penting di berbagai lingkungan, termasuk kampus, karena berdampak langsung terhadap kebersihan, kesehatan, dan kelestarian lingkungan. Penelitian ini bertujuan mengembangkan sistem klasifikasi otomatis sampah organik dan nonorganik menggunakan pendekatan Convolutional Neural Network (CNN). Dataset diperoleh dari koleksi gambar yang disimpan dalam Google Drive, kemudian dibagi menjadi data latih (90%) dan data validasi (10%). Untuk meningkatkan variasi dan mengurangi risiko overfitting, dilakukan augmentasi data dengan teknik rotasi, horizontal flip, shear, zoom, serta width dan height shift. Arsitektur CNN yang digunakan terdiri atas beberapa lapisan utama: Conv2D dan MaxPooling untuk ekstraksi fitur, Flatten untuk transformasi data, Dense sebagai fully connected layers, Dropout untuk regularisasi, serta Softmax sebagai output layer dengan dua kelas. Model dilatih menggunakan optimizer Adam, fungsi loss categorical crossentropy, metrik akurasi, dengan 25 epoch dan batch size 10. Hasil eksperimen menunjukkan bahwa model mampu mencapai akurasi tinggi, bahkan lebih dari 99% pada data latih, dengan akurasi validasi yang stabil sehingga tidak menunjukkan gejala overfitting signifikan. Model juga berhasil mengklasifikasikan gambar baru dengan probabilitas yang jelas antara kelas organik dan nonorganik. Kesimpulannya, CNN terbukti efektif sebagai metode klasifikasi sampah berbasis citra, dan penelitian ini membuka peluang pengembangan lebih lanjut ke arah sistem deteksi real-time serta integrasi dengan sistem pengelolaan sampah di kampus maupun masyarakat.