Claim Missing Document
Check
Articles

Found 16 Documents
Search

Microsoft Copilot Training for Monitoring Student Learning: A Case Study Vocational High School Makassar - Indonesia Dikwan Moeis; Nasir Usman; Muhammad Faisal; Andi Harmin; Ida Mulyadi; Musdalifa Thamrin
I-Com: Indonesian Community Journal Vol 4 No 3 (2024): I-Com: Indonesian Community Journal (September 2024)
Publisher : Fakultas Sains Dan Teknologi, Universitas Raden Rahmat Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33379/icom.v4i3.5134

Abstract

Artificial intelligence (AI) has become an increasingly popular technology and brings significant educational benefits. This technology increases the learning process's efficiency and productivity, allowing for the development of students' abilities in a more focused manner. AI is a catalyst in preparing generations to face future challenges. One example of AI's application in education is Microsoft Copilot, an artificial intelligence model developed by Microsoft in collaboration with OpenAI. Microsoft Copilot is designed to understand and support various academic tasks through human-like interactions. Training on using Microsoft Copilot was carried out for students of SMKS Wahyu Makassar. This training aims to support the learning process, increase learning effectiveness, and assist students in doing academic assignments. The evaluation results showed that Microsoft Copilot provided significant benefits, with positive feedback from participants. Most students found this training useful, easy to understand and improved their knowledge.
Machine learning for global trade analysis: a hybrid clustering approach using DBSCAN, elbow, and SOM Thamrin, Musdalifa; Mulyadi, Ida; Made Widia, I Dewa; Faisal, Muhammad; Hi Baharuddin, Suardi; Prihatmono, Medy Wismu; Nurdiansyah, Nurdiansyah; Usman, Nasir
IAES International Journal of Artificial Intelligence (IJ-AI) Vol 14, No 4: August 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijai.v14.i4.pp3033-3046

Abstract

Global trade constitutes a highly complex and interdependent system influenced by diverse economic, geographic, and political factors. This study proposes a hybrid clustering framework that integrates density-based spatial clustering of applications with noise (DBSCAN), elbow, and self-organizing maps (SOM) methods to uncover latent structures in international trade patterns. Utilizing averaged trade data from 25 countries spanning the period from 2013 to 2023, the framework identifies distinct clusters based on export-import characteristics. The DBSCAN is employed to detect dense trade hubs and outlier behaviors, the elbow method determines the optimal number of clusters, and SOM facilitates the visualization of non-linear, high-dimensional trade relationships. The analysis reveals three prominent trade clusters: Global Trade Leaders, Emerging Trade Powers, and Niche Exporters, each reflecting varying degrees of trade diversification and dependency. These empirical findings align with established economic theories, including the Heckscher Ohlin model and dependency theory, and provide actionable insights for policymakers seeking to enhance trade competitiveness and regional integration strategies.
PENERAPAN ALGORITMA K-MEANS TERHADAP EVALUASI WEBSITE E-COMMERCE Febriyanto A.; Dzulqornain Sabri S. Anggie; Mulyadi, Ida
Nusantara Hasana Journal Vol. 3 No. 12 (2024): Nusantara Hasana Journal, May 2024
Publisher : Yayasan Nusantara Hasana Berdikari

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59003/nhj.v3i12.1124

Abstract

Facing large amounts of high-dimensional transaction data, clustering approaches often face challenges that include elasticity, weak high-dimensional data processing capabilities, sensitivity to data order over time, independence from parameters, and the ability to manage noise. These problems can limit a method from producing accurate predictions. Experiments conducted with data samples collected from 50 different mobile phones purchased on Lazada yielded the following results: K-means outperforms Single-pass in evaluating e-commerce transactions because it has higher intra-class dissimilarity and inter-class similarity. K-means clustering is an approach to the effective and flexible organization of large datasets. The results of a clustering algorithm are sensitive not only to the total number of clusters but also to how they were originally arranged. Therefore, it is easy to show that the clustering results are locally optimized. Further research conducted into the elements that influence the number of clusters produced by this method as well as the initial location of clustering centers is a very important endeavor.
Penerapan Metode Best First Search pada Sistem Informasi Penjualan Online Mulyadi, Ida
Journal of Computer and Information System ( J-CIS ) Vol 4 No 2 (2021): J-CIS Vol 4 No. 2 Tahun 2021
Publisher : Universitas Sulawesi Barat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31605/jcis.v4i2.1203

Abstract

Kasih dan Sayang merupakan produsen kue cokelat makalate yang berpusat di Makassar. Perusahaan tidak pernah mengukur sejauh mana kegiatan pemasarannya berdampak pada penjualan dan dianggap tidak efektif untuk menarik konsumen, karena belum memanfaatkan teknologi didalam memasarkan atau menginformasikan hasil produksinya ke msayarakat. Tujuan dari penelitian adalah untuk membantu perusahaan dalam memasarkan produk kue coklat dengan pemanfaatan aplikasi sistem informasi penjualan, sehingga dapat menarik minat konsumen dalam pembelian berbagai macam jenis kue coklat yang ditawarkan. Dalam penelitian ini menggunakan metode Best First Search yang merupakan pencarian Heuriristic sebagai pencarian kata pada sistem informasi penjualan. Hasil dari penelitian ini berbentuk website yang dibangun dan dirancang menggunakan bahasa pemrograman PHP. Pengujian kualitas sistem ini menggunakan metode System Usability Scale dari para pengguna dengan perolehan nilai 72,75 dengan grade C berstatus memuaskan.
Utilization of Artificial Intelligence to Support Technology Development at PT. Aplikanusa Lintasarta – Makassar Muhammad Faisal; Nasir Usman; Ida Mulyadi; Rosnani Rosnani; Darniati Darniati; Musdalifa Thamrin; Mardiah Mardiah; Alvina Felicia Watratan
I-Com: Indonesian Community Journal Vol 5 No 2 (2025): I-Com: Indonesian Community Journal (Juni 2025)
Publisher : Fakultas Sains Dan Teknologi, Universitas Raden Rahmat Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70609/icom.v5i2.6945

Abstract

This community service activity aimed to enhance the understanding of Machine Learning (ML) and Deep Learning (DL) technologies among employees of PT. Aplikanusa Lintasarta, as an academic contribution to supporting the company’s digital transformation acceleration. Conducted in a hybrid format (offline and online) on April 21, 2025, the program featured expert speakers and employed an interactive outreach approach combined with applicable case studies. To assess its effectiveness, pre-test and post-test instruments were utilized, revealing an average increase of 45% in participants’ comprehension. Participants' responses were highly positive, as demonstrated by their enthusiasm during discussions and interest in implementing ML/DL within the workplace. This activity not only strengthened internal technological literacy but also supported the development of the national AI ecosystem, in alignment with the launch of GPU Merdeka by Lintasarta.
Penerapan Sistem Pencarian Dokumen Berdasarkan Frasa di Abstrak Perpustakaan Digital Menggunakan Algoritma BM25 dan Word2Vec Fahrim Irhmna Rachman; Ida Mulyadi; Fajar, Nur
Ainet : Jurnal Informatika Vol. 7 No. 2 (2025): September (2025)
Publisher : Universitas Muhammadiyah Makassar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26618/t9pgjs86

Abstract

Perkembangan perpustakaan digital menyebabkan meningkatnya volume abstrak dokumen sehingga menuntut metode pencarian yang akurat untuk menemukan buku relevan. Penelitian ini mengusulkan penerapan sistem pencarian berbasis frasa pada abstrak dengan menggabungkan algoritma BM25 dan Word2Vec untuk meningkatkan relevansi hasil. Dataset terdiri dari 500 abstrak skripsi yang dipreproses (lowercasing, tokenisasi, stopword removal); model Word2Vec dilatih dengan arsitektur skip-gram (vector_size=100, window=5, epochs=50) dan BM25 diinisialisasi pada representasi token dokumen. Skor BM25, Word2Vec (cosine similarity) dan TF-IDF dinormalisasi lalu digabungkan (rata-rata) untuk pemeringkatan akhir. Evaluasi dilakukan menggunakan metrik Precision, Recall dan F1-Score pada beberapa query uji. Hasil menunjukkan peningkatan performa pada banyak query (rata-rata F1 ≈ 0.80) dengan beberapa kasus mencapai nilai sempurna (1.00), meskipun ada variabilitas antar tipe query. Temuan ini menegaskan bahwa penggabungan pencocokan lesikal BM25 dan representasi semantik Word2Vec dapat meningkatkan relevansi pencarian; pengembangan lanjutan direkomendasikan pada metode penggabungan skor dan perluasan korpus.