Article Per Year (5 Year)
p-Index From 2021 - 2026
1.704
P-Index
This Author published in this journals
All Journal TELKOMNIKA (Telecommunication Computing Electronics and Control) Insect (Informatics and Security) : Jurnal Teknik Informatika Indonesian Journal of Data and Science International Journal of Industrial Optimization (IJIO) Jurnal Indonesia : Manajemen Informatika dan Komunikasi Nusantara Hasana Journal Indonesian Community Journal Buletin Sistem Informasi dan Teknologi Islam Jurnal Informatika Progres Journal of Muhammadiyah’s Application Technology
Darniati
Universitas Muhammadiyah Makassar
Agriculture, Biological Sciences & Forestry Humanities Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Engineering Environmental Science Industrial & Manufacturing Engineering Mathematics Nursing Public Health Social Sciences Other

Published : 14 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 14 Documents
Search

 1   2 
Education on Hybrid Multi-Criteria Decision Making and Machine Learning through the Morning Class Program: Integration of Engineering and Technology Nasir Usman; Muhammad Faisal; Sri Wahyuni; Saharuddin Saharuddin; Lisa Fitriani Ishak; Darniati Darniati; Musdalifa Thamrin; Emil Agusalim Habi Talib; Alvina Felicia Watratan
I-Com: Indonesian Community Journal Vol 6 No 2 (2026): I-Com: Indonesian Community Journal (Juni 2026)
Publisher : Fakultas Sains Dan Teknologi, Universitas Raden Rahmat Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70609/i-com.v6i2.9453

Abstract

The Society 5.0 era requires mastery of transparent and intelligent decision systems, yet practical understanding of integrating Machine Learning (ML) and Multi-Criteria Decision Making (MCDM) through Hybrid Intelligence frameworks remains limited in academic environments. This community service aims to enhance the scientific capacity of academics through the "Morning Class" international program. The methodology employed an online joint lecture approach involving collaboration between Universitas Muhammadiyah Makassar and Multimedia University Malaysia. The activity involved 48 participants and was divided into three phases: initial evaluation, delivery of theoretical-practical integration modules, and final evaluation. Results indicate a significant increase in understanding, with the average score rising from 65.8 in the pre-test to 87.5 in the post-test. The highest improvement (36%) was recorded in the hybrid framework implementation indicator. These findings confirm that the synergy between human expert ethical values and machine data processing speed is a crucial solution for modern decision-making. The program recommends further technical workshops to support deeper research implementation for partner institutions.
A Hybrid K-Means and Neural Network for Enhancing Students’ Academic Performance Suriani Suriani; Muhammad Faisal; Darniati Darniati; Emil Agusalim H. T; Muhammad Syafaat S. Kuba; Swa Lee Lee; Nurdiansyah Nurdiansyah
Buletin Sistem Informasi dan Teknologi Islam (BUSITI) Vol 7, No 2 (2026)
Publisher : Universitas Muslim Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33096/busiti.v7i2.3467

Abstract

Ketersediaan data pada Learning Management System (LMS) mendorong penerapan pembelajaran adaptif di pendidikan tinggi. Penelitian ini mengusulkan kerangka kerja hybrid berbasis kecerdasan buatan yang mengintegrasikan K-Means clustering dan Neural Network untuk profil mahasiswa berbasis perilaku dan prediksi kinerja akademik. Model divalidasi menggunakan Open University Learning Analytics Dataset yang mencakup data demografi, interaksi, dan performa akademik. Hasil menunjukkan akurasi sebesar 0,68 dan F1-score sebesar 0,66, melampaui metode dasar dengan stabilitas yang lebih baik. Clustering menghasilkan silhouette score 0,62 yang menunjukkan pemisahan kelompok yang jelas. Selain itu, sistem meningkatkan relevansi konten sebesar 27% dan menurunkan risiko putus studi sebesar 18%, dengan waktu inferensi rata-rata 0,85 detik. Temuan ini menunjukkan efektivitas kerangka dalam mendukung pembelajaran adaptif yang dipersonalisasi dan skalabel. Model hybrid yang diusulkan dapat mendukung pembelajaran adaptif melalui jalur belajar yang dipersonalisasi serta membantu perguruan tinggi melakukan intervensi dini terhadap mahasiswa berisiko berdasarkan pemantauan berbasis data.
Model Autoencoder untuk Deteksi Anomali pada Log Email Mahasiswa Universitas Muhammadiyah  Makassar Alvina Damayanti; Fahrim Irhamna Rachman; Darniati Darniati
Journal of Muhammadiyah’s Application Technology Vol. 5 No. 2 (2026)
Publisher : Universitas Muhammadiyah Makassar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26618/1wvarw57

Abstract

ABSTRAK Perkembangan teknologi informasi meningkatkan penggunaan email institusi sebagai sarana komunikasi akademik, namun juga menimbulkan risiko keamanan seperti spam, phishing, dan akses tidak sah. Penelitian ini bertujuan untuk mengimplementasikan model Autoencoder dalam mendeteksi anomali pada log email mahasiswa Universitas Muhammadiyah Makassar. Metode yang digunakan adalah pendekatan kuantitatif berbasis unsupervised learning dengan memanfaatkan data log email yang telah melalui tahap preprocessing dan feature engineering. Model Autoencoder dirancang menggunakan arsitektur encoder-decoder dengan lima hidden layer untuk mempelajari pola aktivitas email normal. Proses deteksi anomali dilakukan menggunakan nilai reconstruction error dengan threshold pada persentil ke-99. Hasil penelitian menunjukkan bahwa model mampu mendeteksi aktivitas anomali dengan baik, di mana sekitar 1% data teridentifikasi sebagai anomali dari keseluruhan dataset. Temuan ini menunjukkan bahwa metode Autoencoder efektif digunakan untuk mendeteksi aktivitas mencurigakan pada sistem email institusi dan berpotensi mendukung peningkatan keamanan sistem informasi di lingkungan perguruan tinggi. Kata Kunci: Autoencoder, deteksi anomali, log email, unsupervised learning, keamanan sistem informasi. ABSTRACT The development of information technology has increased the use of institutional email as a medium for academic communication, but it has also introduced security risks such as spam, phishing, and unauthorized access. This study aims to implement an Autoencoder model for anomaly detection in student email logs at Universitas Muhammadiyah Makassar. The research employed a quantitative approach based on unsupervised learning using email log data that had undergone preprocessing and feature engineering. The Autoencoder model was designed using an encoder-decoder architecture with five hidden layers to learn normal email activity patterns. Anomaly detection was performed using reconstruction error values with a threshold set at the 99th percentile. The results showed that the model was able to detect anomalous activities effectively, where approximately 1% of the data were identified as anomalies from the entire dataset. These findings indicate that the Autoencoder method is effective for detecting suspicious activities in institutional email systems and has the potential to enhance information system security in higher education environments. Keywords: Autoencoder, anomaly detection, email logs, unsupervised learning, information system security.
Implementasi Metode TF-IDF dan Cosine Similarity pada Sistem Pencarian Artikel yang Relevan Selfira Madoa; Ida Mulyadi; Darniati Darniati
Journal of Muhammadiyah’s Application Technology Vol. 5 No. 2 (2026)
Publisher : Universitas Muhammadiyah Makassar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26618/a6wkdt68

Abstract

ABSTRAKPerkembangan teknologi informasi menyebabkan peningkatan volume data teks digital, khususnya artikel ilmiah, yang menuntut adanya sistem pencarian informasi yang mampu menyajikan hasil secara relevan dan kontekstual. Pencarian berbasis pencocokan kata kunci secara literal dinilai belum optimal dalam menangani variasi bahasa dan konteks kueri. Oleh karena itu, penelitian ini bertujuan untuk mengimplementasikan dan mengevaluasi metode Term Frequency–Inverse Document Frequency (TF-IDF) dan Cosine Similarity pada sistem pencarian artikel ilmiah berbahasa Indonesia. Penelitian ini menggunakan pendekatan kuantitatif dengan metode eksperimen, di mana data berupa judul dan abstrak artikel diperoleh dari repositori digital terbuka. Tahapan preprocessing teks meliputi case folding, tokenisasi, stopword removal, dan stemming untuk meningkatkan kualitas representasi data. Hasil penelitian menunjukkan bahwa sistem mampu menghasilkan nilai precision hingga 0,75 dan F1-score sebesar 0,67, yang mengindikasikan bahwa metode TF-IDF dan Cosine Similarity efektif dalam meningkatkan relevansi hasil pencarian. Dengan demikian, sistem yang dikembangkan mampu memberikan hasil pencarian yang lebih akurat dan kontekstual dibandingkan metode pencarian berbasis kata kunci literal, serta layak diterapkan pada repositori artikel ilmiah berskala kecil hingga menengah. Kata Kunci: TF-IDF, Cosine Similarity, Sistem Pencarian Informasi, Artikel Ilmiah, Text Mining ABSTRACTThe rapid growth of information technology has led to a significant increase in digital text data, particularly scientific articles, thereby requiring effective information retrieval systems capable of providing relevant and contextual results. Conventional keyword-based search methods are often insufficient in handling linguistic variations and complex query contexts. Therefore, this study aims to implement and evaluate the Term Frequency–Inverse Document Frequency (TF-IDF) and Cosine Similarity methods in an Indonesian scientific article search system. This research adopts a quantitative approach with an experimental method, using article titles and abstracts obtained from open-access digital repositories as the research dataset.Text preprocessing stages include case folding, tokenization, stopword removal, and stemming to improve data consistency and representation quality. The results indicate that the proposed system achieves a precision value of up to 0.75 and an F1-score of 0.67, demonstrating that the combination of TF-IDF and Cosine Similarity effectively enhances the relevance of search results. Thus, the developed system provides more accurate and contextual article retrieval compared to literal keyword matching and is suitable for implementation in small to medium-scale academic repositories. Keywords: TF-IDF, Cosine Similarity, Information Retrieval System, Scientific Articles, Text Mining
Co-Authors Ahmad Faisal Alvina Damayanti Alvina Felicia Watratan Desi Anggreani Emil Agusalim H. T Emil Agusalim Habi Talib Fachrim Irhamna Rachman Ida Mulyadi Ida Mulyadi, Ida Irmawati Irmawati Khadijah Lisa Fitriani Ishak Lukman Mallu, Satriawaty Mardiah Mardiah Muh Khayyir Muhammad Faisal Muhyiddin A.M Hayat Musdalifa Thamrin Musdalifa Thamrin Nasir Usman Nasir Usman Nur Ramadhan Nurdiansyah Nurdiansyah Rosnani Rosnani Rosnani Rosnani S. Kuba, Muhammad Syafa'at Saharuddin Saharuddin Selfira Madoa Sri Wahyuni Suardi Hi Baharuddin Suriani Suriani Swa Lee Lee