Article Per Year (5 Year)
p-Index From 2021 - 2026
6.403
P-Index
This Author published in this journals
All Journal Bianglala Informatika : Jurnal Komputer dan Informatika Akademi Bina Sarana Informatika Yogyakarta Jurnal INSYPRO (Information System and Processing) Journal of Information Systems and Informatics Ainet : Jurnal Informatika Madaniya Jurnal FASILKOM (teknologi inFormASi dan ILmu KOMputer) Indonesian Community Journal Jurnal Ilmu Komputer Jurnal Informatika Progres Mechatronics Journal in Professional and Entrepreneur (MAPLE) Jurnal Intelek Dan Cendikiawan Nusantara Journal of Computer Science and Information Technology ARUS JURNAL SAINS DAN TEKNOLOGI Journal of Muhammadiyah’s Application Technology
Fachrim Irhamna Rachman
Universitas Muhammadiyah Makassar
Religion 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 Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Library & Information Science Mathematics Public Health Social Sciences Other

Published : 52 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 52 Documents
Search

 1   2   3   4   5 
IMPLEMENTASI METODE HYBRID FUZZY JARO WINKLER DAN COSINE SIMILARITY PADA SISTEM PENCARIAN AYAT AL-QURAN BERBASIS TRANSLITERASI LATIN Tahir, Gempar Perkasa; Habi Talib, Emil Agusalim; Rachman, Fahrim Irhamna
PROGRESS Vol 17 No 2 (2025): September
Publisher : P3M STMIK Profesional Makassar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56708/progres.v17i2.482

Abstract

This research addresses the challenge of retrieving Qur’anic verses in Latin transliteration, which is hindered by the absence of a standardized orthography, leading to diverse spelling variations. The study aims to design and implement a hybrid information retrieval system that integrates Fuzzy Jaro-Winkler for lexical similarity and Cosine Similarity on fine-tuned DistilBERT embeddings for semantic relevance. The system workflow begins with preprocessing and normalization of the dataset, followed by initial candidate selection using Jaro-Winkler, and final reranking through semantic similarity scoring. Evaluation was conducted using black-box testing across scenarios including ideal queries, spelling variations, incomplete queries, and varying query lengths. Results show high accuracy for ideal (96%) and varied spelling queries (92%), with performance improving as query length increases, reaching 96% for four-word queries. The hybrid approach effectively bridges lexical and semantic gaps, outperforming single-method baselines, and demonstrates robustness in handling non-standard transliteration in Qur’anic text retrieval.
Prediksi Tingkat Kelulusan Menggunakan K-Means Pada Program Studi Informatika Unismuh Makassar Irhamna Rachman, Fahrim; Mujadilah, Siti; Wahyuni, Titin; Anas, Lukman
JURNAL FASILKOM Vol. 13 No. 3 (2023): Jurnal FASILKOM (teknologi inFormASi dan ILmu KOMputer)
Publisher : Unversitas Muhammadiyah Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37859/jf.v13i3.6061

Abstract

Predicting timely graduation brings numerous benefits not only to students but also to the university itself. Creating a graduation prediction model assists students and academic advisors in fostering a positive environment that encourages on-time graduation by developing a predictive model for graduation rates using the K-means data mining method in the Informatics study program at Universitas Muhammadiyah Makassar. This method is used to cluster students based on attributes such as total credits taken, semester Grade Point Average (GPA), and overall Cumulative Grade Point Average (CGPA). The clustering aims to identify patterns and characteristics of student graduation. Data from several semesters is collected and preprocessed, including data normalization and transformation. The research steps involve data preprocessing, cluster labeling, distance calculation to cluster centers, and result analysis. The analysis shows that the K-means method can generate student clusters with varying graduation rate patterns. The formed clusters can be interpreted as groups of students with potential for timely graduation or groups needing more attention to achieve on-time graduation. Empirical validation is performed by comparing K-means prediction results with actual graduation data. Accuracy measurement involves calculating the percentage of similarity between predictions and actual data. Empirical validation results demonstrate the accuracy level, which can serve as a benchmark for assessing the performance of this prediction model. This study aims to provide deeper insights into factors influencing student graduation and potentially support decision-making at the academic level. Keywords: Graduation Prediction, Data Mining, K-Means, Analysis, Clustering, Empirical Validation.
Analisis Sentimen Text Dengan Metode CNN Study Kasus Tempat Wisata Makassar Kamal, Safutri; Rachman, Fahrim Irhamna; Wahyuni, Titin
Ainet : Jurnal Informatika Vol. 7 No. 1 (2025): Maret (2025)
Publisher : Universitas Muhammadiyah Makassar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26618/n1gcbb74

Abstract

Penelitian ini bertujuan untuk mengevaluasi dan menentukan sejauh mana metode CNN (Convolutional Neural Network) dapat menghasilkan prediksi sentimen yang akurat terhadap ulasan mengenai tempat wisata Makassar. Metode analisis sentimen ini menggunakan data ulasan yang dikumpulkan dari platform Google Maps. Dalam penelitian ini, dilakukan tahap preprocessing untuk membersihkan data, seperti cleaning, transform cases, tokenizing, stopword dan stemming. Selanjutnya, dilakukan pembagian dataset menjadi data latih dan data uji dengan scenario 90 : 10, 80 : 20 dan 70 : 30 untuk melatih dan menguji model dengan tiga kategori ulasan yaitu positif, negatif dan netral. Hasil dari analisis sentimen menunjukkan bahwa metode CNN memiliki kemampuan yang baik dalam memprediksi sentimen positif, negatif, dan netral pada ulasan mengenai Tempat Wisata Makassar. Tingkat akurasi yang tinggi pada tahap pelatihan menunjukkan bahwa model mampu belajar dengan baik dari dataset yang disediakan. Meskipun tingkat akurasi pada tahap validasi sedikit lebih rendah, tetapi masih mencapai angka yang memadai, menunjukkan bahwa model memiliki kemampuan generalisasi yang cukup baik dalam mengklasifikasikan sentimen pada ulasan-ulasan tersebut. Diperoleh hasil akurasi tertinggi dengan Training Accuracy yang meningkat memperoleh nilai akurasi training 95%, serta Validation Accuracy memperoleh nilai 73%.
Pengenalan Bahasa Isyarat Menggunakan Deteksi Objek Deep Learning Virgiawan, David Arian; Fachrim Irhamna Rahman; Rizki Yusliana Bakti
Ainet : Jurnal Informatika Vol. 7 No. 1 (2025): Maret (2025)
Publisher : Universitas Muhammadiyah Makassar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26618/qkztgb55

Abstract

Berdasarkan perkembangan teknologi, khususnya di bidang komputasi, semakin memungkinkan pengembangan sistem yang mampu mendeteksi bahasa isyarat dengan lebih efisien. Salah satu masalah utama yang dihadapi adalah bagaimana cara mendeteksi dan mengklasifikasi gerakan bahasa isyarat secara akurat menggunakan algoritma YOLOv8. Penelitian ini bertujuan untuk mengimplementasikan YOLOv8 dalam mendeteksi dan mengklasifikasi abjad pada bahasa isyarat Indonesia (SIBI). Penelitian ini dilakukan di Universitas [Nama Universitas], dengan menggunakan dataset yang dikumpulkan melalui pengambilan foto simbol tangan abjad A-Z yang kemudian diproses untuk pelabelan dan pelatihan model. Proses pelatihan model dilakukan menggunakan data yang dibagi menjadi tiga bagian: pelatihan (60%), validasi (20%), dan pengujian (20%). Pengujian model menghasilkan tingkat akurasi yang sangat tinggi sebesar 99,5%, dengan presisi 99,1%, dan recall 99,4%. Hasil ini menunjukkan bahwa sistem yang dikembangkan sangat andal dalam mendeteksi bahasa isyarat secara real-time. Penelitian ini menyarankan agar penelitian selanjutnya menambahkan variasi data isyarat dari berbagai pengguna untuk memperkaya dataset, serta mempertimbangkan penggunaan algoritma terbaru atau penggabungan beberapa algoritma untuk meningkatkan kinerja deteksi .Kata Kunci : Pengenalan Bahasa Isyarat, YOLOv8, Deep Learning, Deteksi Objek, SIBI
KLASIFIKASI SARAN DAN KRITIK PADA SIMAK UNISMUH DENGAN MENGGUNAKAN ALGORTIMA RECCURENCT NEURAL NETWORK (RNN) faisal, Ahmad; Wahyuni, Titin; Rachman, Fahrim Irhamna
Ainet : Jurnal Informatika Vol. 7 No. 1 (2025): Maret (2025)
Publisher : Universitas Muhammadiyah Makassar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26618/8ttaxq04

Abstract

SIMAK Unismuh Makassar is an important platform used by students to submit suggestions and criticisms related to various academic aspects. In this study, researchers implemented the Recurrent Neural Network (RNN) algorithm to classify suggestions and criticisms received through SIMAK Unismuh. The purpose of this study was to determine the implementation of the RNN Algorithm in classifying suggestions and criticisms on the SIMAK Unismuh page and how successful the RNN Algorithm was in classifying suggestions and criticisms on the SIMAK Unismuh page. RNN was chosen because of its ability to process sequential text data, such as input in the form of sentences, which allows the model to capture the context of the input more effectively. The dataset used in this study consists of a number of suggestion and criticism data that have been categorized manually. The RNN model that was built was then trained and tested using the data to assess its accuracy and performance. The results showed that the model achieved the highest accuracy of 91% and the lowest accuracy of 90%. Although there were variations in model performance, these results indicate that RNN has good potential in classifying suggestion and criticism texts. The RNN model can help institutions understand and respond to user input more effectively, although it still requires further optimization to improve the consistency and accuracy of the results. The conclusion of this study shows that the RNN model is able to classify suggestions and criticisms with an adequate level of accuracy. The application of this model is expected to help the Unismuh administration in managing student input more efficiently, as well as providing more appropriate and faster responses to academic needs.Keywords: Text Classification, Recurrent Neural Network (RNN), SIMAK Unismuh, Suggestions and Criticisms, Academic Information System.
Penggunaan CNN Dalam Analisis Sentimen Pada Review Tempat Wisata Makassar Kamal, Safutri; Rachman, Fahrim Irhamna; Wahyuni, Titin
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: 10.26618/73mrdb71

Abstract

Penelitian ini bertujuan untuk menganalisis sentimen pada ulasan tempat wisata di Makassar menggunakan metode Convolutional Neural Network (CNN). Makassar, sebagai salah satu destinasi wisata utama di Indonesia, menerima banyak ulasan dari pengunjung yang beragam. Setiap ulasan diproses secara tekstual melalui tahapan pembersihan data, tokenisasi, penghapusan kata-kata umum (stop words), dan stemming. Model CNN yang dibangun terdiri dari beberapa lapisan konvolusi dan pooling yang berfungsi untuk mengekstraksi fitur penting dari teks ulasan. Hasil penelitian ini memberikan wawasan yang berharga mengenai persepsi pengunjung terhadap tempat wisata di Makassar. Analisis sentimen ini dapat digunakan oleh pengelola tempat wisata dan pihak terkait untuk meningkatkan kualitas layanan dan pengalaman wisatawan.
Optimasi Ukuran Dataset untuk Analisis Sentimen Menggunakan Teknik Pembelajaran Mesin dan Pembelajaran Mendalam Halisah Duli, St Nur; Rahman, Fahrim Irhamna; Wahyuni, Titin
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/xsq0pg68

Abstract

Penelitian ini bertujuan untuk mengoptimalkan ukuran dataset yang digunakan dalam analisis sentimen melalui penerapan teknik pembelajaran mesin dan pembelajaran mendalam. Metode pembelajaran mesin yang digunakan mencakup Naive Bayes, Regresi Logistik, dan Support Vector Machine, sedangkan Convolutional Neural Network digunakan untuk metode pembelajaran mendalam. Data yang digunakan dalam penelitian ini berasal dari ulasan Google Maps mengenai beberapa tempat wisata, seperti Bugis Waterpark, Akkarena, Tanjung Bayang, Pantai Bosowa, dan Wisata Kebun. Tahap pra-pemrosesan data meliputi pembersihan data, casefolding, penghapusan stopwords, tokenisasi, dan stemming. Pengujian dilakukan dengan sembilan ukuran dataset yang berbeda (4500, 4000, 3500, 3000, 2500, 2000, 1500, 1000, dan 500) serta pembagian data latih dan data uji dengan rasio 90:10, 80:20, dan 70:30. Hasil pengujian menunjukkan bahwa Regresi Logistik dengan ukuran dataset 1000 dan Pembagian 90:10 mencapai tingkat akurasi tertinggi sebesar 85%. Studi ini menyimpulkan bahwa ukuran dataset yang optimal bervariasi tergantung pada metode yang digunakan dan menggarisbawahi pentingnya pemilihan ukuran dataset yang tepat untuk meningkatkan kinerja analisis sentimen. .
Implementasi Algoritma Simulated Annealing dalam Optimasi Waktu Tempuh pada Sistem Pengantaran J&T Express di Kecamatan Mariso Dika, Andika Saputra; Fachrim, Fachrim Irhamna Rahman; Chyquitha, Chyquitha Danu Putri; saputra, andika
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: 10.26618/6qf28j63

Abstract

Meningkatnya volume pengiriman paket di perusahaan logistik membutuhkan perencanaan rute yang efisien, terutama di daerah perkotaan dengan kepadatan lalu lintas yang tinggi. Distrik Mariso dicirikan oleh kondisi lalu lintas yang padat yang secara signifikan memengaruhi waktu tempuh pengiriman bagi kurir J&T Express. Studi ini bertujuan untuk mengoptimalkan rute pengiriman paket dengan meminimalkan total waktu tempuh menggunakan Simulated Annealing (SA). Dataset dikumpulkan melalui observasi lapangan, wawancara kurir, dan analisis peta digital, termasuk titik pengiriman, jarak antar titik, dan perkiraan waktu tempuh berdasarkan kondisi lalu lintas historis. Masalah pengiriman dirumuskan sebagai Traveling Salesman Problem menggunakan model grafik berbobot. Hasil eksperimen menunjukkan bahwa metode yang diusulkan menghasilkan rute pengiriman yang lebih efisien dengan pengurangan total waktu tempuh dibandingkan dengan praktik perutean manual. Temuan ini menunjukkan bahwa Simulated Annealing efektif untuk optimasi rute pengiriman dan dapat digunakan sebagai pendekatan pendukung keputusan untuk meningkatkan efisiensi logistik di daerah perkotaan.
Enhancing YOLOv12-Based Rice Leaf Disease Detection through Evaluation of Three Data-Split Scenarios Ida Mulyadi; Fahrim Irhamna; Chyquitha Danuputri; Ridwang; Ridha Awalia
Journal of Information System and Informatics Vol 8 No 2 (2026): April
Publisher : Asosiasi Doktor Sistem Informasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63158/journalisi.v8i2.1580

Abstract

One of the most significant staple crops in the world is rice, and one of the main causes of the drop in agricultural yields is illnesses that affect rice leaves. To avoid large agricultural losses, early diagnosis of these illnesses is essential. The goal of this project is to use YOLOv12, the most recent deep learning-based object detection architecture, to create a rice leaf disease detection system. The model was trained using a dataset of 4,744 photos of rice leaves that included three disease classes: Leaf Blast, Brown Spot, and Bacterial Leaf Blight. Methods to boost variability and enhance detection performance, image preprocessing with data augmentation was used. Standard object detection criteria, such as mean Average Precision (mAP), precision, and recall, were used to assess the model. The YOLOv12 model was highly effective in detecting rice leaf illnesses. According to the experimental data, it achieved a mAP of 97%, a precision of 96%, and a recall of 96.5%. The use of YOLOv12's greater efficiency and quality in detecting small objects—which is essential for identifying illness symptoms on leaves—is what makes this study successful. These results lay the groundwork for upcoming precision agricultural real-time monitoring applications.
IMPLEMENTASI SISTEM DETEKSI PRODUK BOIKOT BERBASIS WEBSITE REAL-TIME MENGGUNAKAN METODE YOLOv10 Nur Rahman, Ahmad; Habi Talib, Emil Agusalim; Rachman, Fahrim Irhamna; Bakti, Rizki Yusliana; Faisal, Muhammad; S. Kuba, Muhammad Syafaat
PROGRESS Vol 18 No 1 (2026): April
Publisher : P3M STMIK Profesional Makassar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56708/progres.v18i1.525

Abstract

Manual identification ofboycott products remains a challenge for the public due to limited access to information and the complexity of brand affiliations. This study aims to develop a real-time, website-based boycott product detection system using the You Only Look Once version 10 (YOLOv10) algorithm. The dataset consists of images of food and beverage product packaging collected from various online sources, annotated using the bounding box method, and classified into five categories. The model was trained and tested using separate test data, while performance evaluation was conducted using a confusion matrix with precision, recall, and f1-score metrics. In addition, functional testing of the system was performed using the Black Box Testing method. The result indicate that the YOLOv10 model is capable of detecting boycott product with good performance and can be effectively integrated into a real-time web-based system. The proposed system is expected to assist users in identifying boycott products more quickly and accurately.
Co-Authors Adrianingsih, Rizka Afifah Auliyah Ahmad Faisal Ahmad Fathir Ahmad Nur Rahman Aiman , Ailul ANDIKA SAPUTRA Annisa Alfrini Aras, Dara Ugi Ardiansyah Uddin Bakti, Rizki Yusliana Basyar, Muhammad Yusuf Besse Taleha Chyquita Danuputri Chyquitha Danu Putri Chyquitha Danuputri Chyquitha Danuputri Chyquitha Danuputri Chyquitha, Chyquitha Danu Putri Chyquithadanuputri Darniati Desi Anggreani Dika, Andika Saputra Emil Agus Salim Habi Talib Erick Yusuf Kotte Ferdiansyah Gempar Perkasa Tahir Halisah Duli, St Nur Hanna Maryam Hasbir, Syahrul Hildayati, Hildayati Ida Mulyadi Ida Mulyadi, Ida Indriani, Lis Iskandar, Aryansyah Ismail, La Ode Taufik Kamal, Safutri La Ode Taufik Ismail La Ode Taufik Ismail LUKMAN ANAS Lukman Lukman LUKMAN, LUKMAN Mohammad Ramadhan Zainuddin Muhammad Alif Syafan Muhammad Daffa Ruwaid Aras Muhammad Faisal Muhammad Syafaat S. Kuba Muhyiddin A.M Hayat Mujadilah, Siti Mustakim Mustakim Nur Alam Nur Fadillah Sari Nur Rahman, Ahmad Rayhanatul Jannah Reski Awalia Ridha Awalia Ridwang Rinaldy, Muh Rizki Yusliana Rizky Maulia Rosnani Rosnani Salam, Abd Sari, Selvi Permata Setiawan, Tommy Reynaldy Sri Hastati Sry Yunarti Suhardi, Syahrul Syahrul Hasbir Syahrul Suhardi Tahir, Gempar Perkasa Titin Wahyuni Titin Wahyuni Virgiawan, David Arian Wibawa. Ar, Arya Yanti, Wilda Zulkifli Halim