Claim Missing Document
Check
Articles

Found 39 Documents
Search

KLASIFIKASI PENYAKIT TANAMAN NILAM BERDASARKAN CITRA DAUN MENGGUNAKAN GLCM DAN SVM Sarina; Bakti, Rizki Yusliana; Muhammad Faisal; Muhammad Syafaat; Syamsuri, Andi Makbul; AM Hayat, Muhyiddin; Anas, Andi Lukman
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.v17i2.469

Abstract

This study presents a classification model for detecting diseases in patchouli (Pogostemon cablin Benth) leaves using image processing techniques. The method combines Grey Level Co-occurrence Matrix (GLCM) for texture feature extraction and Support Vector Machine (SVM) for classification, optimised using the Particle Swarm Optimisation (PSO) algorithm. A total of 2,080 leaf images were collected and categorized into four classes: healthy, leaf spot, yellowing, and mosaic. Each image was augmented and converted to grayscale to enhance the dataset and reduce computational complexity. Four GLCM features—contrast, correlation, energy, and homogeneity—were extracted to represent leaf textures. The classification model achieved an accuracy of 89.74% using SVM alone, and improved to 97.12% when optimized with PSO. The results indicate that the integration of GLCM, SVM, and PSO provides an effective and accurate solution for early detection of patchouli leaf diseases, potentially supporting farmers in decision-making and improving crop productivity and quality.
PREDIKSI PEMAKAIAN AIR BULANAN DI PDAM KECAMATAN TAMALATE MENGGUNAKAN METODE AUTOREGRESSIVE INTEGRATED MOVING AVERAGE (ARIMA) Syarifuddin, Nur Annisa; Wahyuni, Titin; Faisal, Muhammad; Syafaat, Muhammad; Syamsuri, Andi Makbul; AM Hayat, Muhyiddin; Anas, Andi Lukman
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.v17i2.471

Abstract

Water consumption forecasting is a crucial aspect of efficient water resource management, particularly in urban areas with increasing demand. This study aims to predict the monthly water usage volume at the PDAM of Tamalate District using the Autoregressive Integrated Moving Average (ARIMA) method. The dataset consists of historical water usage data from January 2022 to December 2024, totaling 36 monthly observations. The analysis process includes stationarity testing using the Augmented Dickey-Fuller (ADF) test, model parameter identification through ACF and PACF plots, and performance evaluation using MAE, RMSE, and MAPE metrics. The results show that the best-performing model is ARIMA, which demonstrates high prediction accuracy, with a MAE of 26,049.80 m³, RMSE of 37,459.00 m³, and MAPE of 4.12%. This model is capable of generating predictions close to actual values and can be relied upon as a basis for PDAM’s water distribution planning. It is expected that this research will contribute to data-driven decision-making and support digital transformation in the public service sector.
IMPLEMENTASI HYBRID LEXICON-BASED DAN SVM UNTUK KLASIFIKASI ANALISIS SENTIMEN TERHADAP PELATIHAN BBPSDMP KOMINFO MAKASSAR Alam, Nur; Faisal, Muhammad; Bakti, Rizki Yusliana; Syafaat, Muhammad; Syamsuri, Andi Makbul; AM Hayat, Muhyiddin; Anas, Andi Lukman
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.v17i2.473

Abstract

The evaluation of government training programs is often hindered by manual analysis of unstructured qualitative feedback, making the process inefficient and subjective. This study aims to implement and evaluate a sentiment classification model using a hybrid Lexicon-Based and Support Vector Machine approach to analyze participants’ perceptions of the Vocational School Graduate Academy training organized by BBPSDMP Kominfo Makassar, as well as to compare the performance of a standard SVM model with a model optimized using Particle Swarm Optimization. This quantitative research employs 2,313 unstructured review data, which undergo text preprocessing, initial lexicon-based labeling, and TF-IDF feature extraction before being classified using an SVM with an RBF kernel. The results show that the SVM model optimized with PSO consistently outperforms the standard model across all four evaluation aspects, with the most significant accuracy improvement observed in the instructor category from 84.71% to 89.02% and in the assessor category reaching 91.46%. PSO optimization has proven effective in enhancing the model’s ability to identify negative sentiments, which represent the minority class. The hybrid approach with PSO optimization is capable of producing a more accurate and balanced classification system, with practical implications as an objective automated evaluation tool.
IMPLEMENTASI HYBRID CNN, FACIAL LANDMARK DAN LIVENESS DETECTION PADA SISTEM ABSENSI WAJAH Akbar DB, Andi Muhammad; Faisal, Muhammad; AM Hayat, Muhyiddin
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.v17i2.483

Abstract

This paper presents the implementation of a hybrid approach for face recognition attendance systems, combining Convolutional Neural Network (CNN), facial landmark detection, and liveness detection. The CNN model extracts facial features for identity recognition, while facial landmark detection captures dynamic movements such as eye blinking and mouth motion. Liveness detection ensures system robustness against spoofing attempts including photo and video replay. The system was developed using Python with OpenCV, MediaPipe, and TensorFlow, and tested under multiple spoofing scenarios. Results show a detection accuracy of 95.5%, with real-time performance and resilience against common spoofing threats.
A Bluetooth-Based Attendance System for Educational Administration at SMA Muhammadiyah: Cross-Platform Development and Usability Validation Hayat, Muhyddin A.M.; Rasyidi, Muhammad Fachri; Faisal, Muhammad; Bakti, Rizki Yusliana; Syamsuri, Andi Makbul
Jurnal Teknik Informatika (Jutif) Vol. 6 No. 5 (2025): JUTIF Volume 6, Number 5, Oktober 2025
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2025.6.5.4873

Abstract

The transformation of educational administration through technology has accelerated significantly, particularly in attendance systems, which have traditionally relied on manual roll calls. These conventional methods are time-consuming, error-prone, and susceptible to manipulation. This study presents a novel Bluetooth-based attendance system that contributes to the field by demonstrating passive MAC address detection for automated attendance recording, eliminating the need for additional software installations on student devices. The system was developed using React Native for cross-platform compatibility, with PostgreSQL for data management and NestJS for backend processing. The software engineering process followed Rapid Application Development (RAD) methodology, combined with comprehensive system validation through experimental testing. Usability evaluation with 133 participants using the System Usability Scale (SUS) yielded a score of 79.85, categorizing the system within the "Good to Excellent" usability range. The findings demonstrate significant improvements in efficiency and a reduction in attendance fraud compared to conventional methods. However, hardware quality and device proximity remain key limitations. Future research should explore the integration of Bluetooth Low Energy (BLE) technology, the implementation of machine learning algorithms for anomaly detection, or the development of hybrid validation models that combine multiple authentication factors. This system demonstrates the potential to modernize educational administration through seamless, device-level integration while maintaining high user acceptance.
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.
Enhancing Faculty Digital Competence through Learning Management System Training: A Case Study at STMIK Profesional Makassar Nasir Usman; Muhammad Faisal; Sri Wahyuni; Lisa Fitriani Ishak; A. Muhammad Syafar; Saharuddin Saharuddin; Nurdiansyah Nurdiansyah; Andi Muhammad Nur Hidayat
I-Com: Indonesian Community Journal Vol 5 No 3 (2025): I-Com: Indonesian Community Journal (September 2025)
Publisher : Fakultas Sains Dan Teknologi, Universitas Raden Rahmat Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70609/i-com.v5i3.7787

Abstract

The digital transformation in higher education necessitates the enhancement of faculty capacity in leveraging online learning technologies, one of which is the Moodle Learning Management System (LMS). This community service initiative aimed to strengthen the competencies of lecturers at STMIK Profesional Makassar in effectively and independently utilizing Moodle LMS. The training was conducted in two sessions using a hands-on approach, covering the management of instructional materials, discussion forums, quizzes, assignments, and learning evaluations. The results indicated significant improvements in mastering Moodle’s structure and core features, lecturers’ readiness to manage an inclusive, flexible, and adaptive digital learning ecosystem, as well as their ability to develop digital learning materials, manage discussion forums, and design system-based evaluations. These enhancements had a direct impact on the quality of interaction and student learning outcomes. Moreover, this initiative supported sustainable digital transformation at the institutional level, reinforcing STMIK Profesional Makassar’s image as a progressive higher education institution responsive to the challenges of the Fourth Industrial Revolution.
OPTIMALISASI DISTRIBUSI PEMILIH TERHADAP TPS MENGGUNAKAN METODE CLUSTERING FUZZY C-MEANS Djalil, Sony Achmad; Muhammad Faisal; Muhyiddin AM Hayat; Titin Wahyuni
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: 10.26618/6jc0a759

Abstract

General elections are a fundamental pillar of modern democratic systems, requiring an implementation that is efficient, fair, and inclusive. One of the key factors influencing the success of an election is the determination of polling station locations, as their placement directly affects voter accessibility, travel distance, and public participation. Inappropriate polling station allocation can lead to service inequality, voter congestion, and a decline in the overall quality of the voting process. At the local administrative level, polling station determination is still largely conducted manually by grouping voters based on neighborhood or administrative boundaries. This conventional approach is often time consuming, prone to administrative errors, and frequently results in an uneven distribution of voters across polling stations. In addition, electoral regulations impose limits on the maximum number of voters per polling station to ensure smooth and orderly voting procedures, which are not always optimally satisfied through manual methods. As voter data complexity and geographic dispersion increase, computational approaches are needed to support more effective decision making. Clustering techniques in unsupervised learning enable objective grouping of voters based on spatial characteristics. The Fuzzy C-Means method represents a suitable approach because it can accommodate data uncertainty and overlapping service areas. The application of this method is expected to produce a more efficient, equitable, and data driven distribution of polling stations, thereby contributing to the improvement of election management quality and democratic integrity
Stacking architecture-endpoint detection: a hybrid multi layered architecture for endpoint threat detection Wahid, Abd Rahman; Anggreani, Desi; Hayat, Muhyiddin A. M.; Abd Rahman, Aedah; Faisal, Muhammad
International Journal of Advances in Applied Sciences Vol 14, No 4: December 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijaas.v14.i4.pp1263-1280

Abstract

Modern endpoint threat detection systems face persistent challenges in balancing detection accuracy, resilience against zero-day attacks, and the interpretability of artificial intelligence (AI) models. Although deep learning (DL) approaches often achieve high accuracy on benchmark datasets, they remain vulnerable to adversarial perturbations and operate as opaque “black boxes,” thereby reducing trust and limiting practical adoption in critical infrastructures. This research introduces stacking architecture-endpoint detection (STACK-ED), a hybrid multi-layered architecture for endpoint threat detection. STACK-ED integrates three complementary paradigms: supervised learning for known attack patterns, self-supervised Fgraph-based learning for structural relationships, and unsupervised anomaly detection for emerging or unknown threats. The outputs are consolidated by a meta learner, followed by a post-hoc correction (PHC) mechanism to minimize false negatives. The framework was evaluated on a combined benchmark dataset (CSE-CIC-IDS2018 and UNSW-NB15, hereafter referred to as HIDS-Set). Experimental results demonstrate state-of-the-art performance, achieving an F2-score of 98.89% after hybrid integration and active learning, with the primary optimization objective being the reduction of undetected attacks. Furthermore, the Shapley additive explanations (SHAP) method enhances interpretability by revealing feature contributions, while the PHC successfully recovered 62.64% of missed zero-day candidates. The findings position STACK-ED not only as a highly accurate detection model but also as an adaptive, resilient, and transparent framework, offering practical implications for enterprise-grade endpoint defense and future zero-trust cybersecurity systems.