Garuda - Garba Rujukan Digital

Digital Image Processing for Detecting Industrial Machine Work Failure with Quantization Vector Learning Method Muhammad Rafli Rasyid; Zulkifli Tahir; nfn Syafaruddin
Jurnal Pekommas Vol 4, No 2 (2019): Oktober 2019
Publisher : BBPSDMP KOMINFO MAKASSAR

Todays, digital image processing is widely used in various fields to facilitate humans in doing work by analyzing videos or images for use in decision making in the industrial world. The use of industrial machine technology is one of the most important factors in efforts to facilitate human work, but an industrial machine is inseparable from work failure that can hinder the production process and cause harm to the industry. This study aims to detect a failure in industrial machinery by using video data of industrial machine movements recorded using a webcam camera. For the preprocessing stage, the image is resized then converted to grayscale imagery and segmented using the thresholding method, then morphological operations are performed with an opening operation, feature extraction is done by changing the binary image into a vector data that is used as input data in the classification process using the Learning Vector Quantization Neural Network Algorithm (LVQ NN) version 1. The results showed the results of the detection of machine working errors can be done well with an accuracy value of 94.24% in training and 92.38% in the testing phase.

Digital Image Processing for Detecting Industrial Machine Work Failure with Quantization Vector Learning Method Rasyid, Muhammad Rafli; Tahir, Zulkifli; Syafaruddin, nfn
Jurnal Pekommas Vol 4 No 2 (2019): October 2019
Publisher : Sekolah Tinggi Multi Media “MMTC” Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30818/jpkm.2019.2040203

Todays, digital image processing is widely used in various fields to facilitate humans in doing work by analyzing videos or images for use in decision making in the industrial world. The use of industrial machine technology is one of the most important factors in efforts to facilitate human work, but an industrial machine is inseparable from work failure that can hinder the production process and cause harm to the industry. This study aims to detect a failure in industrial machinery by using video data of industrial machine movements recorded using a webcam camera. For the preprocessing stage, the image is resized then converted to grayscale imagery and segmented using the thresholding method, then morphological operations are performed with an opening operation, feature extraction is done by changing the binary image into a vector data that is used as input data in the classification process using the Learning Vector Quantization Neural Network Algorithm (LVQ NN) version 1. The results showed the results of the detection of machine working errors can be done well with an accuracy value of 94.24% in training and 92.38% in the testing phase.

Pelatihan Teknologi Digital Chatbot Interaktif Berbasis Poe AI dan Mathpix bagi Guru SMA di Kabupaten Majene Muhammad Abdy; Nursyam Anaguna; Musawwir Musawwir; Muh. Rafli Rasyid; Fadhil Zil Ikram
Sipakaraya : Jurnal Pengabdian Masyarakat Vol. 4 No. 2 (2026): Sipakaraya : Jurnal Pengabdian Masyarakat
Publisher : Universitas Sulawesi Barat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31605/sipakaraya.v4i2.6141

Kurangnya keterampilan guru dalam menggunakan teknologi pembelajaran digital untuk menciptakan efektifitas dan inovasi dalam mengevaluasi pembelajaran matematika yang sesuai dengan perkembangan zaman merupakan masalah yang dialami beberapa guru SMA Kabupaten Majene. Untuk mengatasi masalah tersebut, dilaksanakan kegiatan pelatihan dan pendampingan bagi guru yang bertujuan untuk: 1) meningkatkan keterampilan penggunaan teknologi digital Chatbot Interaktif berbasis Poe AI dan Mathpix dalam pembelajaran, dan 2) meningkatkan efektifitas dan inovasi guru dalam membuat soal dan rubrik penilaian melalui penggunaan teknologi digital Chatbot Interaktif berbasis Poe AI dan Mathpix. Metode pelaksanaan terdiri dari 4 tahapan yaitu: perencanaan, tindakan, observasi, dan evaluasi. Kegiatan pelatihan dilaksanakan selama 1 hari dan kegiatan pendampingan dilakukan selama 2 bulan. Peserta yang terlibat sebanyak 16 guru, di mana lokasi pengabdian dilaksanakan di SMA Negeri 2 Majene. Hasil pelatihan dan pendampingan menunjukkan terdapat peningkatan keterampilan guru dalam menggunakan teknologi digital Poe AI dan Mathpix. Selain itu, ada peningkatan efektifitas dan inovasi guru dalam menyusun soal yang bervariasi dan berkualitas dalam pembelajaran matematika melalui penggunaan teknologi Chatbot interaktif berbasis Poe AI dan Mathpix.

Rancang Bangun dan Evaluasi Sistem Smart-Ponik Untuk Monitoring dan Automatisasi Tanaman Hidroponik Berbasis IOT dengan Protokol MQTT QTT Siti Aulia Rachmini; Muh. Rafli Rasyid; Chairi Nur Insani; Alim Rabbani
Journal of Applied Computer Science and Technology Vol. 6 No. 2 (2025): Desember 2025
Publisher : Indonesian Society of Applied Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52158/tpd2rq94

Hydroponic farming, a soil-free farming method that has grown in popularity due to its efficient land use and ability to deliver high-quality yields. However, when managed manually, it often encounters issues such as inaccurate watering, imprecise nutrient regulation, and delays in detecting environmental changes. These factors can lead to reduced productivity and lower crop quality. This research aims to address these issues by developing Smart-Ponik, an Internet of Things (IoT)-based monitoring and automation system for hydroponic cultivation utilizing the Message Queuing Telemetry Transport (MQTT) protocol. The system integrates DHT22, soil moisture, and pH sensors to monitor key environmental parameters and transmits data in real time to a server for visualization through a web-based dashboard and automated notifications. The study employs a Research and Development (R&D) method consisting of needs analysis, system design, implementation, and testing. Experimental results show that the system achieves a 100% data transmission rate without packet loss, with an average latency of 0.00 seconds, and occasional delays of 0.01–0.02 seconds due to network fluctuations. Automated control of pumps and fans records a 95% success rate, while black-box testing demonstrates a 100% functional pass rate. In conclusion, Smart-Ponik proves effective for real-time monitoring and automation of hydroponic environments. The system minimizes manual errors, enhances environmental stability, and supports more consistent crop yields. These findings highlight the potential of IoT-based automation to improve precision agriculture practices and increase the reliability of hydroponic production.

Deteksi Gerakan Bahasa Isyarat Menggunakan Euclidean Distance Chairi Nur Insani; Nurhikma Arifin; Muh. Rafli Rasyid
Informatik : Jurnal Ilmu Komputer Vol 19 No 1 (2023): April 2023
Publisher : Fakultas Ilmu Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52958/iftk.v19i1.5658

Orang yang memiliki keterbatasan pendengaran/wicara akan sulit berkomunikasi secara lisan dengan orang normal. Cara berkomunikasinya dapat menggunakan tulisan yang lambat dan tidak efisien atau dengan bahasa isyarat. Bahasa isyarat menjadi satu-satunya metode yang efisien digunakan bagi orang dengan keterbatasan pendengaran/wicara. Sedangkan kebanyakan masyarakat normal tidak dapat menggunakan bahasa isyarat. Sehingga sistem untuk mendeteksi bahasa isyarat menjadi sebuah kebutuhan untuk membantu masyarakat dengan keterbatatasan komunikasi secara lisan. Penelitian ini bertujuan untuk mendeteksi bahasa isyarat kedalam teks sesuai dengan makna yang sebenarnya. Pengambilan data dilakukan menggunakan Leap Motion dengan 15 data gerakan isyarat tangan yang memiliki gerakan dasar dan kemiripan dalam gerakannya. Data yang digunakan dalam penelitian ini berupa isyarat abjad A, B, W, M, N, J, Z dan isyarat kata dia, pakai, saya, kakak, adik bingung, kecewa, hai. Metode yang digunakan pada penelitian ini adalah euclidean distance untuk mencari jarak minimum dari nilai support vector yang terdeteksi sama. Inputan pada proses uji adalah huruf W yang dilakukan secara realtime memiliki kemiripan gerakan isyarat dengan huruf B dan kata kecewa nilai Euclidean distance yaitu 0.5475649269013902 maka inputan tersebut dapat terdeteksi sesuai dengan makna yang sebenarnya. Hasil akurasi rata-rata yang didaparkan dari keseluruhan tahap pengujian 15 data gerakan sebesar 88,7%.

Hybrid Machine Learning Models Based on MobileNetV2 Feature Extraction for Robusta Coffee Leaf Disease Classification Rahmatia; Muh. Rafli Rasyid; Nurhikma Arifin
Journal of Embedded Systems, Security and Intelligent Systems Vol 7 No 1 (2026): March 2026
Publisher : Program Studi Teknik Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59562/jessi.v7i1.11896

Purpose – This study aims to evaluate the effectiveness of a hybrid machine learning approach for classifying robusta coffee (Coffea canephora) leaves into healthy and diseased categories, addressing challenges in manual field inspection and limited comparative analyses across classifiers. Design/methods/approach – A hybrid framework was implemented by combining MobileNetV2 as a feature extractor with four machine learning classifiers: Random Forest, K-Nearest Neighbor, Linear Support Vector Machine, and Gaussian Naive Bayes. The dataset comprised 1,560 images (791 healthy and 769 diseased), split into 70% training, 10% validation, and 20% testing using a hash-based grouped strategy to prevent data leakage from duplicate images. Model performance was evaluated using accuracy, F1-score, ROC-AUC, and McNemar’s statistical test. Findings – Gaussian Naive Bayes achieved the highest accuracy (93.89%) and F1-score (93.85%), while Random Forest obtained the highest ROC-AUC (96.94%). However, McNemar’s test showed no statistically significant differences among the models (p > 0.05), indicating comparable classification performance. The results demonstrate that lightweight hybrid approaches can achieve strong performance even with relatively small datasets. Research implications/limitations – The study is limited to binary classification and a relatively small dataset, which may restrict generalizability to more complex, multi-class disease scenarios. Further research with larger and more diverse datasets is recommended. Originality/value – This study provides a systematic comparison of multiple machine learning classifiers using a unified MobileNetV2 feature representation, offering practical insights into efficient and reliable approaches for early-stage coffee leaf disease screening in resource-constrained environments.

Title

Found 6 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 6 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 6 Documents
Search