Garuda - Garba Rujukan Digital

IMPROVEMENT OF HANDWRITING JAVASCRAFT IMAGE QUALITY AND SEGMENTATION WITH CLOSING MORPHOLOGY AND ADAPTIVE THRESHOLDING METHODS Arif Riyandi; Shofwatul 'Uyun
Telematika Vol 19, No 3 (2022): Edisi Oktober 2022
Publisher : Jurusan Teknik Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31315/telematika.v19i3.7564

Tujuan: Perbaikan kualitas citra yang putus-putus atau terlalu tipis pada aksara jawa tulisan tangan menggunakan operasi morfologi dan mengumpulkan dataset secara otomatis dari proses cropping dengan metode Connected Component Labeling.Perancangan/metode/pendekatan: Menerapkan metode operasi morfologi dalam perbaikan citra putus-putus dan metode connected component labeling untuk membantu cropping dalam mengumpulkan dataset secara otomatis.Hasil: Hasil uji coba dengan beberapa kernel yang berbeda antara operasi morfologi opening dan operasi morfologi closing terpilih operasi morfologi closing dengan kernel (45,45) pada bagian dilasi dan kernel (37,37) pada bagian erosi. Hasil dari segmentasi yang terpilih lanjut ke cropping dengan bantuan metode connected component labeling dan klasifikasi convolutional neural network yang diterapkan untuk mengklasifikasi citra aksara jawa dengan baik. Akurasi yang diperoleh adalah sebesar 94,27 % pada proses klasifikasi menggunakan data training dan akurasi 84,53% pada proses klasifikasi menggunakan data validasi.Keaslian/ state of the art: Pengujian dari operasi morfologi opening dan operasi morfologi closing dengan masing-masing 6 kernel berbeda pada proses segmentasi citra aksara jawa untuk perbaikan kualitas citra. Pengumpulan dataset secara otomatis dari hasil cropping citra dengan bantuan metode connected component labeling dan hasil dataset yang terkumpul diklasifikasi untuk masing-masing citra aksara jawa.

Classification of Damaged Road Images Using the Convolutional Neural Network Method Arif Riyandi; Tony Widodo; Shofwatul Uyun
Telematika Vol 19, No 2 (2022): Edisi Juni 2022
Publisher : Jurusan Teknik Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31315/telematika.v19i2.6460

Objective: Automatic identification is carried out with the help of a tool that can take an image of road conditions and automatically distinguish the types of road damage, the location of road damage in the image and calculate the level of road damage according to the type of road damage.Design/method/approach: Identification of damaged roads usually uses manual RCI system which requires high cost. In this study, a comparison framework is proposed to determine the performance of the image pre-processing model on the image classification algorithm.Results: Based on 733 image data classified using the CNN method from 4 models of pre-processing stages, it can be concluded that training from grayscale images produces the best level of accuracy with a training accuracy value of 88% and validation accuracy reaching 99%.Authenticity/state of the art: Testing of 4 pre-processing models against the classification algorithm used as a comparison resulted in the best algorithm/method for managing road images.

Classification of Damaged Road Images Using the Convolutional Neural Network Method Arif Riyandi; Tony Widodo; Shofwatul Uyun
Telematika Vol 19, No 2 (2022): Edisi Juni 2022
Publisher : Jurusan Teknik Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31315/telematika.v19i2.6460

Objective: Automatic identification is carried out with the help of a tool that can take an image of road conditions and automatically distinguish the types of road damage, the location of road damage in the image and calculate the level of road damage according to the type of road damage.Design/method/approach: Identification of damaged roads usually uses manual RCI system which requires high cost. In this study, a comparison framework is proposed to determine the performance of the image pre-processing model on the image classification algorithm.Results: Based on 733 image data classified using the CNN method from 4 models of pre-processing stages, it can be concluded that training from grayscale images produces the best level of accuracy with a training accuracy value of 88% and validation accuracy reaching 99%.Authenticity/state of the art: Testing of 4 pre-processing models against the classification algorithm used as a comparison resulted in the best algorithm/method for managing road images.

Pemanfaatan Alat Berbasis Web untuk Otomatisasi Pengambilan Data Publikasi dari Google Scholar Sulistya, Yudha Islami; Wardhana, Ariq Cahya; Istighosah, Maie; Riyandi, Arif
Jurnal Teknologi Dan Sistem Informasi Bisnis Vol 6 No 4 (2024): Oktober 2024
Publisher : Prodi Sistem Informasi Universitas Dharma Andalas

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47233/jteksis.v6i4.1604

Here’s the revised abstract in English: The rapid growth of academic publications requires efficient tools for publication data extraction and management, especially from widely used platforms like Google Scholar. To address this need, an automated web-based tool was developed, designed to simplify the processes of data crawling, extraction, and publication data management, allowing researchers to handle large volumes of academic publications more effectively. The tool supports both simple and detailed crawling modes, enabling users to input multiple Google Scholar URLs and neatly organize the extracted data into CSV files. For multiple URLs, the data is compiled into a ZIP file containing separate CSV files for each source, ensuring organized and accessible publication data management. The tool was tested with various dataset sizes. When processing 41 entries, the simple mode completed extraction in 9.054 seconds, while the detailed mode took 71.898 seconds. For smaller datasets of 5 entries, the simple mode executed in 3.283 seconds, while the detailed mode required 11.908 seconds. These results indicate that the tool is efficient and performs well with both small and large datasets. The differences in execution time between the simple and detailed modes offer users flexibility in balancing speed and depth of data extraction according to their research needs. This web-based tool not only automates the data extraction process from Google Scholar but also enhances the organization and accessibility of publication data, making it an asset for researchers and institutions in managing publication data.

Classification Of Sleep Disorders Based on Lifestyle and Health Factors Using Random Forest and HistGradientBoosting Fernandez, Sandhy; Riyandi, Arif; Wijayanto, Sena; Sukmadiningtyas, Sukmadiningtyas
Journal of Artificial Intelligence and Software Engineering Vol 5, No 2 (2025): June
Publisher : Politeknik Negeri Lhokseumawe

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30811/jaise.v5i2.6983

Gangguan tidur merupakan salah satu permasalahan kesehatan yang dapat berdampak signifikan terhadap produktivitas dan kualitas hidup individu. Berbagai faktor gaya hidup dan kondisi kesehatan seperti tingkat stres, konsumsi kafein, kebiasaan olahraga, serta kondisi mental dan fisik diketahui mempengaruhi kualitas tidur seseorang. Penelitian ini bertujuan untuk mengklasifikasikan jenis gangguan tidur berdasarkan faktor-faktor tersebut menggunakan pendekatan pembelajaran mesin. Dua algoritma yang digunakan dalam penelitian ini adalah Random Forest dan HistGradientBoosting. Dataset yang digunakan terdiri dari sejumlah fitur gaya hidup dan kesehatan yang relevan, dengan target klasifikasi berupa tiga kategori utama gangguan tidur. Hasil evaluasi menunjukkan bahwa model HistGradientBoosting memberikan performa terbaik dengan akurasi mencapai 91%. Temuan ini menunjukkan potensi pendekatan pembelajaran mesin dalam membantu identifikasi dini gangguan tidur, sehingga dapat menjadi referensi untuk pengembangan sistem pendukung keputusan dalam bidang kesehatan.

User Satisfaction Analysis of the Website Using the E-Servqual Method Zuleffa, Mazia; Hari Widi Utomo; Arif Riyandi
INOVTEK Polbeng - Seri Informatika Vol. 10 No. 2 (2025): July
Publisher : P3M Politeknik Negeri Bengkalis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35314/m9a6r812

This study aims to specifically analyze the key service quality dimensions—Efficiency, Privacy, and Contact—that influence user satisfaction with the PMB website of Madyathika Polytechnic. A structured questionnaire based on the E-SERVQUAL model was distributed to respondents, and the collected data were analyzed using descriptive statistics, SPSS-based validity and reliability testing, and Importance Performance Analysis (IPA). The findings reveal that although several service dimensions meet user expectations, attributes such as cross-device accessibility, user data privacy, and clarity of contact information still show negative service quality gaps. These results provide a foundation for targeted recommendations to improve the overall digital service experience. This research contributes to the strategic enhancement of digital service quality in higher education admissions systems.

Obesity Status Prediction Through Artificial Intelligence and Balanced Label Distribution Using SMOTE Riyandi, Arif; Mahazam Afrad; M Yoka Fathoni; Yogo Dwi Prasetyo
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 9 No 3 (2025): June 2025
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v9i3.6204

Obesity, a global health challenge influenced by genetic and environmental factors, is characterized by excessive body fat that increases the risk of various diseases. With over two billion individuals affected worldwide, addressing this issue is crucial. This study investigated the application of Artificial Intelligence (AI) to predict obesity status using a dataset of 1,610 individuals, including demographic and anthropometric data. Four AI algorithms were analyzed: Artificial Neural Network (ANN), K-Nearest Neighbors (KNN), Random Forest, and Support Vector Machine (SVM). The Synthetic Minority Over-Sampling Technique (SMOTE) was applied to address dataset imbalance. The results demonstrate that SMOTE significantly enhanced the models' performance, especially in recall and F1-score for minority classes, such as obesity. Random Forest achieved the highest accuracy (92%) and recall (92%) post-SMOTE. The ANN showed substantial improvement in recall, increasing from 77% to 89%, whereas the SVM achieved the highest precision (89%), minimizing false positives. Despite these improvements, KNN remained the least effective. The findings underscore the critical role of SMOTE in improving AI model accuracy for obesity prediction and highlight Random Forest as the most reliable algorithm for clinical decision-making. Limitations, such as dataset representativeness, suggest future research directions, including expanding data diversity and advanced feature selection techniques. This study provides valuable insights into leveraging AI and preprocessing methods for obesity management.

Pemanfaatan E-GEPATAN untuk Administrasi Lahan Pertanian dan Distribusi Hasil Panen Petani Muhamad Awiet Wiedanto Prasetyo; Riyatno Riyatno; Arif Riyandi; Fadiana Fadiana; Jamaludin Abdul Karim
Indonesian Journal of Community Service and Innovation Vol. 5 No. 3 (2025): Desember 2025
Publisher : LPPM IT Telkom Purwokerto

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20895/ijcosin.v5i3.9931

The problem of the unavailability of a proper administrative and land-recording system was addressed by developing a digital-based recording system, E-GEPATAN, which can be utilized to systematically document land area, ownership, and land status. The implementation method began with data collection through interviews with the Plana Village Government and the Plana Jaya Farmers’ Group Association (Gapoktan), as well as observations on member registration and documentation of agricultural land, particularly rice fields. The results indicate that most of the predetermined targets were successfully achieved, including the documentation of 95% of agricultural land within E-GEPATAN, 82% of harvests recorded digitally, and 65 farmers actively using the marketing features. Following the facilitation and technical assistance through E-GEPATAN, farmers gradually adapted to the digital system, which allowed agricultural data recording to become more systematic and centrally monitored by Gapoktan as the primary manager. Behavioral changes among farmers were also observed, particularly in their newly established practices of soil quality testing through pH measurement, which had never been conducted before. These outcomes highlight that E-GEPATAN serves not merely as a recording platform but as a digital transformation instrument that promotes transparency, efficiency, and enhanced competitiveness in the agricultural sector of Plana Village

Pengembangan dan Pendampingan ASTAGIS 2.0 dalam Digitalisasi Pertanian Desa Cingebul Sisilia Thya Safitri; Arif Riyandi; Muhamad Awiet Wiedanto Prasetyo; Jamaludin Abdul Karim; Selvia Oktarina Br Haloho; Fahrezi Fikri Al Khafid
Abdibaraya Vol 5 No 01 (2026): Abdibaraya
Publisher : Universitas Ma'arif Nahdlatul Ulama Kebumen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.53863/abdibaraya.v5i01.2268

Agricultural data management at the village level is still dominated by un-integrated manual recording, which complicates planning, the distribution of production facilities, and the marketing of crops. This community service activity aims to implement and support the use of the ASTAGIS 2.0 application to downstream research results and advance the digitalization of land management and agricultural marketing in Cingebul Village, Banyumas Regency. The community service method used is Joint Application Design (JAD) combined with participatory mentoring, involving Gapoktan and Poktan from the needs identification stage to system evaluation. The results of the activity indicate that ASTAGIS 2.0 can be used well by the community, with an average System Usability Scale (SUS) score of 76.39, which is in the good category. Implementing this system increases the community's capacity to manage agricultural data and opens opportunities for broader crop marketing. The current community service results include developing features to facilitate farmers' crop marketing, making their crops more accessible to the wider community, and supporting the digital transformation of village agriculture

Hybrid Model of Isolation Forest and Long Short-Term Memory Autoencoder for Digital Forensic Anomaly Detection in Manufacturing IoT Networks Muammar; Sandhy Fernandez; Arif Riyandi; Sena Wijayanto
JURNAL TEKNOLOGI DAN OPEN SOURCE Vol. 9 No. 1 (2026): Jurnal Teknologi dan Open Source, June 2026
Publisher : Universitas Islam Kuantan Singingi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36378/jtos.v9i1.5732

The development of Internet of Things (IoT) technology in the manufacturing sector creates opportunities for efficiency while also increasing vulnerability to sabotage threats that are difficult to detect manually. This study aims to design and evaluate an artificial intelligence-based hybrid model that combines Isolation Forest and Long Short-Term Memory Autoencoder to detect anomalies in the context of digital forensics in manufacturing industrial IoT networks. The research design uses an experimental approach with a simulated dataset representing 35 working days of smart factory operations, covering 127 sabotage scenarios distributed across six types of logs. The methodology applied is a two-layer cascade architecture, where Isolation Forest serves as a statistical anomaly detector in the first layer, followed by Long Short-Term Memory Autoencoder as a time-series pattern validator in the second layer. The evaluation results show that Isolation Forest independently achieved an F1-score of 0.84, Long Short-Term Memory Autoencoder achieved 0.87, while the hybrid model produced an F1-score of 0.93 with a precision of 0.91 and a recall of 0.95. These findings confirm that the hybrid cascade approach significantly outperforms each individual method. This study concludes that the integration of both methods provides a more accurate and efficient digital forensic solution for detecting sabotage incidents in industrial IoT environments.

Title

Found 13 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 13 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 13 Documents
Search