Article Per Year (5 Year)
p-Index From 2021 - 2026
4.358
P-Index
This Author published in this journals
All Journal Dinamik Jurnal Ilmiah Teknik Elektro Komputer dan Informatika (JITEKI) Jurnal Transformatika Jurnal Edukasi dan Penelitian Informatika (JEPIN) JUITA : Jurnal Informatika Jurnal Sistem dan Informatika Proceedings Konferensi Nasional Sistem dan Informatika (KNS&I) WARTA Jurnal ELTIKOM : Jurnal Teknik Elektro, Teknologi Informasi dan Komputer Emerging Science Journal INTENSIF: Jurnal Ilmiah Penelitian dan Penerapan Teknologi Sistem Informasi JITK (Jurnal Ilmu Pengetahuan dan Komputer) ILKOM Jurnal Ilmiah WIDYABHAKTI Jurnal Ilmiah Populer Jurnal Nasional Pendidikan Teknik Informatika (JANAPATI) Jurnal Tekno Kompak Journal of Electronics, Electromedical Engineering, and Medical Informatics Respati Indonesian Journal of Electrical Engineering and Computer Science Jurnal Teknik Informatika (JUTIF) Melek IT: Information Technology Journal Jurnal Ilmiah IT CIDA : Diseminasi Teknologi Informasi Sevanam: Jurnal Pengabdian Masyarakat Equivalent: Jurnal Ilmiah Sosial Teknik
Roy Rudolf Huizen
Institut Teknologi Dan Bisnis Stikom Bali
Religion Aerospace Engineering Humanities 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 Social Sciences

Published : 41 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 41 Documents
Search

 1   2   3   4   5 
Diabetes Mellitus Classification Using CNN-Based Plantar Thermogram Analysis Rihamzah, Muhamad; Pradipta, Gede Angga; Huizen, Roy Rudolf
Jurnal Ilmiah Teknik Elektro Komputer dan Informatika Vol. 11 No. 3 (2025): September
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26555/jiteki.v11i3.30640

Abstract

Diabetes Mellitus (DM) is a chronic metabolic disorder that often causes serious complications, including neuropathy and lower extremity disorders, which impact the quality of life of patients. Early detection of DM is a major challenge due to limited data and the complexity of image analysis. This study proposes a plantar thermogram image-based approach to support non-invasive diagnosis of DM through the development of a Convolutional Neural Network (CNN)-based model and machine learning techniques. This model integrates data augmentation techniques, such as rotation, flip, and zoom, to improve image variation and model robustness. Two CNN architectures, InceptionV3 and ResNet-50, are used in the training process, followed by feature selection using the Chi-Square method and classification using the Random Forest algorithm. The results showed that the proposed model achieved the best performance with accuracy, F1-score, precision, recall, and AUC (Area Under Curve) of 99.6% each. This approach makes a significant contribution by showing improvement compared to previous methods, while opening up opportunities for the development of more efficient clinical applications in early detection and monitoring of DM.
Optimization of Vehicle Detection at Intersections Using the YOLOv5 Model Wiguna, I Wayan Adi Artha; Huizen, Roy Rudolf; Pradipta, Gede Angga
Jurnal Ilmiah Teknik Elektro Komputer dan Informatika Vol. 10 No. 4 (2024): December
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26555/jiteki.v10i4.29309

Abstract

This study aims to analyze and evaluate the performance of the YOLOv5 model in detecting vehicles at intersections to optimize traffic flow. The methods used in this research include training the YOLOv5 model with traffic datasets collected from various intersections and optimizing hyperparameters to achieve the best detection accuracy. The study results show that the optimized YOLOv5 model can detect multiple types of vehicles with high accuracy. The model achieved a detection accuracy of 85.47% for trucks, 87.12% for pedestrians, 86.54% for buses, 77.20% for cars, 80.48% for motorcycles, and 78.80% for bicycles. Significant improvements in detection performance were achieved compared to the default model. This research concludes that the optimization of the YOLOv5 model is effective in improving vehicle detection accuracy at intersections. Implementing this optimized model can significantly contribute to traffic management, reduce congestion, and improve road safety. It is expected that the implementation of this technology can be more widely applied for more efficient traffic management in various major cities.
Klasifikasi Penyakit Ulkus Kaki menggunakan Metode Pretrained Convolutional Neural Network Yoga, I Gede Dian Permana; Pradipta, Gede Angga; Huizen, Roy Rudolf
JEPIN (Jurnal Edukasi dan Penelitian Informatika) Vol 11, No 2 (2025): Volume 11 No 2
Publisher : Program Studi Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26418/jp.v11i2.91721

Abstract

Ulkus kaki diabetik merupakan salah satu komplikasi berat pada penderita diabetes yang, jika tidak ditangani secara dini dan tepat, dapat menyebabkan infeksi, amputasi, bahkan kematian. Tantangan utama dalam penanganannya terletak pada proses diagnosis dan klasifikasi yang masih mengandalkan pengamatan visual secara manual oleh tenaga medis, yang sering kali bersifat subjektif dan tidak konsisten. Untuk menjawab permasalahan ini, kecerdasan buatan (AI) mulai dimanfaatkan dalam dunia medis, khususnya melalui analisis citra medis digital. AI bekerja dengan mengolah data berupa gambar luka dan mengenali pola visual tertentu menggunakan algoritma pembelajaran mendalam (deep learning) seperti Convolutional Neural Network (CNN), sehingga mampu mendeteksi kondisi luka secara lebih akurat. Penelitian ini bertujuan membangun model klasifikasi ulkus kaki dengan memanfaatkan arsitektur CNN yang telah dilatih sebelumnya (pretrained model) dan ditingkatkan performanya melalui proses fine-tuning. Tiga jenis arsitektur CNN yang digunakan yaitu MobileNet, VGG16, dan ResNet50, yang kemudian dikombinasikan dengan algoritma boosting seperti XGBoost dan AdaBoost untuk meningkatkan hasil klasifikasi. Dataset yang digunakan berupa citra digital luka ulkus kaki yang telah diproses melalui teknik peningkatan kualitas gambar dan seleksi fitur. Hasil evaluasi menunjukkan bahwa kombinasi MobileNet dengan XGBoost menghasilkan kinerja terbaik dengan tingkat akurasi 89%, disusul oleh VGG16 yang dikombinasikan dengan XGBoost dengan akurasi 86%. Temuan ini menunjukkan bahwa model yang dikembangkan memiliki potensi besar sebagai alat bantu diagnosis berbasis AI yang cepat, objektif, dan akurat dalam mendukung proses klinis dan mengurangi risiko komplikasi pada pasien diabetes.
Sistem Deteksi Gangguan Aliran Air Otomatis Menggunakan IoT dan Aplikasi Android: Studi Kasus di Desa Gobleg, Buleleng Susila, I Made Darma; I Made Liandana; Dandy Pramana Hostiadi; Yohanes Priyo Atmojo; Roy Rudolf Huizen; Gede Angga Pradipta; Putu Desiana Wulaning Ayu
WIDYABHAKTI Jurnal Ilmiah Populer Vol. 8 No. 1 (2025): Nopember
Publisher : Direktorat Penelitian, Pengabdian Masyarakat, dan HKI Institut Teknologi dan Bisnis STIKOM Bali

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30864/widyabhakti.v8i1.874

Abstract

Pemantauan aliran air secara real-time pada jaringan distribusi pipa menjadi aspek krusial dalam menjamin ketersediaan air bersih bagi masyarakat, khususnya di daerah pedesaan. Pelaksanaan kegiatan pengabdian kepada masyarakat (PKM) yang telah dilakukan dan merupakan hilirisasi dari pelaksanan penelitian, mengembangkan rancang bangun sistem monitoring berbasis Internet of Things (IoT) untuk mendeteksi keberadaan aliran air pada pipa utama yang mensuplai kebutuhan air warga di Desa Gobleg. Sistem ini mengintegrasikan tiga jenis sensor, yaitu pressure sensor, water flow sensor dan contactless water level sensor, yang dipasang pada beberapa titik kritis jaringan pipa. Data dari sensor dikirimkan secara periodik melalui modul komunikasi GSM menggunakan protokol MQTT ke server pusat. Aplikasi Android dikembangkan untuk menampilkan status aliran air secara langsung dan memberikan notifikasi ketika ketiga sensor secara simultan tidak mendeteksi adanya air, yang mengindikasikan potensi kebocoran atau gangguan distribusi. Hasil pengujian menunjukkan sistem mampu mendeteksi kondisi abnormal dengan tingkat akurasi 95% dan memberikan notifikasi dalam waktu kurang dari 10 detik sejak kejadian terdeteksi. Sistem ini diharapkan dapat menjadi solusi efektif dan terjangkau untuk pengawasan distribusi air di wilayah pedesaan.
Optimization Model for Fake Account Detection on Twitter (X) Social Media using Feature Engineering and Machine Learning Approaches Perimawati, Ni Nyoman Eny; Huizen, Roy Rudolf; Hostiadi, Dandy Pramana
Jurnal ELTIKOM : Jurnal Teknik Elektro, Teknologi Informasi dan Komputer Vol. 9 No. 2 (2025)
Publisher : P3M Politeknik Negeri Banjarmasin

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31961/eltikom.v9i2.1727

Abstract

Twitter (X) has become an important platform for community interaction, but this also creates serious challenges due to the proliferation of fake accounts that can harm users and undermine credibility. Previous studies have proposed detection methods but often lacked forensic analysis based on extracted feature information. This study utilizes labeled datasets and supervised evaluation metrics (precision, recall, and F1-score) to validate model performance. Extracting behavioral information from features is crucial for achieving accurate and reliable detection results. The study introduces a novelty in the form of engineered behavioral features that significantly enhance detection accuracy, achieving up to 99.94% using AdaBoost. The proposed approach detects fake accounts on Twitter (X) by extracting key feature information and developing an optimal detection method through machine learning algorithms, including Random Forest, SVM, and AdaBoost. Furthermore, the model is optimized using feature engineering techniques. The novelty of this work lies in the development of engineered features through distribution analysis based on data characteristics and the improvement of classification performance through feature engineering optimization. The initial experiment without feature engineering shows that Random Forest achieved the highest accuracy of 98.77%, followed by AdaBoost at 98.57% and SVM at 95.90%. After applying feature engineering, performance improved, with AdaBoost reaching 99.94%, Random Forest 99.69%, and SVM 99.32%. The proposed model can assist system analysts in detecting fake accounts and contribute to solving forensic cybercrime challenges, particularly in identifying fake social media profiles.
Combination of VGG19 (Encoder) and U-Net (Decoder) for Colorectal Polyp Segmentation Image Nuri Sutiyaningsih; Putu Desiana Wulaning Ayu; Roy Rudolf Huizen
JUITA: Jurnal Informatika JUITA Vol. 14 Issue 1, March 2026
Publisher : Department of Informatics Engineering, Universitas Muhammadiyah Purwokerto

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30595/juita.v14i1.25783

Abstract

Health involves the proper function of the body and organs, with colon polyps being a common issue. Doctors often face challenges in segmenting medical images, especially endoscopic images for polyp detection. The complexity and variation in the appearance of polyps make accurate identification challenging, and the subjective manual segmentation process can result in misdiagnosis or delayed treatment.  This study examines the effectiveness of the combination of U-Net decoder model architecture and VGG19 encoder in segmentation of colon polyp images.  This study uses a public dataset, namely Kvasir-Seg with a total of 1000 images of colon polyps.  An innovative approach using VGG19 as encoder and U-Net as decoder improves colorectal polyp segmentation, achieving high performance with a Loss of 0.05, Accuracy 0.95, Precision 0.96, Recall 0.92, IoU 0.89, and Dice 0.94. Using optimal parameters such as Nadam Optimizer, 5 Fold Cross Validation, Learning Rate 0.0001, and 25 Epochs significantly improved performance, increasing the Dice Coefficient to 0.92 and IoU to 0.86 compared to previous studies.   This study concludes that the proposed architecture is reliable for colon polyp segmentation. Future work should explore attention mechanisms or transformer-based models to enhance accuracy and efficiency.
HYBRID PSO K-MEANS AND ROBUST SPARSE K-MEANS FOR EMPLOYEE STUDY DECISIONS Luh Dwi Ari Sudawati; Roy Rudolf Huizen; Dandy Pramana Hostiadi
JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer) Vol. 11 No. 3 (2026): JITK Issue February 2026
Publisher : LPPM Nusa Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/jitk.v11i3.7101

Abstract

Human Resources (HR) are a strategic asset in institutional advancement, so employee performance evaluation must be conducted objectively and based on data. This study aims to cluster employee performance data at XYZ University for determining further studies, using the K-Means, PSO K-Means, and Robust Sparse K-Means methods, as well as three types of distance measurements: Euclidean, Manhattan, and Mahalanobis Distance. The dataset consists of 17 attributes. The evaluation was conducted using the Silhouette Score, Davies-Bouldin Index, and visualization using PCA. The results indicate that the combination of PSO K-Means with Euclidean Distance provides the best balance between quantitative performance (Silhouette Score 0.1253 and DBI 2.0521) and a more visually representative distribution of cluster members. The interpretation of the clustering results yielded three clusters: Cluster 0 (no further study) consisting of 8 employees, Cluster 1 (further study) consisting of 97 employees, and Cluster 2 (awaiting study decision) consisting of 58 employees. These findings can be utilized by institutions to design more targeted and data-driven human resource development strategies.
Website Quality Evaluation of LKP Bisma Informatika Using a Combination of Webqual 4.0, Fuzzy Analytical Hierarchy Process and Importance-Performance Analysis Anop Sudiatmika; Gede Angga Pradipta; Roy Rudolf Huizen
Equivalent: Jurnal Ilmiah Sosial Teknik Vol. 8 No. 2 (2026): Equivalent: Jurnal Ilmiah Sosial Teknik
Publisher : Politeknik Siber Cerdika Internasional

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59261/jequi.v8i2.284

Abstract

Background: The development of information technology has progressed significantly, consequently having an impact on the world of education in non-formal institutions such as Kursus dan Pelatihan (LKP). Websites are essential for providing information, registration, and engagement to prospective learners. However, preliminary research on the LKP Bisma Informatika website revealed that its content is still incomplete and not up to date. Objective: This research was conducted to evaluate the quality of LKP Bisma Informatika's website using an integrated approach combining WebQual 4.0, Fuzzy Analytical Hierarchy Process (FAHP), and Importance-Performance Analysis (IPA) methods, and to provide improvement recommendations. Methods: This study used a quantitative descriptive survey design, with respondents from LKP Bisma Informatika. Data were gathered through questionnaires based on three WebQual 4.0 constructs: usability, information quality, and service interaction quality. FAHP was used to determine priority weights, while IPA examined performance gaps based on user perceptions. Results: The results show that the website can be significantly improved, particularly in terms of information quality and usability. The most critical improvements needed are website speed, content accuracy, and user interface design. The integration of WebQual 4.0, FAHP, and IPA highlights a utility-based approach for providing effective recommendations to enhance the functionality of the website. Conclusion: These findings are expected to assist LKP Bisma Informatika in improving its website to better meet user needs and enhance user experience.
Object Classification Model Using Ensemble Learning with Gray-Level Co-Occurrence Matrix and Histogram Extraction Florentina Tatrin Kurniati; Daniel HF Manongga; Eko Sediyono; Sri Yulianto Joko Prasetyo; Roy Rudolf Huizen
Jurnal Ilmiah Teknik Elektro Komputer dan Informatika Vol. 9 No. 3 (2023): September
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26555/jiteki.v9i3.26683

Abstract

In the field of object classification, identification based on object variations is a challenge in itself. Variations include shape, size, color, and texture, these can cause problems in recognizing and distinguishing objects accurately. The purpose of this research is to develop a classification method so that objects can be accurately identified. The proposed classification model uses Voting and Combined Classifier, with Random Forest, K-NN, Decision Tree, SVM, and Naive Bayes classification methods. The test results show that the voting method and Combined Classifier obtain quite good results with each of them, ensemble voting with an accuracy value of 92.4%, 78.6% precision, 95.2% recall, and 86.1% F1-score. While the combined classifier with an accuracy value of 99.3%, a precision of 97.6%, a recall of 100%, and a 98.8% F1-score. Based on the test results, it can be concluded that the use of the Combined Classifier and voting methods is proven to increase the accuracy value. The contribution of this research increases the effectiveness of the Ensemble Learning method, especially the voting ensemble method and the Combined Classifier in increasing the accuracy of object classification in image processing.
GLCM-Based Feature Combination for Extraction Model Optimization in Object Detection Using Machine Learning Florentina Tatrin Kurniati; Irwan Sembiring; Adi Setiawan; Iwan Setyawan; Roy Rudolf Huizen
Jurnal Ilmiah Teknik Elektro Komputer dan Informatika Vol. 9 No. 4 (2023): December
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26555/jiteki.v9i4.27842

Abstract

In the era of modern technology, object detection using the Gray Level Co-occurrence Matrix (GLCM) extraction method plays a crucial role in object recognition processes. It finds applications in real-time scenarios such as security surveillance and autonomous vehicle navigation, among others. Computational efficiency becomes a critical factor in achieving real-time object detection. Hence, there is a need for a detection model with low complexity and satisfactory accuracy. This research aims to enhance computational efficiency by selecting appropriate features within the GLCM framework. Two classification models, namely K-Nearest Neighbours (K-NN) and Support Vector Machine (SVM), were employed, with the results indicating that K-Nearest Neighbours (K-NN) outperforms SVM in terms of computational complexity. Specifically, K-NN, when utilizing a combination of Correlation, Energy, and Homogeneity features, achieves a 100% accuracy rate with low complexity. Moreover, when using a combination of Energy and Homogeneity features, K-NN attains an almost perfect accuracy level of 99.9889%, while maintaining low complexity. On the other hand, despite SVM achieving 100% accuracy in certain feature combinations, its high or very high complexity can pose challenges, particularly in real-time applications. Therefore, based on the trade-off between accuracy and complexity, the K-NN model with a combination of Correlation, Energy, and Homogeneity features emerges as a more suitable choice for real-time applications that demand high accuracy and low complexity. This research provides valuable insights for optimizing object detection in various applications requiring both high accuracy and rapid responsiveness.
Co-Authors Adi Setiawan Adriani, Ni Putu Erica Puspita Andriyan Dwi Putra Anop Sudiatmika Bambang Soedijono Bambang Soedijono W Dadang Hermawan Dadang Hermawan Dadang Hermawan Dandy Hostiadi Dandy Pramana Hostiadi Dandy Pramana Hostiadi Dandy Pramana Hostiadi Daniel HF Manongga Danny Manongga Eko Sediyono Erma Sulistyo Rini Erma Sulistyo Rini, Erma Sulistyo Florentina Tatrin Kurniati Gede Angga Pradipta Gede Angga Pradipta, Gede Angga I Gede Edy Artana I Made Darma Susila I Made Darma Susila, I Made Darma I Made Liandana I Wayan Karang Utama Ipango, Rachmad Arissaputra Irwan Sembiring Iwan Setyawan Kadek Adies Wiranegara Kadek Eka Sapta W karyanto, Nonot wisnu Leny Margaretha Huizen Lilik Jatmiko Prasetyo Lilis Yuningsih Luh Ayu Martini Luh Dwi Ari Sudawati Made Liandana, Made Mahajaya, Nyoman Sarasuartha Mahendra, Tubagus Ni Ketut Dewi Ari Jayanti Nonot Wisnu Karyanto Nuri Sutiyaningsih Perimawati, Ni Nyoman Eny Purnama, I Gusti Agung Vony Putu Desiana Wulaning Ayu Putu Desiana Wulaning Ayu Putu Desiana Wulaning Ayu Rihamzah, Muhamad Rustamaji, Abdullah Saputra, Made Wisnu Adhi Seneng, I Kadek Soedijono W, Bambang Sri Yulianto Joko Prasetyo Sutarto Wijono W Mega Adhi Agam Pradhana Wiguna, I Wayan Adi Artha Wing Wahyu Winamo Wulaning Ayu, Putu Desiana Yoga, I Gede Dian Permana Yohanes Priyo Atmojo Yohanes Priyo Atmojo Yohanes Priyo Atmojo, Yohanes Priyo