Garuda - Garba Rujukan Digital

Sosialisasi dan Workshop Digital Marketing sebagai Upaya Pengembangan Usaha Masyarakat Desa Kalibenda, Kecamatan Ajibarang, Kabupaten Banyumas Yesy Diah Rosita; Dany Candra Febrianto; Andi Prademon Yunus; Aulia Desy Nur Utomo
Indonesian Journal of Community Service and Innovation (IJCOSIN) Vol 4 No 2 (2024): Juli 2024
Publisher : LPPM IT Telkom Purwokerto

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20895/ijcosin.v4i1.1452

Digital marketing has been a foundation for the business development strategy in the digital era. Even though, the utilization of digital marketing is not evenly applied, especially on the rural area such as in Desa Kalibenda, Kabupaten Banyumas. This community service aims to improve understanding and skills on digital marketing to the resident of the Desa Kalibenda for the potential utilization of digital marketing. Through workshop and seminar, participants are introduced to basic concept of the digital marketing such as media social strategies, browser optimization, and data analytics. The workshop shows significant understanding improvement as well as the positive impact on participant skills on utilizing the digital technology for UMKM marketing measured by post-test after the workshop. As a result, the workshop is suggested to continue and extend the similar program for other region to improve the local UMKM competitiveness in the connected digital market.

Dimension-Expanding MLP in Transformer: Inappropriate Sentences and Paragraph Digital Content Filtering Wardhana, Ariq Cahya; Yunus, Andi Prademon; Adhitama, Rifki; Latief, Muhammad Abdul; Sofia, Martryatus
Journal of Applied Data Sciences Vol 6, No 2: MAY 2025
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v6i2.627

The creation of digital content is now a pivotal element of today’s digital environment, driven by the need for both individuals and organizations to engage audiences effectively. As digital platforms grow in scope and impact, ensuring the security, professionalism, and appropriateness of user-generated content has become crucial. This study introduces a new approach for filtering inappropriate digital content by integrating dimension-expanding multi-layer perceptions (MLPs) into transformer architectures. The dimension-expanding MLP processed more high-dimensional features in the Transformers network, giving the ability to understand more specific contexts. Experimental findings reveal that the proposed model outperforms Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU), Transformer (Baseline) in accuracy, computational efficiency, and scalability. The research highlights the model’s practical applications in areas like social media content moderation, legal document compliance monitoring, and filtering harmful content in e-learning and gaming platforms with 0.744 accuracy.

Human Fall Motion Prediction: Fall Motion Forecasting and Detection with GRU Andi Prademon Yunus; Amalia Beladinna Arifa; Yit Hong Choo
JURNAL TEKNIK INFORMATIKA Vol 17, No 2: JURNAL TEKNIK INFORMATIKA
Publisher : Department of Informatics, Universitas Islam Negeri Syarif Hidayatullah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15408/jti.v17i2.41027

The human fall motion prediction system is a preventive tool aimed at reducing the risk of falls. In our research, we developed a deep learning model that utilizes pose estimation to track human body posture and integrated this with a Gated Recurrent Unit (GRU) to forecast human motion and predict falls. GRU, an enhancement of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) models offers improved memorization and more efficient memory usage and performance. Our study presents the human fall motion prediction, which combines the forecasting and classification of potential falls.The CAUCAFall dataset is used as the benchmark of this study, which contains the image sequences of single human motion with ten actions conducted by ten actors. We employed the YOLOv8 Pose model to track the 2D human body pose as the input in our system. A thorough evaluation of the CAUCAFall dataset highlights the effectiveness of our proposed system. Evaluation using the CAUCAFall dataset demonstrates that the model achieved a Mean Per Joint Position Error (MPJPE) of 4.65 pixels from the ground truth, with a 70% accuracy rate in fall prediction. However, the model also exhibited a Mean Relative Error (MRE) of 0.3, indicating that 30% of the predictions were incorrect. These findings underscore the potential of the GRU-based system in fall prevention

Detection of Vulgarity in Anime Character: Implementation of Detection Transformer Amalia Suciati; Dian Kartika Sari; Andi Prademon Yunus; Nuuraan Rizqy Amaliah
JURNAL TEKNIK INFORMATIKA Vol 18, No 1: JURNAL TEKNIK INFORMATIKA
Publisher : Department of Informatics, Universitas Islam Negeri Syarif Hidayatullah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15408/jti.v18i1.46064

Vulgar and pornographic content has become a widespread issue on the internet, appearing in various fields include anime. Vulgar pornographic content in anime is not limited to the sexuality genre; anime from general genres such as action, adventure, and others also contain vulgar visual. The main focus of this research is the implementation of the Detection Transformer (DETR) object detection method to identify vulgar parts of anime characters, particularly female characters. DETR is a deep learning model designed for object detection tasks, adapting the attention mechanism of Transformers. The dataset used consists of 800 images taken from popular anime, based on viewership rankings, which were augmented to a total of 1,689 images. The research involved training models with different backbones, specifically ResNet-50 and ResNet-101, each with dilation convolution applied at different stages. The results show that the DETR model with a ResNet-50 backbone and dilation convolution at stage 5 outperformed other backbones and dilation configurations, achieving a mean Average Precision of 0.479 and of 0.875. The other result is dilated convolution improves small object detection by enlarging the receptive field, applying it in early stages tends to reduce spatial detail and harm performance on medium and large objects. However, the primary focus of this research is not solely on achieving the highest performance but on exploring the potential of transformer-based models, such as DETR, for detecting vulgar content in anime. DETR benefits from its ability to understand spatial context through self-attention mechanisms, offering potential for further development with larger datasets, more complex architectures, or training at larger data scales.

Small Object Detection and Object Counting for Primary Roe Dataset Based on Yolo Wahyu Andi Saputra; Nicolaus Euclides Wahyu Nugroho; Dany Candra Febrianto; Andi Prademon Yunus; Muhammad Azrino Gustalika; Yit Hong Choo
JURNAL TEKNIK INFORMATIKA Vol 18, No 1: JURNAL TEKNIK INFORMATIKA
Publisher : Department of Informatics, Universitas Islam Negeri Syarif Hidayatullah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15408/jti.v18i1.46063

This research offers an initial exploration into the effectiveness of three variations of the YOLOv8 model original, trimmed, and YOLOv8n.pt in combination with two distinct datasets characterized by tight and loose distributions of roe, aimed at enhancing small object detection and counting accuracy. Utilizing a primary roe dataset across 776 images, the research systematically compares these model-dataset configurations to identify the most effective combination for precise object detection. The experimental results reveal that the YOLOv8n.pt model combined with the loosely distributed dataset achieves the highest detection performance, with a mean Average Precision (mAP) of 53.86%. This outcome underscores the critical impact of both model selection and data distribution on the detection accuracy in machine learning applications. The findings highlight the importance of tailored model and dataset synergies in optimizing detection tasks, particularly in complex scenarios involving small, densely clustered objects. This research contributes valuable insights into the strategic deployment of neural network architectures for refined object detection challenges.

Rupiah Banknotes Detection Comparison of The Faster R-CNN Algorithm and YOLOv5 Hanif, Muhammad Zuhdi; Saputra, Wahyu Andi; Choo, Yit Hong; Yunus, Andi Prademon
JURNAL INFOTEL Vol 16 No 3 (2024): August 2024
Publisher : LPPM INSTITUT TEKNOLOGI TELKOM PURWOKERTO

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20895/infotel.v16i3.1189

Money is an essential part of human life. Humans are never separated from activities related to money. As time goes by, money is not only a means of transactions between humans but also between humans and machines. Machines can recognize money in various ways, including object detection. Object detection is one of the most popular branches of computer vision. There are many methods for carrying out object detection, such as Faster R-CNN and YOLO. Faster R-CNN has been widely used in various fields to perform object detection tasks. Faster R-CNN has advantages over its predecessor because it uses a Region Proposal Network (RPN) as a substitute for selective search, which requires less compilation time. YOLO (You Only Look Once) is the most frequently used object detection method. This method divides the image into grids; each part of the grid predicts objects and their probabilities. The main advantages of YOLO are its high speed and ability to recognize objects in various conditions and positions with reasonably high accuracy. This research compares the Faster R-CNN algorithm model using the ResNet-50 architecture with YOLOv5 to recognize rupiah banknotes. The dataset used is 1120 images consisting of 8 classes. The YOLOv5 model trained on RGB data had the best results, with calculation accuracy reaching 1. Test results on three images also showed suitable results. The hope is that this research can be applied in other research to build a system for recognizing rupiah banknotes.

TelUP Human Fall Dataset: A Motion Forecasting Study of Human Falls Widiyanto, Agung; Candraningtyas, Raphon Galuh; F.F, Andi Hisyam Helmi; Prameswari, Mayesq; Bashiran, Himam; Surahmat, Geugeut Nyarikawanti; Rahmah, Balqis Awaluna; Manika Dewi, Anak Agung Istri Candra; Yunus, Andi Prademon
JURNAL INFOTEL Vol 17 No 3 (2025): August
Publisher : LPPM INSTITUT TEKNOLOGI TELKOM PURWOKERTO

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20895/infotel.v17i3.1420

This study investigates multitask learning approaches for human motion forecasting and fall classification using pose data extracted from video sequences. A custom dataset, the TelUP HumanFall Forecasting Dataset, was developed, containing annotated video frames representing fall and non-fall scenarios captured from six participants. Pose information was extracted using YOLOv11, producing 17 keypoints per frame, which were normalized and segmented into temporal sequences for training. Three deep learning architectures, Multilayer Perceptron (MLP), Recurrent Neural Network (RNN), and Long Short-Term Memory (LSTM), were implemented and evaluated. The models were assessed in a subject-independent test set consisting of two participants to ensure generalization. Quantitative evaluation measured the forecast error using the mean per joint position error (MPJPE) and classification accuracy. The MLP achieved the lowest MPJPE of 0.2630 (131.5 pixels), while the LSTM obtained the highest classification accuracy of 92.89%. Qualitative analysis revealed limitations in the capture of complex joint dynamics. Despite fast training convergence, the results emphasize a trade-off between forecast precision and classification accuracy. Future work will explore more expressive architectures and improved pose extraction methods to enhance forecast realism.

Human Fall Motion Prediction: Fall Motion Forecasting and Detection with GRU Yunus, Andi Prademon; Arifa, Amalia Beladinna; Choo, Yit Hong
JURNAL TEKNIK INFORMATIKA Vol. 17 No. 2: JURNAL TEKNIK INFORMATIKA
Publisher : Department of Informatics, Universitas Islam Negeri Syarif Hidayatullah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15408/jti.v17i2.41027

The human fall motion prediction system is a preventive tool aimed at reducing the risk of falls. In our research, we developed a deep learning model that utilizes pose estimation to track human body posture and integrated this with a Gated Recurrent Unit (GRU) to forecast human motion and predict falls. GRU, an enhancement of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) models offers improved memorization and more efficient memory usage and performance. Our study presents the human fall motion prediction, which combines the forecasting and classification of potential falls.The CAUCAFall dataset is used as the benchmark of this study, which contains the image sequences of single human motion with ten actions conducted by ten actors. We employed the YOLOv8 Pose model to track the 2D human body pose as the input in our system. A thorough evaluation of the CAUCAFall dataset highlights the effectiveness of our proposed system. Evaluation using the CAUCAFall dataset demonstrates that the model achieved a Mean Per Joint Position Error (MPJPE) of 4.65 pixels from the ground truth, with a 70% accuracy rate in fall prediction. However, the model also exhibited a Mean Relative Error (MRE) of 0.3, indicating that 30% of the predictions were incorrect. These findings underscore the potential of the GRU-based system in fall prevention

Small Object Detection and Object Counting for Primary Roe Dataset Based on Yolo Saputra, Wahyu Andi; Nugroho, Nicolaus Euclides Wahyu; Febrianto, Dany Candra; Yunus, Andi Prademon; Gustalika, Muhammad Azrino; Choo, Yit Hong
JURNAL TEKNIK INFORMATIKA Vol. 18 No. 1: JURNAL TEKNIK INFORMATIKA
Publisher : Department of Informatics, Universitas Islam Negeri Syarif Hidayatullah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15408/jti.v18i1.46063

This research offers an initial exploration into the effectiveness of three variations of the YOLOv8 model original, trimmed, and YOLOv8n.pt in combination with two distinct datasets characterized by tight and loose distributions of roe, aimed at enhancing small object detection and counting accuracy. Utilizing a primary roe dataset across 776 images, the research systematically compares these model-dataset configurations to identify the most effective combination for precise object detection. The experimental results reveal that the YOLOv8n.pt model combined with the loosely distributed dataset achieves the highest detection performance, with a mean Average Precision (mAP) of 53.86%. This outcome underscores the critical impact of both model selection and data distribution on the detection accuracy in machine learning applications. The findings highlight the importance of tailored model and dataset synergies in optimizing detection tasks, particularly in complex scenarios involving small, densely clustered objects. This research contributes valuable insights into the strategic deployment of neural network architectures for refined object detection challenges.

Detection of Vulgarity in Anime Character: Implementation of Detection Transformer Suciati, Amalia; Sari, Dian Kartika; Yunus, Andi Prademon; Amaliah, Nuuraan Rizqy
JURNAL TEKNIK INFORMATIKA Vol. 18 No. 1: JURNAL TEKNIK INFORMATIKA
Publisher : Department of Informatics, Universitas Islam Negeri Syarif Hidayatullah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15408/jti.v18i1.46064

Vulgar and pornographic content has become a widespread issue on the internet, appearing in various fields include anime. Vulgar pornographic content in anime is not limited to the sexuality genre; anime from general genres such as action, adventure, and others also contain vulgar visual. The main focus of this research is the implementation of the Detection Transformer (DETR) object detection method to identify vulgar parts of anime characters, particularly female characters. DETR is a deep learning model designed for object detection tasks, adapting the attention mechanism of Transformers. The dataset used consists of 800 images taken from popular anime, based on viewership rankings, which were augmented to a total of 1,689 images. The research involved training models with different backbones, specifically ResNet-50 and ResNet-101, each with dilation convolution applied at different stages. The results show that the DETR model with a ResNet-50 backbone and dilation convolution at stage 5 outperformed other backbones and dilation configurations, achieving a mean Average Precision of 0.479 and of 0.875. The other result is dilated convolution improves small object detection by enlarging the receptive field, applying it in early stages tends to reduce spatial detail and harm performance on medium and large objects. However, the primary focus of this research is not solely on achieving the highest performance but on exploring the potential of transformer-based models, such as DETR, for detecting vulgar content in anime. DETR benefits from its ability to understand spatial context through self-attention mechanisms, offering potential for further development with larger datasets, more complex architectures, or training at larger data scales.

Title

Found 11 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 11 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 11 Documents
Search