Yu-Yong Luo
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Yu-Yong Luo has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Chia-Hsin Cheng
Department of Electrical Engineering, National Formosa University, Yunlin 632301, Taiwan
5 shared publications - Chien-Chih Lin
Department of Electrical Engineering, National Formosa University, Yunlin 632301, Taiwan
3 shared publications - Cheng-Hsiung Hsieh
Department of Computer Science and Information Engineering, Chaoyang University of Technology, Taichung 413310, Taiwan
1 shared publication - Jia-You Cai
Department of Electrical Engineering, National Formosa University, Yunlin 63201, Taiwan
1 shared publication - Yung-Fa Huang
Department of Information and Communication Engineering, Chaoyang University of Technology, Taichung 413310, Taiwan
1 shared publication
Latest Publications
- Open Access
- 17 August 2026
- Published by MDPI AG in Electronics
- Vol. 15 (16) , 3668
A Deep Learning-Based Vision-Sharing System with Image Stitching for Blind Spot Reduction in Vehicle-Following Scenarios
This study presents a small-scale application-oriented vehicle vision-sharing prototype for blocked-view observation in vehicle-following scenarios. The system was implemented using two DuckieBot vehicles and integrates socket-based image transmission, JPEG image compression, You Only Look Once (YOLO)-based object detection, road-plane-aligned image fusion, and fuzzy proportional–integral–derivative (fuzzy-PID) motor control. These modules are adopted as existing techniques and integrated for prototype-level experimental evaluation rather than proposed as new perception, compression, fusion, or control algorithms. Experiments were conducted under controlled small-scale indoor conditions. JPEG compression was quantitatively evaluated using peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), encoded file size, and processing time. Q75 provided a mean PSNR of 39.8777 dB, a mean SSIM of 0.970522, and an average encoded size of 27.78 KB, representing a practical trade-off between reconstructed image quality and encoded data size. The YOLOv8n obstacle detector achieved a precision of 0.9724, a recall of 0.9571, an mAP@0.5 of 0.9851, and an mAP@0.5:0.95 of 0.8585 on an independent test set. Image-fusion evaluation showed that α = 0.60 produced the highest global mean PSNR, whereas α = 0.90 produced the highest global mean SSIM, indicating that the preferred blending coefficient depends on the selected image-quality criterion. A system-level ablation further distinguished shared-view visualization from a warning-only configuration, with the expected obstacle information presented in all 35 positive trials and no false alarms observed in 10 negative trials. The vehicle-following experiment verified the functional operation of the complete perception-to-control pipeline. The results should be interpreted within the controlled miniature-vehicle setting and should not be directly generalized to full-scale vehicles or real-road advanced driver assistance systems.
- 17 August 2026
- Published by MDPI AG in Electronics
- Vol. 15 (16) , 3668
Open AccessA Deep Learning-Based Vision-Sharing System with Image Stitching for Blind Spot Reduction in Vehicle-Following Scenarios
This study presents a small-scale application-oriented vehicle vision-sharing prototype for blocked-view observation in vehicle-following scenarios. The system was implemented using two DuckieBot vehicles and integrates socket-based image transmission, JPEG image compression, You Only Look Once (YOLO)-based object detection, road-plane-aligned image fusion, and fuzzy proportional–integral–derivative (fuzzy-PID) motor control. These modules are adopted as existing techniques and integrated for prototype-level experimental evaluation rather than proposed as new perception, compression, fusion, or control algorithms. Experiments were conducted under controlled small-scale indoor conditions. JPEG compression was quantitatively evaluated using peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), encoded file size, and processing time. Q75 provided a mean PSNR of 39.8777 dB, a mean SSIM of 0.970522, and an average encoded size of 27.78 KB, representing a practical trade-off between reconstructed image quality and encoded data size. The YOLOv8n obstacle detector achieved a precision of 0.9724, a recall of 0.9571, an mAP@0.5 of 0.9851, and an mAP@0.5:0.95 of 0.8585 on an independent test set. Image-fusion evaluation showed that α = 0.60 produced the highest global mean PSNR, whereas α = 0.90 produced the highest global mean SSIM, indicating that the preferred blending coefficient depends on the selected image-quality criterion. A system-level ablation further distinguished shared-view visualization from a warning-only configuration, with the expected obstacle information presented in all 35 positive trials and no false alarms observed in 10 negative trials. The vehicle-following experiment verified the functional operation of the complete perception-to-control pipeline. The results should be interpreted within the controlled miniature-vehicle setting and should not be directly generalized to full-scale vehicles or real-road advanced driver assistance systems.
- Open Access
An Integrated Zero-Trust and Real-Time Detection Scheme for DDoS Protection in 5G IoT Systems
This study presents a laboratory-scale prototype that integrates a zero-trust-based permission-control mechanism with real-time DDoS traffic detection in a 5G NSA IoT testbed. The proposed system was evaluated under three controlled traffic conditions: normal traffic, TCP SYN flood traffic, and UDP flood traffic. Packet-level data were collected from the experimental testbed and used to train and compare LSTM and SVM classifiers. Under the evaluated conditions, the LSTM model achieved the highest accuracy of 99.56%, outperforming the best SVM result of 93.20%. The selected LSTM detector was further deployed in the edge-computing pipeline and correctly identified the three tested traffic conditions during real-time operation. After malicious traffic was identified, the permission-control mechanism updated the corresponding authorization status, generated an alert, and restricted suspicious communication within the testbed. These results demonstrate the feasibility of linking traffic detection with authorization adjustment in a controlled 5G NSA IoT prototype. The findings should not be interpreted as a general validation against all DDoS variants or large-scale commercial 5G IoT deployments.
Open AccessAn Integrated Zero-Trust and Real-Time Detection Scheme for DDoS Protection in 5G IoT Systems
This study presents a laboratory-scale prototype that integrates a zero-trust-based permission-control mechanism with real-time DDoS traffic detection in a 5G NSA IoT testbed. The proposed system was evaluated under three controlled traffic conditions: normal traffic, TCP SYN flood traffic, and UDP flood traffic. Packet-level data were collected from the experimental testbed and used to train and compare LSTM and SVM classifiers. Under the evaluated conditions, the LSTM model achieved the highest accuracy of 99.56%, outperforming the best SVM result of 93.20%. The selected LSTM detector was further deployed in the edge-computing pipeline and correctly identified the three tested traffic conditions during real-time operation. After malicious traffic was identified, the permission-control mechanism updated the corresponding authorization status, generated an alert, and restricted suspicious communication within the testbed. These results demonstrate the feasibility of linking traffic detection with authorization adjustment in a controlled 5G NSA IoT prototype. The findings should not be interpreted as a general validation against all DDoS variants or large-scale commercial 5G IoT deployments.
- Open Access
- 8 September 2025
- Published by MDPI AG in Future Internet
- Vol. 17 (9) , 411
Detection and Mitigation in IoT Ecosystems Using oneM2M Architecture and Edge-Based Machine Learning
Distributed denial-of-service (DDoS) attacks are a prevalent threat to resource-constrained IoT deployments. We present an edge-based detection and mitigation system integrated with the oneM2M architecture. By using a Raspberry Pi 4 client and five Raspberry Pi 3 attack nodes in a smart-home testbed, we collected 200,000 packets with 19 features across four traffic states (normal, SYN/UDP/ICMP floods), trained Decision Tree, 2D-CNN, and LSTM models, and deployed the best model on an edge computer for real-time inference. The edge node classifies traffic and triggers per-attack defenses on the device (SYN cookies, UDP/ICMP iptables rules). On a held-out test set, the 2D-CNN achieved 98.45% accuracy, outperforming the LSTM (96.14%) and Decision Tree (93.77%). In end-to-end trials, the system sustained service during SYN floods (time to capture 200 packets increased from 5.05 s to 5.51 s after enabling SYN cookies), mitigated ICMP floods via rate limiting, and flagged UDP floods for administrator intervention due to residual performance degradation. These results show that lightweight, edge-deployed learning with targeted controls can harden oneM2M-based IoT systems against common DDoS vectors.
- 8 September 2025
- Published by MDPI AG in Future Internet
- Vol. 17 (9) , 411
Open AccessDetection and Mitigation in IoT Ecosystems Using oneM2M Architecture and Edge-Based Machine Learning
Distributed denial-of-service (DDoS) attacks are a prevalent threat to resource-constrained IoT deployments. We present an edge-based detection and mitigation system integrated with the oneM2M architecture. By using a Raspberry Pi 4 client and five Raspberry Pi 3 attack nodes in a smart-home testbed, we collected 200,000 packets with 19 features across four traffic states (normal, SYN/UDP/ICMP floods), trained Decision Tree, 2D-CNN, and LSTM models, and deployed the best model on an edge computer for real-time inference. The edge node classifies traffic and triggers per-attack defenses on the device (SYN cookies, UDP/ICMP iptables rules). On a held-out test set, the 2D-CNN achieved 98.45% accuracy, outperforming the LSTM (96.14%) and Decision Tree (93.77%). In end-to-end trials, the system sustained service during SYN floods (time to capture 200 packets increased from 5.05 s to 5.51 s after enabling SYN cookies), mitigated ICMP floods via rate limiting, and flagged UDP floods for administrator intervention due to residual performance degradation. These results show that lightweight, edge-deployed learning with targeted controls can harden oneM2M-based IoT systems against common DDoS vectors.
- Open Access
- 7 July 2025
- Published by MDPI AG in Electronics
- Vol. 14 (13) , 2738
Research on Autonomous Vehicle Lane-Keeping and Navigation System Based on Deep Reinforcement Learning: From Simulation to Real-World Application
In recent years, with the rapid development of science and technology and the substantial improvement of computing power, various deep learning research topics have been promoted. However, existing autonomous driving technologies still face significant challenges in achieving robust lane-keeping and navigation performance, especially when transferring learned models from simulation to real-world environments due to environmental complexity and domain gaps. Many fields such as computer vision, natural language processing, and medical imaging have also accelerated their development due to the emergence of this wave, and the field of self-driving cars is no exception. The trend of self-driving cars is unstoppable. Many technology companies and automobile manufacturers have invested a lot of resources in the research and development of self-driving technology. With the emergence of different levels of self-driving cars, most car manufacturers have already reached the L2 level of self-driving classification standards and are moving towards L3 and L4 levels. This study applies deep reinforcement learning (DRL) to train autonomous vehicles with lane-keeping and navigation capabilities. Through simulation training and Sim2Real strategies, including domain randomization and CycleGAN, the trained models are evaluated in real-world environments to validate performance. The results demonstrate the feasibility of DRL-based autonomous driving and highlight the challenges in transferring models from simulation to reality.
- 7 July 2025
- Published by MDPI AG in Electronics
- Vol. 14 (13) , 2738
Open AccessResearch on Autonomous Vehicle Lane-Keeping and Navigation System Based on Deep Reinforcement Learning: From Simulation to Real-World Application
In recent years, with the rapid development of science and technology and the substantial improvement of computing power, various deep learning research topics have been promoted. However, existing autonomous driving technologies still face significant challenges in achieving robust lane-keeping and navigation performance, especially when transferring learned models from simulation to real-world environments due to environmental complexity and domain gaps. Many fields such as computer vision, natural language processing, and medical imaging have also accelerated their development due to the emergence of this wave, and the field of self-driving cars is no exception. The trend of self-driving cars is unstoppable. Many technology companies and automobile manufacturers have invested a lot of resources in the research and development of self-driving technology. With the emergence of different levels of self-driving cars, most car manufacturers have already reached the L2 level of self-driving classification standards and are moving towards L3 and L4 levels. This study applies deep reinforcement learning (DRL) to train autonomous vehicles with lane-keeping and navigation capabilities. Through simulation training and Sim2Real strategies, including domain randomization and CycleGAN, the trained models are evaluated in real-world environments to validate performance. The results demonstrate the feasibility of DRL-based autonomous driving and highlight the challenges in transferring models from simulation to reality.
- Open Access
- 21 February 2025
- Published by MDPI AG in Electronics
- Vol. 14 (5) , 865
A Smart Space Focus Enhancement System Based on Grey Wolf Algorithm Positioning and Generative Adversarial Networks for Database Augmentation
In the age of technological advancement, brainwave monitoring and attention tracking are critical for individual productivity and organizational efficiency. However, distractions pose significant challenges, making an effective brainwave monitoring and attention system essential. Generative Adversarial Networks (GANs) enhance medical datasets by synthesizing diverse samples. This paper explores their application in improving datasets for indoor positioning and brainwave monitoring-based attention tracking. The goal is to develop an intelligent lighting system that adjusts settings based on users’ brainwave states and positions. GANs enhance brainwave monitoring and positioning datasets, with Principal Component Analysis (PCA) applied for dimensionality reduction. machine learning and deep learning models train on these augmented datasets, enabling dynamic lighting adjustments to optimize user experience. GANs undergo parameter fine-tuning to improve dataset quality. Various classification models, including neural networks (NN), K-Nearest Neighbors (KNN), Support Vector Machines (SVM), and Long Short-Term Memory (LSTM), are used for brainwave monitoring, attention, and positioning. Fuzzy logic enhances system stability. The trained models are integrated with hardware components, such as the Raspberry Pi 4, to implement an “Indoor Positioning Deep Learning Brainwave Monitoring and Attention Monitoring System Based on the Grey Wolf Optimizer Algorithm”. Experimental results demonstrate a positioning accuracy of 15 cm and significant improvements in brainwave monitoring and attention tracking.
- 21 February 2025
- Published by MDPI AG in Electronics
- Vol. 14 (5) , 865
Open AccessA Smart Space Focus Enhancement System Based on Grey Wolf Algorithm Positioning and Generative Adversarial Networks for Database Augmentation
In the age of technological advancement, brainwave monitoring and attention tracking are critical for individual productivity and organizational efficiency. However, distractions pose significant challenges, making an effective brainwave monitoring and attention system essential. Generative Adversarial Networks (GANs) enhance medical datasets by synthesizing diverse samples. This paper explores their application in improving datasets for indoor positioning and brainwave monitoring-based attention tracking. The goal is to develop an intelligent lighting system that adjusts settings based on users’ brainwave states and positions. GANs enhance brainwave monitoring and positioning datasets, with Principal Component Analysis (PCA) applied for dimensionality reduction. machine learning and deep learning models train on these augmented datasets, enabling dynamic lighting adjustments to optimize user experience. GANs undergo parameter fine-tuning to improve dataset quality. Various classification models, including neural networks (NN), K-Nearest Neighbors (KNN), Support Vector Machines (SVM), and Long Short-Term Memory (LSTM), are used for brainwave monitoring, attention, and positioning. Fuzzy logic enhances system stability. The trained models are integrated with hardware components, such as the Raspberry Pi 4, to implement an “Indoor Positioning Deep Learning Brainwave Monitoring and Attention Monitoring System Based on the Grey Wolf Optimizer Algorithm”. Experimental results demonstrate a positioning accuracy of 15 cm and significant improvements in brainwave monitoring and attention tracking.