Hyago Vieira Lemes Barbosa Silva

Mr. Hyago Vieira Lemes Barbosa Silva


Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
26 June 2026 in Head and Neck Pathology
Verified
Journal Article
Open access
GSGiovanna Calabrese dos Santos
Giovanna Calabrese dos Santos
Hyago Vieira Lemes Barbosa SilvaHyago Vieira Lemes Barbosa Silva
Hyago Vieira Lemes Barbosa Silva
Anna Luíza Damaceno AraújoAnna Luíza Damaceno Araújo
Anna Luíza Damaceno Araújo
TNThaís Cerqueira Reis Nakamura
Thaís Cerqueira Reis Nakamura
MSMicael Gil Scholl Santos
Micael Gil Scholl Santos
MMMatheus Cardoso Moraes
Matheus Cardoso Moraes
Background: Peripheral nerve sheath tumors (PNSTs) of the head and neck (H&N) show histopathological overlap. Although convolutional neural networks (CNNs) have demonstrated feasibility in soft tissue tumor classification, limited intra-class variability related to perineurioma remains a critical constraint for rare tumor subtypes. Methods: This retrospective diagnostic accuracy study with internal validation included 30 patients diagnosed with PNSTs. Whole-slide images were digitized at 20× magnification and partitioned using a strict patient-wise split. Synthetic perineurioma patches were generated using a modified Pix2Pix-based Generative Adversarial Network (GAN) incorporating a bottleneck architecture and self-attention modules. Two morphology-driven augmentation strategies were evaluated: (1) intra-phenotypic expansion by cross-patient patch pairing within the sclerosing subtype and (2) inter-phenotypic interpolation by cross-phenotype patch pairing between sclerosing and intraneural variants. EfficientNetV2-B0 pre-trained on ImageNet was trained under three configurations: original dataset only, original + Experiment A synthetic patches, and original + Experiment B synthetic patches. All performance metrics were computed exclusively on an independent yet internal test set composed of original images. Results: GAN-based augmentation improved global classification performance compared with the baseline model trained on original images only (accuracy 0.733). Intra-phenotypic expansion increased accuracy to 0.767 and achieved the highest balanced accuracy (0.750) and macro-F1 (0.740). Inter-phenotypic interpolation yielded the highest overall accuracy and competitive multiclass agreement metrics. Perineurioma recall improved from 0.34 (baseline) to 0.51 with intra-phenotypic augmentation and 0.47 with inter-phenotypic interpolation, while specificity remained ≥ 0.999 across all strategies. Conclusions: Structured, pathology-informed GAN augmentation improved CNN classification of PNSTs, particularly for the morphologically heterogeneous perineurioma class. Intra-phenotypic expansion primarily improved rare-class sensitivity, whereas inter-phenotypic interpolation improved multiclass agreement and global robustness. These findings support morphology-driven synthetic enrichment as a clinically meaningful strategy to improve AI performance in underrepresented tumor entities and potentially support diagnostic decision-making in digital pathology environments.

1 January 2026 in IEEE Embedded Systems Letters
Verified
Journal Article
Closed access
Hyago Vieira Lemes Barbosa SilvaHyago Vieira Lemes Barbosa Silva
Hyago Vieira Lemes Barbosa Silva
LNLuiz E. A. Nora
Luiz E. A. Nora
EBEvandro Cesar Vilas Boas
Evandro Cesar Vilas Boas
Felipe Augusto Pereira de FigueiredoFelipe Augusto Pereira de Figueiredo
Felipe Augusto Pereira de Figueiredo

25 February 2026 in Applied Sciences
Verified
Journal Article
Open access
PDF file
Hyago Vieira Lemes Barbosa SilvaHyago Vieira Lemes Barbosa Silva
Hyago Vieira Lemes Barbosa Silva
DRDavi Rosim
Davi Rosim
Felipe Augusto Pereira de FigueiredoFelipe Augusto Pereira de Figueiredo
Felipe Augusto Pereira de Figueiredo
SMSamuel Mafra
Samuel Mafra
AKAhmed Shaharyar Khwaja
Ahmed Shaharyar Khwaja
AAAlagan Anpalagan
Alagan Anpalagan
The escalating global rates of traffic accidents in urban areas and the growing demands of smart cities underscore the urgent need for advanced real-time monitoring solutions. This paper presents an EdgeML-based system for vehicle tracking that performs real-time speed and distance analysis and traffic violation detection. This is achieved by deploying a YOLOv8 object detection model on a Raspberry Pi 5 with a Coral USB Edge TPU accelerator. The system integrates computer vision and IoT technologies to enable real-time processing. It utilizes the Message Queuing Telemetry Transport (MQTT) protocol to allow scalable communication between distributed edge devices and a central MongoDB database, facilitating real-time storage and analysis of traffic data. A synthetic dataset generated via the Blender 3D modeling tool validates the system’s accuracy, demonstrating average speed and distance measurement errors of ±2.11 km/h and ±0.58 m, respectively. These findings are further supported by preliminary practical experiments in a real-world environment, where speed estimation errors remained within 0–2 km/h and distance errors stayed below 0.11 m. Key innovations of this work include license plate recognition, speeding and collision detection, and context analysis using Google’s Gemini-2.5-Flash API. A Streamlit dashboard provides real-time visualization of traffic metrics, violations, and aggregated data. A comparative evaluation of YOLOv5n, YOLOv8n, YOLOv11n, and YOLOv12n identifies YOLOv8n as the most suitable model for embedded deployment, achieving 91.07 ± 0.61% mAP@0.5 without quantization, 88.77 ± 3.31% mAP@0.5 with quantization, while maintaining real-time performance of 30–43 frames per second (FPS) on the Edge TPU. The system’s modular architecture, low latency, and robust performance highlight its suitability for smart city applications, enhancing traffic safety and enabling data-driven urban mobility management.

19 June 2024 in Preprints.org
Verified
Preprint
Open access
PDF file
Hyago Vieira Lemes Barbosa SilvaHyago Vieira Lemes Barbosa Silva
Hyago Vieira Lemes Barbosa Silva
Felipe Augusto Pereira de FigueiredoFelipe Augusto Pereira de Figueiredo
Felipe Augusto Pereira de Figueiredo
SMSamuel Mafra
Samuel Mafra
MCMateus R. da Cruz
Mateus R. da Cruz
The exponential growth of maritime traffic has brought with it a multitude of business opportunities, while at the same time posing unprecedented challenges in terms of control and surveillance. Traditional methods struggle to cope with the sheer volume and complexity of maritime activities, which calls for innovative solutions. This study presents a comparative analysis of three prominent computing object detection models applied to maritime surveillance. By evaluating their performance metrics in dynamic maritime environments, this study provides information on the most suitable model for effective maritime monitoring applications, attaining an impressive 91\% mean Average Precision (mAP) using the YOLOv5n model.

9 February 2026 in IEEE Embedded Systems Letters
Verified
Journal Article
Closed access
Hyago Vieira Lemes Barbosa SilvaHyago Vieira Lemes Barbosa Silva
Hyago Vieira Lemes Barbosa Silva
Felipe Augusto Pereira de FigueiredoFelipe Augusto Pereira de Figueiredo
Felipe Augusto Pereira de Figueiredo
SMSamuel Mafra
Samuel Mafra
Adnan ShahidAdnan Shahid
Adnan Shahid
Driver drowsiness and distracting behaviors are leading causes of road accidents. This paper presents a cost-effective, real-time driver monitoring system (DMS) that leverages Edge Machine Learning (EdgeML) to detect multiple risk factors: drowsiness, phone usage, smoking, and seatbelt non-compliance. The proposed solution integrates an ensemble of models, object detection (OD), facial landmark analysis, and posture estimation, deployed on a Raspberry Pi 5 (RPi 5) with a Coral USB Edge TPU (ETPU) accelerator. A dual-validation logic cross-confirms biometric anomalies with OD within a temporal window to minimize false positives. The system achieves an average F1-score of 98.66% and 90.46% for two- and five-class classification, respectively, and supports real-time processing at 40 FPS with low resource utilization (21% CPU, 500 MB RAM). This work offers a retrofittable EdgeML solution for real-time driver monitoring, democratizing access to advanced safety features for the billions of cars already on the road. The source code and model weights are publicly available1.