🔬Pioneering Research and Innovation

Our co-founder’s research in blockchain, IoT, computer vision, deep learning, human recognition, and health monitoring forms the foundation of ChainHealth, enabling advanced solutions like posture detection and fatigue monitoring. These innovations power AI-driven insights, enhancing personalized health management and data integration.

📜 Serious Games and Gamification in Healthcare: A Meta-Review

🔗 Research Gate Link

Explores gamification's impact on rehabilitation, mental health, and chronic disease management, highlighting patient engagement, adherence benefits, and future research opportunities.

---

📜 Human Posture Detection on Lightweight DCNN and SVM in a Digitalized Healthcare System

🔗 Research Gate Link

Combines deep convolutional neural networks with SVMs for precise, efficient posture detection in healthcare systems.

---

📜 Convergence of blockchain and Internet of Things: integration, security, and use cases

🔗 Research Gate Link

Analyzes blockchain integration for addressing IoT vulnerabilities, featuring decentralized control, smart contracts, and use cases across industries.

---

📜 A Human-Adaptive Model for User Performance and Fatigue Evaluation during Gaze-Tracking Tasks

🔗 Research MDPI Link

Introduces a biofeedback-driven model using deep learning to optimize user performance and fatigue monitoring for gaze-controlled interfaces.

---

📜 3D Object Reconstruction from Imperfect Depth Data Using Extended YOLOv3 Network

🔗 Research DMPI Link

Proposes a hybrid neural model for reconstructing 3D objects from imperfect data, achieving 8.53% improved accuracy.

---

📜 Human Recognition Through a Webcam Using Deep Learning Techniques

🔗 Link to IEEE Xplore

Develops a CNN-based framework for real-time human behavior analysis, enhancing applications in security, healthcare, and HCI.

---

📜 Detection of Sitting Posture Using Hierarchical Image Composition and Deep Learning

🔗 Link to PeerJ

Utilizes a hierarchical model to accurately classify sitting postures, achieving 91.47% accuracy, ideal for healthcare ergonomics and rehabilitation.