About
Research & Development
Exploring the Nuances of Voice: Insights from the First Voice Timbre Attribute Detection Challenge
TLDR: The First Voice Timbre Attribute Detection (vTAD) Challenge, held at NCMMSC 2025, focused on comparing the intensity of voice timbre attributes between two...
Research & Development
Navigating Unseen Roads: TrajAware’s Approach to VANET Routing
TLDR: TrajAware is a novel reinforcement learning framework for Vehicular Ad Hoc Networks (VANETs) designed for edge AI. It tackles challenges like dynamic network...
Research & Development
BioLite U-Net: Enabling Real-Time Quality Control in Bioprinting with Compact AI
TLDR: Researchers have developed BioLite U-Net, a lightweight AI model for real-time semantic segmentation in bioprinting. This model accurately differentiates nozzle, bioink, and background,...
Research & Development
Barycentric Neural Networks and Length-Weighted Persistent Entropy: A New Framework for Efficient Function Approximation
TLDR: Researchers introduce Barycentric Neural Networks (BNNs), a shallow neural network that uses geometric base points for function approximation, and Length-Weighted Persistent Entropy (LWPE)...
Research & Development
Advanced AI Model Enhances Brain Tumor Detection with High Accuracy and Interpretability
TLDR: A new deep learning model combines EfficientNetV2 with an attention-based MLP-Mixer architecture to achieve 99.50% accuracy in classifying brain tumors from MRI images....
Research & Development
Automated X-ray Scoring System Enhances Rheumatoid Arthritis Assessment
TLDR: A new deep learning system, Automated Radiographic Total Sharp Scoring (ARTSS), has been developed to automate the assessment of rheumatoid arthritis (RA) severity...