About
Research & Development
Rethinking Homophone Normalization in Machine Translation for Ge’ez Script Languages
TLDR: This research paper investigates the impact of homophone normalization, a common pre-processing step in NLP for languages like Amharic, on machine translation performance...
Research & Development
AI Model for Anemia Detection: Balancing Performance and Efficiency on Portable Devices
TLDR: This research explores using a lightweight AI model (MobileNet) to detect anemia from images of conjunctival pallor, aiming for deployment on portable devices....
Research & Development
Enhancing Multi-Label Prediction with Probabilistic Sequential Models and Logical Constraints
TLDR: This research introduces a two-stage architecture for multi-label classification, particularly effective for large label sets with logical constraints. It uses a base model...
Research & Development
Advancing Emotion Recognition in Conversations with Long-Short Distance Graph Neural Networks and Improved Curriculum Learning
TLDR: This research introduces the Long-Short Distance Graph Neural Network (LSDGNN) and an Improved Curriculum Learning (ICL) strategy for Emotion Recognition in Conversation (ERC)....
Research & Development
Forecasting Food Delivery Demand with Intelligent Graph Networks
TLDR: This research introduces an attention-based Graph Neural Network (GNN) framework for highly accurate spatio-temporal demand prediction in food delivery. By modeling delivery zones...
Research & Development
MEETI: A Comprehensive Multimodal ECG Dataset for Next-Generation AI in Cardiology
TLDR: MEETI is the first large-scale ECG dataset that integrates raw waveform signals, high-resolution plotted images, extracted quantitative parameters, and detailed AI-generated textual interpretations....