/— title: Publications cms_exclude: true
View.
view: citation
Optional header image (relative to
Pattern Recognition Tasks with Personalized Federated Learning
This study proposes a personalized federated learning (PFL) approach for pattern recognition tasks, improving model accuracy by adapting to client-specific data while preserving privacy. It demonstrates superior performance in tasks like image classification, speech recognition, and text analysis compared to traditional federated learning methods.
Jan 1, 2025
xFiTRNN: A hybrid self attent linearized phrase structured contextualized transformer based RNN for financial sentence analysis with sentence level explainability
xFiTRNN is a hybrid model for financial sentence analysis, combining self-attention, linearized phrase structures, and a contextualized transformer-based RNN. It improves accuracy in sentiment classification while providing sentence-level explainability. This model is ideal for financial text analysis and decision-making transparency.
Dec 7, 2024
Large Language Models in Computer Science Education: A Systematic Literature Review
Neonatal death is a major issue worldwide. Early prediction of at-risk babies can help prevent death. Using data from 1.4 million newborns, machine learning models like XGBoost, Random Forest, and LSTM were tested. XGBoost and Random Forest had 94% accuracy, while LSTM achieved 99% accuracy. LSTM is the most effective model for predicting neonatal mortality and guiding care.
Mar 1, 2024
A deep learning and machine learning approach to predict neonatal death in the context of São Paulo
Neonatal death is a major issue worldwide. Early prediction of at-risk babies can help prevent death. Using data from 1.4 million newborns, machine learning models like XGBoost, Random Forest, and LSTM were tested. XGBoost and Random Forest had 94% accuracy, while LSTM achieved 99% accuracy. LSTM is the most effective model for predicting neonatal mortality and guiding care.
Dec 1, 2023