Researchers have developed an enhanced Artificial Neural Network (ANN) using the QHAdamW optimizer for air quality forecasting in Manila, Philippines. This modified optimizer, which combines Quasi-Hyperbolic Momentum (QHAdam) with Adam with decoupled weight decay (AdamW), aims to improve convergence, generalization, and performance over the standard Adam algorithm. The study demonstrated that QHAdamW achieved lower error values and a regression coefficient close to 1, indicating improved model accuracy. The model successfully predicted PM2.5 and PM10 levels, offering a tool for the Department of Environment and Natural Resources-Environmental Monitoring Bureau to manage air quality. AI
IMPACT This research could lead to more accurate and efficient AI models for environmental monitoring and prediction.
RANK_REASON The cluster describes a research paper detailing a novel optimization technique for artificial neural networks applied to a specific forecasting task. [lever_c_demoted from research: ic=1 ai=1.0]
Read on arXiv cs.NE (Neural & Evolutionary) →
- Adam
- AdamW
- artificial neural network
- Department of Environment and Natural Resources-Environmental Monitoring Bureau
- Manila
- PM 2.5
- QHAdam
- QHAdamW
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
