Related Concept Videos
Steps in Outbreak Investigation
Residuals and Least-Squares Property
If the observed data point lies above the line, the residual is positive, and the line underestimates the actual data value for y. If the observed data point lies below the line, the residual is negative, and the line overestimates the actual data value for y.
The process of fitting the best-fit...
Prediction Intervals
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y.
End Point Prediction: Gran Plot
For potentiometric titration, the Gran plot is created by plotting...
Nonlinear Pharmacokinetics: Causes of Nonlinearity
Nonlinear drug absorption can occur when the process is rate-limited by solubility, carrier-mediated transport systems, or saturation of the presystemic gut wall or hepatic metabolism. For instance, high doses of riboflavin...
Statistical Methods for Analyzing Epidemiological Data
You might also read
Related Articles
Articles linked to this work by shared authors, journal, and citation graph.
Inter-hospital secure healthcare data exchange process by using proxy re-encryption and blockchain technology.
Retraction Note: Audio-Visual Automatic Speech Recognition Towards Education for Disabilities.
Vaccine rate forecast for COVID-19 in Africa using hybrid forecasting models.
A Lightweight and Anonymous Mutual Authentication Scheme for Medical Big Data in Distributed Smart Healthcare Systems.
Enhanced Neural Network-Based Univariate Time-Series Forecasting Model for Big Data.
Demand forecasting model for time-series pharmaceutical data using shallow and deep neural network model.
Reinforcement Learning-Based Intelligent Path Planning for Optimal Navigation in Dynamic Environments.
Differential Neural Networks Prediction Using Slow and Fast Hybrid Learning: Application to Prognosis of Infectionsand Deaths of COVID-19 Dynamics.
An Optimal Stacked ResNet-BiLSTM-Based Accurate Detection and Classification of Genetic Disorders.
A Rumor Detection Model Incorporating Propagation Path Contextual Semantics and User Information.
Improving the Polarity of Text through word2vec Embedding for Primary Classical Arabic Sentiment Analysis.
Co-Membership-based Generic Anomalous Communities Detection.
Related Experiment Videos
Nonlinear Neural Network Based Forecasting Model for Predicting COVID-19 Cases.
Suyel Namasudra1, S Dhamodharavadhani2, R Rathipriya2
1Department of Computer Science and Engineering, National Institute of Technology Patna, Bihar, India.
A new Nonlinear Autoregressive Neural Network Time Series (NAR-NNTS) model accurately forecasts COVID-19 cases. Trained with the Levenberg Marquardt algorithm, it offers superior prediction for public health decision-making.
Area of Science:
- Epidemiology
- Computational Biology
- Public Health
Background:
- The COVID-19 pandemic necessitates effective tools for tracking and predicting infection spread.
- Accurate forecasting of confirmed, recovered, and death cases is crucial for public health interventions.
- Existing models may lack the precision required for real-time epidemiological decision-making.
Purpose of the Study:
- To develop and evaluate a novel Nonlinear Autoregressive Neural Network Time Series (NAR-NNTS) model for COVID-19 case prediction.
- To compare the efficacy of different training algorithms (SCG, LM, BR) for the NAR-NNTS model.
- To provide a reliable tool for health consultants to manage the COVID-19 outbreak.
Main Methods:
- Implementation of a Nonlinear Autoregressive (NAR) Neural Network Time Series (NAR-NNTS) model.
- Training the NAR-NNTS model using Scaled Conjugate Gradient (SCG), Levenberg Marquardt (LM), and Bayesian Regularization (BR) algorithms.
- Performance evaluation using Root Mean Square Error (RMSE), Mean Square Error (MSE), and correlation coefficient (R-value).
Main Results:
- The NAR-NNTS model demonstrated capability in forecasting COVID-19 epidemiological data.
- The Levenberg Marquardt (LM) training algorithm yielded superior performance compared to SCG and BR.
- Quantitative metrics (RMSE, MSE, R-value) confirmed the effectiveness of the LM-trained NAR-NNTS model.
Conclusions:
- The proposed NAR-NNTS model, particularly when trained with the LM algorithm, is a promising tool for predicting COVID-19 cases.
- This model can enhance awareness and support health authorities in making informed decisions to control the pandemic.
- Further research can explore advanced neural network architectures for improved epidemiological forecasting.