Related Experiment Video
Updated: Oct 29, 2025
04:17
DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning
Published on: May 10, 2024
1.1K
Improving the performance of deep learning models using statistical features: The case study of COVID-19 forecasting
Hossein Abbasimehr1, Reza Paki1, Aram Bahrini2
1Faculty of Information Technology and Computer Engineering Azarbaijan Shahid Madani University Tabriz Iran.
Mathematical Methods in the Applied Sciences
|July 6, 2021
Summary
This study introduces hybrid deep learning models for COVID-19 case forecasting, enhancing accuracy by integrating statistical features. These novel methods, ATT_FE and CNN_FE, improve upon traditional models for pandemic prediction.
Area of Science:
- Epidemiology
- Data Science
- Computational Biology
Background:
- The COVID-19 pandemic necessitates accurate forecasting for effective public health interventions.
- Existing deep learning models for COVID-19 prediction can be enhanced with auxiliary data.
- Various statistical, mathematical, machine learning, and deep learning techniques have been applied to COVID-19 forecasting.
Purpose of the Study:
- To propose and evaluate two novel hybrid deep learning models for improved COVID-19 case forecasting.
- To investigate the efficacy of incorporating statistical features as auxiliary inputs into deep learning architectures.
- To compare the performance of hybrid models against conventional deep learning methods.
Main Methods:
- Development of two hybrid deep learning models: Attention with Statistical Features (ATT_FE) and Convolutional Neural Network with Statistical Features (CNN_FE).
- Integration of statistical features as auxiliary inputs alongside primary data inputs in the deep learning models.
- Application and evaluation of the proposed models using COVID-19 case data from 10 countries with the highest infection rates.
Main Results:
- The proposed hybrid deep learning models (ATT_FE and CNN_FE) demonstrated superior performance compared to their conventional counterparts.
- Experiments confirmed the effectiveness of integrating statistical features for enhancing COVID-19 forecasting accuracy.
- The hybrid ATT_FE model showed a notable advantage over the Long Short-Term Memory (LSTM) model in predictive performance.
Conclusions:
- Hybrid deep learning approaches incorporating statistical features offer a promising avenue for more accurate COVID-19 forecasting.
- The ATT_FE and CNN_FE models provide enhanced predictive capabilities for pandemic management.
- Further research into hybrid models can significantly contribute to optimizing public health strategies during infectious disease outbreaks.
Related Concept Videos
01:25Statistical Methods for Analyzing Epidemiological Data
643
Epidemiological data primarily involves information on specific populations' occurrence, distribution, and determinants of health and diseases. This data is crucial for understanding disease patterns and impacts, aiding public health decision-making and disease prevention strategies. The analysis of epidemiological data employs various statistical methods to interpret health-related data effectively. Here are some commonly used methods:
643
01:03Prediction Intervals
2.5K
The interval estimate of any variable is known as the prediction interval. It helps decide if a point estimate is dependable.
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.
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.
2.5K
01:18Steps in Outbreak Investigation
266
In the ever-evolving field of public health, statistical analysis serves as a cornerstone for understanding and managing disease outbreaks. By leveraging various statistical tools, health professionals can predict potential outbreaks, analyze ongoing situations, and devise effective responses to mitigate impact. For that to happen, there are a few possible stages of the analysis:
266
02:07Improving Translational Accuracy
12.0K
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
12.0K
02:07Improving Translational Accuracy
3.1K
3.1K
01:11Residuals and Least-Squares Property
8.2K
The vertical distance between the actual value of y and the estimated value of y. In other words, it measures the vertical distance between the actual data point and the predicted point on the line
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...
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...
8.2K