Scholarlink

<p>Dengue outbreaks pose an escalating challenge, especially in northern India, where both affected regions and incidence rates have expanded. Developing a reliable model for accurate dengue incidence forecasting remains a daunting task. This study rigorously evaluates advanced deep learning algorithms, including artificial neural networks (ANN), convolutional neural networks (CNN), and long short-term memory networks (LSTM), to improve predictive accuracy&#xa0;for Jaipur city region. The system integrates a robust recommendation engine, employing CNN to interpret monthly dengue surveillance and meteorological data from 2015 to 2019 in Jaipur, Rajasthan, India. This integration creates a sophisticated fusion, not just a collection of tools, effectively bridging the gap between physical and virtual realms. The result is an interactive, immersive, and more accurate patient prediction, facilitating health infrastructure management. Validation of the proposed one-dimensional CNN (1DCNN) model demonstrates high accuracy and robustness in predicting dengue cases, supported by various performance metrics. This study represents the first comprehensive evaluation of diverse algorithms for dengue incidence prediction, offering the potential to accurately monitor dengue dynamics and optimize health infrastructure management in the region.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Prediction of dengue patients using deep learning methods amid complex weather conditions in Jaipur, India

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年2月15日

查看全文
  • Dheeraj Kumar Dhaked,
  • Omveer Sharma,
  • Yatindra Gopal,
  • Ram Gopal

摘要

Dengue outbreaks pose an escalating challenge, especially in northern India, where both affected regions and incidence rates have expanded. Developing a reliable model for accurate dengue incidence forecasting remains a daunting task. This study rigorously evaluates advanced deep learning algorithms, including artificial neural networks (ANN), convolutional neural networks (CNN), and long short-term memory networks (LSTM), to improve predictive accuracy for Jaipur city region. The system integrates a robust recommendation engine, employing CNN to interpret monthly dengue surveillance and meteorological data from 2015 to 2019 in Jaipur, Rajasthan, India. This integration creates a sophisticated fusion, not just a collection of tools, effectively bridging the gap between physical and virtual realms. The result is an interactive, immersive, and more accurate patient prediction, facilitating health infrastructure management. Validation of the proposed one-dimensional CNN (1DCNN) model demonstrates high accuracy and robustness in predicting dengue cases, supported by various performance metrics. This study represents the first comprehensive evaluation of diverse algorithms for dengue incidence prediction, offering the potential to accurately monitor dengue dynamics and optimize health infrastructure management in the region.