Scholarlink

<p>Heart disease is one of the major causes of mortality globally. Deep Neural Network can be utilized to boost heart disease classification accuracy. The performance of the cardio vascular disease prediction system was significantly enhanced by hybrid deep learning models over single models. In the deep earning model, a smart feature selection technique allows for faster learning while reducing machine effort. The performance of the existing hybrid models is affected due to inefficient feature selection algorithm. Therefore IntellideepNet(Intelligent Deep Neural Network) has been developed to predict the Cardio Vascular Disease(CVD) efficiently and accurately. IntellideepNet is made up of the Improved Extra Tree Classifier (IETC) method, which selects the most efficient features from the Cleveland heart disease and Framingham datasets, and the Convolutional Neural Network (CNN) with Bidirectional Long Short Term Memory (BiLSTM) model, which predicts cardiovascular illness. IETC found the most important features in the Cleveland heart disease dataset by giving precedence to the highly scored aspects. As a result, IETC took the lead in improving the prediction power of the CNN-BiLSTM model. The IntellideepNet was evaluated in a Python simulation environment. IntellideepNet has a 97.67% accuracy rate that is higher than some of the currently available cardiovascular disease prediction systems described in the literature.</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

IntelliNet: intelligent deep net architecture for efficient cardiovascular disease prediction

  • 期刊论文

  • 发表日期：

    2025年3月25日

查看全文
  • Deva Hema D,
  • Rajeeth Jaison T

摘要

Heart disease is one of the major causes of mortality globally. Deep Neural Network can be utilized to boost heart disease classification accuracy. The performance of the cardio vascular disease prediction system was significantly enhanced by hybrid deep learning models over single models. In the deep earning model, a smart feature selection technique allows for faster learning while reducing machine effort. The performance of the existing hybrid models is affected due to inefficient feature selection algorithm. Therefore IntellideepNet(Intelligent Deep Neural Network) has been developed to predict the Cardio Vascular Disease(CVD) efficiently and accurately. IntellideepNet is made up of the Improved Extra Tree Classifier (IETC) method, which selects the most efficient features from the Cleveland heart disease and Framingham datasets, and the Convolutional Neural Network (CNN) with Bidirectional Long Short Term Memory (BiLSTM) model, which predicts cardiovascular illness. IETC found the most important features in the Cleveland heart disease dataset by giving precedence to the highly scored aspects. As a result, IETC took the lead in improving the prediction power of the CNN-BiLSTM model. The IntellideepNet was evaluated in a Python simulation environment. IntellideepNet has a 97.67% accuracy rate that is higher than some of the currently available cardiovascular disease prediction systems described in the literature.