Browsing by Author "Shamim, Muhammad"

Filter results by typing the first few letters
Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Predictive Analytics: Anemia Disease Forecasting with Machine Learning and Deep Learning Models
    (International Islamic University Chittagong, 2024-02) Shamim, Muhammad
    Remarkable breakthroughs in medical research are creating important information that we utilize every day. To gain appropriate details for analysis, prediction, creating suggestions, and establishing choices, this data has to be analyzed. Turn present data into information by applying data mining or machine learning approaches. Accurate illness forecasting is vital in medicine for both preventative and efficient treatment planning. On event, a lack of precision might be deadly. In order to anticipate anemia, this work investigates several machine learning (ML) classification strategies in a large dataset to diagnose anemia , and the performance of these algorithms is confirmed using measurements such as error rate, accuracy, precision, recall, and F-Measure. Strategies were tried in the experiment, and it was determined that Random forest functioned better than any ML methodology, with the maximum accuracy of 100 percent when compared to other algorithms.
  • No Thumbnail Available
    Item
    Predictive Analytics: Anemia Disease Forecasting with Machine Learning and Deep Learning Models
    (2024-02) Shamim, Muhammad
    Remarkable breakthroughs in medical research are creating important information that we utilize every day. To gain appropriate details for analysis, prediction, creating suggestions, and establishing choices, this data has to be analyzed. Turn present data into information by applying data mining or machine learning approaches. Accurate illness forecasting is vital in medicine for both preventative and efficient treatment planning. On event, a lack of precision might be deadly. In order to anticipate anemia, this work investigates several machine learning (ML) classification strategies in a large dataset to diagnose anemia , and the performance of these algorithms is confirmed using measurements such as error rate, accuracy, precision, recall, and F-Measure. Strategies were tried in the experiment, and it was determined that Random forest functioned better than any ML methodology, with the maximum accuracy of 100 percent when compared to other algorithms.