Implementation of machine learning techniques with big data and IoT to create effective prediction models for health informatics

• Main Authors: Zamani, Abu Sarwar, Hassan Abdalla Hashim, Aisha, Shatat, Abdallah Saleh Ali, Akhtar, Md. Mobin, Rizwanullah, Mohammed, Mohamed, Sara Saadeldeen Ibrahim
• Format: Article
• Language: English; English
• Published: Elsevier 2024
• Subjects: TK7885 Computer engineering
• Online Access: http://irep.iium.edu.my/112311/2/112311_Implementation%20of%20machine%20learning%20techniques_SCOPUS.pdf; http://irep.iium.edu.my/112311/3/112311_Implementation%20of%20machine%20learning%20techniques.pdf; http://irep.iium.edu.my/112311/; https://www.sciencedirect.com/science/article/abs/pii/S1746809424003057?via%3Dihub
• Institution: Universiti Islam Antarabangsa Malaysia

As a result of the availability of healthcare data in sheer size, big data analytics has to grow regularly in this industry to ensure new andeffective opportunities. This is helpful in providing early prevention, prediction, and detection of disease, thus helping in the enhancement ofthe overall life quality of the individuals. Likewise, in this paper, a machine learning-based big data analytics model is developed for predictingmulti-diseases to provide a better decision support system for various healthcare applications. This developed framework utilizes theMapReduce framework, where the map phase performs feature extraction and the reduce phase performs feature selection for the purpose ofhandling and processing big data. The required healthcare data is collected from external web sources. In the map phase, the statisticalfeatures and the Principal Component Analysis (PCA) features are extracted. In the reduction phase, the optimal features are selected with theaid of the developed Hybrid Flower Pollination Bumblebees Optimization Algorithm (HFPBOA). Then, the Ensemble Learning (EL) model isdeveloped to predict the multi-diseases. Moreover, the parameters present in the EL classifiers are optimized by using the same HFPBOA. Thefinal prediction output is obtained by averaging the weight function between the outputs of the NN, KNN, and fuzzy classifier. Thus, theoffered model attains 40.1%, 28.7%, 23.6%, and 10.5% improved than SSA-EL, DOA-EL, BOA-EL, and FA-EL respectively in terms of best value. Theeffectiveness computed for the developed multi-disease prediction framework is guaranteed by comparing the results among the recentlydeveloped prediction approaches.