Data and Machine Learning Fusion Architecture for Cardiovascular Disease Prediction

Abstract

Heart disease, which is also known as cardiovascular disease, includes various conditions that affect the heart and has been considered a major cause of death over the past decades. Accurate and timely detection of heart disease is the single key factor for appropriate investigation, treatment, and prescription of medication. Emerging technologies such as fog, cloud, and mobile computing provide substantial support for the diagnosis and prediction of fatal diseases such as diabetes, cancer, and cardiovascular disease. Cloud computing provides a cost-efficient infrastructure for data processing, storage, and retrieval, with much of the extant research recommending machine learning (ML) algorithms for generating models for sample data. ML is considered best suited to explore hidden patterns, which is ultimately helpful for analysis and prediction. Accordingly, this study combines cloud computing with ML, collecting datasets from different geographical areas and applying fusion techniques to maintain data accuracy and consistency for the ML algorithms. Our recommended model considered three ML techniques: Artificial Neural Network, Decision Tree, and Naïve Bayes. Real-time patient data were extracted using the fuzzy-based model stored in the cloud.

Diabetes Prediction Empowered with Multi-level Data Fusion and Machine Learning

“…Then, a range of evaluation metrics are calculated, include accuracy, miss-classification rate, sensitivity, specificity, precision, False positive (FP) rate, False discovery rate, False omission rate, Positive likelihood ratio, Negative likelihood ratio, Prevalence threshold, critical success index, F1 Score, Mathews Correlation coefficient, Fowlkes-Mallows Index, informedness, and Diagnostic odds ratio. The following equations illustrate the equations used to calculate each of these metrics, providing a clear understanding of the underlying mathematical formulas for the statistical measurements [17][18][19][20][21][22][23]. The utilization of this diverse set of metrics ensures a comprehensive assessment of the models' performance, accounting for different aspects of predictive accuracy and error rates.…”

An Optimal Solution to the Overfitting and Underfitting Problem of Healthcare Machine Learning Models

“…Therefore, reliable features and filtered datasets overcome the problem of overfitting. For feature extraction, four techniques are available such as FCBF, LASSO, MRMR, and RELIEF [23,24,25]. These techniques extract valuable features for model training.…”

Global Optimal Time Trajectory Planning of Construction Machinery Robot Considering Ant Colony Algorithm

“…In view of the phenomenon that the average distribution of pheromones at the initial stage of the ACA leads to too long search time, this paper adds information gain to carry out the initial distribution of pheromones; In order to improve the construction efficiency of the initial feasible solution and give full play to the ability of ants to cooperate with each other in path finding, this paper draws on the parallel search strategy of ants facing each other proposed in the literature, and on this basis, a new ant encounter discrimination strategy is proposed to determine when ants meet, which ensures the integrity of all feasible path search and makes up for the shortcomings of the original method that is easy to lose some feasible paths; The pheromone mutual guidance strategy is designed, and the path selection probability formula is newly designed [18].…”