Ambient assisted living predictive model for cardiovascular disease prediction using supervised learning
- PDF / 4,167,235 Bytes
- 29 Pages / 595.276 x 790.866 pts Page_size
- 72 Downloads / 163 Views
SPECIAL ISSUE
Ambient assisted living predictive model for cardiovascular disease prediction using supervised learning Sibo Prasad Patro1 · Neelamadhab Padhy1 · Dukuru Chiranjevi1 Received: 3 June 2020 / Revised: 21 August 2020 / Accepted: 28 August 2020 © Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract The rapid increase of the aged population and challenges towards taking health care and social care become the key point for the industry and researchers nowadays. Heart diseases are typical chronic illnesses with a high recurrence rate. In some of the cases, a heart attack occurs suddenly without any omens. Patients typically live in their homes rather than in hospitals and are often unable to access medical care in an emergency. Cardiovascular disease leads to a significant difficulty for the doctors to know the patient’s status in time, and it becomes one of the significant reasons for death. To overcome these problems, a solution needs to design, implement, and validate adequately through an appropriate base knowledge. To overcome these challenges, remotely real-time patient’s health data can be identified. Today Internet of Things is playing a key role in solving the problem of heart disease. The patients can avail of the medical resource much. This research work aims to propose a framework for prediction of heart disease using major risk factors based on various classifier arrangements; K-nearest neighbors, Naïve Bayes, support vector machine, Lasso and ridge regression algorithms. Apart from these data classification, linear discriminant analysis and principal component analysis were done. The support vector machine provides 92% accuracy, and F1 accuracy is 85%. The performance of the proposed research work is evaluated using precision, accuracy, and sensitivity. Keywords Internet of Things · Healthcare · Real-time monitoring · Wireless sensor networks · ML (machine learning) · K-nearest neighbors (KNN) · Naïve Bayes (NB) · Support vector machine (SVM) · Evolutionary intelligence technique Abbreviations IoT Internet of Things HIoT Healthcare Internet of Things ML Machine learning AI Artificial intelligence ANN Artificial neural network KNN K-nearest neighbors NB Naïve Bayes SVM Support vector machine SSVM Smooth support vector machine LRR Lasso and ridge regression * Sibo Prasad Patro [email protected] Neelamadhab Padhy [email protected] Dukuru Chiranjevi [email protected] 1
Department of Computer Science and Engineering, School of Engineering and Technology, GIET University, Gunupur, India
LDA Linear discriminant analysis PCA Principal component analysis WSN Wireless sensor networks WWSN Wearable wireless sensor network WBAN Wireless body area network SW-SHMS Wearable Sensors for Smart Healthcare Monitoring System AAL Ambient assisted living CVD Cardiovascular disease CART Cardiac regenerative therapy PSO Particle swarm optimization HRFLM Hybrid Random Forest with a Linear Model PUAI Primary use of AI ABC Artificial bee colony ANFIS
Data Loading...
