A Fast Fourier Transform-Coupled Machine Learning-Based Ensemble Model for Disease Risk Prediction Using a Real-Life Dataset
The use of intelligent technologies in clinical decision making have started playing a vital role in improving the quality of patients’ life and helping in reduce cost and workload involved in their daily healthcare. In this paper, a novel fast Fourier transform-coupled machine learning based ensemble model is adopted for advising patients concerning whether they need to take the body test today or not based on the analysis of their medical data during the past a few days. The weighted-vote based ensemble attempts to predict the patients condition one day in advance by analyzing medical measurements of patient for the past k days. A combination of three algorithms namely neural networks, support vector machine and Naive Bayes are utilized to make an ensemble framework. A time series telehealth data recorded from patients is used for experimentations, evaluation and validation. The Tunstall dataset were collected from May to October 2012, from industry collaborator Tunstall. The experimental evaluation shows that the proposed model yields satisfactory recommendation accuracy, offers a promising way for reducing the risk of incorrect recommendations and also saving the workload for patients to conduct body tests every day. The proposed method is, therefore, a promising tool for analysis of time series data and providing appropriate recommendations to patients suffering chronic diseases with improved prediction accuracy.
KeywordsFast Fourier transformation Ensemble model Recommender system Heart failure Time series prediction Telehealth
The authors would like to thank the support from National Science Foundation of China through the research projects (Nos. 61572036, 61370050, and 61672039) and Guangxi Key Laboratory of Trusted Software (No. kx201615).
- 2.Atlas, I.D.: International Diabetes Federation Diabetes Atlas, 6th edn. International Diabetes Federation, Basel (2013)Google Scholar
- 16.Kovacs, P., Samiee, K., Gabbouj, M.: On application of rational discrete short time Fourier transform in epileptic seizure classification. IEEE Trans. Biomed. Eng. 5839–5843 (2014)Google Scholar
- 19.Sharawardi, N.A., Choo, Y.-H., Chong, S.-H., Muda, A.K., Goh, O.S.: Single channel sEMG muscle fatigue prediction: an implementation using least square support vector machine. In: Information and Communication Technologies (WICT), pp. 320–325 (2014)Google Scholar
- 21.Gao, H., Jian, S., Peng, Y., Liu, X.: A subspace ensemble framework for classification with high dimensional missing data. Multidimens. Syst. Sig. Process. 1–16 (2016)Google Scholar
- 24.Şen, B., Peker, M., Çavuşoğlu, A., Çelebi, F.V.: A comparative study on classification of sleep stage based on EEG signals using feature selection and classification algorithms. J. Med. Syst. 38(3), 1–21 (2014)Google Scholar
- 29.Zhang, J., Gao, Q., Wang, H.: SPOT: a system for detecting projected outliers from high-dimensional data streams. In: 24th IEEE International Conference on Data Engineering (ICDE 2008), pp. 1628–1631. IEEE Computer Society, Cancun, April 2008Google Scholar