Continuous m-Health Data Authentication Using Wavelet Decomposition for Feature Extraction

• Published in: Sensors (Basel, Switzerland) Vol. 20; no. 19; p. 5690
• Main Authors: Enamamu, Timibloudi, Otebolaku, Abayomi, Marchang, Jims, Dany, Joy
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 06.10.2020; MDPI
• Subjects: Approximation; approximation coefficients; bioelectrical signals; Biometrics; biorthogonal wavelet; Decomposition; detail coefficient; Heart Rate; Humans; Internet of Things; Noise; Sensors; Smartphones; Social networks; Social research; Telemedicine; Usability; Wavelet Analysis; wavelet transform; Wavelet transforms; Wearable computers; Wireless Technology; smartwatch; approximation coefficients; m-health monitoring; biorthogonal wavelet; wavelet transform; smartphones; detail coefficient; bioelectrical signals
• ISSN: 1424-8220; 1424-8220
• DOI: 10.3390/s20195690

The World Health Organization (WHO) in 2016 considered m-health as: “the use of mobile wireless technologies including smart devices such as smartphones and smartwatches for public health”. WHO emphasizes the potential of this technology to increase its use in accessing health information and services as well as promoting positive changes in health behaviours and overall management of diseases. In this regard, the capability of smartphones and smartwatches for m-health monitoring through the collection of patient data remotely, has become an important component in m-health system. It is important that the integrity of the data collected is verified continuously through data authentication before storage. In this research work, we extracted heart rate variability (HRV) and decomposed the signals into sub-bands of detail and approximation coefficients. A comparison analysis is done after the classification of the extracted features to select the best sub-bands. An architectural framework and a used case for m-health data authentication is carried out using two sub-bands with the best performance from the HRV decomposition using 30 subjects’ data. The best sub-band achieved an equal error rate (EER) of 12.42%.