Unsynchronized wearable sensor data analytics model for improving the performance of smart healthcare systems
- PDF / 3,204,532 Bytes
- 12 Pages / 595.276 x 790.866 pts Page_size
- 45 Downloads / 233 Views
ORIGINAL RESEARCH
Unsynchronized wearable sensor data analytics model for improving the performance of smart healthcare systems Osama Alfarraj1 · Amr Tolba1,2 Received: 15 July 2020 / Accepted: 22 September 2020 © Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract Background A wearable sensor (WS) is a prominent technology application that senses and gathers information from a user for analyzing changes in physiological signs. Analyzing the physiological sign differences enables the better healthcare solutions. Purpose This paper introduces an unsynchronized sensor data analytics (USDA) model for the effective handling of wearable device data regardless of the time factor. Time-dependent healthcare treatments and diagnosis are the themes on which this analytics model focuses. Methods The gathered WS data is classified depending on the time factor and data frequency of occurrence. This occurrence frequency is correlatively analyzed using the diagnosis module to identify defects and to fulfill the missing sensor data consideration. Healthcare diagnoses requiring immediate responses and timely solutions for patients/end-users rely on this model for uncompromising analysis. Results The vital changes in WS data and time factors are analyzed using sophisticated machine learning methods for previous diagnosis correlation and effective accuracy. Conclusion Responsive healthcare solutions using unsynchronized WS data help to achieve better efficiency and reduce complications in assessing the performance of the healthcare systems. Keywords Data analytics · Healthcare system · Machine learning · Time split instances · Wearable sensor
1 Background A wearable sensor (WS) is integrated into the human body to sense body-related information, like ECG, temperature, and skin humidity (Mallires et al. 2019), and to provide the appropriate health condition status (Luo et al. 2019). It is used in healthcare mostly to analyze a patient’s health condition and to send that data to a healthcare provider, where the feedback is provided. Many types of sensors are used to detect the associated body issues and can capture data for every time interval. A sequential data acquisition is achieved for monitoring patient health (Manogaran et al. 2019). In this * Osama Alfarraj [email protected] 1
Computer Science Department, Community College, King Saud University, 11437 Riyadh, Saudi Arabia
Mathematics and Computer Science Department, Faculty of Science, Menoufia University, 32511 Shebin‑El‑Kom, Egypt
2
data transmission state, data delays and errors are considered the system’s main constraint, and these must be reduced. If medical data are lost or a delay happens, it can lead to an emergency state; hence the medical data must be protected. A WS can also provide a patient’s location to direct emergency services. This advanced technique has proven reliable in saving patients’ life (An et al. 2019; Rizwan et al. 2018). Data analysis in the medical field is used to identify a patient’s condition and to remotely
Data Loading...
