Optimization Driven Deep Learning Approach for Health Monitoring and Risk Assessment in Wireless Body Sensor Networks

Optimization Driven Deep Learning Approach for Health Monitoring and Risk Assessment in Wireless Body Sensor Networks

Abdalla Alameen (College of Arts and Sciences, Prince Sattam Bin Abdulaziz University, Al Kharj, Saudi Arabia) and Ashu Gupta (College of Arts and Sciences, Prince Sattam Bin Abdulaziz University, Al Kharj, Saudi Arabia)
DOI: 10.4018/IJBDCN.2020010105
OnDemand PDF Download:
List Price: $37.50
10% Discount:-$3.75


Wireless body sensor networks (WBSNs) plays a vital role in monitoring health conditions of patients and is a low-cost solution for dealing with several healthcare applications. Processing large amounts of data and making feasible decisions in emergency cases are the major challenges for WBSNs. Thus, this article addresses these challenges by designing a deep learning approach for health risk assessment by proposing a Fractional Cat-based Salp Swarm Algorithm (FCSSA). At first, the WBSN nodes are utilized for sensing data from patient health records to acquire certain parameters for making the assessment. Based on the obtained parameters, WBSN nodes transmit the data to the target node. Here, the hybrid Harmony Search Algorithm and Particle Swarm Optimization (hybrid HSA-PSO) is used for determining the optimal cluster head. Then, the results produced by the hybrid HSA-PSO are given to the target node, in which the Deep Belief Network (DBN) is used for classifying the health records for the health risk assessment. Here, the DBN is trained using the proposed FCSSA, which is developed by integrating a Fractional Cat Swarm Optimization (FCSO) and Salp Swarm Algorithm (SSA) for initiating the classification. The proposed FCSSA shows better performance using metrics, namely accuracy, energy and throughput with values 94.604, 0.145, and 0.058, respectively.
Article Preview

1. Introduction

The development of wireless body sensor networks (WBSN) in monitoring the health conditions has gained huge interest on industries and research works in the recent years. These interests are mostly inspired from the expensive healthcare products and due to the progress of health monitoring systems and the rising technologies (Harbouche et al., 2017). WBSN’s are considered as a part of Wireless Sensor Networks (WSN), which can be utilized in the healthcare applications to monitor the health conditions of the patients (Habib et al., 2016). Wireless Body Area Network (WBAN) is a special network that operates automatically and autonomously connects various sensors and interacts with various medical servers. The sensor nodes are implanted inside or outside the human body for monitoring health conditions of the elderly peoples (Kalaiselvi et al., 2018). The WBAN is emerged as a handy tool to monitor the health conditions using real time applications. WBANs offer a channel for constant, prominent and proficient monitoring of patient health using certain health factors, such as temperature and rate of heart from an isolated place (Gambhir & Kathuria, 2018). The usage of various sensors in WBANs initiates heterogeneity in the healthcare applications. Thus, the sensor node with heterogeneous nature in WBAN has dissimilar needs. Moreover, the WBAN describes the destructive situations when the healthcare environments are dynamic (Jeong et al., 2012). WBSNs accumulates and examines essential signs of data by arranging various types of biomedical sensors, like EEG, heartbeat, ECG, temperature of body, and blood pressure. WBSNs can be utilized for monitoring patient in the home and to examine old peoples in homes; thereby, ignoring inessential hospitalization and minimizing the cost of healthcare (Habib et al., 2016). The WBSN is costless solution for dealing with healthcare applications and allows uninterrupted monitoring (Habib et al., 2016).

The vision of WBAN is to provide benefit by improving healthcare monitoring systems and has enormous influence on healthcare system for recognizing the levels of risks and patient severity factors in emergency. The recent technological progress in WBAN updated the field of self-directed monitoring into the highest peak using the imperative signals and can be functioned from a remote area. But, managing heterogeneous packets in the rapidly increasing healthcare situations has sustained as a prospect for examination (Gambhir & Kathuria, 2018). Generally, these health conditions are observed using the WBSN systems which contains physiological signals, cardiac arrhythmia or certain factors like oxygen diffusion, rate of respiration, and activity of heart (Harbouche et al., 2017). The technologies based on the WBSN constructs a network with connected sensor nodes implanted on human, which contribute mainly in monitoring the personalized health and evaluating the diagnosis for the disease. Thus, it is effectual to design a heart rate WBSN environment in which heart-rate signals in real-time would be accumulated, broadcasted and presented (Pirbhulal et al., 2015). But, the recent WBSNs are mostly motorized using a conventional power supply unit, like battery. The autonomous working module is highly needed in WBSN for monitoring the heart rates due to the restricted lifetime of batteries and the pollution problems caused by the battery. The heart rate is considered as a straight manifestation for analyzing the status of health using the cardiovascular system. It plays an important role in sensing the signals for monitoring the healthcare and diagnosis (Yang et al., 2015). The physical activities provide balance in energies and control the body weights, enhance the fitness of cardiorespiratory nodules and health and minimize the coronary heart disease, strokes and hypertension risks (Brzeziński, 2010).

Complete Article List

Search this Journal:
Volume 19: 1 Issue (2023): Forthcoming, Available for Pre-Order
Volume 18: 2 Issues (2022): 1 Released, 1 Forthcoming
Volume 17: 2 Issues (2021)
Volume 16: 2 Issues (2020)
Volume 15: 2 Issues (2019)
Volume 14: 2 Issues (2018)
Volume 13: 2 Issues (2017)
Volume 12: 2 Issues (2016)
Volume 11: 2 Issues (2015)
Volume 10: 4 Issues (2014)
Volume 9: 4 Issues (2013)
Volume 8: 4 Issues (2012)
Volume 7: 4 Issues (2011)
Volume 6: 4 Issues (2010)
Volume 5: 4 Issues (2009)
Volume 4: 4 Issues (2008)
Volume 3: 4 Issues (2007)
Volume 2: 4 Issues (2006)
Volume 1: 4 Issues (2005)
View Complete Journal Contents Listing