A WBAN-Based Framework for Health Condition Monitoring and Faulty Sensor Node Detection Applying ANN

A WBAN-Based Framework for Health Condition Monitoring and Faulty Sensor Node Detection Applying ANN

Koushik Karmakar (Narula Institute of Technology, India), Sohail Saif (Maulana Abul Kalam Azad University of Technology, India), Suparna Biswas (Maulana Abul Kalam Azad University of Technology, India) and Sarmistha Neogy (Jadavpur University, India)
Copyright: © 2021 |Pages: 22
DOI: 10.4018/IJBCE.2021070104
OnDemand PDF Download:
No Current Special Offers


Remote health monitoring framework using wireless body area network with ubiquitous support is gaining popularity. However, faulty sensor data may prove to be critical. Hence, faulty sensor detection is necessary in sensor-based health monitoring. In this paper, an artificial neural network (ANN)-based framework for learning about health condition of patients as well as fault detection in the sensors is proposed. This experiment is done based on human cardiac condition monitoring setup. Related physiological parameters have been collected using wearable sensors from different people. These data are then analyzed using ANN for health condition identification and faulty node detection. Libelium MySignals HW (eHealth Medical Development Shield for Arduino) v2 sensors such as ECG sensor, pulse oximeter sensor, and body temperature sensor have been used for data collection and ARDINO UNO R3 as microcontroller device. ANN method detects faulty sensor data with classification accuracy of 98%. Experimental results and analyses are given to prove the claim.
Article Preview


Significant advancements are taking place in the area of sensor networks, smart phones, devices, Internet of Things (IoT) and their use in modern life. They have different applications including health monitoring and remote diagnosis. Along with life style changes and increase in life expectancy there is an increase of chronic diseases all over the world. Healthcare expenditure is also increasing. But, the quality of healthcare services is declining gradually. This is a matter of great concern. Use of Information and Communication Technology (ICT) in health-care system has become very important in this situation. (Qu Y et al., 2019; I Pandey et al., 2019; Jayalakshmi et al.,2018; Al-Khalifa et al.,2019; N Dey et al. 2017, F Derakhshan et al. 2019). It provides a new dimension and method for remote diagnosis and treatment (Kaur et al.,2019; Khan and Pathan, 2018). According to this technique, small sensor devices are attached to the patients’ body. They continuously monitor human physiological conditions like blood pressure, pulse, and heart beat rate and send them to a server located at a distant place often in the doctor’s chamber. All these physiological information are stored and analyzed there. This system of remote health monitoring system is known as Wireless Body Area Network (WBAN) (Qu Y et al., 2019; I Pandey et al., 2019). In IEEE 802.15.6 its standards have been defined. WBAN supports wide ranges of data like75.9 Kbps to 15.6 Mbps and different wireless technologies like ZigBee, WPAN and Bluetooth. They are for proper functioning of WBAN system. However, transmission delay is there which should always be less than 125 milliseconds (ms)as per medical standards in this field. For non-medical applications, this delay should be up to 250 ms. In case any sensor node is faulty; it may send incorrect physiological data or even may stop working completely. This may cause havoc in patient life. That is why an appropriate fault detection technique is very much important for a healthcare system. In this paper we have proposed a WBAN based framework. This framework detects abnormal health condition and faulty sensor nodes. It uses Artificial Neural Network (ANN) based technique. It is specially designed for cardiac condition monitoring of the patients.

Fault tolerance is a very important issue and several research works have been carried out on this topic based on WBAN (Yu et al.,2007; Paradis et al.,2007; Yang et al.,2015; Wu et al.,2010; Gupta and Younis, 2003; S. K. Nagdeo, J Mahapatro,2019). A survey on this field has been done and results were documented in this research paper (Salayma et al., 2017). Physiological information collection process using sensor nodes and subsequent faulty nodes detection techniques has been described in details in some papers (Mahapatro and Khilar 2011; Salayma et al., 2017).Sometimes, one middleware layer has been added in every sensor node for data fault detection (Galzarano et al.,2012; Salayma et al.,2017).They also suggest faulty node recovery method. Moreover, they suggest self-healing operations technique too to avoid single point of failure. Priority of sensor data is an important factor in WBAN based work especially in fault detection part. In some paper (Abarna and Venkatachalapathy, 2014; Galzarano et al., 2012) priority values to different sensor data are set. Its fault tolerance level is also set accordingly. Collected values are compared with threshold values and subsequently faults are detected. In this paper (Jeong et al. 2014) a cloud based visual monitoring system is used for fault detection. Processing will be done in the cloud server and results will be visible to all. A unique method for fault detection has been proposed in this paper (Yang et al., 2015). One dynamic-local outlier factor algorithm and linear regression model based on trapezoidal fuzzy numbers has been used for data fault detection. As per this method, faults are detected based on judgment criteria as per the prediction values. In modern times few works were also carried out on fault detection on WBAN using Artificial Neural Network (ANN) based fault detection method. Different works on fault detection have been done on ANN and machine learning. One such work is available in this paper (S. K. Nagdeo, J Mahapatro,2019).

Complete Article List

Search this Journal:
Open Access Articles: Forthcoming
Volume 11: 2 Issues (2022): 1 Released, 1 Forthcoming
Volume 10: 2 Issues (2021)
Volume 9: 2 Issues (2020)
Volume 8: 2 Issues (2019)
Volume 7: 2 Issues (2018)
Volume 6: 2 Issues (2017)
Volume 5: 2 Issues (2016)
Volume 4: 2 Issues (2015)
Volume 3: 2 Issues (2014)
Volume 2: 2 Issues (2013)
Volume 1: 2 Issues (2012)
View Complete Journal Contents Listing