An Adaptive Multi-Homogeneous Sensor Weight Calculation Method for Body Sensor Networks
Open Access
- 22 August 2019
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 7, 121629-121644
Abstract
In the Body Sensor Networks (BSNs), a comprehensive and intuitive conclusion can be obtained by analyzing the physiological state in the mode of multi-heterogeneous source fusion. However, if a node in the sensing layer fails, the input-oriented analysis system is no longer reliable. In this paper, we propose a homogenous sensor weight calculation method for a single sensing node in the BSNs. Under the premise of valid sensing, a set of sequences will be randomly selected as a referee to make the rules of weight allocation. Weak competitiveness means that sensors have a high degree of antagonism, which indicates that the measuring results have errors or there may be abnormal sensors in the sensing module. Meanwhile, we introduce the trend factor of human body state to strengthen the connection between adjacent data in time series, so as to further improve the reliability of trust weight. The proposed algorithm is helpful for sensing nodes in BSNs to obtain more reliable original physiological data and ensure the accuracy of subsequent feature analysis and system decision. Specifically, it can (1) improve the robustness of sensing in BSNs applications, (2) suppress the interference of abnormal signals, (3) solve data conflict, and (4) be universal to the sensors in BSNs devices. The ECG simulations verify the validity of the algorithm in all extreme cases of valid sensing, and the PPG experiments show that the proposed algorithm is applicable to different types of biosensors. Finally, the evaluation and comparison with other four known data-level fusion methods show that the proposed algorithm has better fusion performance.Keywords
Funding Information
- Fundamental Research Funds for the Central Universities (N161608001)
- National Social Science Fund of China (NSSFC) for the Art Major Project (18ZD23)
- Fundamental Research Funds for the Central Universities (N180716019)
This publication has 39 references indexed in Scilit:
- Real-time activity monitoring with a wristband and a smartphoneInformation Fusion, 2018
- Multisensor data fusion using Elman neural networksApplied Mathematics and Computation, 2018
- Design of an accurate end-of-arm force display system based on wearable arm gesture sensors and EMG sensorsInformation Fusion, 2018
- Improvement of DS Evidence Theory for Multi-Sensor Conflicting InformationSymmetry, 2017
- Multi-sensor fusion in body sensor networks: State-of-the-art and research challengesInformation Fusion, 2017
- Adaptive penalized splines for data smoothingComputational Statistics & Data Analysis, 2017
- An Intelligent Body Posture Analysis Model Using Multi-Sensors for Long-Term Physical RehabilitationJournal of Medical Systems, 2017
- Generalizing the Wilcoxon rank-sum test for interval dataInternational Journal of Approximate Reasoning, 2015
- A new class of discrete orthogonal polynomials for blind fitting of finite dataSignal Processing, 2013
- Mobile Multi-parametric Sensor System for Diagnosis of Epilepsy and Brain Related Disorders2013