Advances in multisensor information fusion: A Markov–Kalman viscosity fuzzy statistical predictor for analysis of oxygen flow, diffusion, speed, temperature, and time metrics in CPAP

Abstract

The efficacies of continuous positive airway pressure (CPAP) are well documented in decreasing the apnoea–hypopnoea index in patients with obstructive sleep apnoea. To guarantee these efficacies, CPAP manufacturers must thoroughly test these devices to ensure the flow of oxygenated air to the patient at various temperatures during a prescribed time frame. The calculation of the percent oxygen in a “bimixture” of gas can be done by measuring the travel time of a sound wave through the gas, and the travel time is proportional to the density of the air. We utilized existing multisensor tubes that were developed to collect and measure oxygen flow, diffusion, speed, temperature, and time metrics. Then these metrics were analysed using a Markov fuzzy, statistical, artificial neural network, nearest‐neighbour predictive approach to determine the interactions between these variables. An improved Kalman filter method was employed to reduce noise, increase viscosity, and obtain correct data from the CPAP system.

Distributed Error Correction of EKF Algorithm in Multi-Sensor Fusion Localization Model

“…Hosseinyalamdary [22] optimized and improved the measurement error of inertial measurement unit through deep Kalman filter. Rodger [23] used Markov fuzzy, statistical, artificial neural network and nearest neighbor prediction methods to analyze multi-sensor indexes and used improved Kalman filter method to reduce noise in the localization system. Li et al [24] converted the measured values of different sensors into a set of measurement matrices, which are solved by improving PHD filtering.…”

An adaptive stacked hourglass network with Kalman filter for estimating 2D human pose in video

“…The displacement change of the human centre and human joints during a certain period can be approximated by a linear motion. The implementation of the optimization method includes the local outlier factor (Lu, Wei, Xing, and Liu (2017); Salehi, Leckie, Bezdek, Vaithianathan, and Zhang (2016); Fanaee‐T and Gama (2015)) to determine the outlier of the input time series data and uses a Kalman filter (Liang, Yuan, and Thalmann (2012); Nguyen, Mann, Vardy, and Gosine (2017); Rodger (2018)) to update the value of the outlier. In this manner, we can address self‐occlusion and improve the accuracy of stacked hourglass network.…”