ABSTRACT
INTRODUCTION: The six-minute walk test (6MWT) contains two independent components: walk distance (6MWD) and oxygen saturation (SpO2). 6MWD does not give detailed data on numerous COPD associated disorders. As oxygen desaturation plays a key role in exercise limita-tions, a few new parameters integrating oxygen desaturation during exercise along with walk distance are necessary. So, this study was conducted to assess the relationships between ΔSpO2/distance ratio and pulmonary function test in addition to extent of pulmonary emphysema in COPD patients. MATERIAL AND METHODS: 57 stable COPD patients who attended the outpatient clinic of chest medicine department. Mansoura university. were enrolled. Included patients were classified according to GOLD airflow limitation. Age, sex, and modified Medical Research Council dyspnea score (mMRC) were recorded. furthermore, every patient completed the 6MWT and underwent a pulmonary function test and a CT scan to evaluate the degree of pulmonary emphysema. RESULTS: ΔSpO2/distance ratio was moderately correlated with DLCO%, FVC % and GOLD classification. However, strong correlation was found with FEV1% and RV%. mMRC was weakly correlated with ΔSpO2/distance ratio. In addition, weak nonsignificant correlation was found between ΔSpO2/distance ratio and extent of pulmonary emphysema as measured by HRCT volumetry. A significant moderate cor-relation was noticed between the ΔSpO2/distance ratio and 6MWD (r = -0.5, P < 0.001). a significant strong cor-relation was observed between the ΔSpO2/distance ratio and ΔSpO2 (r = 0.87, P < 0.001). CONCLUSION: ΔSpO2/distance ratio could be a simple and valuable index for the evaluation of exercise capacity in COPD individuals and might be utilized to predict severity of airway obstruction, pulmonary diffusing capacity disorder and severe hyperinflation.
ABSTRACT
Although wireless fingerprinting has been well researched and widely used for indoor localization, its performance is difficult to quantify. Therefore, when wireless fingerprinting solutions are used as location updates in multi-sensor integration, it is challenging to set their weight accurately. To alleviate this issue, this paper focuses on predicting wireless fingerprinting location uncertainty by given received signal strength (RSS) measurements through the use of machine learning (ML). Two ML methods are used, including an artificial neural network (ANN)-based approach and a Gaussian distribution (GD)-based method. The predicted location uncertainty is evaluated and further used to set the measurement noises in the dead-reckoning/wireless fingerprinting integrated localization extended Kalman filter (EKF). Indoor walking test results indicated the possibility of predicting the wireless fingerprinting uncertainty through ANN the effectiveness of setting measurement noises adaptively in the integrated localization EKF.