الفهرس 
IntroductionOnly 14 pages are availabe for public view
 |  | from | 126 |  |  |
| | | from | 126 | | |
Abstract
The huge spreading of COVID-19 viral outbreak to several countries motivates many of the research institutions everywhere in numerous disciplines to decrease the spread rate of this pandemic. Among these researchs are the robotics with different payloads and sensory devices. The wireless communication of the robots helps to remotely track the patients’ diagnosis and their treatment. In addition, it reduces direct contact between the patients and the medical team members. This work presents a prototype of wireless medical robot (MR) to communicate between patients and doctors. Also, it discusses the modelling of a four-wheeled MR using system identification methodology, that help in controller design. Additionally, the development of the sensor signal analysis using advanced techniques to estimate vital signs from a simple sensor. Towards the intended application, some medical sensors and a camera are added on board to acquire vital signs and physical parameters of patients. Such robots necessitate controller development which is regarded as the most important topic. The MR model is obtained via an experimental test which is executed to record and analyze the MR input/output signals in an open-loop system configuration with single-input-single-output (SISO). The estimation and validation results demonstrate that the obtained identified model about 89% of the output variation/dynamics. Then, proportional-integral-derivative (PID) and Fuzzy logic (FLC) controllers are designed and gives good results for heading angle tracking.
Additionally, this work presents a non-invasive method for Blood Pressure (BP) estimation based on extracted features from photoplethysmography (PPG) and Electrocardiogram (ECG) signals. The proposed method depends on a machine learning technique, namely Artificial Neural Networks (ANN), to estimate blood pressure. The training is conducted on a real data set (more than 2000 BP, ECG and PPG signals) recorded by patients’ monitoring at various hospitals between 2001 and 2008. In addition to the ten features that are usually used in literature, the proposed method uses cross validation technique between features to provide more robust estimation of the blood pressure. Furthermore, the proposed method provides accurate and reliable blood pressure estimation while it is calibration-free. Compared to previous works, we used half of the data and the results clarified that we achieved more accuracy in the systolic pressure measurements. These results are expected to improve more by increasing the training samples, which is planned in future work. Additionally, more than two real thousands recorded Photoplethysmography (PPG) signals and Blood Pressure (BP) are used to find the appropriate BP estimation model without the need of the ECG signals. Finally, the Blood Pressure (BP) can be estimated with mean absolute error of about 4.7 mmHg in systolic and 4.8 mmHg in diastolic using Artificial Neural Network (ANN).
Unfortunately, accurate the proposed method requires several synchronous medical devices. Thus, this work enhances the BP estimation by training BP and Photoplethysmography (PPG) data signals only without need of ECG signals. Many machine learning (ML) regression models are estimated and the best one is selected. The proposed method overcomes drawbacks of BP measurement accuracy and provides enough capability for reliable and calibration-free BP estimation. The obtained results clarify that the error standard deviation (STD) is about 5.3 and 6.4 mmHg of systolic pressure (SP) and diastolic pressure (DP), respectively. In addition, the mean absolute error (MAE) is about 4.2 and 4.5 mmHg of SP and DP, respectively.
More enhancement is done by division of dataset with building an estimation model to each division. Theis improves the results and becomes better than that published in literature studies by about 89%, 72%, and 35% for error STD of SBP in low, normal, and high BP, respectively.
These results achieve grade “A” for both SP and DP based on the Britain Hypertension Society (BHS) standard. Finally, the results of BP estimation regression models meet the International Organization for Standardization (ISO) requirements for non-invasive BP devices and consequently they can be utilized later in life experiments.