MEDICAL GAS SYSTEMS PROFESSOR GAOYONG LUO – R&D MANAGER, SHJ MEDICAL GAS SPECIALISTS, UK
Deep learning-based remote monitoring
Professor Gaoyong Luo of SHJ Medical Gas Specialists outlines a novel machine learning system to collect data and remotely monitor oxygen flow rate and line pressure to keep an eye on performance of medical gas systems in hospitals.
Medical gas systems (MGS) are one of the key elements of every hospital, where oxygen, nitrous oxide, nitrogen, carbon dioxide, and medical air are continuously delivered to hospital areas through pipelines. For patient care, it is of the utmost importance to keep MGS operating with the best efficiency and creating the safest possible environment. In particular, the outbreak of the COVID-19 pandemic has greatly increased the demand for oxygen supply. To help hospitals manage the situation,
and keep an eye on performance of MGS systems, it has become critical to remotely monitor oxygen flow rate and line pressure measured by multi-sensors with data wirelessly transmitted over built
internet of things (IoT) networks, where sensing, data processing, communication technology, and artificial intelligence (AI) can be integrated to enable the MGS to make confident decisions and to optimise the operations and maintenance of processes of prediction and prevention.1 Remotely monitoring MGS in real-time using the cellular IoT networks also allows hospitals to optimize usage and reduce risk. By either simply monitoring levels to ensure continuous supply, or monitoring location to ensure access, 4G/5G mobile network-based monitoring ensures real- time data communication independent of wi-fi availability, and the system designed is connected to all devices over the IoT networks to allow a global vision and
The proposed real-time machine learning system can give valuable insights, track everything that is relevant to operations, and perform qualitative and quantitative data analysis to monitor machine conditions, detect faults, and predict and optimise system performance
Professor Gaoyong Luo
Professor Gaoyong Luo is research & development manager at SHJ Medical Gas Specialists and has been the field chair of electronics information and communication engineering at Guangzhou University in China. He has a PhD in electrical engineering from Brunel University, UK. He has taught
thousands of students and supervised the work of master and PhD students. His main research interests are in the field of
wavelets, artificial intelligence, spread spectrum communications, angular momentum modulation, remote sensing and audio coding, with expertise in control and modulation theory and applications to
automation and communication systems. Professor Luo has published over 100 referred journal/conference papers and 20 patents. He is the author of Wavelets in Engineering Applications.
IFHE DIGEST 2022
report any parameter/anomaly. This would allow the hospital equipment maintenance provider to constantly verify that the system is operating safely as required by the reference documents, make reasonable adjustments to optimal performance, and provide on-call emergency services for malfunctioning equipment. To keep a stable supply of all medical gases during a pandemic - particularly oxygen – it has been shown very helpful to deploy more advanced sensors such as oxygen flow meters, and to remotely and continuously monitor the measurement data in real-time, so that rapid decisions can be made. This increases the number of sensors installed and can generate added value along the entire value chain. It also means that the systems and architectures for data processing are becoming more and more complex. Although technology advancements
have enabled the systems to interact with the environment and optimize processes via learning through interactions,2
it may
still be difficult to interpret the discrete sensor data correctly and extract the desired information. Equipped with many sensors over the IoT networks, and enabled by deep learning to detect relevant status information of the systems and to monitor the health status of specific components,3
this data-driven
decision model is improving and dramatically changing the way in which system/machine/engine failures can be predicted before they happen and the downtime of industrial machines/engines can be prevented or reduced, extending from detection of anomalies to complex fault diagnostics and immediate initiation of fault elimination. For real-time decision-making to give an early warning for catastrophic system damage, the voluminous sensor data generated needs remote analysis. In recent times, data-driven prognosis methods have been proven to be very effective due to the availability of better data acquisition methods and the deployment of AI techniques.
71
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50 |
Page 51 |
Page 52 |
Page 53 |
Page 54 |
Page 55 |
Page 56 |
Page 57 |
Page 58 |
Page 59 |
Page 60 |
Page 61 |
Page 62 |
Page 63 |
Page 64 |
Page 65 |
Page 66 |
Page 67 |
Page 68 |
Page 69 |
Page 70 |
Page 71 |
Page 72 |
Page 73 |
Page 74 |
Page 75 |
Page 76 |
Page 77 |
Page 78 |
Page 79 |
Page 80 |
Page 81 |
Page 82 |
Page 83 |
Page 84 |
Page 85 |
Page 86 |
Page 87 |
Page 88 |
Page 89 |
Page 90 |
Page 91 |
Page 92 |
Page 93 |
Page 94 |
Page 95 |
Page 96 |
Page 97 |
Page 98 |
Page 99 |
Page 100 |
Page 101 |
Page 102 |
Page 103 |
Page 104 |
Page 105 |
Page 106 |
Page 107 |
Page 108 |
Page 109 |
Page 110 |
Page 111 |
Page 112 |
Page 113 |
Page 114 |
Page 115 |
Page 116
