In recent years, smart healthcare IoT devices have become ubiquitous, but they work in isolated networks due to their policy. Having these devices connected in a network enables us to perform medical distributed data analysis. However, the presence of diverse IoT devices in terms of technology, structure, and network policy, makes it a challenging issue while applying traditional centralized learning algorithms on decentralized data collected from the IoT devices. In this study, we present an extensive review of the state-of-the-art machine learning applications particularly in healthcare, challenging issues in IoT, and corresponding promising solutions. Finally, we highlight some open-ended issues of IoT in healthcare that leaves further research studies and investigation for scientists.
翻译:近年来,智能保健的IOT装置已经变得无处不在,但由于政策,它们在孤立的网络中工作。这些装置连接在一个网络中,使我们能够进行医疗分布的数据分析。然而,由于在技术、结构和网络政策方面存在着不同的IOT装置,因此在对从IOT装置收集的分散数据应用传统的集中学习算法的同时,这是一个具有挑战性的问题。在本研究报告中,我们广泛审查了最先进的机器学习应用,特别是在医疗保健方面的应用,在IOT中具有挑战性的问题,以及相应的有希望的解决办法。最后,我们强调了在保健方面一些开放的IOT问题,这些问题留给科学家进一步研究和调查。